Advertisement putting processing method and device

Abstract

The embodiment of the invention provides an advertisement putting processing method and device, and the method comprises the steps: carrying out the advertisement putting based on an advertisement putting strategy, and firstly obtaining the user behavior data, advertisement putting data and putting node data of a commodity combination which carries out the advertisement putting, secondly, calculating an advertisement accuracy coefficient according to the user behavior data and the advertisement putting data, calculating an advertisement return index according to the advertisement putting data, and calculating an advertisement safety coefficient according to the advertisement putting data and the putting node data; the method comprises the following steps: calculating an advertisement accuracy coefficient, an advertisement return index and an advertisement safety coefficient, calculating a putting effect index based on the calculated advertisement accuracy coefficient, the advertisement return index and the advertisement safety coefficient, comparing the putting effect index with a preset putting adjustment threshold, and adjusting an advertisement putting strategy according to a comparison result so as to optimize and upgrade an advertisement putting effect.

Description

Technical Field

[0001] This document relates to the technical field of advertisement delivery, and in particular to a method and device for processing advertisement delivery. Background Art

[0002] With the continuous development of the Internet, advertising has become an important means for companies and brands to acquire potential customers and promote product sales. Accurate advertising can not only increase the brand's return on investment, but also improve user experience and reduce the interference of irrelevant advertisements.

[0003] At present, many advertising delivery systems achieve accurate advertising delivery by collecting, processing and analyzing massive amounts of user data. However, in actual applications, when processing massive amounts of data, due to the complexity and diversity of the data, the advertising delivery accuracy of the advertising delivery system may decrease as the redundancy of the data increases, or the advertising delivery system may have certain defects in security in order to achieve a certain degree of accurate delivery. Therefore, how to improve the accuracy of advertising delivery while ensuring the security of advertising content has become an urgent problem to be solved in the current field of advertising delivery technology. Summary of the invention

[0004] The purpose of one embodiment of the present specification is to provide a method and device for processing advertisement delivery, so as to optimize and upgrade the effect of advertisement delivery.

[0005] To solve the above technical problems, an embodiment of this specification is implemented as follows: In a first aspect, an embodiment of the present specification provides a method for processing advertisement delivery, including: Obtain user behavior data, advertisement delivery data, and delivery node data for the product combination for advertisement delivery; Calculating an advertisement precision coefficient based on the user behavior data and the advertisement delivery data, calculating an advertisement return index based on the advertisement delivery data, and calculating an advertisement safety coefficient based on the advertisement delivery data and the delivery node data; Calculate the delivery effect index according to the advertisement precision coefficient, the advertisement return index and the advertisement safety coefficient; The delivery effect index is compared with a preset delivery adjustment threshold to obtain a comparison result.

[0006] In a second aspect, an embodiment of the present specification provides an advertisement delivery processing device, including: A data acquisition module is configured to acquire user behavior data, advertisement delivery data, and delivery node data of a product combination for advertisement delivery; a data calculation module configured to calculate an advertisement accuracy coefficient according to the user behavior data and the advertisement delivery data, calculate an advertisement return index according to the advertisement delivery data, and calculate an advertisement safety coefficient according to the advertisement delivery data and the delivery node data; An effect index calculation module is configured to calculate a delivery effect index according to the advertisement precision coefficient, the advertisement return index and the advertisement safety coefficient; The comparison module is configured to compare the delivery effect index with a preset delivery adjustment threshold to obtain a comparison result.

[0007] In a third aspect, another embodiment of the present specification provides an advertising delivery processing device, comprising: a memory, a processor, and computer executable instructions stored on the memory and executable on the processor, wherein the computer executable instructions, when executed by the processor, implement the steps of the advertising delivery processing method as described in the first aspect above.

[0008] In a fourth aspect, another embodiment of the present specification provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store computer-executable instructions, and when the computer-executable instructions are executed by a processor, the steps of the advertising delivery processing method as described in the first aspect above are implemented.

[0009] In a fifth aspect, another embodiment of the present specification provides a computer program product, wherein the computer program product includes an advertisement delivery processing program, and the advertisement delivery processing program is executed by a processor to implement the steps of the advertisement delivery processing method as described in the first aspect above.

[0010] The present embodiment provides a method for processing advertisement delivery. After advertisement delivery is performed based on an advertisement delivery strategy, user behavior data, advertisement delivery data, and delivery node data of a product combination for advertisement delivery are obtained. On the one hand, an advertisement precision coefficient is calculated based on the user behavior data and the advertisement delivery data to reflect the degree of matching between advertisement delivery and users. On the other hand, an advertisement return index is calculated based on the advertisement delivery data to evaluate the economic benefits of advertisement delivery. Furthermore, an advertisement safety factor is calculated based on the advertisement delivery data and the delivery node data to evaluate whether there are security risks on the delivery platform for advertisement delivery. Then, a delivery effect index is calculated based on the calculated advertisement precision coefficient, advertisement return index, and advertisement safety factor to evaluate the overall effect of advertisement delivery. Finally, the delivery effect index is compared with a preset delivery adjustment threshold to optimize and upgrade the advertisement delivery accuracy and delivery effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in one or more embodiments of the present specification, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0012] Figure 1 A processing flow chart of a method for processing advertisement delivery provided in one embodiment of this specification; Figure 2 A processing flow chart of a method for processing advertisement delivery applied to an advertisement delivery scenario within an application provided by an embodiment of the present specification; Figure 3 A schematic diagram of the structure of an advertisement delivery system for advertisement delivery provided in one embodiment of the present specification; Figure 4 A schematic diagram of an advertisement delivery processing device provided in one embodiment of this specification; Figure 5 A schematic diagram of the structure of an advertisement delivery processing device provided in one embodiment of the present specification. DETAILED DESCRIPTION

[0013] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will be combined with the drawings in one or more embodiments of this specification to clearly and completely describe the technical solutions in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0014] This specification provides an example of an advertising processing method: Reference Figure 1 , which shows a processing flow chart of an advertisement delivery processing method provided in this embodiment. The advertisement delivery processing method provided in this embodiment specifically includes the following steps S102 to S108.

[0015] Step S102, obtaining user behavior data, advertisement delivery data, and delivery node data of the product combination to be advertised.

[0016] In actual applications, in order to optimize advertising delivery strategies and improve advertising delivery effects and user experience, after advertising is delivered based on the advertising delivery strategy, relevant data of the advertising delivery process can be obtained, that is, user behavior data, advertising delivery data, and delivery node data of the product combination for the advertising delivery can be obtained.

[0017] Among them, the product combination refers to a collection of multiple related or complementary products or services, that is, a group of products or services that users can purchase on one platform, which can be sold in combination (i.e., packages) to provide users with more comprehensive or more attractive choices; for example, the product combination can be a combination of different service packages, which may include but are not limited to: combinations of different types of communication services such as call minutes, SMS packages, data traffic packages, etc.; various value-added services, such as cloud storage space, video memberships, etc.; packages combined with hardware sales, such as the combination sale of mobile phones and traffic packages; customized service packages designed for specific user groups, such as family packages, corporate user packages, etc.

[0018] The user behavior data refers to the interaction records of users performing operations such as querying and purchasing product combinations in relevant applications, including but not limited to users' browsing data, i.e., the number of times users browse product combination advertisements and the length of time they browse; users' search data, i.e., the frequency with which users search for related product combination advertisements, search keywords entered for product combination advertisements, and the viewing of search results; users' product combination purchase data, i.e., the amount of product combination types, duration of use of product combinations, and the number of product combination purchases that users have purchased through advertising portals, as well as the amount of product combination types, duration of use of product combinations, and the number of product combination purchases that users have purchased without using advertising portals.

[0019] The advertising data refers to various statistical data and information generated during the advertising process, which are used to measure the effectiveness of advertising, including but not limited to the number of advertising types delivered, such as video ads, image ads, etc. The effectiveness of different types of ads can be evaluated by counting the number of each type; advertising share; advertising exposure, that is, the number of times the ad is displayed to users; ad clicks, that is, the number of times the ad is clicked by users; and ad conversion rate, that is, the number of conversions (such as purchases, registrations, etc.) after the ad is clicked.

[0020] The delivery node data refers to the relevant information of all network nodes involved in the process of advertising delivery; including but not limited to the number of network nodes for advertising delivery, that is, how many different network nodes or servers the advertisements are distributed to, to reflect the breadth of advertising coverage; the number of abnormal nodes, that is, the number of nodes with potential risks in the network, or the number of nodes that may affect the security and effectiveness of advertising delivery; the number of pop-up windows, that is, the number of unexpected pop-up windows that appear during the advertising delivery process; and network information of the advertising delivery platform, including but not limited to the response time of advertising requests, the health of the advertising server, the speed of advertising loading, etc.

[0021] During the specific execution process, after the user logs in to the relevant application on the device, each browsing, searching, clicking, purchasing and other behaviors of the user in the application can be recorded, and the corresponding user behavior data can be generated; at the same time, the relevant data of the advertisements that have been placed in the application will also be recorded. For example, for each displayed advertisement, it can track whether a user has clicked on the advertisement and record the corresponding number of advertisement clicks. It can also record the conversion status after the user clicks on the advertisement, such as whether the user has made subsequent behaviors such as purchase, registration, and filling out forms; during the advertising delivery process, it can also record the information of each network node involved in advertising display and transmission, such as evaluating the status of the advertising delivery node by recording the response time of the advertising request; it can also detect the health status of each node, such as network delay, and mark the abnormal node status; the user behavior data, advertising delivery data and delivery node data recorded above are read to calculate relevant indicators in the subsequent execution process.

[0022] For example, when a user wants to buy a certain type of package, he can log in to the relevant application to compare different package options. In this process, the user may browse different package pages, view detailed information of the package, etc.; accordingly, in this process, the user's relevant user behavior data can be obtained, such as which page the user stays on for a longer time, which advertising links the user clicks, how many times the user performs search operations, which package combination the user finally purchases, etc.; at the same time, it is also necessary to collect advertising data within the application, such as the number of times the advertisement corresponding to a certain package is displayed in the application, the number of times the advertisement is clicked, the type of advertisement, the number of conversions ultimately caused by the advertisement, etc.; in addition, in addition to collecting the above-mentioned user behavior data and advertising delivery data, it is also necessary to obtain the delivery node data for advertising delivery within the application to evaluate the security and effectiveness of the advertising delivery environment, such as the response time of the advertising request after the user clicks on an advertisement, whether the advertisement is successfully loaded to be displayed to the user, whether there is abnormal software, etc.; in the subsequent process, based on the above-mentioned user behavior data, advertising delivery data and delivery node data, the advertising delivery process can be evaluated and adjusted.

[0023] Step S104, calculating an advertisement precision coefficient based on the user behavior data and the advertisement delivery data, calculating an advertisement return index based on the advertisement delivery data, and calculating an advertisement safety coefficient based on the advertisement delivery data and the delivery node data.

[0024] After obtaining the user behavior data, advertising delivery data and delivery node data of the product combination for advertising delivery, relevant data calculations can be performed based on the obtained user behavior data, advertising delivery data and delivery node data to obtain data indicators for measuring the effectiveness of advertising delivery.

[0025] It should be noted that after obtaining the user behavior data, advertising delivery data and delivery node data of the product combination for advertising delivery, before performing relevant calculations based on the obtained data, the obtained data can also be pre-processed, that is, the obtained user behavior data, advertising delivery data and delivery node data can be cleaned and denoised, so as to ensure that subsequent analysis can be based on high-quality data, so as to improve the accuracy and reliability of the analysis results.

[0026] Among them, preprocessing of the acquired data includes but is not limited to cleaning the acquired data, that is, removing erroneous information, duplicate information, incomplete records, etc. in the acquired data, such as deleting or correcting erroneous data entries, removing duplicate data records, supplementing missing data fields, etc.; and performing noise reduction on the acquired data to make the data clearer and more accurate.

[0027] In specific implementation, after preprocessing the acquired data, relevant data calculations can be performed based on the preprocessed user behavior data, advertising delivery data, and delivery node data. The following describes the calculation process of calculating the advertising precision coefficient based on the user behavior data and advertising delivery data, calculating the advertising return index based on the advertising delivery data, and calculating the advertising safety factor based on the advertising delivery data and delivery node data.

[0028] (1) Calculate the advertising precision coefficient Specifically, in order to quantify the accuracy of advertisement delivery to reflect the degree of matching between advertisement delivery and user interests, an optional implementation manner provided in this embodiment calculates the advertisement accuracy coefficient based on user behavior data and advertisement delivery data, including: a. Inputting the user behavior data into a user reliable cardinality algorithm to obtain a user reliable cardinality; For example, the user reliability cardinality of the package can be calculated based on the number of times the user browses the package advertisement, the frequency of the user searching for the package advertisement, the number of times the user purchases the package through the advertisement entrance, the number of times the user purchases the package not through the advertisement entrance, the duration of the user browsing the package advertisement, the amount of the package purchased by the user through the advertisement entrance, and the amount of the package purchased by the user not through the advertisement entrance in the acquired user behavior data; specifically, the user reliability cardinality K can be calculated using the following formula:

[0029] Where n is the total number of users, i=1, 2, 3...n, is the number of times the i-th user browses the package advertisement, The frequency of searching for package advertisements for the i-th user, is the number of times the i-th user purchases a package through the advertising portal, is the number of times the i-th user purchased a package not through the advertising portal, is the duration of the i-th user browsing the package advertisement, is the package amount purchased by the i-th user through the advertising portal, The package amount purchased by the i-th user not through the advertising portal.

[0030] b. inputting the advertisement delivery data into an advertisement delivery base number algorithm to obtain an advertisement delivery base number; For example, firstly, the advertising proportion of the package is calculated based on the advertising area and the total advertising area of ​​the package in the advertising data, and then based on the calculated advertising proportion, combined with the advertising clicks, advertising exposures, number of advertising types and advertising conversion rate of the package in the advertising data, the advertising base of the package is calculated; specifically, the advertising proportion p gIt can be calculated using the following formula:

[0031] Among them, S g is the area of ​​advertisement placement, S0 is the total area of ​​the placement interface; if the advertisement placement area corresponding to a package is larger, the advertisement proportion of the package will be larger; if the advertisement placement area is smaller, the corresponding advertisement proportion will be smaller; Based on the calculated advertising proportion p g As well as other advertising data, the advertising base G can be calculated using the following formula:

[0032] Among them, f g is the number of ad clicks, e g is the advertising exposure, p g is the advertising ratio, s g is the number of advertisement types, h g is the advertising conversion rate; when the number of ad clicks and / or the advertising conversion rate is greater, the advertising delivery base is larger; when the advertising exposure, advertising proportion and / or the number of advertising types are greater, the advertising delivery base is smaller.

[0033] c. Calculate the advertisement precision coefficient based on the user reliability base and the advertisement delivery base.

[0034] The advertising precision coefficient refers to a quantitative indicator used to measure the degree of match between advertising and the interests of the target audience, so as to reflect the extent to which the matching user group can be hit when the advertisement is delivered; the user reliability base refers to a quantitative indicator used to measure the user's interest or credibility in the advertisement, so as to reflect the user's response to the advertisement and the user's activity; the advertising delivery base refers to a quantitative indicator used to measure the advertising display effect, so as to reflect the effectiveness and influence of the advertisement during the display process.

[0035] Further, according to the calculated user reliable cardinality and advertisement delivery cardinality, the advertisement precision coefficient may be calculated. In an optional implementation manner provided in this embodiment, the advertisement precision coefficient is calculated based on the user reliable cardinality and advertisement delivery cardinality, including: Calculating the cardinality sum of the user reliable cardinality and the advertisement delivery cardinality; Calculating the ratio of the number of times the user purchased the product combination based on the delivered advertisement to the number of times the user did not purchase the product combination based on the delivered advertisement; The product of the base number and the ratio of the number of times is used as the advertisement precision coefficient.

[0036] During the specific implementation process, when a user logs in to a relevant application to purchase a relevant product combination, if the user sees an advertisement for the product combination on the application page and clicks on the advertisement, a corresponding touch instruction can be generated based on the user's touch action, and the user can be redirected to a purchase page corresponding to the product combination based on the touch instruction. When the user purchases the relevant product combination on the page, the number of times the user has purchased the product combination based on the placed advertisements can be recorded and updated based on the user's purchase behavior this time; when a user purchases a product combination that is not advertised in the application, that is, the user does not see an advertisement for the product combination in the application after logging in to the application, but searches for the corresponding product combination through keyword search or the like and purchases the product combination, the number of times the user has not purchased the product combination based on the placed advertisements can be recorded and updated based on the user's purchase behavior this time.

[0037] For example, in the process of calculating the advertising precision coefficient, after obtaining the calculated user reliability base and advertising base, it is also necessary to calculate the number of times users purchase the package based on the delivered advertisements and the number of times users purchase the package not based on the delivered advertisements (but through other methods, such as searching keywords, etc.); specifically, the advertising precision coefficient β can be calculated using the following formula:

[0038] Among them, K is the user reliable base, G is the advertising base, is the number of times the i-th user purchases a package through the advertisement. is the number of times the i-th user purchases a package without using the delivered advertisements; when the user reliability base, the advertisement delivery base and / or the number of times the user purchases a package through the delivered advertisements are larger, the advertisement precision coefficient is larger, that is, the accuracy of the advertisement delivery is higher; when the number of times the user purchases a package without using the delivered advertisements is larger, the advertisement precision coefficient is smaller, that is, the accuracy of the advertisement delivery is lower.

[0039] (2) Calculation of advertising return index Specifically, in order to quantify the economic benefits of advertising, optimize the allocation of advertising resources, and provide data support for advertising delivery strategies, an optional implementation method provided in this embodiment calculates the advertising return index based on advertising delivery data, including: The advertising revenue and the advertising cost included in the advertising data are obtained, and the ratio of the advertising revenue to the advertising cost is used as the advertising return index.

[0040] The advertising return index refers to a quantitative indicator used to evaluate the economic benefits of advertising; the advertising return index can reflect the relationship between the net income brought by advertising and the input cost. The higher the advertising return index, the better the economic benefits of advertising; the lower the advertising return index, the lower the economic benefits of advertising have not met expectations; based on the advertising return index, it can be intuitively seen whether the advertising has achieved or exceeded the expected benefits, thereby evaluating the overall effect of advertising.

[0041] The so-called advertising revenue refers to the total direct or indirect revenue obtained after the advertising is placed; the advertising revenue may include but is not limited to: direct sales revenue, that is, the increase in direct sales brought about by advertising, such as the revenue generated by users purchasing goods or services after clicking on the advertisement; brand exposure revenue, although this part of the revenue is not immediately converted into sales, it increases brand awareness and favorability, and can create conditions for future sales; as well as increase in potential customers, long-term benefits, etc.

[0042] The so-called advertising cost refers to all costs incurred in the process of advertising; advertising costs may include media purchasing costs, planning and design costs, operation and maintenance costs, technical support costs, etc.

[0043] For example, the advertising return index can be calculated based on the advertising revenue and advertising cost in the advertising data. Specifically, the advertising return index It can be calculated using the following formula:

[0044] in, The revenue from advertising, The total cost of advertising. Based on a certain advertising cost, the greater the profit brought by advertising, the higher the advertising return index. The higher the value, the less profit the advertisement brings. Correspondingly, when a certain advertising strategy can bring certain benefits, the lower the advertising cost invested in the advertising strategy, the higher the advertising return index. The higher.

[0045] (3) Calculate the advertising safety factor Specifically, in order to evaluate whether there are security risks in the advertising delivery platform during the advertising delivery process, so as to reflect the security level of the advertising delivery interface for users, an optional implementation method provided by this embodiment calculates the advertising safety factor according to the advertising delivery data and the delivery node data, including: a. Calculating node security parameters based on the advertisement delivery data and the delivery node data; Furthermore, in an optional implementation manner provided by this embodiment, the node security parameter is calculated based on the advertisement delivery data and the delivery node data, including: Calculating the abnormal ratio of the number of abnormal nodes for each placed advertisement to the number of network nodes as the abnormal ratio of each placed advertisement; Adding the abnormal proportions of the delivered advertisements to obtain a sum; The ratio of the sum to the number of the delivered advertisements is used as the node security parameter.

[0046] The network node in this embodiment refers to each entity or device that participates in the display, transmission and reception of advertisements during the advertisement delivery process. The network node can be a physical device (such as a server, router, etc.) or a logical entity (such as an advertisement trading platform, an advertisement server, etc.), including but not limited to network devices such as servers, advertisement trading platforms, user terminals, routers and switches; the abnormal node in this embodiment refers to a node that has potential risks or has been confirmed to be abnormal during the network advertisement delivery process. The abnormal node may have adverse effects on users, including but not limited to the spread of abnormal software, false links or other forms of network attacks.

[0047] The node security parameters refer to security indicators related to each network node in the advertising delivery platform, which are used to evaluate the security status of each network node. The node security parameters can be used to identify and prevent potential abnormal nodes to ensure the security and user experience during the advertising delivery process; the node security parameters include but are not limited to the number of abnormal nodes detected during the advertising delivery process, the total number of network nodes in the advertising delivery platform, and the ratio of the number of abnormal nodes to the total number of network nodes; by calculating the node security parameters, nodes that may have security risks can be identified, so that for nodes with low security, corresponding measures can be taken to optimize or temporarily stop delivery until the security problem is resolved.

[0048] For example, first obtain the number of advertisements delivered in the advertisement delivery data, and at the same time obtain the number of abnormal nodes that have delivered advertisements and the total number of network nodes to calculate the node security parameter; specifically, the node security parameter A can be calculated using the following formula:

[0049] Where Q is the number of advertisements placed, q=1, 2, 3...Q, is the number of abnormal nodes, is the total number of network nodes that deliver advertisements, is the number of abnormal nodes in the qth advertisement, is the total number of network nodes that deliver the qth advertisement; when the number of abnormal nodes is higher, the node security parameter is larger, that is, the security status at this time is lower; when the total number of network nodes is higher, the node security parameter is smaller, that is, the network environment for advertisement delivery at this time is relatively safe.

[0050] b. Calculating network security parameters based on the delivery node data; Furthermore, in order to calculate the advertisement safety factor, network security parameters need to be calculated. In an optional implementation provided by this embodiment, the network security parameters are calculated based on the delivery node data, including: Calculate the total number of network links, pop-up ads, and abnormal ads blocked by the advertising platform; The ratio of the number of safe advertisements on the advertisement delivery platform to the total number is calculated as the network security parameter.

[0051] The network security parameters refer to the network performance and security information related to the advertising delivery platform and its surrounding environment, which are used to evaluate the effectiveness and security of the advertising delivery environment. The network security parameters include but are not limited to the number of abnormal network links intercepted by the advertising delivery platform, the number of unexpected pop-up windows that appear during the advertising delivery process, the number of abnormal advertisements detected during the advertising delivery process, and the number of normal and safe advertisements during the advertising delivery process.

[0052] For example, after the advertisement is delivered, the number of safe advertisements on the advertisement delivery platform, the number of network links intercepted by the advertisement delivery platform, the number of pop-up advertisements intercepted by the advertisement delivery platform, and the number of abnormal advertisements on the advertisement delivery platform can be obtained. Based on the above-obtained delivery node data, the network security parameters are calculated; the network security parameter W can be calculated using the following formula:

[0053] Among them, W is the network security parameter of the advertising platform, The number of safe ads for the advertising platform. The number of web links blocked for the ad delivery platform, The number of pop-up ads blocked by the advertising platform. It is the number of abnormal advertisements on the advertising platform; when the number of safe advertisements on the advertising platform is higher, the network security parameter is larger, which means that the advertising platform that is delivering advertisements at this time publishes more safe advertisements, and the overall security of the network environment is higher; when the number of intercepted network links, the number of intercepted pop-up advertisements and / or the number of abnormal advertisements is higher, the network security parameter is smaller, which means that the advertising platform that is delivering advertisements at this time has relatively more security risks.

[0054] c. Performing weighted summation of the node security parameter and the network security parameter according to a preset weight factor to obtain the advertisement security coefficient.

[0055] The advertising safety factor refers to a comprehensive indicator for evaluating whether there are security risks in the advertising delivery platform during the advertising delivery process; by evaluating the advertising safety factor, it can be ensured that the advertising content delivered by the advertising delivery platform does not contain abnormal software, abnormal links or other abnormal information, so as to protect the security of users' devices and personal information.

[0056] For example, firstly, node security parameters are calculated based on the advertisement delivery data and delivery node data, and network security parameters are calculated based on the delivery node data. Secondly, the advertisement security factor is calculated based on the calculated node security parameters and network security parameters. Specifically, the advertisement security factor It can be calculated using the following formula:

[0057] Among them, A is the node security parameter, W is the network security parameter, is the node safety parameter proportional constant, is the network security parameter proportional constant of the advertising platform, and satisfy + =1, where 0.5 1,0 0.5, and The value can be set according to the specific situation.

[0058] Step S106, calculating the delivery effect index according to the advertisement precision coefficient, the advertisement return index and the advertisement safety coefficient.

[0059] After obtaining the user behavior data of the product combination for advertising, the advertising data of the product combination, and the delivery node data of the delivery platform for advertising the product combination, the above-mentioned data are preprocessed, and the advertising precision coefficient, advertising return index and advertising safety factor are calculated based on the preprocessed data. Furthermore, the delivery effect index can be calculated based on the calculated advertising precision coefficient, advertising return index and advertising safety factor.

[0060] The advertising effectiveness index refers to a quantitative indicator used to evaluate the overall effectiveness of advertising, so as to reflect the economic benefits, user engagement, and security of advertising.

[0061] Specifically, in order to more comprehensively reflect the overall performance of advertising delivery, a more comprehensive analysis of the overall effect of advertising delivery can be conducted from three aspects: advertising delivery accuracy, advertising return index, and advertising delivery safety. In an optional implementation provided by this embodiment, the delivery effect index is calculated based on the advertising accuracy coefficient, the advertising return index, and the advertising safety coefficient, including: Taking the logarithm of the sum of the advertising precision coefficient, the advertising return index, and the advertising safety coefficient to obtain a logarithmic value; The delivery effect index is calculated based on the fluctuation constant and the logarithmic value.

[0062] Among them, the fluctuation constant refers to a preset parameter used to measure the stability of the advertising effect index over time and reflect the fluctuation of the advertising effect; the larger the fluctuation constant, the more unstable the advertising effect; the smaller the fluctuation constant, the more stable the advertising effect.

[0063] For example, after obtaining the advertising precision coefficient, advertising return index and advertising safety factor, the advertising delivery effect index can be calculated in combination with the preset fluctuation constant; the delivery effect index It can be calculated using the following formula:

[0064] in, is the advertising precision coefficient, is the advertising return index, is the advertising safety factor, is a fluctuation constant. Since the effect of advertising delivery is also affected by other factors, the value of the delivery effect index φ will fluctuate up and down. Satisfy 0.5 1.5.

[0065] Step S108, comparing the delivery effect index with a preset delivery adjustment threshold to obtain a comparison result.

[0066] After obtaining the user behavior data of the product combination for advertising, the advertising data of the product combination, and the delivery node data of the delivery platform for advertising the product combination, the above-mentioned data are preprocessed, and the advertising precision coefficient, advertising return index and advertising safety factor are calculated based on the preprocessed data. Based on the advertising precision coefficient, advertising return index and advertising safety factor, the advertising delivery effect index is calculated. Furthermore, the calculated delivery effect index can be compared with a preset delivery adjustment threshold, so as to optimize or adjust the advertising delivery process according to the comparison result.

[0067] Among them, the delivery adjustment threshold refers to a set value or a series of values, which is used to define the standard for taking corresponding measures when the advertising delivery effect reaches a certain level. That is, the delivery adjustment threshold is a reference value used to determine whether the advertising delivery strategy needs to be adjusted during the advertising delivery process.

[0068] In specific implementation, after calculating the delivery effect index based on the advertising precision coefficient, the advertising return index and the advertising safety factor, and comparing the delivery effect index with the preset delivery adjustment threshold, an optional implementation provided by this embodiment compares the delivery effect index with the preset delivery adjustment threshold to obtain a comparison result, including: If the delivery effect index is less than or equal to the delivery adjustment threshold, a strategy adjustment coefficient of the advertisement delivery strategy is calculated, and the delivery strategy is adjusted based on the strategy adjustment coefficient.

[0069] The strategy adjustment coefficient refers to a quantitative indicator calculated based on the comparison result of the delivery effect index and the delivery adjustment threshold, which is used to guide the next delivery strategy adjustment.

[0070] Specifically, in order to set a reasonable strategy adjustment coefficient to avoid large fluctuations in advertising delivery effects and improve the stability of advertising delivery effects, in an optional implementation provided by this embodiment, the strategy adjustment coefficient of the advertising delivery strategy is calculated, including: Calculate the product of the advertising precision coefficient, the advertising return index and the advertising safety coefficient; Calculating the difference between the delivery adjustment threshold and the delivery effect index; The strategy adjustment coefficient is calculated according to the product, the difference and a preset constant.

[0071] In the specific implementation process, after obtaining the advertisement delivery effect index through calculation, the delivery effect index can be compared with the preset delivery adjustment threshold to determine whether the advertisement delivery effect reaches the expected level. If the advertisement delivery effect index is less than or equal to the delivery adjustment threshold, it is considered that the advertisement delivery based on the current advertisement delivery strategy has not reached the expected level. In other words, it can be considered that the current advertisement delivery strategy is not effective and needs to be adjusted and optimized. For example, the targeting rules of advertisement delivery can be changed, the delivery frequency can be adjusted, and the advertisement materials or content can be modified. In order to better control the process of advertisement delivery, improve the controllability of advertisement delivery, and more reasonably allocate advertisement delivery resources, the adjustment of the advertisement delivery strategy needs to be based on the strategy adjustment coefficient.

[0072] For example, after obtaining user behavior data, advertising delivery data, and delivery node data and preprocessing the above data, the advertising precision coefficient, advertising return index, and advertising safety coefficient can be calculated based on the preprocessed user behavior data, advertising delivery data, and delivery node data, and the strategy adjustment coefficient of the advertising strategy can be calculated in combination with the preset delivery adjustment threshold. It can be calculated using the following formula:

[0073] in, is the advertising precision coefficient, is the advertising return index, is the advertising safety factor, is the delivery effect index, and R is the delivery adjustment threshold; After calculating and obtaining the advertising strategy adjustment coefficient, the optimization of advertising delivery can be carried out based on the advertising strategy adjustment coefficient. That is, based on the advertising strategy adjustment coefficient, an optimization instruction can be sent to the automatic optimization unit of the advertising delivery system to adjust the advertising delivery strategy, thereby optimizing the advertising delivery. By continuously optimizing and upgrading the advertising delivery, the accuracy and effectiveness of the advertising delivery can be guaranteed, thereby providing a data basis for improving the effectiveness of the advertising delivery.

[0074] In addition, after the delivery effect index is compared with the preset delivery adjustment threshold, if the delivery effect index of the advertisement is greater than the delivery adjustment threshold, it can be considered that the current advertising delivery strategy is effective and does not need to be adjusted. At this time, the delivery effect index of the advertisement can be transmitted to the interactive system for further analysis or display. For example, after the delivery effect index is transmitted to the interactive system, the interactive system can display that the current advertising delivery strategy is effective based on the delivery effect index, and can continue to maintain the current advertising delivery strategy or further optimize the advertising delivery strategy to maintain good results.

[0075] To summarize, the present embodiment provides a method for processing advertising delivery. After delivering advertisements based on an advertising delivery strategy, the method first obtains user behavior data, advertising delivery data, and delivery node data of the product combination to be delivered, and then calculates the advertising precision coefficient based on the user behavior data and the advertising delivery data, calculates the advertising return index based on the advertising delivery data, and calculates the advertising safety factor based on the advertising delivery data and the delivery node data. Then, the delivery effect index is calculated based on the calculated advertising precision coefficient, advertising return index, and advertising safety factor. Finally, the delivery effect index is compared with a preset delivery adjustment threshold, and the delivery strategy of the advertising delivery is adjusted according to the comparison result to optimize and upgrade the advertising delivery accuracy and delivery effect.

[0076] The following combination Figure 2 , taking the application of the advertising delivery processing method provided by this embodiment in the advertising delivery scenario within an application as an example, the advertising delivery processing method provided by this embodiment is further described. Figure 2 The processing method for advertisement delivery applied to the advertisement delivery scenario within an application program specifically includes steps S202 to S236.

[0077] Step S202, obtaining user behavior data, advertisement delivery data, and delivery node data of the package for advertisement delivery; and pre-processing the obtained data.

[0078] Step S204: input the user behavior data into a user reliability cardinality algorithm to obtain a user reliability cardinality.

[0079] Step S206: input the advertisement delivery data into an advertisement delivery base algorithm to obtain an advertisement delivery base.

[0080] Step S208, calculating the advertisement precision coefficient based on the user reliability base, the advertisement delivery base, the number of times the user purchases the package based on the delivered advertisements, and the number of times the user purchases the package not based on the delivered advertisements.

[0081] Step S210: Calculate the ratio of the delivery revenue and delivery cost contained in the advertisement delivery data as the advertisement return index.

[0082] Step S212: Calculate node security parameters based on the advertisement delivery data and delivery node data.

[0083] Step S214, calculating network security parameters based on the delivery node data.

[0084] Step S216, calculating the advertisement security factor based on the node security parameters and the network security parameters.

[0085] Step S218, calculating the delivery effect index based on the advertising precision coefficient, the advertising return index, the advertising safety coefficient and the preset fluctuation constant.

[0086] Step S220, compare the delivery effect index with the preset delivery adjustment threshold to determine whether the delivery effect index is less than or equal to the delivery adjustment threshold; if so, execute step S222; if not, the delivery effect index can be transmitted to the interactive system.

[0087] Step S222, calculating the strategy adjustment coefficient of the advertisement delivery strategy.

[0088] Step S224, adjusting the delivery strategy based on the strategy adjustment coefficient.

[0089] like Figure 3 As shown, Figure 2The processing method for advertising delivery in the invention can be configured with a distributed computing storage module, an advertising delivery module, an advertising data collection module, an advertising data preprocessing module, an advertising delivery accuracy analysis module, an advertising investment return rate analysis module, an advertising safety analysis module, an overall delivery effect analysis module, a distribution delivery optimization module and an interactive module; the above-mentioned step S202 can be executed by the distributed computing storage module, the advertising data collection module and the advertising data preprocessing module, steps S204 to S208 can be executed by the advertising delivery accuracy analysis module, step S210 can be executed by the advertising investment return rate analysis module, steps S212 to S216 can be executed by the advertising safety analysis module, step S218 can be executed by the overall delivery effect analysis module, steps S220 to S224 can be executed by the distribution delivery optimization module and the advertising delivery module, and if the delivery effect index is greater than the delivery adjustment threshold, the delivery effect index is transmitted to the interactive system.

[0090] The advertising delivery processing method provided in the present embodiment first obtains user behavior data, advertising delivery data, and delivery node data of the product combination to be advertised, and then calculates the advertising precision coefficient according to the user behavior data and the advertising delivery data, calculates the advertising return index according to the advertising delivery data, and calculates the advertising safety factor according to the advertising delivery data and the delivery node data, and then calculates the delivery effect index based on the calculated advertising precision coefficient, advertising return index, and advertising safety factor, and finally compares the delivery effect index with a preset delivery adjustment threshold, and adjusts the delivery strategy of the advertising delivery according to the comparison result, so as to optimize and upgrade the advertising delivery precision and delivery effect.

[0091] Figure 4 A schematic diagram of an advertisement delivery processing device provided by an embodiment of the present invention is shown in FIG. Figure 4 As shown, the device comprises: The data acquisition module 402 is configured to acquire user behavior data, advertisement delivery data, and delivery node data of the product combination to be advertised; The data calculation module 404 is configured to calculate an advertisement accuracy coefficient according to the user behavior data and the advertisement delivery data, calculate an advertisement return index according to the advertisement delivery data, and calculate an advertisement safety coefficient according to the advertisement delivery data and the delivery node data; The effect index calculation module 406 is configured to calculate the delivery effect index according to the advertisement precision coefficient, the advertisement return index and the advertisement safety coefficient; The comparison module 408 is configured to compare the delivery effect index with a preset delivery adjustment threshold to obtain a comparison result.

[0092] The advertising delivery processing device provided in the present embodiment firstly executes the data acquisition module 402 to acquire the user behavior data, the advertising delivery data and the delivery node data of the product combination to be advertised, and then executes the data calculation module 404 to calculate the advertising precision coefficient according to the user behavior data and the advertising delivery data, calculates the advertising return index according to the advertising delivery data, and calculates the advertising safety factor according to the advertising delivery data and the delivery node data, and then executes the effect index calculation module 406 to calculate the delivery effect index according to the advertising precision coefficient, the advertising return index and the advertising safety factor, and finally executes the comparison module 408 to compare the delivery effect index with the preset delivery adjustment threshold to obtain a comparison result.

[0093] An advertisement delivery processing device provided in one embodiment of the present specification can implement each process in the aforementioned method embodiment and achieve the same functions and effects, which will not be repeated here.

[0094] Furthermore, an embodiment of the present specification also provides an advertisement delivery processing device, Figure 5 A schematic diagram of a structure of an advertisement delivery processing device provided in one embodiment of the present specification, such as Figure 5 As shown, the device includes: a memory 501, a processor 502, a bus 503 and a communication interface 504. The memory 501, the processor 502 and the communication interface 504 communicate through the bus 503, and the communication interface 504 may include an input and output interface, which includes but is not limited to a keyboard, a mouse, a display, a microphone, a loudspeaker, etc.

[0095] Figure 5 In the embodiment, the memory 501 stores computer executable instructions that can be run on the processor 502. When the computer executable instructions are executed by the processor 502, the following process is implemented: Obtain user behavior data, advertisement delivery data, and delivery node data for the product combination for advertisement delivery; Calculate an advertisement precision coefficient based on the user behavior data and the advertisement delivery data, continue to calculate an advertisement return index based on the advertisement delivery data, and calculate an advertisement safety coefficient based on the advertisement delivery data and the delivery node data; Calculate the delivery effect index according to the advertisement precision coefficient, the advertisement return index and the advertisement safety coefficient; The delivery effect index is compared with a preset delivery adjustment threshold to obtain a comparison result.

[0096] The advertising delivery processing device provided in this embodiment, through the cooperation of the memory 501, the processor 502, the bus 503 and the communication interface 504, first obtains the user behavior data, the advertising delivery data and the delivery node data of the product combination for advertising delivery, and then calculates the advertising precision coefficient according to the user behavior data and the advertising delivery data, calculates the advertising return index according to the advertising delivery data, and calculates the advertising safety factor according to the advertising delivery data and the delivery node data, and then calculates the delivery effect index based on the calculated advertising precision coefficient, advertising return index and advertising safety factor, and finally compares the delivery effect index with the preset delivery adjustment threshold, and adjusts the delivery strategy of the advertising delivery according to the comparison result, so as to optimize and upgrade the advertising delivery accuracy and delivery effect.

[0097] An advertisement delivery processing device provided in one embodiment of the present specification can implement each process in the aforementioned method embodiment and achieve the same functions and effects, which will not be repeated here.

[0098] Furthermore, another embodiment of the present specification provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store computer-executable instructions, and when the computer-executable instructions are executed by a processor, the following process is implemented: Obtain user behavior data, advertisement delivery data, and delivery node data for the product combination for advertisement delivery; Calculating an advertisement precision coefficient based on the user behavior data and the advertisement delivery data, calculating an advertisement return index based on the advertisement delivery data, and calculating an advertisement safety coefficient based on the advertisement delivery data and the delivery node data; Calculate the delivery effect index according to the advertisement precision coefficient, the advertisement return index and the advertisement safety coefficient; The delivery effect index is compared with a preset delivery adjustment threshold to obtain a comparison result.

[0099] The computer-readable storage medium provided in this embodiment first obtains user behavior data, advertising delivery data, and delivery node data of a product combination for advertising delivery, and then calculates an advertising precision coefficient based on the user behavior data and the advertising delivery data, calculates an advertising return index based on the advertising delivery data, and calculates an advertising safety factor based on the advertising delivery data and the delivery node data, and then calculates a delivery effect index based on the calculated advertising precision coefficient, advertising return index, and advertising safety factor, and finally compares the delivery effect index with a preset delivery adjustment threshold, and adjusts the delivery strategy of the advertising delivery according to the comparison result, so as to optimize and upgrade the advertising delivery accuracy and delivery effect.

[0100] The computer-readable storage medium includes a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0101] The computer-readable storage medium provided in an embodiment of this specification can implement each process in the aforementioned method embodiment and achieve the same functions and effects, which will not be repeated here.

[0102] Furthermore, another embodiment of the present specification also provides a computer program product, which implements the following process when executed by a processor: Obtain user behavior data, advertising data, and delivery node data for the product combination being advertised; Calculating an advertisement precision coefficient based on the user behavior data and the advertisement delivery data, calculating an advertisement return index based on the advertisement delivery data, and calculating an advertisement safety coefficient based on the advertisement delivery data and the delivery node data; Calculate the delivery effect index according to the advertisement precision coefficient, the advertisement return index and the advertisement safety coefficient; The delivery effect index is compared with a preset delivery adjustment threshold to obtain a comparison result.

[0103] The computer program product provided in this embodiment first obtains user behavior data, advertising delivery data, and delivery node data of a product combination to be advertised, and then calculates an advertising precision coefficient based on the user behavior data and the advertising delivery data, calculates an advertising return index based on the advertising delivery data, and calculates an advertising safety factor based on the advertising delivery data and the delivery node data, and then calculates a delivery effect index based on the calculated advertising precision coefficient, advertising return index, and advertising safety factor, and finally compares the delivery effect index with a preset delivery adjustment threshold, and adjusts the delivery strategy of the advertising delivery according to the comparison result, so as to optimize and upgrade the advertising delivery precision and delivery effect.

[0104] The computer program product provided in one embodiment of this specification can implement each process in the aforementioned method embodiment and achieve the same functions and effects, which will not be repeated here.

[0105] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0106] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0107] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0108] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0109] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0110] Memory may include non-permanent storage in a computer-readable storage medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable storage medium.

[0111] Computer-readable storage media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable storage media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0112] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0113] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0114] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for processing advertisement delivery, characterized in that: The method comprises: Obtain user behavior data, advertisement delivery data, and delivery node data for the product combination for advertisement delivery; Calculating an advertisement precision coefficient based on the user behavior data and the advertisement delivery data, calculating an advertisement return index based on the advertisement delivery data, and calculating an advertisement safety coefficient based on the advertisement delivery data and the delivery node data; Calculate the delivery effect index according to the advertisement precision coefficient, the advertisement return index and the advertisement safety coefficient; The delivery effect index is compared with a preset delivery adjustment threshold to obtain a comparison result.

2. The method for processing advertisement delivery according to claim 1, wherein the step of calculating the advertisement precision coefficient based on the user behavior data and the advertisement delivery data comprises: Inputting the user behavior data into a user reliability cardinality algorithm to obtain a user reliability cardinality; Inputting the advertisement delivery data into an advertisement delivery base number algorithm to obtain an advertisement delivery base number; The advertisement precision coefficient is calculated based on the user reliability base and the advertisement delivery base.

3. The method for processing advertisement delivery according to claim 2, wherein the step of calculating the advertisement precision coefficient based on the user reliability base and the advertisement delivery base comprises: Calculating the cardinality sum of the user reliable cardinality and the advertisement delivery cardinality; Calculating the ratio of the number of times the user purchased the product combination based on the delivered advertisement to the number of times the user did not purchase the product combination based on the delivered advertisement; The product of the base number and the ratio of the number of times is used as the advertisement precision coefficient.

4. The method for processing advertisement delivery according to claim 1, wherein the step of calculating the advertisement return index according to the advertisement delivery data comprises: The advertising revenue and the advertising cost included in the advertising data are obtained, and the ratio of the advertising revenue to the advertising cost is used as the advertising return index.

5. The method for processing advertisement delivery according to claim 1, wherein the step of calculating the advertisement safety factor based on the advertisement delivery data and the delivery node data comprises: Calculate node security parameters according to the advertisement delivery data and the delivery node data; Calculate network security parameters based on the delivery node data; The node security parameter and the network security parameter are weighted and summed according to a preset weight factor to obtain the advertisement security coefficient.

6. The method for processing advertisement delivery according to claim 5, wherein calculating node security parameters according to the advertisement delivery data and the delivery node data comprises: Calculating the abnormal ratio of the number of abnormal nodes for each placed advertisement to the number of network nodes as the abnormal ratio of each placed advertisement; Adding the abnormal proportions of the delivered advertisements to obtain a sum; The ratio of the sum to the number of the delivered advertisements is used as the node security parameter.

7. The method for processing advertisement delivery according to claim 5, wherein the step of calculating network security parameters according to the delivery node data comprises: Calculate the total number of network links, pop-up ads, and abnormal ads blocked by the advertising platform; The ratio of the number of safe advertisements on the advertisement delivery platform to the total number is calculated as the network security parameter.

8. The method for processing advertisement delivery according to claim 1, wherein the step of calculating the delivery effect index according to the advertisement precision coefficient, the advertisement return index and the advertisement safety coefficient comprises: Taking the logarithm of the sum of the advertising precision coefficient, the advertising return index, and the advertising safety coefficient to obtain a logarithmic value; The delivery effect index is calculated based on the fluctuation constant and the logarithmic value.

9. The method for processing advertisement delivery according to claim 1, wherein the step of comparing the delivery effect index with a preset delivery adjustment threshold to obtain a comparison result comprises: If the delivery effect index is less than or equal to the delivery adjustment threshold, a strategy adjustment coefficient of the advertisement delivery strategy is calculated, and the delivery strategy is adjusted based on the strategy adjustment coefficient.

10. The method for processing advertisement delivery according to claim 9, wherein the step of calculating the strategy adjustment coefficient of the advertisement delivery strategy comprises: Calculate the product of the advertising precision coefficient, the advertising return index and the advertising safety coefficient; Calculating the difference between the delivery adjustment threshold and the delivery effect index; The strategy adjustment coefficient is calculated according to the product, the difference and a preset constant.

Images