CN113393270B - Determination method and device for advertisement point contribution value, electronic equipment and storage medium - Google Patents

Determination method and device for advertisement point contribution value, electronic equipment and storage medium Download PDF

Info

Publication number
CN113393270B
CN113393270B CN202110653864.3A CN202110653864A CN113393270B CN 113393270 B CN113393270 B CN 113393270B CN 202110653864 A CN202110653864 A CN 202110653864A CN 113393270 B CN113393270 B CN 113393270B
Authority
CN
China
Prior art keywords
exposure
advertisement
crowd
training data
contribution
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110653864.3A
Other languages
Chinese (zh)
Other versions
CN113393270A (en
Inventor
王同乐
周星杰
王硕
李霞
孙泽懿
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Minglue Artificial Intelligence Group Co Ltd
Original Assignee
Shanghai Minglue Artificial Intelligence Group Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Minglue Artificial Intelligence Group Co Ltd filed Critical Shanghai Minglue Artificial Intelligence Group Co Ltd
Priority to CN202110653864.3A priority Critical patent/CN113393270B/en
Publication of CN113393270A publication Critical patent/CN113393270A/en
Application granted granted Critical
Publication of CN113393270B publication Critical patent/CN113393270B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0242—Determining effectiveness of advertisements
    • G06Q30/0245—Surveys

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)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application provides a method and a device for determining advertisement point position contribution values, electronic equipment and a storage medium, wherein the method comprises the following steps: obtaining a plurality of crowd packs, wherein each crowd pack comprises a plurality of advertisement points, each advertisement point corresponds to a plurality of exposure records under a plurality of statistical dimensions, and the crowd packs are sample data for evaluating contribution values of the advertisement points; constructing a plurality of feature vectors by using the exposure records and the statistical dimension; calculating each feature vector by using a first scheme to obtain first training data; determining second training data by using the converted number of people in each crowd pack and the total exposure number of the corresponding crowd pack, wherein the converted number of people is the number of the initial users converted into target users through advertisement exposure; and determining a target model according to the training model, the first training data and the second training data, wherein the target model is used for obtaining the contribution value of each advertisement point. The method and the device solve the problem that the contribution value of each advertisement point cannot be acquired well in the prior art.

Description

Determination method and device for advertisement point contribution value, electronic equipment and storage medium
Technical Field
The present disclosure relates to the field of data processing, and in particular, to a method and apparatus for determining an advertisement point contribution value, an electronic device, and a storage medium.
Background
Advertisement attribution refers to a quantitative evaluation behavior of an advertiser to track the impression on each advertisement spot in reverse after obtaining the impression. The traceability of the user browsing behavior of the internet lays the foundation for the realization of advertisement attribution. Since the birth of the mobile internet, marketing researchers have been researching how to realize matching and series connection of behaviors of a specific user on a plurality of platforms through tracking interactive behavior data such as exposure, searching, purchasing and the like so as to solve the long-standing advertisement putting effect evaluation and investment optimization problems which plague people.
In the related art, a multi-point attribution model is proposed to evaluate advertisement delivery effects, the purpose of which is to evaluate contributions at each advertisement point in the batch of data based on the recovered delivery data. The common practice is to use the whole data to carry out Markov time series modeling on all the points and estimate the contribution of a global point; and then discarding data related to the point to be estimated from the whole data, and estimating a contribution value again by using Markov modeling, wherein the difference value of the front contribution value and the rear contribution value is the contribution of the point. However, this method can reconstruct the time sequence only when the user identifier of each advertisement exposure record can be obtained, but is limited by the problems of "walled garden" technology of the internet, privacy policy, incomplete advertisement data acquisition, etc., and the advertisement platform has the situation that any information related to the user cannot be returned.
Therefore, the application range of the multipoint attribution model in the related technology is narrower, and the corresponding contribution value of each advertisement point position can not be better obtained, so that the difficulty of investment optimization of advertisers is solved.
Disclosure of Invention
The application provides a method and a device for determining contribution values of advertisement points, a storage medium and electronic equipment, and aims to at least solve the problem that the application range of a multipoint attribution model is narrow and corresponding contribution values of all advertisement points cannot be acquired well in the related technology.
According to an aspect of the embodiments of the present application, there is provided a method for determining a contribution value of an advertisement spot, including: obtaining a plurality of crowd packs, wherein each crowd pack comprises a plurality of advertisement points, each advertisement point corresponds to a plurality of exposure records under a plurality of statistical dimensions, and the crowd packs are sample data for evaluating contribution values of the advertisement points; constructing a plurality of feature vectors by using the exposure records and the statistical dimension; calculating each feature vector by using a first scheme to obtain first training data; determining second training data by using the converted number of people in each crowd pack and the total exposure number of the corresponding crowd pack, wherein the converted number of people is the number of initial users converted into target users through advertisement exposure; and determining a target model according to the training model, the first training data and the second training data, wherein the target model is used for obtaining the contribution value of each advertisement point.
According to another aspect of the embodiments of the present application, there is also provided a device for determining a contribution value of an advertisement spot, where the device includes: the first acquisition unit is used for acquiring a plurality of crowd packs, wherein each crowd pack comprises a plurality of advertisement points, each advertisement point corresponds to a plurality of exposure records under a plurality of statistical dimensions, and the crowd packs are sample data for evaluating contribution values of the advertisement points; a construction unit for constructing a plurality of feature vectors using the exposure record and the statistical dimension; the first calculation unit is used for calculating each characteristic vector by utilizing a first scheme to obtain first training data; the first determining unit is used for determining second training data by utilizing the converted number of people in each crowd pack and the total exposure number of the corresponding crowd pack, wherein the converted number of people is the number of the original users converted into the target users through advertisement exposure; and the second determining unit is used for determining a target model according to the training model, the first training data and the second training data, wherein the target model is used for obtaining the contribution value of each advertisement point position.
Optionally, the second determining unit obtains a contribution value of each advertisement point to be evaluated as follows: the acquisition module is used for acquiring advertisement points to be evaluated; and the determining module is used for determining the contribution value of the advertisement point to be evaluated according to the advertisement point to be evaluated, the first training data and the target model.
Optionally, the determining module includes: the first input subunit is used for inputting the first training data into the target model to obtain contribution values of all points in each crowd pack, wherein the first training data is first training data of the current crowd pack; the acquisition subunit is used for acquiring first exposure records under a plurality of statistical dimensions corresponding to the advertisement points to be evaluated; a first subtracting subunit, configured to subtract the first exposure record from all exposure records of the current crowd pack to obtain a second exposure record; a determining subunit, configured to determine a corresponding reference feature vector according to the second exposure record; a calculation subunit, configured to calculate the reference feature vector by using the first scheme, so as to obtain third training data; a second input subunit, configured to input the third training data into the target model, to obtain contribution values of other advertisement points except the advertisement point to be evaluated; and a second subtracting subunit, configured to subtract the contribution values of the advertisement points except for the advertisement point to be evaluated from the contribution values of all points to obtain the contribution value of the advertisement point to be evaluated.
Optionally, the calculation formula of the first calculation unit is as follows:
wherein f i Representing an m-dimensional feature vector, wherein i is more than or equal to 1 and less than or equal to the total number of crowd-packs,representing the corresponding exposure record on the t-th dimension, wherein t is more than or equal to 0 and less than or equal to M, and all the value sets of the first statistical dimension are M 0 ，M 0 Comprises m 0 The number of the exposure records and all the valued sets of the second statistical dimension are M 1 ，M 1 Comprises m 1 The number of the exposure records and all the value sets of the third statistical dimension are M 2 ，M 2 Comprises m 2 The number of the exposure records and all the value sets of the fourth statistical dimension are M 3 ，M 3 Comprises m 3 The number of exposure records, and the union set of all values is recorded as M=M 0 ∪M 1 ∪M 2 ∪M 3 ，m＝m 0 +m 1 +m 2 +m 3 ，m t T-th item of set M, I (M t ) Represents m t A field corresponding to this dimension, r i,j The j-th exposure record representing the i-th crowd-sourced, r i,j (x) Watch (watch)Show exposure record r i，j Is represented by x field, imp represents exposure record, r i,j (imp) represents the value of the field corresponding to the exposure record imp, K i ＝k i,1 +...+k i,z +...+k i, total advertisement point position Indicating that the ith crowd-pack has the Kth in total i Stripe exposure record, k i，z The number of exposure records at the z-th point is represented, and the I-function and sign-function are defined as follows:
optionally, the first determining unit calculates according to the following formula:
wherein,representing the conversion rate, i represents the crowd-sourced number, i is more than or equal to 1 and less than or equal to the crowd-sourced total number, gp imp Representing the total exposure number of each of said crowd-bags, < >>Representing the number of transformants in each of the crowd-packs.
Optionally, the apparatus further comprises: the second obtaining unit is used for determining a target model according to the training model, the first training data and the second training data, wherein the target model is used for obtaining the contribution value of each advertisement point location and then obtaining the actual contribution value corresponding to each advertisement point location; the second calculation unit is used for calculating the correlation between the actual contribution value and the contribution value by using a second scheme to obtain a calculation result; and a third determining unit, configured to determine that the contribution value meets an evaluation condition when the calculation result is greater than a preset threshold, where the evaluation condition is used to indicate that the accuracy of the contribution value is greater than an accuracy threshold.
Optionally, the calculation result is obtained in the second calculation unit according to the following formula:
wherein y is i The actual contribution value is represented and,representing a contribution value->Representing y i Average value of R 2 ∈[0,1]The total quantity of crowd packs is more than or equal to 1 and less than or equal to 1.
According to yet another aspect of the embodiments of the present application, there is also provided an electronic device including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory complete communication with each other through the communication bus; wherein the memory is used for storing a computer program; a processor for performing the method steps of any of the embodiments described above by running the computer program stored on the memory.
According to a further aspect of the embodiments of the present application, there is also provided a computer-readable storage medium having stored therein a computer program, wherein the computer program is arranged to perform the method steps of any of the embodiments described above when run.
In the embodiment of the application, a plurality of crowd packs are obtained, wherein each crowd pack comprises a plurality of advertisement points, each advertisement point corresponds to a plurality of exposure records in a plurality of statistical dimensions, and the crowd packs are sample data for evaluating contribution values of the advertisement points; constructing a plurality of feature vectors by using exposure records, wherein the number of the exposure records is the same as the number of the feature vectors; calculating each feature vector by using a first scheme to obtain first training data; determining second training data by using the converted number of people in each crowd pack and the total exposure number of the corresponding crowd pack, wherein the converted number of people is the number of the initial users converted into target users through advertisement exposure; and determining the contribution value of each advertisement point position according to the training model, the first training data and the second training data. According to the embodiment of the application, the contribution value of each advertisement point position can be obtained by only giving out the exposed statistical dimension output according to the exposure record of each advertisement point position in the obtained crowd pack without specific individual level, the method solves the problem of presuming the point position contribution of finer granularity from the crowd pack conversion rate of coarser granularity, has very high application value, achieves the technical effect of accurately presuming the contribution value of each advertisement point position, and further solves the problem that the corresponding contribution value of each advertisement point position cannot be obtained well due to the narrow application range of a multi-point attribution model in the related technology.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, and it will be obvious to a person skilled in the art that other drawings can be obtained from these drawings without inventive effort.
FIG. 1 is a schematic diagram of a hardware environment of an alternative method of determining advertisement spot contribution values, according to an embodiment of the present invention;
FIG. 2 is a flow chart of an alternative method of determining ad spot contribution values according to an embodiment of the application;
FIG. 3 is a block diagram of an alternative ad spot contribution value determination apparatus according to an embodiment of the present application;
fig. 4 is a block diagram of an alternative electronic device according to an embodiment of the present application.
Detailed Description
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The purpose of the multi-point attribution model is to evaluate the contribution at each advertisement point in the batch of data based on the reclaimed impression data. The common practice is to use the whole data to carry out Markov time series modeling on all the points and estimate the contribution of a global point; and then discarding data related to the point to be estimated from the whole data, and estimating a contribution value again by using Markov modeling, wherein the difference value of the front contribution value and the rear contribution value is the contribution of the point. However, the method can reconstruct the time sequence only when the user identification of each advertisement exposure record can be obtained, is limited by laws and regulations such as privacy protection in certain scenes, cannot return any information related to the user, and can only provide exposure record statistical results based on crowd packages. Therefore, we have devised a method based on crowd sourcing statistics to infer contributions at each advertisement spot. The method does not need exposure data of a user level, so that the method is more suitable for the commercial environment of current advertisement delivery and data recovery, and has wider applicability.
At present, due to conditions such as attribution investment cost, time efficiency, data acquisition difficulty and the like, three typical attribution practice methods in the market mainly exist: AB Test (A/B Test), multi-Point attribution model MTA (Multiple Touchpoint Attribution), and marketing combination model MMM (Marketing Mix Model). The AB test method is very widely used, and it observes the effect of a key variable on the final effect by controlling the key variable setting control group and experimental group. The AB test has the advantages of low implementation cost, quick aging and good universality, but has the biggest disadvantages of being incapable of simultaneously analyzing a plurality of factors, and having poor data recovery efficiency, statistical deviation and the like. The multi-point attribution model MTA refers to achieving a desired advertising effect by performing a specific set of operations, and then inversely analyzing the contribution of each operation to the effect. Multiple models exist for multi-point advertising attribution, where first click attribution and final click attribution are more widely used because of the ease of measurement and use, and the relative detection tools are more sophisticated. However, the defects of the two methods are obvious, because the contact weight distribution of the two methods is relatively broken, the contribution weight of each channel cannot be carefully measured, and the optimization of the delivery is difficult to finely guide. MMM considers the total sales over a period of time to be equal to the sum of the base sales (sales that would occur without advertising, i.e., natural sales) and the incremental sales (sales due to advertising). Based on this logic, MMM opens a "black box" of marketing investment input and sales output in combination with measurement data, time series, multiple regression. The MMM has the advantages that after the model is modeled through historical data, the model can be continuously monitored according to time, new data can be continuously collected, and the relation between the target index calculated through simulation and the actual market performance is observed, so that the effectiveness of the model is ensured. But its drawbacks are also evident, too slow, inflexible, and insufficient details of the measurement. In summary, the common disadvantage of the above three methods is that the point location contribution evaluation problem under the condition of data missing can not be well solved.
According to one aspect of the embodiment of the application, a method for determining a contribution value of an advertisement point is provided. Alternatively, in this embodiment, the method for determining the advertisement spot contribution value may be applied to the hardware environment shown in fig. 1. As shown in fig. 1, the terminal 102 may include a memory 104, a processor 106, and a display 108 (optional components). The terminal 102 may be communicatively coupled to a server 112 via a network 110, the server 112 being operable to provide services (e.g., gaming services, application services, etc.) to the terminal or to clients installed on the terminal, and a database 114 may be provided on the server 112 or independent of the server 112 for providing data storage services to the server 112. In addition, a processing engine 116 may be run in the server 112, which processing engine 116 may be used to perform the steps performed by the server 112.
Alternatively, the terminal 102 may be, but is not limited to, a terminal capable of calculating data, such as a mobile terminal (e.g., a mobile phone, a tablet computer), a notebook computer, a PC (Personal Computer ) or the like, which may include, but is not limited to, a wireless network or a wired network. Wherein the wireless network comprises: bluetooth, WIFI (Wireless Fidelity ) and other networks that enable wireless communications. The wired network may include, but is not limited to: wide area network, metropolitan area network, local area network. The server 112 may include, but is not limited to, any hardware device that can perform calculations.
In addition, in this embodiment, the method for determining the contribution value of the advertisement point may be applied to, but not limited to, an independent processing device with a relatively high processing capability, without performing data interaction. For example, the processing device may be, but is not limited to being, a more processing-capable terminal device, i.e., the various operations of the above-described method of determining the advertisement spot contribution value may be integrated into a single processing device. The above is merely an example, and is not limited in any way in the present embodiment.
Alternatively, in this embodiment, the method for determining the contribution value of the advertisement spot may be performed by the server 112, may be performed by the terminal 102, or may be performed by both the server 112 and the terminal 102. The method for determining the contribution value of the advertisement point performed by the terminal 102 in the embodiment of the present application may also be performed by a client installed thereon.
Taking a server as an example, fig. 2 is a schematic flow chart of an alternative method for determining a contribution value of an advertisement point, as shown in fig. 2, where the flow of the method may include the following steps:
step S201, a plurality of crowd-packs are obtained, wherein each crowd-pack includes a plurality of advertisement points, each advertisement point corresponds to a plurality of exposure records in a plurality of statistical dimensions, and the crowd-packs are sample data for evaluating contribution values of the advertisement points.
Optionally, the embodiment of the present application first obtains a data set, where the data set is composed of a plurality of crowd packs, each crowd pack includes a plurality of advertisement points, and each advertisement point includes exposure record data of a plurality of statistical dimensions. Each crowd-sourced has a conversion index and each point has a contribution index.
Wherein, the conversion rate refers to the percentage of the number of converted people to the total number of people. For example, in a video broadcasting platform, by playing an advertisement on the platform, after a user clicks on the advertisement and successfully places a commodity, the user is called a conversion crowd, and then, how many users click on the platform to place a commodity can be counted, and then, the user who is successfully converted/the total user who views the video=conversion rate.
The point location refers to the advertisement putting position, such as a position where the video platform is played to open a screen, b position where the patch is played before the advertisement of the video platform, c position where the video platform is played to pause, etc. In the case of placing advertisements at these points, the advertisements may be touched by a plurality of users, for example, by touching 100 users (100 people in a crowd pack), and at this time, the exposure data generated by the 100 people at these 3 points is obtained, and more specifically, in the embodiment of the present application, a plurality of statistical dimensions may be defined, for example, a first statistical dimension: advertisement exposure equipment, second statistical dimension: advertisement exposure behavior, third statistical dimension: media platform where advertisement exposure is located, fourth statistical dimension: the area where the advertisement is exposed can be obtained by the exposure record under each statistical dimension.
The contribution value, as the name implies, is that the user who browses the advertisement currently is converted into the user who places an order of commodity, so that the advertisement point browsed by the user can correspond to one contribution value, and therefore, the contribution value of the advertisement point is as follows: the conversion number of each advertisement point is the percentage of the total number of the current point.
Specifically, as shown in the exposure table in table 1, one row in table 1 represents one exposure record, and groups represent a total of 5000 groups of crowd-sourced groups; tpid represents the ad spot, each crowd pack contains 15 tpid (tpid discontinuity, 467 through 514); each tpid is according to a first statistical dimension: the different values of the device (device where the exposure is located, typically a mobile phone (denoted by 1 in table 1) or a notebook (denoted by 2 in table 1)), the second statistical dimension action (exposure behavior, typically a front patch (denoted by 531211 in table 1), pause (denoted by 531214 in table 1)), the third statistical dimension media (medium where the exposure is located, typically a platform such as aaa (denoted by 467 in table 1), bbb (denoted by 359 in table 1), the fourth statistical dimension mark (region where the exposure is located, typically a city (denoted by 1001 in table 1), a city (denoted by 10 in table 1), etc.), include a number of exposure records (imp indicates how many exposure records are in the case of the current tpid being valued by the parameters of current device, action, media, market).
It should be noted that one line in table 1 is actually an exposure record at a point in a crowd-sourced, e.g. group of the first line 1 The exposure record for the front patch position of the 467 media platform with the advertisement spot 467 in the device 1 is 15, and the area where the advertisement exposure is located is city a.
TABLE 1
Step S202, constructing a plurality of feature vectors by using the exposure records and the statistical dimension.
Optionally, a plurality of feature vectors are constructed for a plurality of statistical dimensions device (i.e. first statistical dimension), action (i.e. second statistical dimension), media (i.e. third statistical dimension), mark (i.e. fourth statistical dimension) and a plurality of advertisement points in table 1, wherein any value in each statistical dimension can correspondingly generate a feature vector.
Step S203, calculating each feature vector by using the first scheme to obtain first training data.
Optionally, in an embodiment of the present application, group is packaged for each group of people i We can construct an m-dimensional vector using f i Specifically, the following formula (1) may be used to calculate each feature vector, and all the obtained values may be collected to obtain the first training data. Wherein the first training data is a set of feature vectors for all exposures in each crowd-sourced.
The calculation formula is as follows:
wherein f i Representing an m-dimensional feature vector, wherein i is more than or equal to 1 and less than or equal to the total number of crowd packs, and f is the 0 th dimension i 0 Represented in set M 0 The first element device in (a) 0 The total number of exposures on such an apparatus, 1 st dimension f i 1 Is shown in the device 1 Total exposure number on the apparatus, and so on, mth 0 Dimension(s)Is indicated at->Total exposure quantity on equipment, last dimension m-1 dimension tableThe last element shown in the M set +.>Total number of exposures in the area, therefore, f i t Representing the corresponding exposure record on the t-th dimension, wherein t is more than or equal to 0 and less than or equal to M, and all the value sets of the first statistical dimension are M 0 ，/>M 0 Comprises m 0 The number of the exposure records and all the valued sets of the second statistical dimension are M 1 ，/>M 1 Comprises m 1 The number of the exposure records and all the value sets of the third statistical dimension are M 2 ，/>M 2 Comprises m 2 The number of the exposure records and all the value sets of the fourth statistical dimension are M 3 ，/>M 3 Comprises m 3 The number of exposure records, and the union set of all values is recorded as M=M 0 ∪M 1 ∪M 2 ∪M 3 ，m＝m 0 +m 1 +m 2 +m 3 ，m t T-th item of set M, I (M t ) Represents m t A field corresponding to this dimension, r i,j The j-th exposure record representing the i-th crowd-sourced, r i,j (x) Representing exposure record r i，j Is represented by x field, imp represents exposure record, r i,j (imp) represents the value of the field corresponding to the exposure record imp, K i ＝k i,1 +...+k i,z +...+k i, total advertisement point position Indicating that the ith crowd-pack has the Kth in total i Stripe exposure record, k i，z The number of exposure records at the z-th point is represented, and the I-function and sign-function are defined as follows:
step S204, determining second training data by using the converted number of people in each crowd-sourced and the total exposure number of the corresponding crowd-sourced, wherein the converted number of people is the number of the initial users converted into the target users through advertisement exposure.
Alternatively, in the embodiment of the present application, a conversion index related to the number of exposures may be defined:
wherein,representing the newly defined conversion rate related to exposure, i represents the crowd-sourced number, i is more than or equal to 1 and less than or equal to the crowd-sourced total number, and +.>Represents the converted exposure, gp imp Representing the total exposure number of the crowd-sourced +.>Representing the number of transformants in the crowd-sourced. />I.e. each transformed person was transformed by 1 exposure. But the exposure to each transformed individual is 1 or more, +.>The value is about->So set->
According to the above formula (3), the conversion index corresponding to each crowd pack, that is, the second training data, can be obtained.
Step S205, determining a target model according to the training model, the first training data and the second training data, wherein the target model is used for obtaining the contribution value of each advertisement point.
Optionally, in an embodiment of the present application, a gradient boost decision tree (Gradient Boosting Decision Tree, GBDT) may be selected as the training model to calculate the first training data and the second training data, and more specifically, generate the training data set from the first training data and the second training dataThe total number of the crowd packs selected is 5000, i is more than or equal to 1 and less than or equal to 5000, so that the data in the training data set are input into a training model to train the relation between the feature vector and the conversion rate, a model obtained after training is further obtained, and the trained model is recorded as a target model: and gModel, wherein the contribution value of each advertisement point can be obtained by using gModel, so that the target model can be directly taken for use in the subsequent business operation, and the intermediate training process is omitted.
In the embodiment of the application, a plurality of crowd packs are obtained, wherein each crowd pack comprises a plurality of advertisement points, each advertisement point corresponds to a plurality of exposure records in a plurality of statistical dimensions, and the crowd packs are sample data for evaluating contribution values of the advertisement points; constructing a plurality of feature vectors by using exposure records, wherein the number of the exposure records is the same as the number of the feature vectors; calculating each feature vector by using a first scheme to obtain first training data; determining second training data by using the converted number of people in each crowd pack and the total exposure number of the corresponding crowd pack, wherein the converted number of people is the number of the initial users converted into target users through advertisement exposure; and determining the contribution value of each advertisement point position according to the training model, the first training data and the second training data. According to the embodiment of the application, the contribution value of each advertisement point position can be obtained by only giving out the exposed statistical dimension output according to the exposure record of each advertisement point position in the obtained crowd pack without specific individual level, the method solves the problem of presuming the point position contribution of finer granularity from the crowd pack conversion rate of coarser granularity, has very high application value, achieves the technical effect of accurately presuming the contribution value of each advertisement point position, and further solves the problem that the corresponding contribution value of each advertisement point position cannot be obtained well due to the narrow application range of a multi-point attribution model in the related technology.
As an alternative embodiment, determining the target model according to the training model, the first training data and the second training data, wherein the target model is used for obtaining the contribution value of each advertisement point location comprises obtaining the contribution value of each advertisement point location to be evaluated according to the following manner:
acquiring advertisement points to be evaluated;
and determining the contribution value of the advertisement point to be evaluated according to the advertisement point to be evaluated, the first training data and the target model.
Alternatively, consider the point bit feature vector h i，z And f i The only difference is that the exposure record of the current point to be evaluated is not considered, but the construction thought and f i Is consistent, thus h i，z Can also be input into the target model to predict other than tpid i,z The contribution value of this point location.
As an alternative embodiment, determining the contribution value of the advertisement point to be evaluated according to the advertisement point to be evaluated, the first training data and the target model includes:
inputting first training data into a target model to obtain contribution values of all points in each crowd pack, wherein the first training data is first training data of the current crowd pack;
acquiring first exposure records under a plurality of statistical dimensions corresponding to advertisement points to be evaluated;
Subtracting the first exposure records from all the exposure records of the current crowd pack to obtain second exposure records;
determining a corresponding reference feature vector according to the second exposure record;
calculating the reference feature vector by using the first scheme to obtain third training data;
inputting the third training data into the target model to obtain contribution values of other advertisement points except the advertisement point to be evaluated;
subtracting the contribution values of the other advertisement spots except the advertisement spot to be evaluated from the contribution values of all spots to obtain the contribution value of the advertisement spot to be evaluated.
Alternatively, f can be i (i.e. first training data) is input into the target model, the group is predicted i (i.e., the current crowd-sourced i may be any number less than the total number of crowd-sourced) contains contributions of all ad spots.
Then obtaining a first exposure record under a plurality of statistical dimensions corresponding to the advertisement point to be evaluated, subtracting the first exposure record from all exposure records of all advertisement points of the current crowd to obtain a second exposure record, constructing a corresponding reference feature vector according to the second exposure record, calculating the reference feature vector by using a formula (1) to obtain third training data, inputting the third training data into a target model to obtain contribution values of other advertisement points except the advertisement point to be evaluated, and then obtaining the tpid to be evaluated by the difference between the contribution values of all the points and the contribution values of the other advertisement points except the advertisement point to be evaluated i,z Is a contribution value of (a).
As an alternative embodiment, after determining the target model according to the training model, the first training data and the second training data, the target model is used to obtain the contribution value of each advertisement point, the method further includes:
acquiring an actual contribution value corresponding to each advertisement point position;
calculating the correlation between the actual contribution value and the contribution value by using a second scheme to obtain a calculation result;
and under the condition that the calculation result is larger than a preset threshold value, determining that the contribution value meets an evaluation condition, wherein the evaluation condition is used for indicating that the accuracy of the contribution value is larger than an accuracy threshold value.
Alternatively, embodiments of the present application may divide a data set into: the exposure table in table 1 and the contribution table as shown in table 2 in the above-described embodiment:
TABLE 2
The actual contribution value y corresponding to each advertisement point location is already provided in table 2, so the contribution value of each point location calculated by the target model and the actual contribution value y can be used for calculating to obtain a calculation result, so as to evaluate whether the target model is good or bad.
The specific calculation formula is as follows:
wherein y is i The actual contribution value is represented and,representing a contribution value->Representing y i Average value of R 2 ∈[0,1]The total quantity of crowd packs is more than or equal to 1 and less than or equal to 1.
Using R 2 The quality of the target model can be evaluated by performing correlation calculation, if R 2 If the contribution value of each point calculated by the target model is larger than the preset threshold value, the contribution value of each point calculated by the target model meets the evaluation condition, wherein the evaluation condition is used for indicating the contribution valueThe accuracy of the model is larger than an accuracy threshold, the representative target model is good, reference, evaluation and prediction can be made for subsequent advertiser investment optimization, and the model has certain guiding significance.
It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.
From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus the necessary general hardware platform, but of course also by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM (Read-Only Memory)/RAM (Random Access Memory), magnetic disk, optical disk), including instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method of the embodiments of the present application.
According to another aspect of the embodiments of the present application, there is also provided a determination apparatus for determining an advertisement spot contribution value for implementing the determination method for an advertisement spot contribution value. Fig. 3 is a block diagram of an alternative apparatus for determining a contribution value of an advertisement spot according to an embodiment of the present application, and as shown in fig. 3, the apparatus may include:
the first obtaining unit 301 is configured to obtain a plurality of crowd packs, where each crowd pack includes a plurality of advertisement points, each advertisement point corresponds to a plurality of exposure records in a plurality of statistical dimensions, and the crowd pack is sample data for evaluating contribution values of the advertisement points;
a construction unit 302 for constructing a plurality of feature vectors using the exposure records and the statistical dimension;
a first calculating unit 303, configured to calculate each feature vector by using a first scheme, so as to obtain first training data;
a first determining unit 304, configured to determine second training data by using a converted population number in each crowd-sourced group and a total exposure number of the corresponding crowd-sourced group, where the converted population number is a number of the initial user converted into the target user through advertisement exposure;
the second determining unit 305 is configured to determine a target model according to the training model, the first training data, and the second training data, where the target model is used to obtain a contribution value of each advertisement point.
It should be noted that the first obtaining unit 301 in this embodiment may be used to perform the above-mentioned step S201, the constructing unit 302 in this embodiment may be used to perform the above-mentioned step S202, the first calculating unit 303 in this embodiment may be used to perform the above-mentioned step S203, the first determining unit 304 in this embodiment may be used to perform the above-mentioned step S204, and the second determining unit 305 in this embodiment may be used to perform the above-mentioned step S205.
Through the module, a plurality of crowd packs are obtained, wherein each crowd pack comprises a plurality of advertisement points, each advertisement point corresponds to a plurality of exposure records in a plurality of statistical dimensions, and the crowd packs are sample data for evaluating contribution values of the advertisement points; constructing a plurality of feature vectors by using exposure records, wherein the number of the exposure records is the same as the number of the feature vectors; calculating each feature vector by using a first scheme to obtain first training data; determining second training data by using the converted number of people in each crowd pack and the total exposure number of the corresponding crowd pack, wherein the converted number of people is the number of the initial users converted into target users through advertisement exposure; and determining the contribution value of each advertisement point position according to the training model, the first training data and the second training data. According to the embodiment of the application, the contribution value of each advertisement point position can be obtained by only giving out the exposed statistical dimension output according to the exposure record of each advertisement point position in the obtained crowd pack without specific individual level, the method solves the problem of presuming the point position contribution of finer granularity from the crowd pack conversion rate of coarser granularity, has very high application value, achieves the technical effect of accurately presuming the contribution value of each advertisement point position, and further solves the problem that the corresponding contribution value of each advertisement point position cannot be obtained well due to the narrow application range of a multi-point attribution model in the related technology.
As an alternative embodiment, the contribution value of each advertisement point to be evaluated is obtained in the second determining unit as follows: the acquisition module is used for acquiring advertisement points to be evaluated; and the determining module is used for determining the contribution value of the advertisement point to be evaluated according to the advertisement point to be evaluated, the first training data and the target model.
As an alternative embodiment, the determining module includes: the first input subunit is used for inputting first training data into the target model to obtain contribution values of all points in each crowd pack, wherein the first training data is first training data of the current crowd pack; the acquisition subunit is used for acquiring first exposure records under a plurality of statistical dimensions corresponding to the advertisement points to be evaluated; a first subtracting subunit, configured to subtract the first exposure record from all exposure records of the current crowd pack to obtain a second exposure record; a determining subunit, configured to determine a corresponding reference feature vector according to the second exposure record; the calculating subunit is used for calculating the reference feature vector by utilizing the first scheme to obtain third training data; the second input subunit is used for inputting third training data into the target model to obtain contribution values of other advertisement points except the advertisement point to be evaluated; and the second subtracting subunit is used for subtracting the contribution values of the advertisement points except the advertisement point to be evaluated from the contribution values of all the points to obtain the contribution values of the advertisement points to be evaluated.
As an alternative embodiment, the calculation formula of the first calculation unit is as follows:
wherein f i Representing an m-dimensional feature vector, wherein i is more than or equal to 1 and less than or equal to the total number of crowd-packs,representing the corresponding exposure record on the t-th dimension, wherein t is more than or equal to 0 and less than or equal to M, and all the value sets of the first statistical dimension are M 0 ，M 0 Comprises m 0 The number of the exposure records and all the valued sets of the second statistical dimension are M 1 ，M 1 Comprises m 1 The number of the exposure records and all the value sets of the third statistical dimension are M 2 ，M 2 Comprises m 2 The number of the exposure records and all the value sets of the fourth statistical dimension are M 3 ，M 3 Comprises m 3 The number of exposure records, and the union set of all values is recorded as M=M 0 ∪M 1 ∪M 2 ∪M 3 ，m＝m 0 +m 1 +m 2 +m 3 ，m t T-th item of set M, I (M t ) Represents m t A field corresponding to this dimension, r i,j The j-th exposure record representing the i-th crowd-sourced, r i,j (x) Representing exposure record r i，j Is represented by x field, imp represents exposure record, r i,j (imp) represents the value of the field corresponding to the exposure record imp, K i ＝k i,1 +...+k i,z +...+k i, total advertisement point position Indicating that the ith crowd-pack has the Kth in total i Stripe exposure record, k i，z The number of exposure records at the z-th point is represented, and the I-function and sign-function are defined as follows:
as an alternative embodiment, the first determining unit calculates according to the following formula:
Wherein,representing the conversion rate, i represents the crowd-sourced number, i is more than or equal to 1 and less than or equal to the crowd-sourced total number, gp imp Representing the total exposure number of each crowd-sourced, < >>Representing the number of transformants in each crowd-sourced.
As an alternative embodiment, the apparatus further comprises: the second acquisition unit is used for determining a target model according to the training model, the first training data and the second training data, wherein the target model is used for acquiring the contribution value of each advertisement point location and then acquiring the actual contribution value corresponding to each advertisement point location; the second calculation unit is used for calculating the correlation between the actual contribution value and the contribution value by using a second scheme to obtain a calculation result; and a third determining unit configured to determine that the contribution value satisfies an evaluation condition if the calculation result is greater than a preset threshold, where the evaluation condition is used to indicate that the accuracy of the contribution value is greater than an accuracy threshold.
As an alternative embodiment, the second calculation unit obtains the calculation result according to the following formula:
/>
wherein y is i The actual contribution value is represented and,representing a contribution value->Representing y i Average value of R 2 ∈[0,1]The total quantity of crowd packs is more than or equal to 1 and less than or equal to 1.
It should be noted that the above modules are the same as examples and application scenarios implemented by the corresponding steps, but are not limited to what is disclosed in the above embodiments. It should be noted that the above modules may be implemented in software or in hardware as part of the apparatus shown in fig. 1, where the hardware environment includes a network environment.
According to still another aspect of the embodiments of the present application, there is further provided an electronic device for implementing the method for determining an advertisement point contribution value described above, where the electronic device may be a server, a terminal, or a combination thereof.
Fig. 4 is a block diagram of an alternative electronic device according to an embodiment of the present application, as shown in fig. 4, including a processor 401, a communication interface 402, a memory 403, and a communication bus 404, wherein the processor 401, the communication interface 402, and the memory 403 perform communication with each other via the communication bus 404, wherein,
a memory 403 for storing a computer program;
the processor 401, when executing the computer program stored in the memory 403, implements the following steps:
s1, obtaining a plurality of crowd packs, wherein each crowd pack comprises a plurality of advertisement points, each advertisement point corresponds to a plurality of exposure records under a plurality of statistical dimensions, and the crowd packs are sample data for evaluating contribution values of the advertisement points;
s2, constructing a plurality of feature vectors by using the exposure records and the statistical dimension;
s3, calculating each feature vector by using a first scheme to obtain first training data;
s4, determining second training data by using the converted number of people in each crowd pack and the total exposure number of the corresponding crowd pack, wherein the converted number of people is converted into the number of target users by advertisement exposure of initial users;
S5, determining a target model according to the training model, the first training data and the second training data, wherein the target model is used for obtaining the contribution value of each advertisement point.
Alternatively, in the present embodiment, the above-described communication bus may be a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus, or an EISA (Extended Industry Standard Architecture ) bus, or the like. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, only one thick line is shown in fig. 4, but not only one bus or one type of bus.
The communication interface is used for communication between the electronic device and other devices.
The memory may include RAM or may include non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
As an example, as shown in fig. 4, the above memory 403 may be, but not limited to, a first obtaining unit 301, a constructing unit 302, a first calculating unit 303, a first determining unit 304, and a second determining unit 305 in the determining apparatus including the above advertisement point contribution value. In addition, other module units in the above-mentioned determination device of the advertisement point position contribution value may be further included, but are not limited to, and are not described in detail in this example.
The processor may be a general purpose processor and may include, but is not limited to: CPU (Central Processing Unit ), NP (Network Processor, network processor), etc.; but also DSP (Digital Signal Processing, digital signal processor), ASIC (Application Specific Integrated Circuit ), FPGA (Field-Programmable Gate Array, field programmable gate array) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
In addition, the electronic device further includes: and the display is used for displaying the determined result of the advertisement point position contribution value.
Alternatively, specific examples in this embodiment may refer to examples described in the foregoing embodiments, and this embodiment is not described herein.
It will be appreciated by those skilled in the art that the structure shown in fig. 4 is only illustrative, and the device implementing the method for determining the contribution value of the advertisement point may be a terminal device, and the terminal device may be a smart phone (such as an Android mobile phone, an iOS mobile phone, etc.), a tablet computer, a palm computer, a mobile internet device (Mobile Internet Devices, MID), a PAD, etc. Fig. 4 is not limited to the structure of the electronic device described above. For example, the terminal device may also include more or fewer components (e.g., network interfaces, display devices, etc.) than shown in fig. 4, or have a different configuration than shown in fig. 4.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program for instructing a terminal device to execute in association with hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: flash disk, ROM, RAM, magnetic or optical disk, etc.
According to yet another aspect of embodiments of the present application, there is also provided a storage medium. Alternatively, in this embodiment, the storage medium may be used for executing the program code of the method for determining the advertisement spot contribution value.
Alternatively, in this embodiment, the storage medium may be located on at least one network device of the plurality of network devices in the network shown in the above embodiment.
Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of:
s1, obtaining a plurality of crowd packs, wherein each crowd pack comprises a plurality of advertisement points, each advertisement point corresponds to a plurality of exposure records under a plurality of statistical dimensions, and the crowd packs are sample data for evaluating contribution values of the advertisement points;
s2, constructing a plurality of feature vectors by using the exposure records and the statistical dimension;
S3, calculating each feature vector by using a first scheme to obtain first training data;
s4, determining second training data by using the converted number of people in each crowd pack and the total exposure number of the corresponding crowd pack, wherein the converted number of people is converted into the number of target users by advertisement exposure of initial users;
s5, determining a target model according to the training model, the first training data and the second training data, wherein the target model is used for obtaining the contribution value of each advertisement point.
Alternatively, specific examples in the present embodiment may refer to examples described in the above embodiments, which are not described in detail in the present embodiment.
Alternatively, in the present embodiment, the storage medium may include, but is not limited to: various media capable of storing program codes, such as a U disk, ROM, RAM, a mobile hard disk, a magnetic disk or an optical disk.
According to yet another aspect of embodiments of the present application, there is also provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium; the computer instructions are read from a computer-readable storage medium by a processor of a computer device, and executed by the processor, cause the computer device to perform the method steps of determining the advertisement spot contribution value in any of the embodiments described above.
The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.
The integrated units in the above embodiments may be stored in the above-described computer-readable storage medium if implemented in the form of software functional units and sold or used as separate products. Based on such understanding, the technical solution of the present application may be embodied essentially or partly in the form of a software product, or all or part of the technical solution, which is stored in a storage medium, and includes several instructions to cause one or more computer devices (which may be personal computers, servers or network devices, etc.) to perform all or part of the steps of the method for determining the advertisement spot contribution value according to the embodiments of the present application.
In the foregoing embodiments of the present application, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.
In several embodiments provided in the present application, it should be understood that the disclosed client may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and are merely a logical functional division, and there may be other manners of dividing the apparatus in actual implementation, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution provided in the present embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The foregoing is merely a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application and are intended to be comprehended within the scope of the present application.

Claims (8)

1. A method for determining a contribution value of an advertisement spot, the method comprising:
obtaining a plurality of crowd packs, wherein each crowd pack comprises a plurality of advertisement points, each advertisement point corresponds to a plurality of exposure records under a plurality of statistical dimensions, and the crowd packs are sample data for evaluating contribution values of the advertisement points;
Constructing a plurality of feature vectors by using the exposure records and the statistical dimension;
calculating each feature vector by using a first scheme to obtain first training data;
determining second training data by using the converted number of people in each crowd pack and the total exposure number of the corresponding crowd pack, wherein the converted number of people is the number of initial users converted into target users through advertisement exposure;
determining a target model according to the training model, the first training data and the second training data, wherein the target model is used for obtaining a contribution value of each advertisement point position;
the calculation formula for obtaining the first training data is as follows, wherein the calculation is performed on each feature vector by using a first scheme:
wherein f i Representing an m-dimensional feature vector, wherein i is more than or equal to 1 and less than or equal to the total number of crowd packs, and f i t Representing the corresponding exposure record on the t-th dimension, wherein t is more than or equal to 0 and less than or equal to M, and all the value sets of the first statistical dimension are M 0 ，M 0 Apparatus for exposing advertisements, M 0 Comprises m 0 The number of the exposure records and all the valued sets of the second statistical dimension are M 1 ，M 1 For advertisement exposure behavior, M 1 Comprises m 1 The number of the exposure records and all the value sets of the third statistical dimension are M 2 ，M 2 Media platform for exposing advertisements, M 2 Comprises m 2 The number of the exposure records and all the value sets of the fourth statistical dimension are M 3 ，M 3 For the area where the advertisement is exposed, M 3 Comprises m 3 The number of exposure records, and the union set of all values is recorded as M=M 0 ∪M 1 ∪M 2 ∪M 3 ，m＝m 0 +m 1 +m 2 +m 3 ，m t T-th item of set M, I (M t ) Represents m t A field corresponding to this dimension, r i,j The j-th exposure record representing the i-th crowd-sourced, r i,j (x) Representing exposure record r i，j Is represented by x field, imp represents exposure record, r i,j (imp) represents the value of the field corresponding to the exposure record imp, K i ＝k i,1 +...+k i,z +...+k i, total advertisement point position Indicating that the ith crowd-pack has the Kth in total i Stripe exposure record, k i，z The number of exposure records at the z-th point is represented, and the I-function and sign-function are defined as follows:
wherein, the determining the second training data includes calculating according to the following formula by using the converted population number in each crowd-sourced group and the total exposure number of the corresponding crowd-sourced group:
wherein,representing the conversion rate, i represents the crowd-sourced number, i is more than or equal to 1 and less than or equal to the crowd-sourced total number, gp imp Representing the total exposure number of each of said crowd-bags, < >>Representing the number of transformants in each of the crowd-packs.
2. The method of claim 1, wherein determining a target model from the training model, the first training data, and the second training data, wherein the target model is configured to obtain a contribution value for each of the ad spots comprises obtaining a contribution value for each of the ad spots to be evaluated as follows:
Acquiring advertisement points to be evaluated;
and determining the contribution value of the advertisement point to be evaluated according to the advertisement point to be evaluated, the first training data and the target model.
3. The method of claim 2, wherein the determining the contribution value of the ad spot to be evaluated based on the ad spot to be evaluated, the first training data, and the target model comprises:
inputting the first training data into the target model to obtain contribution values of all points in each crowd pack, wherein the first training data is first training data of a current crowd pack;
acquiring first exposure records under a plurality of statistical dimensions corresponding to the advertisement points to be evaluated;
subtracting the first exposure records from all exposure records of the current crowd pack to obtain a second exposure record;
determining a corresponding reference feature vector according to the second exposure record;
calculating the reference feature vector by using the first scheme to obtain third training data;
inputting the third training data into the target model to obtain contribution values of other advertisement points except the advertisement point to be evaluated;
And subtracting the contribution values of the other advertisement points except the advertisement point to be evaluated from the contribution values of all the points to obtain the contribution value of the advertisement point to be evaluated.
4. A method according to any one of claims 1 to 3, wherein after said determining a target model from the training model, the first training data and the second training data, wherein the target model is used to derive a contribution value for each of the advertisement spots, the method further comprises:
acquiring an actual contribution value corresponding to each advertisement point position;
calculating the correlation between the actual contribution value and the contribution value by using a second scheme to obtain a calculation result;
and under the condition that the calculation result is larger than a preset threshold value, determining that the contribution value meets an evaluation condition, wherein the evaluation condition is used for indicating that the accuracy of the contribution value is larger than an accuracy threshold value.
5. The method of claim 4, wherein calculating the correlation between the actual contribution and the contribution using a second scheme, the calculation result comprising using the formula:
Wherein y is i The actual contribution value is represented and,representing a contribution value->Representing y i Average value of R 2 ∈[0,1]The total quantity of crowd packs is more than or equal to 1 and less than or equal to 1.
6. An apparatus for determining a contribution value of an advertisement spot, the apparatus comprising:
the first acquisition unit is used for acquiring a plurality of crowd packs, wherein each crowd pack comprises a plurality of advertisement points, each advertisement point corresponds to a plurality of exposure records under a plurality of statistical dimensions, and the crowd packs are sample data for evaluating contribution values of the advertisement points;
a construction unit for constructing a plurality of feature vectors using the exposure record and the statistical dimension;
the first calculation unit is used for calculating each characteristic vector by utilizing a first scheme to obtain first training data;
the first determining unit is used for determining second training data by utilizing the converted number of people in each crowd pack and the total exposure number of the corresponding crowd pack, wherein the converted number of people is the number of the original users converted into the target users through advertisement exposure;
the second determining unit is used for determining a target model according to the training model, the first training data and the second training data, wherein the target model is used for obtaining the contribution value of each advertisement point position;
Wherein the first computing unit is configured to:
wherein f i Representing an m-dimensional feature vector, wherein i is more than or equal to 1 and less than or equal to the total number of crowd packs, and f i t Representing the corresponding exposure record on the t-th dimension, wherein t is more than or equal to 0 and less than or equal to M, and all the value sets of the first statistical dimension are M 0 ，M 0 Apparatus for exposing advertisements, M 0 Comprises m 0 The number of the exposure records and all the valued sets of the second statistical dimension are M 1 ，M 1 For advertisement exposure behavior, M 1 Comprises m 1 The number of the exposure records and all the value sets of the third statistical dimension are M 2 ，M 2 Media platform for exposing advertisements, M 2 Comprises m 2 The number of the exposure records and all the value sets of the fourth statistical dimension are M 3 ，M 3 For the area where the advertisement is exposed, M 3 Comprises m 3 The number of exposure records, and the union set of all values is recorded as M=M 0 ∪M 1 ∪M 2 ∪M 3 ，m＝m 0 +m 1 +m 2 +m 3 ，m t T-th item of set M, I (M t ) Represents m t A field corresponding to this dimension, r i,j The j-th exposure record representing the i-th crowd-sourced, r i,j (x) Representing exposure record r i，j Is represented by x field, imp represents exposure record, r i,j (imp) represents the value of the field corresponding to the exposure record imp, K i ＝k i,1 +...+k i,z +...+k i, total advertisement point position Indicating that the ith crowd-pack has the Kth in total i Stripe exposure record, k i，z The number of exposure records at the z-th point is represented, and the I-function and sign-function are defined as follows:
Wherein the first determining unit is configured to:
wherein,representing the conversion rate, i represents the crowd-sourced number, i is more than or equal to 1 and less than or equal to the crowd-sourced total number, gp imp Representing the total exposure number of each of said crowd-bags, < >>Representing the number of transformants in each of the crowd-packs.
7. An electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus, characterized in that,
the memory is used for storing a computer program;
the processor is configured to perform the method steps of any of claims 1 to 5 by running the computer program stored on the memory.
8. A computer-readable storage medium, characterized in that the storage medium has stored therein a computer program, wherein the computer program is arranged to perform the method steps of any of claims 1 to 5 when run.
CN202110653864.3A 2021-06-11 2021-06-11 Determination method and device for advertisement point contribution value, electronic equipment and storage medium Active CN113393270B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110653864.3A CN113393270B (en) 2021-06-11 2021-06-11 Determination method and device for advertisement point contribution value, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110653864.3A CN113393270B (en) 2021-06-11 2021-06-11 Determination method and device for advertisement point contribution value, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113393270A CN113393270A (en) 2021-09-14
CN113393270B true CN113393270B (en) 2024-04-09

Family

ID=77620580

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110653864.3A Active CN113393270B (en) 2021-06-11 2021-06-11 Determination method and device for advertisement point contribution value, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113393270B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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

Citations (4)

* Cited by examiner, † Cited by third party
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
CN111242687A (en) * 2020-01-13 2020-06-05 腾讯科技（深圳）有限公司 Advertisement data analysis method and device, electronic equipment and storage medium
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

Patent Citations (4)

* Cited by examiner, † Cited by third party
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
CN111242687A (en) * 2020-01-13 2020-06-05 腾讯科技（深圳）有限公司 Advertisement data analysis method and device, electronic equipment and storage medium
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

Also Published As

Publication number Publication date
CN113393270A (en) 2021-09-14

Similar Documents

Publication Publication Date Title
US20210329094A1 (en) Discovering signature of electronic social networks
CN104993946B (en) Appraisal procedure, the device and system of gray scale publication
US20160210657A1 (en) Real-time marketing campaign stimuli selection based on user response predictions
CN110472879B (en) Resource effect evaluation method and device, electronic equipment and storage medium
CN109840782B (en) Click rate prediction method, device, server and storage medium
CN107689008A (en) A kind of user insures the method and device of behavior prediction
CN109308552A (en) A kind of business game appraisal procedure, device and electronic equipment
US20160055320A1 (en) Method and system for measuring effectiveness of user treatment
US20170221092A1 (en) System and a method for surveying advertisements in mobile applications
CN108932582A (en) Risk information determines method, apparatus, computer equipment and storage medium
CN111461827B (en) Push method and device for product evaluation information
CN108133390A (en) For predicting the method and apparatus of user behavior and computing device
CN113076416A (en) Information heat evaluation method and device and electronic equipment
CN112365007B (en) Model parameter determining method, device, equipment and storage medium
CN113393270B (en) Determination method and device for advertisement point contribution value, electronic equipment and storage medium
CN111159541A (en) Method and device for determining account behavior preference
CN110348947A (en) Object recommendation method and device
CN114219540A (en) Method and device for determining user behavior period, electronic equipment and storage medium
CN111724043A (en) Performance assessment method and system
CN114283017A (en) Resource information pushing method and device, electronic equipment and storage medium
CN113837318A (en) Method and device for determining flow judgment scheme, electronic equipment and storage medium
CN115345635A (en) Processing method and device for recommended content, computer equipment and storage medium
CN108629610B (en) Method and device for determining popularization information exposure
CN113570409B (en) Determination method and device for conversion event weight value, storage medium and electronic device
CN113282857B (en) Method and device for determining contribution degree of drop point, and readable storage medium

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
GR01 Patent grant
GR01 Patent grant