WO2019161731A1 - 渠道的归因方法和装置 - Google Patents

渠道的归因方法和装置 Download PDF

Info

Publication number
WO2019161731A1
WO2019161731A1 PCT/CN2019/073695 CN2019073695W WO2019161731A1 WO 2019161731 A1 WO2019161731 A1 WO 2019161731A1 CN 2019073695 W CN2019073695 W CN 2019073695W WO 2019161731 A1 WO2019161731 A1 WO 2019161731A1
Authority
WO
WIPO (PCT)
Prior art keywords
channel
promotion information
target
access
path
Prior art date
Application number
PCT/CN2019/073695
Other languages
English (en)
French (fr)
Inventor
葛婷
Original Assignee
北京国双科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京国双科技有限公司 filed Critical 北京国双科技有限公司
Publication of WO2019161731A1 publication Critical patent/WO2019161731A1/zh

Links

Images

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

Definitions

  • the present application relates to the field of Internet data analysis, and in particular, to a method and apparatus for attribution of a channel.
  • the search promotion information is provided, and the payment method is CPC. (Cost Per Click), that is, charging per click, the promotion information in some media is the promotion information of a promotion information.
  • the payment method is CPM (Cost Per Mille), which is the cost of thousands of people. The cost of up to 1000 people is paid as a unit, and there is also a distribution platform for the Internet (Demand Side Platform), which is an Internet promotion information demand platform.
  • the user may have a preliminary understanding of the products involved in the promotion information through the promotion information of the A media, and then click on the in-depth understanding of the promotion information of the product of the B media, and finally in the media C conducted a product search, entered the official website according to the search results, and produced the behavior of purchasing the product.
  • the main purpose of the present application is to provide a method and device for attribution of a channel, so as to solve the problem in the related art that it is difficult to effectively evaluate the contribution of each channel to the final successful conversion in the process of transforming the promotion information.
  • a method of attribution of a channel includes: collecting access data of the target promotion information through multiple channels in a preset time period, and obtaining a access data set, wherein the multiple channels are channels for the target promotion information, and the access data set includes multiple pieces of data, each The strip data includes at least a channel ID, a user ID, and an access time of accessing the target promotion information through each channel; the data in the access data set is aggregated according to the user ID and the access time sequence of the target user, and the access including at least one path is generated.
  • the path network wherein the path includes at least one channel; and the contribution ratio of each channel in the access path network to the promotion of the promotion information into the preset indicator is calculated.
  • calculating the contribution value of each channel by promoting the information conversion model includes: calculating a contribution ratio of each channel in the access path network to converting the promotion information into a preset indicator, including: calculating a conversion corresponding to each path in the access path network Success rate and summation, get the total probability of promotion information conversion; set a channel as the target channel, calculate the total probability of promotion information conversion after the access path network removes the target channel; convert the total probability according to the promotion information and the promotion after removing the target channel The total probability of information conversion, calculating the proportion of the target channel's contribution to the promotion of information into a preset indicator.
  • calculating the conversion success rate corresponding to each path in the access path network and summing, and obtaining the total probability of the promotion information conversion includes: obtaining the number of target users accessing the target promotion information through each channel; and promoting the access target according to each channel The number of target users of the information, the jump rate from each channel to the next channel when calculating the access promotion information; the jump from each channel to the next channel according to the probability of selecting each path and accessing the target promotion information The jump rate and the conversion rate of the last channel in each path are calculated, and the conversion success rate corresponding to each path is calculated; the conversion success rate corresponding to each path in the access path network is summed, and the total probability of promotion information conversion is obtained.
  • the jump rate from the respective channels to the next channel when calculating the access target promotion information includes: accessing the next channel to be accessed through each channel The ratio of the number of target users of the target promotion information to the number of target users who access the target promotion information through various channels, and the jump rate from the respective channels to the next channel when the target promotion information is accessed.
  • an attribution device for a channel includes: an acquisition unit configured to collect access data of the target promotion information through multiple channels in a preset time period, and obtain a access data set, wherein the multiple channels are channels for the target promotion information, and the access data set includes a plurality of pieces of data, each of which includes at least a channel ID, a user ID, and an access time for accessing the target promotion information through each channel; and an aggregation unit configured to set the user ID and access time order of the data in the access data set according to the target user Aggregating, generating an access path network including at least one path, wherein the path includes at least one channel; and the calculating unit is configured to calculate a contribution ratio of each channel in the access path network to the promotion index into a preset indicator.
  • the calculation unit includes: a first calculation module, configured to calculate a conversion success rate corresponding to each path in the access path network and sum, to obtain a total probability of promotion information conversion; and a second calculation module, configured to set a channel The target channel is calculated, and the total probability of the promotion information conversion after the target path is removed from the target path is calculated; the third calculation module is set to convert the total probability according to the promotion information and the total probability of the promotion information after the target channel is removed, and calculate the target channel to promote The proportion of information that is converted into a preset indicator.
  • the first calculation module includes: an acquisition sub-module, configured to acquire a quantity of target users that access the target promotion information through the respective channels; and a jump rate calculation sub-module configured to be based on the target users that access the target promotion information through the respective channels. Quantity, the jump rate from each channel to the next channel when calculating the access promotion information; the conversion rate calculation sub-module is set to jump from each channel according to the probability of selecting each path and accessing the target promotion information. Calculating the conversion success rate of each path by the jump rate of one channel and the conversion rate of the last channel in each path; the generalization probability calculation sub-module of the promotion information conversion is set to correspond to each path in the access path network. The conversion success rate is summed to obtain the total probability of promotion information transformation.
  • the jump rate calculation sub-module further includes: a ratio of the number of target users accessing the target promotion information to the next channel that is jumped to by the respective channels and the number of target users accessing the target promotion information through the respective channels, as an access The jump rate from the various channels to the next channel when the target promotes the information.
  • a storage medium including a stored program, wherein the program performs an attribution method of a channel of any of the above.
  • a processor for running a program in which an attribution method of any of the above-described channels is executed while the program is running is provided.
  • the following steps are adopted: collecting access data of the target promotion information through multiple channels in a preset time period, and obtaining an access data set, wherein multiple channels are channels for the target promotion information, and the access data set includes multiple Strip data, each of which includes at least a channel ID, a user ID, and an access time for accessing the target promotion information through each channel; and the data in the access data set is aggregated according to the user ID and the access time sequence of the target user, and the generation includes at least An access path network of a path, wherein the path includes at least one channel; and calculating a contribution ratio of each channel in the access path network to the promotion of the promotion information into a preset indicator.
  • the contribution value of each channel is calculated, and the effect of each channel on the final successful conversion in the process of effectively evaluating the promotion information conversion is achieved.
  • FIG. 1 is a flowchart of a method for attribution of a channel according to an embodiment of the present application
  • FIG. 2 is a schematic diagram of an access path network in a method for attribution of a channel according to an embodiment of the present application
  • FIG. 3 is a schematic diagram of forming a path in a visited path network according to an embodiment of the present application
  • FIG. 4 is a schematic diagram of an attribution device of a channel according to an embodiment of the present application.
  • Markov chain reflects the transformation relationship in state space. In a sequence of states, each state is only related to the previous state.
  • Removal effect refers to the contribution value of a point in the evaluation graph model (in actual application, we regard it as a channel), which can be regarded as: the total contribution value when the point (channel) is included, minus the removal The point (channel) when the overall contribution value.
  • Channel attribution means that users have reached out to a number of promotional channels for this conversion item before they complete the conversion, and analyze these channels to properly attribute this conversion to multiple channels.
  • FIG. 1 is a flow chart of a method for attribution of a channel according to an embodiment of the present invention. As shown in FIG. 1, the method includes the following steps:
  • Step S101 Collecting access data of the target promotion information through multiple channels in a preset time period, and obtaining an access data set, wherein the multiple channels are channels for the target promotion information, and the access data set includes multiple pieces of data, each of which The data includes at least a channel ID, a user ID, and an access time for accessing the target promotion information through each channel;
  • the preset time period is 3 months
  • the target promotion information is the A brand mobile phone advertisement
  • the merchants put the A brand mobile phone advertisement in the C1 browser, the C2 browser and the C3 browser;
  • Access data set includes multiple pieces of data, at least each piece of data Including C1 browser, C2 browser and C3 browser ID, user ID and access time of mobile phone advertisements accessing A brand through each channel, average access duration, average access depth, average jump time interval and other information.
  • Step S102 The data in the access data set is aggregated according to the user ID and the access time sequence of the target user, and the access path network including at least one path is generated, wherein the path includes at least one channel.
  • the channel through which the user accesses the promotion information is connected in a path according to the actual time when the user accesses the promotion information, and the path involves one or more channels, and the Markov model generated by the aggregation of multiple paths is an advertisement conversion model, wherein the advertisement conversion model
  • the method includes multiple paths, and each path includes at least: a jump relationship between each channel and each channel, each channel forms a node of the path, and a jump relationship between the channels forms a directed edge of the path.
  • the target user Specify the target user. If the target user first accesses the A-brand mobile phone advertisement through the C1 browser within the preset time period of 3 months, then jump to the C2 browser to access the A-brand mobile phone advertisement, and finally jump to When the C3 browser accesses the mobile advertising of the A brand, the target user's jump access constitutes the first path, and the first path includes three channels; after some target users access the A brand mobile phone advertisement through the C1 browser for the first time, Jump to the C3 browser to access the A brand mobile phone advertisement, the target user's jump access constitutes the second path, and the second path includes 2 channels; some target users access the A brand mobile phone advertisement through the C3 browser for the first time.
  • the access of the target user constitutes a third path, and the third path includes one channel, and the first path, the second path, and the third path are aggregated into an access path network.
  • Step S103 Calculate the contribution ratio of each channel in the access path network to the promotion of the promotion information into the preset indicator.
  • the user's behavior of searching and clicking the promotion information has Markov property, that is, the channel used by the user to access the promotion information only depends on the channel used when accessing the promotion information last time, and on this basis, the user's access process ( The channel involved in the interview will satisfy the Markov property. Therefore, the path formed by the jump between different channels when the user accesses the promotion information can be regarded as a Markov chain, and the access path network generated by the aggregation is regarded as a Mar
  • the Cove model on the basis of this, can use the removal effect algorithm to calculate the contribution ratio of each channel to the promotion of the promotion information into the preset indicators.
  • setting promotion information into preset indicators is for the user to view the mobile phone advertisement of the A brand and then place an order on the official website to purchase the brand mobile phone.
  • the user browses the mobile phone advertisement of the A brand in the current browser only with the previous browsing.
  • the access path network formed by the user accessing the A brand mobile phone advertisement in the C1 browser, the C2 browser and the C3 browser satisfies the Markov property, and the C1 browser, the C2 browser and the C3 can be calculated by the removal effect algorithm.
  • the three channels of the browser respectively purchase the mobile phone's contribution ratio after the user views the A brand mobile phone advertisement and places an order on the official website.
  • calculating a contribution ratio of each channel in the access path network to converting the promotion information into the preset indicator comprises: calculating, corresponding to each path in the access path network Converting the success rate and summing, obtaining the total probability of promotion information conversion; setting a channel as the target channel, calculating the total probability of the promotion information conversion after the access path network removes the target channel; converting the total probability according to the promotion information and removing the target channel Promote the total probability of information conversion, and calculate the contribution ratio of the target channel to the conversion of the promotion information to the preset indicator.
  • 600 target users first viewed the A-brand mobile phone advertisement in the C1 browser, and 300 of them did not view the brand's mobile phone advertisements in other channels and did not purchase the brand's mobile phone; Another 300 users have viewed the mobile phone advertisements in the C2 browser and the C3 browser. 150 users finally went to the official website to place an order to purchase the brand's mobile phone, and another 150 users did not purchase it;
  • FIG. 2 is a schematic diagram of an access path network in a method for attribution of a channel according to an embodiment of the present application.
  • the access path network formed by the above behavior there are three paths, and the first path is composed of The data composition of the mobile phone advertisement of the A brand is accessed through the C1 browser; the second path is composed of the data of the mobile phone advertisement of the A brand accessed by the C1 browser jumping to the C2 browser and then to the C3 browser; The path consists of the data of the mobile phone advertisement of the A brand accessed by the order of the jump to the C3 browser through the C2 browser.
  • the conversion success rate corresponding to each path in the access path network is calculated and summed, and the total probability of obtaining the promotion information conversion includes: obtaining the access target through each channel. The number of target users who promote the information; according to the number of target users accessing the target promotion information through various channels, the jump rate from each channel to the next channel when calculating the access promotion information is calculated; according to the probability of selecting each path, When the target promotion information is accessed, the jump rate from each channel to the next channel and the conversion rate of the last channel in each path are calculated, and the conversion success rate corresponding to each path is calculated; corresponding to each path in the access path network The conversion success rate is summed to obtain the total probability of promotion information transformation.
  • the probability of the user selecting the first path that is, the probability of accessing the A brand mobile phone advertisement through the C1 browser for the first time
  • the probability that the user selects the second path that is, the first time accessing the A brand mobile phone advertisement through the C1 browser Probability
  • the probability that the user selects the third path that is, the probability of accessing the A-brand mobile phone advertisement through the C2 browser for the first time
  • the last channel in the first path, the second path, and the third path is acquired.
  • Conversion rate the probability that a user will access an A-branded mobile ad through the last channel of each route and purchase the branded phone.
  • the corresponding purchase behavior is not generated, that is, the probability of accessing the A brand mobile phone advertisement and purchasing the brand mobile phone in the last channel of the path is 0, the conversion success rate corresponding to the first path is 0; for the second path For example, calculate the probability that a user will first view a brand-name mobile phone advertisement through a C1 browser, and jump from a C1 browser to a C2 browser.
  • the probability of the user viewing the A-brand mobile phone advertisement through the C2 browser for the first time, the jump rate from the C2 browser to the C3 browser, and the probability of generating the purchase behavior after viewing the advertisement through the C3 browser will be calculated.
  • the three probabilities are multiplied to obtain the conversion success rate corresponding to the third path; the conversion success rate corresponding to the first path, the conversion success rate corresponding to the second path, and the conversion success rate corresponding to the third path are summed After obtaining the mobile phone advertisement of the A brand through the C1 browser, the C2 browser and the C3 browser, the probability that the user has the corresponding purchase behavior after viewing the advertisement, that is, the total conversion probability of the A brand mobile phone advertisement.
  • the jump from each channel to the next channel when calculating the access promotion information is calculated.
  • the rate includes: the ratio of the number of target users who access the target promotion information to the next channel that is jumped to by each channel and the number of target users who access the target promotion information through each channel, and jumps from various channels as the access target promotion information. The jump rate to the next channel.
  • the target user of the A brand mobile phone advertisement is 900 people for the first time, and the first time to view the A brand mobile phone through the C1 browser.
  • the number of users of the advertisement is 900, and the number of users who view the A-brand mobile advertisement through the C2 browser for the first time is 300; then, the probability of viewing the first time from the C1 browser is 2/3, that is, the first path is selected.
  • the probability of selecting the second path is 2/3.
  • the user accessing the A brand mobile phone advertisement in the C1 browser does not generate corresponding purchase behavior, and the conversion success rate corresponding to the first path is 0;
  • the second path there are 300 users who jump from the C1 browser to the C2 browser, that is, the jump rate from the C1 browser to the C2 browser is 1/2, jumping from the C2 browser.
  • the jump rate from C2 browser to C3 browser is 1, and 150 of them have the purchase behavior, the purchase rate is 1/2, which will be viewed from the C1 browser.
  • Probability, jump rate from C1 browser to C2 browser The jump rate of the C2 browser jumping to the C3 browser is multiplied by the purchase rate after viewing the advertisement from the C3 browser, and the probability that the user views the A-brand mobile phone advertisement from the second path and generates the purchase behavior is 1/6. That is, the conversion success rate corresponding to the second path is 1/6; similarly, the number of users who view the mobile phone advertisement of the A brand through the C2 browser for the first time is 300, and the probability of viewing the first time from the C2 browser is 1/3.
  • the probability of selecting the third path is 2/3. In the third path, there are 300 users who jump from the C2 browser to the C3 browser, that is, the jump from the C2 browser to the C3 browser.
  • the conversion rate is 1, of which 150 has generated purchase behavior, the purchase rate is 1/2, the probability of viewing from the C2 browser, the jump rate from the C2 browser to the C3 browser, and the viewing of the advertisement from the C3 browser. After the purchase rate is multiplied, the probability that the user views the A-brand mobile phone advertisement from the second path and generates the purchase behavior is 1/6, that is, the conversion success rate corresponding to the third path is 1/6.
  • the probability that the user views the A-branded mobile phone advertisement from the second path and generating the purchase behavior, and the user viewing the A-brand mobile phone advertisement from the third path and generating The probability of purchase behavior is summed, and the total probability of advertisement conversion after accessing the A brand mobile phone advertisement through C1 browser, C2 browser and C3 webpage within 3 months is 1/3.
  • FIG. 3 is a schematic diagram of forming a path in a visited path network according to an embodiment of the present application.
  • the user is removed from the advertisement through the C1 browser.
  • the amount of traffic, the conversion rate of the ad after it’s served in the C1 browser, and the amount of ad conversions from subsequent channels of the C1 browser based on the channel’s jump probability (considered as conversions and visits from C1 browser point diversion), without C1 browsing
  • the subsequent channels affected by the device jump will not be affected; thus there is only one path left in the access path network: the order from the C2 browser to the C3 browser, which is equivalent to the third path in the original access path network, and the third path
  • the corresponding conversion success rate is 1/6, and the total probability of ad conversion is also 1/6.
  • the total probability of ad conversion is 1/3; after removing the C1 browser, the total probability of ad conversion is 1/6, and the difference between the conversion probabilities of the advertisement before the C1 browser is removed and the C1 browser is removed is 1 /6, The contribution of the C1 browser is 1/6.
  • the method for attribution of the channel obtains the access data set by accessing the access data of the target promotion information through multiple channels within a preset time period, wherein multiple channels are channels for the target promotion information to be accessed.
  • the data set includes a plurality of pieces of data, each of which includes at least a channel ID, a user ID, and an access time of accessing the target promotion information through each channel; and the data in the access data set is performed according to the user ID and the access time order of the target user.
  • the embodiment of the present application further provides a channel attribution device. It should be noted that the attribution device of the channel in the embodiment of the present application may be used to perform the attribution method for the channel provided by the embodiment of the present application. The attribution device of the channel provided by the embodiment of the present application is introduced below.
  • the apparatus includes an acquisition unit 10, an aggregation unit 20, and a calculation unit 30.
  • the collecting unit 10 is configured to collect access data of the target promotion information through multiple channels in a preset time period, and obtain an access data set, where multiple channels are channels for the target promotion information, and the access data set includes Multiple pieces of data, each of which includes at least a channel ID, a user ID, and an access time for accessing the target promotion information through each channel;
  • the aggregation unit 20 is configured to aggregate the data in the access data set according to the user ID and the access time sequence of the target user, and generate an access path network including at least one path, where the path includes at least one channel;
  • the calculating unit 30 is configured to calculate a contribution ratio of each channel in the access path network to the promotion of the promotion information into a preset indicator.
  • the calculating unit includes: a first calculating module, configured to calculate a conversion success rate corresponding to each path in the access path network, and obtain a summation, and obtain the promotion.
  • the total probability of information conversion is configured to set a channel as the target channel, and calculate the total probability of the promotion information conversion after the access path network removes the target channel;
  • the third calculation module is set to convert the total probability according to the promotion information and The total probability of promotion information conversion after removing the target channel, and calculating the contribution ratio of the target channel to the promotion of the promotion information into the preset indicator.
  • the first calculation module includes: an acquisition sub-module, configured to acquire the number of target users that access the target promotion information through each channel; and a jump rate calculation sub-module , configured to calculate a jump rate from each channel to the next channel when accessing the target promotion information according to the number of target users accessing the target promotion information through each channel; the conversion rate calculation sub-module is set to select each path according to Probability, the jump rate from each channel to the next channel when accessing the target promotion information, and the conversion rate of the last channel in each path, calculate the conversion success rate corresponding to each path; The sub-module is set to sum the conversion success rate corresponding to each path in the access path network, and obtain the total probability of the promotion information transformation.
  • the jump rate calculation sub-module further includes: the number of target users who access the target promotion information by using the next channel to which each channel is redirected The ratio of the number of target users who access the target promotion information by the channel, and the jump rate from each channel to the next channel when the target promotion information is accessed.
  • the attribution device of the channel collects access data of the target promotion information through multiple channels in a preset time period, and obtains an access data set, wherein multiple channels are targeted for promotion information.
  • the access data set includes a plurality of data, each of the data includes at least a channel ID, a user ID, and an access time of accessing the target promotion information through each channel;
  • the aggregation unit 20 is configured to follow the data in the access data set according to The user ID and the access time sequence of the target user are aggregated to generate an access path network including at least one path, wherein the path includes at least one channel;
  • the calculating unit 30 is configured to calculate the promotion information of each channel in the access path network into
  • the contribution ratio of the preset indicators solves the problem that it is difficult to effectively evaluate the contribution of each channel to the final successful conversion in the process of transforming the promotion information in related technologies.
  • the attribution device of the channel includes a processor and a memory, and the above-mentioned collection unit 10, aggregation unit 20, calculation unit 30, and the like are all stored as a program unit in a memory, and the processor executes the above-mentioned program unit stored in the memory to implement the corresponding The function.
  • the processor contains a kernel, and the kernel removes the corresponding program unit from the memory.
  • the kernel can set one or more, and adjust the kernel parameters to effectively evaluate the contribution of each channel to the final successful conversion in the promotion information conversion process.
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory (flash RAM), the memory including at least one Memory chip.
  • RAM random access memory
  • ROM read only memory
  • flash RAM flash memory
  • Embodiments of the present invention provide a storage medium on which a program is stored, and when the program is executed by a processor, an attribution method of the channel is implemented.
  • An embodiment of the present invention provides a processor, where the processor is configured to run a program, where the program is executed to perform an attribution method of the channel.
  • An embodiment of the present invention provides a device, including a processor, a memory, and a program stored on the memory and executable on the processor.
  • the processor executes the program, the following steps are implemented: collecting multiple channels through a preset time period Accessing the access data of the target promotion information, and obtaining the access data set, wherein the plurality of channels are channels for the target promotion information, and the access data set includes a plurality of data, each of the data includes at least a channel ID, a user ID, and each The access time of the channel access target promotion information; the data in the access data set is aggregated according to the user ID and the access time sequence of the target user, and the access path network including at least one path is generated, wherein the path includes at least one channel; the calculation access The proportion of each channel in the path network that contributes to the promotion of information into a preset indicator.
  • calculating the contribution value of each channel by using the access path network includes: calculating a contribution ratio of each channel in the access path network to converting the promotion information into a preset indicator, including: calculating a conversion success corresponding to each path in the access path network Rate and sum, get the total probability of promotion information conversion; set a channel as the target channel, calculate the total probability of promotion information conversion after the access path network removes the target channel; convert the total probability according to the promotion information and the promotion information after removing the target channel Total conversion probability, calculate the contribution ratio of the target channel to the promotion of the promotion information into the preset indicators.
  • calculating the conversion success rate corresponding to each path in the access path network and summing, and obtaining the total probability of the promotion information conversion includes: obtaining the number of target users accessing the target promotion information through each channel; and promoting the access target according to each channel The number of target users of the information, the jump rate from each channel to the next channel when calculating the access promotion information; the jump from each channel to the next channel according to the probability of selecting each path and accessing the target promotion information The jump rate and the conversion rate of the last channel in each path are calculated, and the conversion success rate corresponding to each path is calculated; the conversion success rate corresponding to each path in the access path network is summed, and the total probability of promotion information conversion is obtained.
  • the jump rate from the respective channels to the next channel when calculating the access target promotion information includes: accessing the next channel to be accessed through each channel The ratio of the number of target users of the target promotion information to the number of target users who access the target promotion information through various channels, and the jump rate from the respective channels to the next channel when the target promotion information is accessed.
  • the devices in this document can be servers, PCs, PADs, mobile phones, and the like.
  • the present application further provides a computer program product, when executed on a data processing device, is adapted to perform a process of initializing the following method steps: collecting access data of the target promotion information through multiple channels within a preset time period, and obtaining Accessing the data collection, wherein the plurality of channels are channels for the targeted promotion information, and the access data set includes a plurality of data, and each of the data includes at least a channel ID, a user ID, and an access time of accessing the target promotion information through each channel; Aggregating the data in the access data set according to the user ID and the access time sequence of the target user, and generating an access path network including at least one path, wherein the path includes at least one channel; and calculating the promotion information of each channel in the access path network The percentage of contribution to a default metric.
  • calculating the contribution value of each channel by using the access path network includes: calculating a contribution ratio of each channel in the access path network to converting the promotion information into a preset indicator, including: calculating a conversion success corresponding to each path in the access path network Rate and sum, get the total probability of promotion information conversion; set a channel as the target channel, calculate the total probability of promotion information conversion after the access path network removes the target channel; convert the total probability according to the promotion information and the promotion information after removing the target channel Total conversion probability, calculate the contribution ratio of the target channel to the promotion of the promotion information into the preset indicators.
  • calculating the conversion success rate corresponding to each path in the access path network and summing, and obtaining the total probability of the promotion information conversion includes: obtaining the number of target users accessing the target promotion information through each channel; and promoting the access target according to each channel The number of target users of the information, the jump rate from each channel to the next channel when calculating the access promotion information; the jump from each channel to the next channel according to the probability of selecting each path and accessing the target promotion information The jump rate and the conversion rate of the last channel in each path are calculated, and the conversion success rate corresponding to each path is calculated; the conversion success rate corresponding to each path in the access path network is summed, and the total probability of promotion information conversion is obtained.
  • the jump rate from the respective channels to the next channel when calculating the access target promotion information includes: accessing the next channel to be accessed through each channel The ratio of the number of target users of the target promotion information to the number of target users who access the target promotion information through various channels, and the jump rate from the respective channels to the next channel when the target promotion information is accessed.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment in combination of software and hardware.
  • the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
  • RAM random access memory
  • ROM read only memory
  • Memory is an example of a computer readable medium.
  • Computer readable media includes both permanent and non-persistent, removable and non-removable media.
  • Information storage can be implemented by any method or technology.
  • the information can be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device.
  • computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment in combination of software and hardware.
  • the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

一种渠道的归因方法和装置。该方法包括：采集预设时间段内通过多个渠道访问目标推广信息的访问数据，得到访问数据集合（S101），其中，多个渠道为目标推广信息投放的渠道，访问数据集合中包括多条数据，每条数据中至少包括渠道ID，用户ID以及通过每个渠道访问目标推广信息的访问时间；对访问数据集合中的数据按照目标用户的用户ID和访问时间顺序进行聚合，生成至少包括一条路径的访问路径网（S102），其中，路径中至少包括一个渠道；计算访问路径网中每个渠道对推广信息转化为预设指标的贡献比例（S103）。通过该方法，解决了相关技术中难以有效评价推广信息转化过程中每个渠道对最终成功转化的贡献度的问题。

Description

渠道的归因方法和装置 技术领域
本申请涉及互联网数据分析领域，具体而言，涉及一种渠道的归因方法和装置。
背景技术
在互联网时代的在线推广信息投放中，一个客户往往会通过多个媒体渠道进行投放，并且在各个媒体渠道的投放形式会有不同，例如在有的媒体投放的是搜索推广信息，付费方式是CPC(Cost Per Click)，即以每点击一次计费，在有的媒体投放的推广信息是某推广信息位的展现推广信息，付费方式是CPM(Cost Per Mille)，即千人成本，按媒体送达1000人的成本作为单位来付费，还有互联网推广信息DSP(Demand Side Platform)，即互联网推广信息需求平台等投放方式。面对这么多的推广信息投放媒体渠道，有些媒体投放的推广信息转化效果非常好，有些媒体投放的推广信息却几乎没有转化，但是，没有对推广信息进行直接转化的媒体并不一定对转化没有任何作用，例如，用户可能通过A媒体的推广信息，对推广信息涉及的产品有了初步了解，然后在看到了B媒体的该产品的推广信息时，点击并进行了深入的了解，最后在媒体C进行了产品搜索，根据搜索结果进入了官网，并产生了购买该产品的行为。这种情况下如何评价各个媒体渠道在这次推广信息转化中起到的作用，如果停止某个媒体的推广信息投放，会对最终的转化产生多大的影响，怎么明确各个渠道关联作用、合理利用历史数据有效评价每个媒体的推广信息投放对整体转化产生了多大的贡献，是亟待解决的问题。
针对相关技术中难以有效评价推广信息转化过程中每个渠道对最终成功转化的贡献度的问题，目前尚未提出有效的解决方案。
发明内容
本申请的主要目的在于提供一种渠道的归因方法和装置，以解决相关技术中难以有效评价推广信息转化过程中每个渠道对最终成功转化的贡献度的问题。
为了实现上述目的，根据本申请的一个方面，提供了一种渠道的归因方法。该方法包括：采集预设时间段内通过多个渠道访问目标推广信息的访问数据，得到访问数据集合，其中，多个渠道为目标推广信息投放的渠道，访问数据集合中包括多条数据，每条数据中至少包括渠道ID，用户ID以及通过每个渠道访问目标推广信息的访问时间；对访问数据集合中的数据按照目标用户的用户ID和访问时间顺序进行聚合，生成 至少包括一条路径的访问路径网，其中，路径中至少包括一个渠道；计算访问路径网中每个渠道对推广信息转化为预设指标的贡献比例。
进一步地，通过推广信息转换模型计算每个渠道的贡献值包括：计算访问路径网中每个渠道对推广信息转化为预设指标的贡献比例包括：计算访问路径网中的每条路径对应的转化成功率并求和，得到推广信息转化总概率；将一个渠道设定为目标渠道，计算访问路径网去除目标渠道后的推广信息转化总概率；根据推广信息转化总概率和去除目标渠道后的推广信息转化总概率，计算目标渠道对推广信息转化为预设指标的贡献比例。
进一步地，计算访问路径网中的每条路径对应的转化成功率并求和，得到推广信息转化总概率包括：获取通过各个渠道访问目标推广信息的目标用户的数量；根据通过各个渠道访问目标推广信息的目标用户的数量，计算访问目标推广信息时从各个渠道跳转到下一渠道的跳转率；根据选择每条路径的概率、访问目标推广信息时从各个渠道跳转到下一渠道的跳转率以及每条路径中的最后一个渠道的转化率，计算每条路径对应的转化成功率；对访问路径网中每条路径对应的转化成功率进行求和，得到推广信息转化总概率。
进一步地，根据通过各个渠道访问目标推广信息的目标用户的数量，计算访问目标推广信息时从各个渠道跳转到下一渠道的跳转率包括：将通过各个渠道跳转到的下一渠道访问目标推广信息的目标用户的数量与通过各个渠道访问目标推广信息的目标用户的数量的比值，作为访问目标推广信息时从各个渠道跳转到下一渠道的跳转率。
为了实现上述目的，根据本申请的另一方面，提供了一种渠道的归因装置。该装置包括：采集单元，设置为采集预设时间段内通过多个渠道访问目标推广信息的访问数据，得到访问数据集合，其中，多个渠道为目标推广信息投放的渠道，访问数据集合中包括多条数据，每条数据中至少包括渠道ID，用户ID以及通过每个渠道访问目标推广信息的访问时间；聚合单元，设置为对访问数据集合中的数据按照目标用户的用户ID和访问时间顺序进行聚合，生成至少包括一条路径的访问路径网，其中，路径中至少包括一个渠道；计算单元，设置为计算访问路径网中每个渠道对推广信息转化为预设指标的贡献比例。
进一步地，计算单元包括：第一计算模块，设置为计算访问路径网中的每条路径对应的转化成功率并求和，得到推广信息转化总概率；第二计算模块，设置为将一个渠道设定为目标渠道，计算访问路径网去除目标渠道后的推广信息转化总概率；第三计算模块，设置为根据推广信息转化总概率与去除目标渠道后的推广信息转化总概率，计算目标渠道对推广信息转化为预设指标的贡献比例。
进一步地，第一计算模块包括：获取子模块，设置为获取通过各个渠道访问目标推广信息的目标用户的数量；跳转率计算子模块，设置为根据通过各个渠道访问目标推广信息的目标用户的数量，计算访问目标推广信息时从各个渠道跳转到下一渠道的跳转率；转化率计算子模块，设置为根据选择每条路径的概率、访问目标推广信息时从各个渠道跳转到下一渠道的跳转率以及每条路径中的最后一个渠道的转化率，计算每条路径对应的转化成功率；推广信息转化总概率计算子模块，设置为对访问路径网中每条路径对应的转化成功率进行求和，得到推广信息转化总概率。
进一步地，跳转率计算子模块还包括：将通过各个渠道跳转到的下一渠道访问目标推广信息的目标用户的数量与通过各个渠道访问目标推广信息的目标用户的数量的比值，作为访问目标推广信息时从各个渠道跳转到下一渠道的跳转率。
为了实现上述目的，根据本申请的另一方面，提供了一种存储介质，所述存储介质包括存储的程序，其中，所述程序执行上述任意一种的渠道的归因方法。
为了实现上述目的，根据本申请的另一方面，提供了一种处理器，该处理器用于运行程序，其中，程序运行时执行上述任意一种渠道的归因方法。
通过本申请，采用以下步骤：采集预设时间段内通过多个渠道访问目标推广信息的访问数据，得到访问数据集合，其中，多个渠道为目标推广信息投放的渠道，访问数据集合中包括多条数据，每条数据中至少包括渠道ID，用户ID以及通过每个渠道访问目标推广信息的访问时间；对访问数据集合中的数据按照目标用户的用户ID和访问时间顺序进行聚合，生成至少包括一条路径的访问路径网，其中，路径中至少包括一个渠道；计算访问路径网中每个渠道对推广信息转化为预设指标的贡献比例。通过将历史访问数据聚合形成访问路径网中，算出每个渠道的贡献值，进而达到了有效评价推广信息转化过程中每个渠道对最终成功转化的贡献度的效果。
附图说明
构成本申请的一部分的附图用来提供对本申请的进一步理解，本申请的示意性实施例及其说明用于解释本申请，并不构成对本申请的不当限定。在附图中：
图1是根据本申请实施例提供的渠道的归因方法的流程图；
图2是根据本申请实施例提供的渠道的归因方法中访问路径网的示意图；
图3是根据本申请实施例提供的访问路径网中去除目标渠道后形成的示意图；
图4是根据本申请实施例提供的渠道的归因装置的示意图。
具体实施方式
需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本申请。
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分的实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本申请保护的范围。
需要说明的是，本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本申请的实施例。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
为了便于描述，以下对本申请实施例涉及的部分名词或术语进行说明：
马尔科夫链：马尔科夫链体现的是状态空间中的转换关系，在一组状态序列中，每个状态只与前一个状态有关。
Removal effect：Removal effect是指评价图模型中的一个点(在实际应用中，我们视为一个渠道)的贡献值，可视为：包含该点(渠道)时，整体的贡献值，减去去除该点(渠道)时，整体的贡献值。
渠道归因：渠道归因是指用户在完成转化之前，接触过多个关于本次转化商品的宣传推广渠道，对这些渠道进行分析，把本次转化合理的归因到多个渠道中。
下面结合优选的实施步骤对本发明进行说明，图1是根据本发明实施例的渠道的归因方法的流程图，如图1所示，该方法包括如下步骤：
步骤S101，采集预设时间段内通过多个渠道访问目标推广信息的访问数据，得到访问数据集合，其中，多个渠道为目标推广信息投放的渠道，访问数据集合中包括多条数据，每条数据中至少包括渠道ID，用户ID以及通过每个渠道访问目标推广信息的访问时间；
例如，预设时间段为3个月，目标推广信息为A品牌的手机广告，商家在C1浏 览器，C2浏览器和C3浏览器均投放了A品牌的手机广告；
采集3个月内各个用户通过C1浏览器、C2浏览器和C3浏览器访问A品牌的手机广告的访问数据，得到访问数据集合，其中，访问数据集合中包括多条数据，每条数据中至少包括C1浏览器、C2浏览器和C3浏览器的ID、用户ID以及通过每个渠道访问A品牌的手机广告的访问时间，平均访问时长、平均访问深度、平均跳转时间间隔等信息。
步骤S102，对访问数据集合中的数据按照目标用户的用户ID和访问时间顺序进行聚合，生成至少包括一条路径的访问路径网，其中，路径中至少包括一个渠道。
对用户访问推广信息经过的渠道按照用户访问推广信息的实际时间串联成路径，路径中涉及一个或多个渠道，多条路径聚合生成的马尔科夫模型即为广告转换模型，其中，广告转换模型包括多条路径，每条路径至少包括：各个渠道和各个渠道之间的跳转关系，各个渠道形成路径的节点，各个渠道之间的跳转关系形成路径的有向边。
指定目标用户，若在3个月的预设时间段内，部分目标用户首次通过C1浏览器访问A品牌的手机广告后，又跳转到C2浏览器访问A品牌的手机广告，最后跳转到C3浏览器访问A品牌的手机广告，则目标用户的此次跳转访问构成第一路径，第一路径中包括3个渠道；部分目标用户首次通过C1浏览器访问A品牌的手机广告后，又跳转到C3浏览器访问A品牌的手机广告，则目标用户的此次跳转访问构成第二路径，第二路径中包括2个渠道；部分目标用户首次通过C3浏览器访问A品牌的手机广告，则目标用户的此次访问构成第三路径，第三路径中包括1个渠道，将第一路径、第二路径和第三路径聚合为访问路径网。
步骤S103，计算访问路径网中每个渠道对推广信息转化为预设指标的贡献比例。
假设用户进行搜索和点击推广信息的行为具有马尔科夫性，即用户当前访问推广信息时所用的渠道，仅与其上一次访问推广信息时所用的渠道有关，在此基础上，用户的访问过程(访问时涉及的渠道)将满足马尔科夫性，由此，可以将用户访问推广信息时在不同渠道之间跳转形成的路径视为马尔科夫链，将聚合生成的访问路径网视为马尔科夫模型，在此基础上可以利用removal effect算法计算每个渠道对推广信息转化为预设指标的贡献比例。例如，设定推广信息化为预设指标为用户查看A品牌的手机广告后登陆官网下订单购买了该品牌手机的行为，用户在当前浏览器查看A品牌的手机广告的行为仅与上一浏览器有关，用户在C1浏览器、C2浏览器和C3浏览器上跳转访问A品牌手机广告形成的访问路径网满足马尔科夫性，可以通过removal effect算法计算C1浏览器、C2浏览器和C3浏览器三个渠道分别对用户查看A品牌的手机广告后登陆官网下订单购买了手机的贡献比例。
可选地，在本申请实施例提供的渠道的归因方法中，计算访问路径网中每个渠道对推广信息转化为预设指标的贡献比例包括：计算访问路径网中的每条路径对应的转化成功率并求和，得到推广信息转化总概率；将一个渠道设定为目标渠道，计算访问路径网去除目标渠道后的推广信息转化总概率；根据推广信息转化总概率和去除目标渠道后的推广信息转化总概率，计算目标渠道对推广信息转化为预设指标的贡献比例。
例如，在3个月内，有600个目标用户首次在C1浏览器中查看了A品牌的手机广告，其中300个用户之后没有在其他渠道查看该品牌的手机广告也未购买该品牌的手机；另外300个用户在此之后先后在C2浏览器和C3浏览器查看了该手机广告，其中150个用户最终登陆官网下订单购买了该品牌的手机，另外150个用户没有购买；
另外，有300个用户并没有在C1浏览器中查看A品牌的手机广告，而是首次在C2浏览器查看了该品牌的手机广告，之后又跳转到C3浏览器上查看了该品牌的手机广告，在C3浏览器上查看后，其中150个用户登陆官网下订单购买了该品牌的手机，另外150个用户没有购买；
图2是根据本申请实施例提供的渠道的归因方法中访问路径网的示意图，如图2所示，在以上行为形成的访问路径网中，共包含3条路径，第一条路径，由通过C1浏览器访问A品牌的手机广告的数据构成；第二条路径，由通过C1浏览器跳转到C2浏览器再到C3浏览器的顺序访问A品牌的手机广告的数据构成；第三条路径，由通过C2浏览器跳转到C3浏览器的顺序访问A品牌的手机广告的数据构成。
分别计算在3条路径上用户查看了A品牌的手机且最终购买了该品牌的手机的概率，将3条路径上的购买概率求和，得到投放A品牌的手机广告后广告转化的总概率；将C1浏览器设定为目标渠道，计算去除C1浏览器后用户最终购买了A品牌的手机的概率，去除C1浏览器后的广告转化总概率；根据广告转化总概率与去除C1浏览器后的广告转化总概率进行计算，得到通过C1浏览器投放广告对用户查看A品牌的手机广告后产生购买行为的贡献值。
可选地，在本申请实施例提供的渠道的归因方法中，计算访问路径网中的每条路径对应的转化成功率并求和，得到推广信息转化总概率包括：获取通过各个渠道访问目标推广信息的目标用户的数量；根据通过各个渠道访问目标推广信息的目标用户的数量，计算访问目标推广信息时从各个渠道跳转到下一渠道的跳转率；根据选择每条路径的概率、访问目标推广信息时从各个渠道跳转到下一渠道的跳转率以及每条路径中的最后一个渠道的转化率，计算每条路径对应的转化成功率；对访问路径网中每条路径对应的转化成功率进行求和，得到推广信息转化总概率。
例如，获取用户选择第一条路径的概率，即首次通过C1浏览器访问A品牌的手 机广告的概率；用户选择第二条路径的概率，也即首次通过C1浏览器访问A品牌的手机广告的概率；用户选择第三条路径的概率，也即首次通过C2浏览器访问A品牌的手机广告的概率；同时，获取第一条路径中、第二条路径中和第三条路径的最后一个渠道的转化率，即用户通过每条路径的最后一个渠道访问A品牌的手机广告并购买该品牌手机的概率。
分别获取用户通过C1浏览器、C2浏览器和C3浏览器访问A品牌的手机广告的数量，并计算用户在当前渠道查看了手机广告后跳转到下一渠道查看该手机广告的跳转率；分别针对用户最终购买了A品牌的手机广告的三条路径，将用户选择每条路径的概率、用户在当前渠道查看了手机广告后跳转到下一渠道查看手机广告的跳转率以及在该条路径的最后一个渠道访问A品牌的手机广告并购买该品牌手机的概率相乘，得到每条路径对应的转化成功率；对于第一条路径来说，用户在C1浏览器访问A品牌的手机广告最终未产生相应的购买行为，即在该条路径的最后一个渠道访问A品牌的手机广告并购买该品牌手机的概率为0，第一条路径对应的转化成功率为0；对于第二条路径来说，计算用户首次通过C1浏览器查看A品牌的手机广告的概率、从C1浏览器跳转到C2浏览器的跳转率、从C2浏览器跳转到C3浏览器的跳转率、通过C3浏览器查看广告后产生购买行为的概率，将4个概率相乘，得到第二条路径对应的转化成功率；对于第三条路径来说，计算用户首次通过C2浏览器查看A品牌的手机广告的概率、从C2浏览器跳转到C3浏览器的跳转率、通过C3浏览器查看广告后产生购买行为的概率，将3个概率相乘，得到第三条路径对应的转化成功率；对第一条路径对应的转化成功率、第二条路径对应的转化成功率和第三条路径对应的转化成功率进行求和，得到通过C1浏览器、C2浏览器和C3浏览器投放A品牌的手机广告后用户查看广告后产生了相应购买行为的概率，即A品牌的手机广告的转化总概率。
可选地，在本申请实施例提供的渠道的归因方法中，根据通过各个渠道访问目标推广信息的目标用户的数量，计算访问目标推广信息时从各个渠道跳转到下一渠道的跳转率包括：将通过各个渠道跳转到的下一渠道访问目标推广信息的目标用户的数量与通过各个渠道访问目标推广信息的目标用户的数量的比值，作为访问目标推广信息时从各个渠道跳转到下一渠道的跳转率。
例如，商家在C1浏览器、C2浏览器和C3浏览器均投放了A品牌的手机广告后，首次查看A品牌的手机广告的目标用户为900人，其中首次通过C1浏览器查看A品牌的手机广告的用户的数量为900人，其中首次通过C2浏览器查看A品牌的手机广告的用户的数量为300人；那么，首次从C1浏览器查看的概率为2/3，即选择第一条路径、选择第二条路径的概率均为2/3，在第一条路径中，用户在C1浏览器访问A品牌的手机广告最终未产生相应的购买行为，第一条路径对应的转化成功率为0；在第二条路径中，从C1浏览器跳转到C2浏览器的用户有300人，即从C1浏览器跳转到 C2浏览器的跳转率为1/2，从C2浏览器跳转到C3浏览器的用户有300人，即从C2浏览器跳转到C3浏览器的跳转率为1，其中有150产生了购买行为，购买率为1/2，将从C1浏览器查看的概率、从C1浏览器跳转到C2浏览器的跳转率、从C2浏览器跳转到C3浏览器的跳转率与从C3浏览器查看广告后的购买率相乘，得到用户从第二路径查看A品牌的手机广告并产生购买行为的概率为1/6，即第二条路径对应的转化成功率为1/6；同理，其中首次通过C2浏览器查看A品牌的手机广告的用户的数量为300人，首次从C2浏览器查看的概率为1/3，即选择第三条路径的概率为2/3，在第三条路径中，从C2浏览器跳转到C3浏览器的用户有300人，即从C2浏览器跳转到C3浏览器的跳转率为1，其中有150产生了购买行为，购买率为1/2，将从C2浏览器查看的概率、从C2浏览器跳转到C3浏览器的跳转率与从C3浏览器查看广告后的购买率相乘，得到用户从第二路径查看A品牌的手机广告并产生购买行为的概率为1/6，即第三条路径对应的转化成功率为1/6。
将用户从第一路径查看A品牌的手机广告并产生购买行为的概率、用户从第二路径查看A品牌的手机广告并产生购买行为的概率以及用户从第三路径查看A品牌的手机广告并产生购买行为的概率求和，得到3个月内通过C1浏览器、C2浏览器和C3网页访问A品牌的手机广告后的广告转化总概率为1/3。
图3是根据本申请实施例提供的访问路径网中去除目标渠道后形成的示意图，如图3所示，假设去除C1浏览器这一广告投放渠道后，即去除用户通过C1浏览器访问广告的访问量、广告在C1浏览器投放后的转化率以及根据渠道跳转概率去掉C1浏览器后续渠道的广告转化量(视为由C1浏览器点引流得到的转化及访问量)，没有经过C1浏览器跳转影响的后续渠道不会受到影响；这样访问路径网仅剩一条路径：由C2浏览器到C3浏览器的顺序构成，相当于原访问路径网中的第三条路径，第三条路径对应的转化成功率为1/6，广告转化总概率也为1/6。
即去掉C1浏览器前，广告转化总概率为1/3；去掉C1浏览器后，广告转化总概率为1/6，去掉C1浏览器前与去掉C1浏览器后广告的转化概率之差为1/6，C1浏览器的贡献值为1/6。
本申请实施例提供的渠道的归因方法，通过采集预设时间段内通过多个渠道访问目标推广信息的访问数据，得到访问数据集合，其中，多个渠道为目标推广信息投放的渠道，访问数据集合中包括多条数据，每条数据中至少包括渠道ID，用户ID以及通过每个渠道访问目标推广信息的访问时间；对访问数据集合中的数据按照目标用户的用户ID和访问时间顺序进行聚合，生成至少包括一条路径的访问路径网，其中，路径中至少包括一个渠道；计算访问路径网中每个渠道对推广信息转化为预设指标的贡献比例。解决了相关技术中难以有效评价推广信息转化过程中每个渠道对最终成功转 化的贡献度的问题。通过将历史访问数据聚合形成访问路径网中，算出每个渠道的贡献值，进而达到了有效评价推广信息转化过程中每个渠道对最终成功转化的贡献度的效果。
需要说明的是，在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行，并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。
本申请实施例还提供了一种渠道的归因装置，需要说明的是，本申请实施例的渠道的归因装置可以用于执行本申请实施例所提供的用于渠道的归因方法。以下对本申请实施例提供的渠道的归因装置进行介绍。
图4是根据本申请实施例的渠道的归因装置的示意图。如图4所示，该装置包括：采集单元10、聚合单元20和计算单元30。
具体地，采集单元10，设置为采集预设时间段内通过多个渠道访问目标推广信息的访问数据，得到访问数据集合，其中，多个渠道为目标推广信息投放的渠道，访问数据集合中包括多条数据，每条数据中至少包括渠道ID，用户ID以及通过每个渠道访问目标推广信息的访问时间；
聚合单元20，设置为对访问数据集合中的数据按照目标用户的用户ID和访问时间顺序进行聚合，生成至少包括一条路径的访问路径网，其中，路径中至少包括一个渠道；
计算单元30，设置为计算访问路径网中每个渠道对推广信息转化为预设指标的贡献比例。
可选地，在本申请实施例提供的渠道的归因装置中，计算单元包括30：第一计算模块，设置为计算访问路径网中的每条路径对应的转化成功率并求和，得到推广信息转化总概率；第二计算模块，设置为将一个渠道设定为目标渠道，计算访问路径网去除目标渠道后的推广信息转化总概率；第三计算模块，设置为根据推广信息转化总概率与去除目标渠道后的推广信息转化总概率，计算目标渠道对推广信息转化为预设指标的贡献比例。
可选地，在本申请实施例提供的渠道的归因装置中，第一计算模块包括：获取子模块，设置为获取通过各个渠道访问目标推广信息的目标用户的数量；跳转率计算子模块，设置为根据通过各个渠道访问目标推广信息的目标用户的数量，计算访问目标推广信息时从各个渠道跳转到下一渠道的跳转率；转化率计算子模块，设置为根据选择每条路径的概率、访问目标推广信息时从各个渠道跳转到下一渠道的跳转率以及每条路径中的最后一个渠道的转化率，计算每条路径对应的转化成功率；推广信息转化 总概率计算子模块，设置为对访问路径网中每条路径对应的转化成功率进行求和，得到推广信息转化总概率。
可选地，在本申请实施例提供的渠道的归因装置中，跳转率计算子模块还包括：将通过各个渠道跳转到的下一渠道访问目标推广信息的目标用户的数量与通过各个渠道访问目标推广信息的目标用户的数量的比值，作为访问目标推广信息时从各个渠道跳转到下一渠道的跳转率。
本申请实施例提供的渠道的归因装置，通过采集单元10，采集预设时间段内通过多个渠道访问目标推广信息的访问数据，得到访问数据集合，其中，多个渠道为目标推广信息投放的渠道，访问数据集合中包括多条数据，每条数据中至少包括渠道ID，用户ID以及通过每个渠道访问目标推广信息的访问时间；聚合单元20，设置为对访问数据集合中的数据按照目标用户的用户ID和访问时间顺序进行聚合，生成至少包括一条路径的访问路径网，其中，路径中至少包括一个渠道；计算单元30，设置为计算访问路径网中每个渠道对推广信息转化为预设指标的贡献比例，解决了相关技术中难以有效评价推广信息转化过程中每个渠道对最终成功转化的贡献度的问题。通过将历史访问数据聚合形成访问路径网中，算出每个渠道的贡献值，进而达到了有效评价推广信息转化过程中每个渠道对最终成功转化的贡献度的效果。
所述渠道的归因装置包括处理器和存储器，上述采集单元10、聚合单元20和计算单元30等均作为程序单元存储在存储器中，由处理器执行存储在存储器中的上述程序单元来实现相应的功能。
处理器中包含内核，由内核去存储器中调取相应的程序单元。内核可以设置一个或以上，通过调整内核参数来有效评价推广信息转化过程中每个渠道对最终成功转化的贡献度的效果。
存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)，存储器包括至少一个存储芯片。
本发明实施例提供了一种存储介质，其上存储有程序，该程序被处理器执行时实现所述渠道的归因方法。
本发明实施例提供了一种处理器，所述处理器用于运行程序，其中，所述程序运行时执行所述渠道的归因方法。
本发明实施例提供了一种设备，设备包括处理器、存储器及存储在存储器上并可在处理器上运行的程序，处理器执行程序时实现以下步骤：采集预设时间段内通过多个渠道访问目标推广信息的访问数据，得到访问数据集合，其中，多个渠道为目标推 广信息投放的渠道，访问数据集合中包括多条数据，每条数据中至少包括渠道ID，用户ID以及通过每个渠道访问目标推广信息的访问时间；对访问数据集合中的数据按照目标用户的用户ID和访问时间顺序进行聚合，生成至少包括一条路径的访问路径网，其中，路径中至少包括一个渠道；计算访问路径网中每个渠道对推广信息转化为预设指标的贡献比例。
进一步地，通过访问路径网计算每个渠道的贡献值包括：计算访问路径网中每个渠道对推广信息转化为预设指标的贡献比例包括：计算访问路径网中的每条路径对应的转化成功率并求和，得到推广信息转化总概率；将一个渠道设定为目标渠道，计算访问路径网去除目标渠道后的推广信息转化总概率；根据推广信息转化总概率和去除目标渠道后的推广信息转化总概率，计算目标渠道对推广信息转化为预设指标的贡献比例。
进一步地，计算访问路径网中的每条路径对应的转化成功率并求和，得到推广信息转化总概率包括：获取通过各个渠道访问目标推广信息的目标用户的数量；根据通过各个渠道访问目标推广信息的目标用户的数量，计算访问目标推广信息时从各个渠道跳转到下一渠道的跳转率；根据选择每条路径的概率、访问目标推广信息时从各个渠道跳转到下一渠道的跳转率以及每条路径中的最后一个渠道的转化率，计算每条路径对应的转化成功率；对访问路径网中每条路径对应的转化成功率进行求和，得到推广信息转化总概率。
进一步地，根据通过各个渠道访问目标推广信息的目标用户的数量，计算访问目标推广信息时从各个渠道跳转到下一渠道的跳转率包括：将通过各个渠道跳转到的下一渠道访问目标推广信息的目标用户的数量与通过各个渠道访问目标推广信息的目标用户的数量的比值，作为访问目标推广信息时从各个渠道跳转到下一渠道的跳转率。本文中的设备可以是服务器、PC、PAD、手机等。
本申请还提供了一种计算机程序产品，当在数据处理设备上执行时，适于执行初始化有如下方法步骤的程序：采集预设时间段内通过多个渠道访问目标推广信息的访问数据，得到访问数据集合，其中，多个渠道为目标推广信息投放的渠道，访问数据集合中包括多条数据，每条数据中至少包括渠道ID，用户ID以及通过每个渠道访问目标推广信息的访问时间；对访问数据集合中的数据按照目标用户的用户ID和访问时间顺序进行聚合，生成至少包括一条路径的访问路径网，其中，路径中至少包括一个渠道；计算访问路径网中每个渠道对推广信息转化为预设指标的贡献比例。
进一步地，通过访问路径网计算每个渠道的贡献值包括：计算访问路径网中每个渠道对推广信息转化为预设指标的贡献比例包括：计算访问路径网中的每条路径对应的转化成功率并求和，得到推广信息转化总概率；将一个渠道设定为目标渠道，计算 访问路径网去除目标渠道后的推广信息转化总概率；根据推广信息转化总概率和去除目标渠道后的推广信息转化总概率，计算目标渠道对推广信息转化为预设指标的贡献比例。
进一步地，计算访问路径网中的每条路径对应的转化成功率并求和，得到推广信息转化总概率包括：获取通过各个渠道访问目标推广信息的目标用户的数量；根据通过各个渠道访问目标推广信息的目标用户的数量，计算访问目标推广信息时从各个渠道跳转到下一渠道的跳转率；根据选择每条路径的概率、访问目标推广信息时从各个渠道跳转到下一渠道的跳转率以及每条路径中的最后一个渠道的转化率，计算每条路径对应的转化成功率；对访问路径网中每条路径对应的转化成功率进行求和，得到推广信息转化总概率。
进一步地，根据通过各个渠道访问目标推广信息的目标用户的数量，计算访问目标推广信息时从各个渠道跳转到下一渠道的跳转率包括：将通过各个渠道跳转到的下一渠道访问目标推广信息的目标用户的数量与通过各个渠道访问目标推广信息的目标用户的数量的比值，作为访问目标推广信息时从各个渠道跳转到下一渠道的跳转率。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算 机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。存储器是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括要素的过程、方法、商品或者设备中还存在另外的相同要素。
本领域技术人员应明白，本申请的实施例可提供为方法、系统或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
以上仅为本申请的实施例而已，并不用于限制本申请。对于本领域技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本申请的权利要求范围之内。

Claims (10)

  1. 一种渠道的归因方法，包括：
    采集预设时间段内通过多个渠道访问目标推广信息的访问数据，得到访问数据集合，其中，所述多个渠道为所述目标推广信息投放的渠道，所述访问数据集合中包括多条数据，每条数据中至少包括渠道ID、用户ID以及通过每个渠道访问所述目标推广信息的访问时间；
    对所述访问数据集合中的数据按照目标用户的用户ID和访问时间顺序进行聚合，生成至少包括一条路径的访问路径网，其中，所述路径中至少包括一个渠道；
    计算所述访问路径网中每个渠道对推广信息转化为预设指标的贡献比例。
  2. 根据权利要求1所述的方法，其中，计算所述访问路径网中每个渠道对推广信息转化为预设指标的贡献比例包括：
    计算所述访问路径网中的每条路径对应的转化成功率并求和，得到推广信息转化总概率；
    将一个渠道设定为目标渠道，计算所述访问路径网去除所述目标渠道后的推广信息转化总概率；
    根据所述推广信息转化总概率和去除所述目标渠道后的推广信息转化总概率，计算所述目标渠道对推广信息转化为预设指标的贡献比例。
  3. 根据权利要求2所述的方法，其中，计算所述访问路径网中的每条路径对应的转化成功率并求和，得到推广信息转化总概率包括：
    获取通过各个渠道访问目标推广信息的目标用户的数量；
    根据通过各个渠道访问目标推广信息的目标用户的数量，计算访问目标推广信息时从各个渠道跳转到下一渠道的跳转率；
    根据选择每条路径的概率、访问目标推广信息时从各个渠道跳转到下一渠道的跳转率以及每条路径中的最后一个渠道的转化率，计算每条路径对应的转化成功率；
    对所述访问路径网中每条路径对应的转化成功率进行求和，得到推广信息转化总概率。
  4. 根据权利要求3所述的方法，其中，根据通过各个渠道访问目标推广信息的目标用户的数量，计算访问目标推广信息时从各个渠道跳转到下一渠道的跳转率包括：
    将通过各个渠道跳转到的下一渠道访问目标推广信息的目标用户的数量与通过各个渠道访问目标推广信息的目标用户的数量的比值，作为访问目标推广信息时从各个渠道跳转到下一渠道的跳转率。
  5. 一种渠道的归因装置，包括：
    采集单元，设置为采集预设时间段内通过多个渠道访问目标推广信息的访问数据，得到访问数据集合，其中，所述多个渠道为所述目标推广信息投放的渠道，所述访问数据集合中包括多条数据，每条数据中至少包括渠道ID，用户ID以及通过每个渠道访问所述目标推广信息的访问时间；
    聚合单元，设置为对所述访问数据集合中的数据按照目标用户的用户ID和访问时间顺序进行聚合，生成至少包括一条路径的访问路径网，其中，所述路径中至少包括一个渠道；
    计算单元，设置为计算所述访问路径网中每个渠道对推广信息转化为预设指标的贡献比例。
  6. 根据权利要求5所述的装置，其中，所述计算单元包括：
    第一计算模块，设置为计算所述访问路径网中的每条路径对应的转化成功率并求和，得到推广信息转化总概率；
    第二计算模块，设置为将一个渠道设定为目标渠道，计算所述访问路径网去除所述目标渠道后的推广信息转化总概率；
    第三计算模块，设置为根据所述推广信息转化总概率与去除所述目标渠道后的推广信息转化总概率，计算所述目标渠道对推广信息转化为预设指标的贡献比例。
  7. 根据权利要求6所述的装置，其中，所述第一计算模块包括：
    获取子模块，设置为获取通过各个渠道访问目标推广信息的目标用户的数量；
    跳转率计算子模块，设置为根据通过各个渠道访问目标推广信息的目标用户的数量，计算访问目标推广信息时从各个渠道跳转到下一渠道的跳转率；
    转化率计算子模块，设置为根据选择每条路径的概率、访问目标推广信息时从各个渠道跳转到下一渠道的跳转率以及每条路径中的最后一个渠道的转化率，计算每条路径对应的转化成功率；
    推广信息转化总概率计算子模块，设置为对所述访问路径网中每条路径对应 的转化成功率进行求和，得到推广信息转化总概率。
  8. 根据权利要求7所述的装置，其中，所述跳转率计算子模块还包括：
    将通过各个渠道跳转到的下一渠道访问目标推广信息的目标用户的数量与通过各个渠道访问目标推广信息的目标用户的数量的比值，作为访问目标推广信息时从各个渠道跳转到下一渠道的跳转率。
  9. 一种存储介质，其中，所述存储介质包括存储的程序，其中，所述程序执行权利要求1至4中任意一项所述的渠道的归因方法。
  10. 一种处理器，其中，所述处理器用于运行程序，其中，所述程序运行时执行权利要求1至4中任意一项所述的渠道的归因方法。
PCT/CN2019/073695 2018-02-23 2019-01-29 渠道的归因方法和装置 WO2019161731A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810155682.1A CN110189152A (zh) 2018-02-23 2018-02-23 渠道的归因方法和装置
CN201810155682.1 2018-02-23

Publications (1)

Publication Number Publication Date
WO2019161731A1 true WO2019161731A1 (zh) 2019-08-29

Family

ID=67687438

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/073695 WO2019161731A1 (zh) 2018-02-23 2019-01-29 渠道的归因方法和装置

Country Status (2)

Country Link
CN (1) CN110189152A (zh)
WO (1) WO2019161731A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110704779A (zh) * 2019-09-27 2020-01-17 杭州迪普科技股份有限公司 一种网站页面访问合规性检测方法、装置及设备

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112215636B (zh) * 2020-01-21 2021-11-19 华为技术有限公司 一种广告归因方法及设备
CN111582934A (zh) * 2020-05-07 2020-08-25 北京点众科技股份有限公司 确定购买电子书的选项贡献度的方法、终端和存储介质
CN111784380B (zh) * 2020-06-05 2024-05-24 北京沃东天骏信息技术有限公司 广告投放归因方法和装置
CN112035749A (zh) * 2020-09-04 2020-12-04 贝壳技术有限公司 用户行为特征分析方法、推荐方法及相应装置
CN112200618B (zh) * 2020-10-29 2022-05-17 度小满科技(北京)有限公司 消息渠道归因方法、装置及系统
CN112529634A (zh) * 2020-12-18 2021-03-19 恩亿科(北京)数据科技有限公司 基于大数据的转化链路分析方法、系统和计算机设备
CN113095892B (zh) * 2021-04-30 2024-05-31 北京大米科技有限公司 一种数据处理方法及装置
CN113256335B (zh) * 2021-05-27 2021-10-12 腾讯科技（深圳）有限公司 数据筛选方法、多媒体数据的投放效果预测方法及装置
CN114693361A (zh) * 2022-03-31 2022-07-01 北京明略软件系统有限公司 确定渠道的贡献度的方法、装置、设备和存储介质
CN114970762A (zh) * 2022-06-22 2022-08-30 阿维塔科技(重庆)有限公司 一种数据处理方法、装置、设备和计算机存储介质
CN116137004B (zh) * 2023-04-19 2023-07-07 江西时刻互动科技股份有限公司 广告投放效果的归因方法、系统及计算机

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150046249A1 (en) * 2012-03-19 2015-02-12 Beijing Gridsum Technology Co., Ltd. Method and system for measuring web advertising effect based on multiple-contact attribution model
CN104657882A (zh) * 2015-02-06 2015-05-27 百度在线网络技术（北京）有限公司 推广效果数据的获取方法及装置
CN107343047A (zh) * 2017-07-06 2017-11-10 北京奇虎科技有限公司 应用推广系统及方法
CN107438138A (zh) * 2017-09-12 2017-12-05 中国联合网络通信集团有限公司 一种渠道触达方式的推荐方法及装置
CN107481062A (zh) * 2017-08-21 2017-12-15 小草数语（北京）科技有限公司 广告投放预算的分配方法和装置
CN107563781A (zh) * 2016-06-30 2018-01-09 阿里巴巴集团控股有限公司 一种信息投放效果归因方法及装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130035975A1 (en) * 2011-08-05 2013-02-07 David Cavander Cross-media attribution model for allocation of marketing resources
US8788339B2 (en) * 2011-05-27 2014-07-22 Google Inc. Multiple attribution models with return on ad spend

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150046249A1 (en) * 2012-03-19 2015-02-12 Beijing Gridsum Technology Co., Ltd. Method and system for measuring web advertising effect based on multiple-contact attribution model
CN104657882A (zh) * 2015-02-06 2015-05-27 百度在线网络技术（北京）有限公司 推广效果数据的获取方法及装置
CN107563781A (zh) * 2016-06-30 2018-01-09 阿里巴巴集团控股有限公司 一种信息投放效果归因方法及装置
CN107343047A (zh) * 2017-07-06 2017-11-10 北京奇虎科技有限公司 应用推广系统及方法
CN107481062A (zh) * 2017-08-21 2017-12-15 小草数语（北京）科技有限公司 广告投放预算的分配方法和装置
CN107438138A (zh) * 2017-09-12 2017-12-05 中国联合网络通信集团有限公司 一种渠道触达方式的推荐方法及装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110704779A (zh) * 2019-09-27 2020-01-17 杭州迪普科技股份有限公司 一种网站页面访问合规性检测方法、装置及设备

Also Published As

Publication number Publication date
CN110189152A (zh) 2019-08-30

Similar Documents

Publication Publication Date Title
WO2019161731A1 (zh) 渠道的归因方法和装置
JP6110943B2 (ja) 広告課金方法および広告課金装置
JP7105700B2 (ja) サービス対象のための時分割推薦方法及び装置
CN106407210B (zh) 一种业务对象的展示方法和装置
US8732015B1 (en) Social media pricing engine
US10776816B2 (en) System and method for building a targeted audience for an online advertising campaign
US20080313040A1 (en) Content distribution system including cost-per-engagement based advertising
WO2018223672A1 (zh) 数据处理方法及装置
US20170061515A1 (en) Systems and methods for setting allocations and prices for content in an online marketplace
US20140195339A1 (en) Media Mix Modeling Tool
Gohad et al. Cloud pricing models: A survey and position paper
KR102097045B1 (ko) 사용자의 특성을 반영하여 상품을 추천하는 방법 및 장치
US20150039418A1 (en) Content item distribution based on user interactions
WO2013119987A1 (en) Compensation systems and methods for a network marketing organization
WO2019161718A1 (zh) 归因方法和装置
CN111612560A (zh) 用于促销对象的推荐方法、系统、存储介质及电子设备
CN115775163A (zh) 一种基于大数据的程序化广告投放方法、设备及介质
KR101274759B1 (ko) 광고 시스템 및 광고 성과 평가 방법
CN110533479A (zh) 一种标识分配方法、装置及电子设备
JP5153926B1 (ja) 出稿リソース最適化システム、出稿リソース最適化方法、および出稿リソース最適化プログラム
WO2011014422A2 (en) System and method for generating a valuation of online users and websites from user activities
CN113191830A (zh) 资源分配方法、装置、设备及计算机可读介质
CN104331823B (zh) 确定发布信息中关键词保留价格的方法及装置
JP6183955B2 (ja) データセンター装置
US20150195593A1 (en) Content direction based on cumulative user cost

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19757495

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19757495

Country of ref document: EP

Kind code of ref document: A1