Advertisement putting method and device based on cross-platform tea e-commerce data integration

Abstract

The invention relates to an advertisement putting method based on cross-platform tea e-commerce data integration, and the method comprises the following steps: obtaining tea e-commerce data of a plurality of platforms; performing data collection on the tea e-commerce data of the plurality of platforms to obtain feature representation data; searching active high-quality users based on the feature representation data; and advertisement putting is carried out for the active high-quality users. According to the method, the tea e-commerce data is obtained from multiple platforms, the tea e-commerce data is collected to obtain the feature representation data of the associated user ID, then the feature representation data of the associated user ID is analyzed to find the active high-quality users, and the active high-quality users are subjected to advertisement putting, so that the advertisement putting efficiency is improved. The method can help to reduce a large amount of manpower screening cost, and then workers only need to carry out research according to the feedback condition of advertisement putting, so that the advertisement putting task can be completed more accurately, and convenience is provided for the workers.

Description

Technical Field

[0001] The present invention relates to the technical field related to advertisement placement, and in particular to an advertisement placement method and device based on cross-platform tea e-commerce data integration. Background Art

[0002] Advertising is the process by which a company or individual displays advertising content to the target audience through various media channels in order to promote products, services or brands.

[0003] The current advertising method is often carried out by staff with rich relevant professional experience to screen and evaluate data. This method often requires a lot of manpower to check relevant data, and the data analysis ideas required for different industry scenarios are also very different. In the field of tea e-commerce, the population base is large. If advertisements are placed to every browsing user, the cost is high and the benefits are low. Therefore, if advertising can be estimated by intelligently analyzing the behavior of user groups, it can bring great improvements to the work of relevant staff. Summary of the invention

[0004] The purpose of the present invention is to solve at least one of the deficiencies of the prior art and to provide an advertising delivery method and device based on cross-platform tea e-commerce data integration.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] Specifically, an advertising method based on cross-platform tea e-commerce data integration is proposed, including the following:

[0007] Obtain tea e-commerce data from multiple platforms;

[0008] Collect tea e-commerce data from multiple platforms to obtain feature representation data;

[0009] Find active and high-quality users based on the feature characterization data;

[0010] Deliver advertisements to active and high-quality users.

[0011] Further, specific tea e-commerce data from multiple platforms include:

[0012] Obtain the registration IDs of all registered users on multiple platforms, and read their associated online time, number of times they shared tea products, and total amount of payments based on the registration IDs;

[0013] By the first array Ar 1 Record the user's registration ID through the second array Ar 2 Record the online time associated with the registration ID through the third array Ar 3Record the number of times of sharing tea products associated with the registered ID through the fourth array Ar 4 Record the total payment amount associated with the registered ID and make Ar 1 、Ar 2 、Ar 3 And Ar 4 Stored in the cloud server.

[0014] Furthermore, specifically, data aggregation is performed on the tea e-commerce data of multiple platforms to obtain feature representation data. Specifically, in the cloud server, denote Ar 1 i as the i-th element in the array Ar 1 . Sort all the elements in the array Ar 2 , the array Ar 3 , and the array Ar 4 based on the order relationship of the registered ID in the array Ar 1 . Define the element corresponding to the minimum value in the array Ar 3 as Q1, denote the element corresponding to the minimum value in the array Ar3 as Q2, and denote G1 = Q1 / Avg, G2 = Q2 / Avg Ar3 , where Avg Ar3 represents the average value of all elements in Ar 3 . Define Ar 5 i = G1+(G2 - G1)*(Ar 4 i - Ar 4 Min) / (Ar 4 Max - Ar 4 Min), where Ar 4 i is the i-th element in Ar 4 , Ar 4 Min is the minimum value of the elements in Ar 4 , and Ar 4 Max is the maximum value of the elements in Ar 4 . Combine all Ar 5 i to form the fifth array, that is, Ar 5 i is the i-th element in the fifth array, and assume that the fifth array has N elements, that is, i ∈ [1, N]; denote Ar 2 i as the i-th element in Ar 2 . Perform the following operation on each element Ar 2 i in Ar 2 : Ar 2 i / Ar 2 1 to obtain the updated Ar 2 , denoted as the sixth array Ar 6 . Then, the fifth array, the sixth array, the third array, and the first array together form the feature representation data.

[0015] Further, specifically, finding out active and high-quality users based on the feature characterization data includes:

[0016] Step 410: Denote the element corresponding to the minimum value in Ar 5 as Ar 5s , and denote the elements in the temporary array Tem as Tem j , where Tem is composed of the elements in Ar 6 in the order of [1, N - 1], that is, j ∈ [1, N - 1], and go to Step 420;

[0017] Step 420: Starting from the first element in Tem, that is, from j = 1 to j = N - 1, update Tem j sequentially to Tem j - Ar 5s . Denote the updated array as Tem'. Then find the minimum value element in Tem' and mark it as Tem' jv . Delete the elements with serial numbers v and s in Ar 5 to obtain the updated array denoted as Ar 5 '. Pre-establish an empty data set and initialize the verification variable k, that is, let k = 1, and the value range of k is [1, N - 1], and go to Step 430;

[0018] Step 430: Starting from the first element in Ar 5 ', subtract each element in Ar 5 ' by Tem' k to obtain N - 2 values, that is, Ar 5 '(1),..., Ar 5 '(N - 2), and construct an optimization model

[0019]

[0020] where p is a variable, p ∈ [1, N - 2], and all elements of So p together form the importance degree array of users, and α is an adjustment coefficient set artificially;

[0021] Find the minimum value element in the importance degree array, assume it is r, that is, p = r, and compare So r with Ar 5s and Tem' jv respectively. If So r is less than min{Ar 5s , Tem' jv}, then add r to the data set, and min{Ar 5s , Tem' jv} means taking the smaller value between Ar 5s and Tem'jv The smaller value among them, go to step 440;

[0022] Step 440: Determine whether k is less than N - 1. If not, go to step 450; if so, go to step 430;

[0023] Step 450: Output the data set, and find the registration ID of the user corresponding to the elements in the data set. The registration ID of the user at this time is the active high-quality user.

[0024] The present invention also provides an advertising placement device based on cross-platform tea e-commerce data integration, including the following:

[0025] A data acquisition module, configured to acquire tea e-commerce data of multiple platforms;

[0026] A data collection module, configured to collect tea e-commerce data of multiple platforms to obtain feature representation data;

[0027] An active high-quality user search module, configured to find active high-quality users based on the feature representation data;

[0028] An advertising placement module, configured to perform advertising placement for active high-quality users.

[0029] The beneficial effects of the present invention are as follows:

[0030] The advertising placement method based on cross-platform tea e-commerce data integration provided by the present invention obtains tea e-commerce data on multiple platforms, collects the tea e-commerce data to obtain feature representation data associated with user IDs, then analyzes the feature representation data associated with user IDs to find active high-quality users among them, and then performs advertising placement for these active high-quality users, which can help reduce a large amount of manual screening costs. After that, it only requires staff to conduct research based on the feedback of advertising placement to more accurately complete the advertising placement task, providing convenience for the staff. Description of the Drawings

[0031] By describing the embodiments shown in the accompanying drawings in detail, the above and other features of the present disclosure will become more obvious. The same reference numerals in the drawings of the present disclosure represent the same or similar output voltages. Obviously, the drawings in the following description are only some embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. In the drawings:

[0032] Figure 1 It shows a flowchart of the advertising placement method based on cross-platform tea e-commerce data integration of the present invention. Detailed Embodiments

[0033] The concept, specific structure and technical effects of the present invention will be clearly and completely described below in conjunction with embodiments and drawings, so as to fully understand the purpose, solution and effects of the present invention. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The same reference numerals used throughout the drawings indicate the same or similar parts.

[0034] Referring to Figure 1 , Embodiment 1, the present invention proposes an advertising placement method based on cross-platform tea e-commerce data integration, including the following

[0035] Step 110: Obtain tea e-commerce data of multiple platforms;

[0036] Step 120: Aggregate the tea e-commerce data of multiple platforms to obtain feature representation data;

[0037] Step 130: Find out active and high-quality users based on the feature representation data;

[0038] Step 140: Perform advertising placement for active and high-quality users.

[0039] In this Embodiment 1, by obtaining tea e-commerce data on multiple platforms, aggregating the tea e-commerce data to obtain feature representation data associated with user IDs, then analyzing the feature representation data associated with user IDs to find out the active and high-quality users among them, and then performing advertising placement for these active and high-quality users, it can help reduce a large amount of manual screening costs. After that, only the staff needs to conduct research based on the feedback of the advertising placement to more accurately complete the advertising placement task, which provides convenience for the staff.

[0040] As a preferred implementation manner of the present invention, specifically, the tea e-commerce data of multiple platforms includes

[0041] Obtain the registration IDs of all registered users on multiple platforms, and read the associated online duration, the number of times of sharing tea products, and the total payment amount based on the registration IDs;

[0042] Through the first array Ar 1 Record the registration IDs of users, through the second array Ar 2 Record the online duration associated with the registration IDs, through the third array Ar 3 Record the number of times of sharing tea products associated with the registration IDs, through the fourth array Ar 4 Record the total payment amount associated with the registration IDs, and store Ar 1 、Ar 2 、Ar 3 And Ar 4 To the cloud server.

[0043] In this preferred embodiment, considering that the above parameters can largely reflect the user's purchase-related situation when the user browses and purchases products on the platform, the above parameters are selected for analysis.

[0044] As a preferred embodiment of the present invention, specifically, data collection is performed on the tea e-commerce data of multiple platforms to obtain feature representation data, including

[0045] In the cloud server, denote Ar 1 i as the i-th element in the array Ar 1 Sort all the elements in the array Ar 2 , the array Ar 3 , and the array Ar 4 based on the order relationship of the registered IDs in the array Ar 1 . Define the element corresponding to the minimum value in the array Ar 3 as Q1, denote the element corresponding to the minimum value in the array Ar3 as Q2, and denote G1 = Q1 / Avg, G2 = Q2 / Avg Ar3 , Avg Ar3 represents the average value of all elements in Ar 3 . Define Ar 5 i = G1 + (G2 - G1) * (Ar 4 i - Ar 4 Min) / (Ar 4 Max - Ar 4 Min), where Ar 4 i is the i-th element in Ar 4 , Ar 4 Min is the minimum value of the elements in Ar 4 , Ar 4 Max is the maximum value of the elements in Ar 4 . Combine all Ar 5 i to form the fifth array, that is, Ar 5 i is the i-th element in the fifth array, and assume that the fifth array has a total of N elements, that is, i ∈ [1, N]; denote Ar 2 i as the i-th element in Ar 2 . Perform the following operation on each element Ar 2 i in Ar 2 : Ar 2 i / Ar 2 1 to obtain the updated Ar 2 , denoted as the sixth array Ar 6 . Then, the fifth array, the sixth array, the third array, and the first array together form the feature representation data.

[0046] In this preferred embodiment, by collecting the tea e-commerce data of multiple platforms in the above manner to obtain feature representation data, it is convenient for subsequent algorithm analysis to find active and high-quality users.

[0047] As a preferred embodiment of the present invention, specifically, finding active and high-quality users based on the feature representation data includes:

[0048] Step 410: Denote the element corresponding to the minimum value in Ar 5 as Ar 5s , and denote the elements in the temporary array Tem as Tem j , Tem is composed of the [1, N - 1]th elements in Ar 6 in sequence, that is, j ∈ [1, N - 1], and go to step 420;

[0049] Step 420: Starting from the first element in Tem, that is, starting from j = 1 to j = N - 1, update Tem j sequentially to Tem j - Ar 5s , and denote the updated array as Tem'. Then find the minimum value element in Tem' and mark it as Tem' jv , delete the elements with serial numbers v and s in Ar 5 to obtain the updated array denoted as Ar 5 ', pre-establish an empty data set, and initialize the verification variable k, that is, let k = 1, and the value range of k is [1, N - 1], and go to step 430;

[0050] Step 430: Starting from the first element in Ar 5 ', subtract each element in Ar 5 ' by Tem' k to obtain N - 2 values, that is, Ar 5 '(1),..., Ar 5 '(N - 2), and construct an optimization model

[0051]

[0052] where p is a variable, p ∈ [1, N - 2], and all elements of So p together form an array of user importance levels, and α is an adjustment coefficient set artificially (here, it is considered that there may be audience differences among people in different regions, so an adjustment coefficient can be set to balance the tea consumption differences among regional populations);

[0053] Find the minimum value element in the array of importance levels and assume it is r, that is, p = r, and compare So r with Ar 5s and Tem'jv If the magnitude relationship among the three is So r less than min{Ar 5s , Tem' jv}, then add r to the data set, and min{Ar 5s , Tem' jv} means taking the smaller value between Ar 5s and Tem' jv , and go to step 440;

[0054] Step 440: Determine whether k is less than N - 1. If not, go to step 450; if so, go to step 430;

[0055] Step 450: Output the data set, and find the registration ID of the user corresponding to the elements in the data set. The registration ID of the user at this time is the active high-quality user.

[0056] In this preferred embodiment, by screening in the above manner, the registration ID of the active high-quality user can be accurately found, and then precise advertisement placement can be carried out.

[0057] The present invention also proposes an advertisement placement device based on cross-platform tea e-commerce data integration, including the following,

[0058] A data acquisition module for acquiring tea e-commerce data of multiple platforms;

[0059] A data collection module for collecting tea e-commerce data of multiple platforms to obtain feature representation data;

[0060] An active high-quality user search module for finding active high-quality users based on the feature representation data;

[0061] An advertisement placement module for performing advertisement placement for active high-quality users.

[0062] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical modules, that is, they may be located in one place, or may be distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution in this embodiment.

[0063] In addition, in each embodiment of the present invention, the functional modules can be integrated in a processing module, or each module can exist physically alone, or two or more modules can be integrated in one module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules.

[0064] When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0065] Although the description of the present invention has been quite detailed and several of the described embodiments have been described in particular, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but rather should be regarded as providing a broad interpretation of these claims in light of the prior art by reference to the appended claims, thereby effectively covering the intended scope of the present invention. In addition, the present invention has been described above with embodiments foreseeable by the inventor for the purpose of providing a useful description, and non-substantive modifications to the present invention that are not currently foreseeable may still represent equivalent modifications of the present invention.

[0066] As described above, these are only the preferred embodiments of the present invention. The present invention is not limited to the above-described embodiments. As long as it achieves the technical effects of the present invention by the same means, it should fall within the protection scope of the present invention. Within the protection scope of the present invention, various different modifications and variations can be made to its technical solutions and / or embodiments.

Claims

1. An advertising method based on cross-platform tea e-commerce data integration, characterized in that: Including the following, Obtain tea e-commerce data from multiple platforms; Collect tea e-commerce data from multiple platforms to obtain feature representation data; Find active and high-quality users based on the feature characterization data; Deliver advertisements to active and high-quality users.

2. The advertising method based on cross-platform tea e-commerce data integration according to claim 1 is characterized in that: Specifically, tea e-commerce data from multiple platforms, including: Obtain the registration IDs of all registered users on multiple platforms, and read their associated online time, number of times they shared tea products, and total amount of payments based on the registration IDs; The user's registration ID is recorded through the first array Ar1, the online time associated with the registration ID is recorded through the second array Ar2, the number of times the tea product is shared associated with the registration ID is recorded through the third array Ar3, the total amount of payment associated with the registration ID is recorded through the fourth array Ar4, and Ar1, Ar2, Ar3 and Ar4 are stored in the cloud server.

3. The advertising method based on cross-platform tea e-commerce data integration according to claim 2 is characterized in that: Specifically, tea e-commerce data from multiple platforms are aggregated to obtain feature representation data, including: In the cloud server, Ar1i is denoted as the i-th element in array Ar1. All elements in arrays Ar2, Ar3, and Ar4 are sorted based on the order of the registration IDs in array Ar1. The element corresponding to the minimum value in array Ar3 is defined as Q1. The element corresponding to the minimum value in array Ar3 is denoted as Q2. G1=Q1 / Avg, G2=Q2 / Avg Ar3 , Avg Ar3 Represents the mean of all elements in Ar3, and defines Ar5i=G1+(G2-G1)*(Ar4i-Ar4Min) / (Ar4Max-Ar4Min), wherein Ar4i is the i-th element in Ar4, Ar4Min is the minimum value of the elements in Ar4, and Ar4Max is the maximum value of the elements in Ar4. All Ar5i are grouped into the fifth array, that is, Ar5i is the i-th element in the fifth array, and it is assumed that the fifth array has a total of N elements, that is, i∈[1,N]; Ar2i is the i-th element in Ar2, and each element Ar2i in Ar2 is subjected to the following operation Ar2i / Ar21 to obtain the updated Ar2, which is recorded as the sixth array Ar6. Then the fifth array, the sixth array, the third array and the first array together constitute the feature characterization data.

4. The advertising method based on cross-platform tea e-commerce data integration according to claim 3 is characterized in that: Specifically, finding active high-quality users based on the feature representation data includes: Step 410: record the element corresponding to the minimum value in Ar5 as Ar 5s , let the elements in the temporary array Tem be Tem j , Tem is the [1, N-1]th in Ar6 in order, that is, j∈[1, N-1], go to step 420; Step 420: Starting from the first element in Tem, i.e., from j=1 to j=N-1, j Update to Tem in sequence j -Ar 5s , the updated array is recorded as Tem', and then the minimum element is found from Tem' and marked as Tem' jv , delete the elements with serial numbers v and s in Ar5 to obtain an updated array, record it as Ar5', pre-establish a blank data set, and initialize the check variable k, that is, set k=1, and the value range of k is [1, N-1], and go to step 430; Step 430: Starting from the first element in Ar5', subtract Tem' from each element in Ar5' in turn. k Get N-2 values, namely Ar5'(1), ..., Ar5'(N-2), and build an optimization model. Among them, p is a variable, p∈[1, N-2], So p All elements of compose the user's importance array, and α is an adjustment coefficient set manually; Find the minimum value of the element in the importance array, assuming it is r, that is, p = r, and compare So r with Ar 5s And Tem' jv The size relationship between the three is So r Less than min{Ar 5s , Tem' jv }, then add r to the data set, min{Ar 5s , Tem' jv } means taking Ar 5s With Tem' jv The smaller value of , go to step 440; Step 440, determine whether k is less than N-1, if not, go to step 450, if yes, go to step 430; Step 450: output the data set, and find out the registration ID of the user corresponding to the element in the data set. At this time, the registration ID of the user is an active high-quality user.

5. An advertising device based on cross-platform tea e-commerce data integration, characterized in that: Including the following, Data acquisition module, used to obtain tea e-commerce data from multiple platforms; The data collection module is used to collect tea e-commerce data from multiple platforms to obtain feature representation data; An active high-quality user search module, used to search for active high-quality users based on the feature characterization data; The advertising delivery module is used to deliver advertisements to active and high-quality users.

Images