CN114581128A

CN114581128A - Advertisement putting method and device, electronic equipment and computer readable medium

Info

Publication number: CN114581128A
Application number: CN202210188249.4A
Authority: CN
Inventors: 温雅; 周晓蕾; 姜家立; 王学强; 崔波; 赫南
Original assignee: Beijing Wodong Tianjun Information Technology Co Ltd
Current assignee: Beijing Wodong Tianjun Information Technology Co Ltd
Priority date: 2022-02-28
Filing date: 2022-02-28
Publication date: 2022-06-03

Abstract

The application discloses an advertisement putting method, an advertisement putting device, electronic equipment and a computer readable medium, which relate to the technical field of computers, and the method comprises the following steps: receiving an advertisement putting request, acquiring a corresponding putting identifier, and acquiring a corresponding user identifier based on the putting identifier; determining each passenger group category to which the user corresponding to the user identification belongs based on the user identification; acquiring historical advertisement putting data of users corresponding to each customer group type, and calling an algorithm model output strategy to determine a serialized putting strategy corresponding to each customer group type based on the historical advertisement putting data of the users; and respectively determining the serialized advertisement identifications corresponding to the serialized advertisement putting strategies, and sending the serialized advertisement identifications to the playing ends of the advertisement service lines corresponding to the guest group classes, so that the playing ends play the advertisements in order based on the serialized advertisement identifications. The advertisement effect is increased while the advertisement cost is reduced, and the conversion rate of the advertisement is improved.

Description

Advertisement putting method and device, electronic equipment and computer readable medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to an advertisement delivery method and apparatus, an electronic device, and a computer-readable medium.

Background

The consumer shopping path analysis is to evaluate the post-delivery effect based on the historical delivery data of the merchant, restore the order delivery path of the user, analyze and diagnose the consumer shopping path based on the restored order delivery path of the user, but cannot provide detailed and specific subsequent advertisement path delivery suggestions capable of being landed.

In the process of implementing the present application, the inventor finds that at least the following problems exist in the prior art:

after the user ordering path is restored based on the historical putting data of the merchant, detailed and specific subsequent advertisement path putting suggestions which can be landed on the ground cannot be provided.

Disclosure of Invention

In view of this, embodiments of the present application provide an advertisement delivery method, an advertisement delivery device, an electronic device, and a computer-readable medium, which can solve the problem that a detailed, specific and touchable follow-up advertisement path delivery suggestion cannot be provided after a user order placement path is restored based on historical delivery data of a merchant in the prior art.

To achieve the above object, according to an aspect of the embodiments of the present application, there is provided an advertisement delivery method including:

receiving an advertisement putting request, acquiring a corresponding putting identifier, and acquiring a corresponding user identifier based on the putting identifier;

determining each passenger group category to which the user corresponding to the user identification belongs based on the user identification;

acquiring historical advertisement putting data of users corresponding to each customer group type, and calling an algorithm model output strategy to determine a serialized putting strategy corresponding to each customer group type based on the historical advertisement putting data of the users;

and respectively determining the serialized advertisement identifications corresponding to the serialized advertisement putting strategies, and sending the serialized advertisement identifications to the playing ends of the advertisement service lines corresponding to the guest group classes, so that the playing ends play the advertisements in order based on the serialized advertisement identifications.

Optionally, determining a serialized delivery strategy corresponding to each customer class includes:

determining sequential trigger information, exposure frequency and budget allocation information of channels corresponding to each customer group type according to historical advertisement delivery data of each user;

and generating a serialized delivery strategy corresponding to each customer group type based on the sequential trigger information, the exposure frequency and the budget allocation information.

Optionally, after sending each serialized advertisement identifier to the playing end of the advertisement service line corresponding to each guest group category, the method further includes:

and obtaining advertisement playing feedback data and correcting a serialized delivery strategy.

determining channel exposure frequency and conversion state of users corresponding to each customer group type, determining users with channel exposure frequency reaching a preset threshold and without conversion, and transferring the users without conversion to the channels without exposure for exposure.

and determining the channel exposure frequency corresponding to each user, removing the users corresponding to the channel exposure frequency exceeding the maximum exposure frequency and the converted users from the serialized delivery strategy, and not exposing the serialized advertisements.

serializing the advertisement exposure information;

and discarding the advertisement exposure information which does not contain the user identification, and calculating and updating the conversion state of each corresponding user in real time.

serializing the advertisement order information, determining the converted user, and updating the conversion state of the user corresponding to the user identification.

Optionally, determining each guest group category to which the user corresponding to the user identifier belongs includes:

and acquiring asset state distribution of each corresponding user, and determining each guest group category to which the user corresponding to the user identifier belongs based on each asset state distribution.

In addition, this application still provides an advertisement putting device, includes:

the receiving unit is configured to receive an advertisement putting request, acquire a corresponding putting identification and acquire a corresponding user identification based on the putting identification;

the class determination unit is configured to determine each passenger group class to which the user corresponding to the user identifier belongs based on the user identifier;

the strategy determining unit is configured to acquire user historical advertisement delivery data corresponding to each customer group type, and call an algorithm model output strategy to determine a serialized delivery strategy corresponding to each customer group type based on the user historical advertisement delivery data;

and the advertisement putting unit is configured to respectively determine the serialized advertisement identifications corresponding to the serialized putting strategies and send the serialized advertisement identifications to the playing ends of the advertisement service lines corresponding to the guest group classes so that the playing ends play the advertisements in order based on the serialized advertisement identifications.

Optionally, the policy determination unit is further configured to:

Optionally, the advertisement delivery device further comprises a correction unit configured to:

Optionally, the advertisement delivery device further comprises a circulation unit configured to:

Optionally, the advertisement delivery device further comprises a culling unit configured to:

Optionally, the advertisement delivery device further comprises a status updating unit configured to:

serializing the advertisement exposure information;

Optionally, the category determination unit is further configured to:

In addition, this application still provides an advertisement delivery electronic equipment, includes: one or more processors; a storage device for storing one or more programs which, when executed by one or more processors, cause the one or more processors to implement the method of advertising as described above.

In addition, the present application also provides a computer readable medium, on which a computer program is stored, which when executed by a processor implements the advertisement delivery method as described above.

One embodiment of the above invention has the following advantages or benefits: the method comprises the steps of obtaining a corresponding release identifier by receiving an advertisement release request, and obtaining a corresponding user identifier based on the release identifier; determining each passenger group category to which the user corresponding to the user identification belongs based on the user identification; acquiring historical advertisement putting data of users corresponding to each guest group category, and calling an algorithm model output strategy to determine a serialized putting strategy corresponding to each guest group category; and respectively determining the serialized advertisement identifications corresponding to the serialized advertisement putting strategies, and sending the serialized advertisement identifications to the playing ends of the advertisement service lines corresponding to the guest group classes, so that the playing ends play the advertisements in order based on the serialized advertisement identifications. By classifying the users, correspondingly recommending an optimal serialized delivery strategy based on the user classification and delivering the advertisements according to the optimal serialized delivery strategy, the method has strong reusability, achieves the purposes of reducing the advertisement cost, increasing the advertisement effect and improving the advertisement conversion rate.

Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.

Drawings

The drawings are included to provide a further understanding of the application and are not to be construed as limiting the application. Wherein:

fig. 1 is a schematic diagram of a main flow of an advertisement delivery method according to a first embodiment of the present application;

fig. 2 is a schematic diagram of a main flow of an advertisement delivery method according to a second embodiment of the present application;

fig. 3 is a schematic view of an application scenario of an advertisement delivery method according to a third embodiment of the present application;

FIG. 4 is a flow chart of a serialized delivery technique of a method of advertisement delivery according to an embodiment of the application;

FIG. 5 is a schematic view of a serialized playback flow of an advertisement delivery method according to an embodiment of the present application

FIG. 6 is a schematic diagram of the main elements of an advertisement delivery device according to an embodiment of the present application;

FIG. 7 is an exemplary system architecture diagram to which embodiments of the present application may be applied;

fig. 8 is a schematic structural diagram of a computer system suitable for implementing the terminal device or the server according to the embodiment of the present application.

Detailed Description

The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness. According to the technical scheme, the data acquisition, storage, use, processing and the like meet relevant regulations of national laws and regulations.

Fig. 1 is a schematic diagram of a main flow of an advertisement delivery method according to a first embodiment of the present application, and as shown in fig. 1, the advertisement delivery method includes:

step S101, receiving an advertisement putting request, obtaining a corresponding putting mark, and obtaining a corresponding user mark based on the putting mark.

In this embodiment, the corresponding user identifier is obtained based on the drop identifier, that is, the corresponding guest group selection is performed based on the drop identifier. An execution subject (for example, a server) of the advertisement delivery method may receive an advertisement delivery request through a wired connection or a wireless connection. After receiving the advertisement delivery request, the execution subject may obtain corresponding delivery identifiers, such as an effect association bidding identifier XGLT and a quality effect association bidding identifier PXLT. The effect joint delivery can be specifically advertisement joint delivery taking advertisement delivery effect as a main part. The product-effect joint delivery can be specifically the advertisement joint delivery mainly based on the brand effect. After determining the release identifier, the execution subject may obtain a corresponding user identifier based on the release identifier. As shown in fig. 4, at the data policy flow level, before advertisement delivery, the execution subject may call the algorithm model output policy, input the optimization target and the total budget, determine whether to perform effect joint delivery or product-effect joint delivery based on the obtained delivery identifier, and perform DMP-defined customer group circle selection, customer group circle selection based on the optimization target, and direct-cast exposure customer group circle selection when determining that the effect joint delivery is performed. And (3) issuing an in-station RTB channel strategy based on the subdivided circled passenger groups, wherein the strategy comprises channel combination, sequence, budget and offer, frequency control suggestion and the like. And then setting an initial passenger group package magnitude threshold according to the in-station RTB channel strategy to limit passenger group selection and obtain a more optimized selected passenger group, thereby realizing the optimization of the closed-loop passenger group-in-station RTB channel strategy. Channel policy parameters and other settings are made by the advertiser. Before the advertisement is put, the executive subject can issue creative strategies according to the strategies of circled passenger groups and RTB channels in the station. And when the product effect joint casting is determined, the customers are circled based on the brand exposure. All guest groups are associated with 5A to divide the guests, new guests and old guests.

The RTB advertisement is not fixed on a certain page, and when a consumer opens a certain page, the advertisement platform and the DSP obtain basic information of the person who opens the page through various technical means, and finally determine what advertisement is put to the user through the basic information. That is, different users will see different advertisements on the same page, and the advertisements are customized for each person seeing the advertisements.

Data Management Platform (DMP for short). The DMP can provide the customer group label for advertisement putting to carry out audience accurate orientation, establish a user portrait through putting data, and manage and put the customer group label again.

And step S102, determining each passenger group category to which the user corresponding to the user identification belongs based on the user identification.

After determining the circled guest group based on the user identifier, the executing agent may further determine each class of guest groups to which the circled guest group belongs, for example, a hidden guest, a new guest, and an old guest. And a guest group segmentation step: and based on the initial passenger group package, carrying out asset state identification on the users in the passenger group package, and clustering the passenger groups according to the asset state to finally form three subdivided passenger groups of the hidden passengers, the new passengers and the old passengers. And (3) defining the subdivided guest groups: the hidden customers are customers who do not know and purchase the commodities of the product; the new customers are a customer group which browses, clicks, pays attention to, purchases, searches, shares, meets or receives the coupons once or for multiple times, but does not purchase the goods of the product card; the old guests are the group of guests who have bought the product card for one or more times.

Step S103, obtaining historical advertisement putting data of users corresponding to each customer group, and calling an algorithm model output strategy to determine a serialized putting strategy corresponding to each customer group based on the historical advertisement putting data of the users.

On the data strategy flow level, before advertisement putting, an executive body can call an algorithm model output strategy, input an optimization target, user historical advertisement putting data corresponding to each passenger group type and total budget, determine whether effect joint putting or product-effect joint putting is carried out based on an obtained putting identification, and when the effect joint putting is determined, DMP self-defined passenger group selection, passenger group selection based on the optimization target, direct-throwing exposure passenger group selection and passenger group selection are carried out, and an intra-station channel strategy is obtained based on subdivided circle selection, namely a serialized putting strategy corresponding to each passenger group type, and the strategy comprises channel combinations, sequences, budgets, bids, frequency control suggestions and the like corresponding to each passenger group type. Wherein the optimization objectives include GMV (order amount), conversion amount (order bank) and selection of the type of the released customer group.

The serialized advertisement delivery in the embodiment of the application is an advertisement delivery tool for sequentially reaching the serialized advertisements for the targeted guest group; the whole process is from the making of a serialization strategy before the investment to the one-key investment according to the strategy, the daily adjustment (budget & bid price) of the investment strategy, the orderly circulation of the guest group by utilizing the serialization play control and the real-time data settlement of the strategy effect after the investment; the strategy analysis before delivery is triggered by a serialized strategy analysis task newly built in the platform by an advertiser, and after a strategy suggestion report is generated, the advertiser can automatically judge whether to carry out serialized delivery according to a strategy or not; and if the user needs to throw, clicking a throw configuration button in the strategy to trigger the whole throw flow. Therefore, the whole process needs 2 triggers, 1 trigger is for generating a strategy report, and the other trigger is for entering a release link.

Specifically, determining the serialized delivery strategy corresponding to each customer group category includes:

determining sequence reaching information, exposure frequency and budget allocation information of channels corresponding to the customer classes according to historical advertisement delivery data of the users; and generating a serialized delivery strategy corresponding to each customer group type based on the sequential trigger information, the exposure frequency and the budget allocation information.

Illustratively, the executive body analyzes historical delivery data based on the customer group based on the preposed input information and the segmented customer group package, and outputs a serialized delivery strategy, which comprises information such as channel combination, reach order, budget allocation and bid suggestion, frequency control suggestion and the like; wherein, each of the potential, new and old segment passenger groups corresponds to a strategy of channel sequential touch.

Specifically, the executive body can obtain a serialized delivery strategy comprising information such as channel combination sequence, budget allocation and offer, customer group circulation rules and the like through analysis of historical synchronization data and data insight of CVR (conversion rate) of circled customer groups according to strategy basic information input when a user creates a strategy, and based on shopping path analysis, and adjust the offer and the budget of the next day according to accumulated delivery effect data in the delivery process, thereby continuously optimizing the delivery strategy. (CVR (conversion Rate) is an index that measures the effectiveness of CPA ads, i.e., simply the conversion of a user clicking on an ad to become an active or registered or even paid user (conversion/click) 100%)

Illustratively, the channel policy solution is as follows: searching a feasible solution space: performing data simulation on the optimized customer group based on the exposure table and the request table to obtain exhibition point consumption data (namely displaying click consumption data, displaying that a customer searches for a keyword to trigger keyword matching and displays originality to the customer as a display); determining channel combination and sequence: optimizing channel combinations and reach orders according to historical release data of category levels, exhausting sequential combinations of different channels from user dimensions, analyzing historical release data effects of each combination, and selecting optimal channel combinations and reach orders based on optimization targets; frequency selection: evaluating the influence of the exposure frequency on CTR, CVR equivalent rate indexes and channel transfer rate on different categories through a model, and determining the exposure frequency of each channel according to the single exposure profit maximum principle by combining with a release target; solver: calculating optimal bids and budgets of different channels according to an optimization target and by means of the customer group circulation data; thermal correction: and in the releasing process, the releasing data accumulated is utilized to correct the next day bidding price and the budget strategy.

And step S104, respectively determining the serialized advertisement identifications corresponding to the serialized advertisement delivery strategies, and sending the serialized advertisement identifications to the playing ends of the advertisement service lines corresponding to the guest group classes so that the playing ends play the advertisements in order based on the serialized advertisement identifications.

As shown in fig. 4, at the delivery end, the execution subject may create a corresponding serialized delivery plan, a unit, and bind the material according to the determined serialized channel delivery policy corresponding to each customer group category. It will be appreciated that the same serialized created unit is identified by the serialized ad ID. Each policy ID corresponds to a serialization ID. Namely, the corresponding relation is as follows: policy ID-serialization ID-unit ID. As shown in fig. 4, in the advertisement delivery execution, the execution subject may invoke a joint broadcast control service for advertisement delivery, and push corresponding advertisements to the broadcasting end according to the channel policy by referring to the guest group package and the serialized advertisement ID, so that the broadcasting end performs ordered broadcasting of the advertisements based on the received pushed advertisements. Of course, the execution subject may also push the serialized delivery policy (i.e., channel policy) to the playback end, and the playback end invokes the corresponding advertisement to play based on the serialized channel delivery policy. And executing the control of the advertisement playing frequency and the circulation of the guest group in real time, filtering and recording in an advertisement putting log. The execution main body can call data reporting/computing service, obtain an advertisement putting log, obtain corresponding advertisement putting exhibition point data and documentary data and 5A passenger group circulation/distribution data (wherein, 5A comprises A0, A1, A2, A3 and A4, A0 is a hidden passenger, A1+ A2 is a new passenger and A3+ A4 is an old passenger), so that after the advertisement putting, an effect reply/plan settlement service is called to generate an effect report.

Specifically, after sending each serialized advertisement identifier to the playing end of the advertisement service line corresponding to each guest group category, the method further includes:

and obtaining advertisement playing feedback data, and correcting a serialized delivery strategy.

Illustratively, the broadcasting end receives frequency control output by the channel policy and serialization related identifiers (serialization ID identifiers and serialization first channel identifiers on a unit level) in the delivery end, obtains advertisement broadcasting feedback data, such as the sequence and frequency of exposure of each user in the guest group package, controls the sequence and frequency of exposure of each user (user pin) in the guest group package by the serialization advertisement, performs sequence funnel-type streaming on the guest group, and performs streaming and removal of the guest group in real time to correct the serialization delivery policy, so that the corrected serialization delivery policy can generate the maximum benefit.

determining the channel exposure frequency and the conversion state of the user corresponding to each customer class, determining the user with the channel exposure frequency reaching a preset threshold value and without conversion, and transferring the user without conversion to the channel without exposure for exposure.

For example, a user who would meet a certain frequency requirement at an earlier channel exposure (frequency output by the channel policy algorithm) and not be converted would be streamed in real-time to a later channel exposure.

For example, users that are exposed above a certain frequency cap or have been converted will be culled in real-time.

serializing the advertisement exposure information;

As shown in fig. 5, at a Service (server) end of the serialized advertisement real-time flow control system, after sending each serialized advertisement identifier to a playing end of an advertisement Service line corresponding to each guest group category, the advertisement exposure information is serialized, for example, ad _ group _ id, seq _ ad _ id, user _ pin, and the like. And then accessing the user service UserServer, acquiring a user _ pin, discarding the exposure information which cannot acquire the user _ pin, inquiring the play strategy information and the current user state information to calculate the current conversion state of the user, updating the conversion state of the user, and issuing the conversion state of the user to the JDQ message queue.

Specifically, after sending each serialized advertisement identifier to the playing end of the advertisement service line corresponding to each guest group, the method further includes:

As shown in fig. 5, at a Service (server) end of the serialized advertisement real-time flow control system, after sending each serialized advertisement identifier to a play end of an advertisement Service line corresponding to each guest group category, serialize advertisement order information, for example, deal _ id, user _ pin, seq _ ad _ id, and the like, then query play policy information, query conversion state information of a current user, calculate a current conversion state of the user, update the conversion state of the user, and send the conversion state of the user to a JDQ message queue.

In the embodiment, a corresponding advertisement putting request is received, and a corresponding user identifier is obtained based on the putting identifier; determining each passenger group category to which the user corresponding to the user identification belongs based on the user identification; acquiring historical advertisement putting data of users corresponding to each customer group type, and calling an algorithm model output strategy to determine a serialized putting strategy corresponding to each customer group type based on the historical advertisement putting data of the users; and respectively determining the serialized advertisement identifications corresponding to the serialized advertisement putting strategies, and sending the serialized advertisement identifications to the playing ends of the advertisement service lines corresponding to the guest group classes, so that the playing ends play the advertisements in order based on the serialized advertisement identifications. By classifying the users, correspondingly recommending an optimal serialized delivery strategy based on the user classification and delivering the advertisements according to the optimal serialized delivery strategy, the method has strong reusability, achieves the purposes of reducing the advertisement cost, increasing the advertisement effect and improving the advertisement conversion rate.

Fig. 2 is a schematic main flow diagram of an advertisement delivery method according to a second embodiment of the present application, and as shown in fig. 2, the advertisement delivery method includes:

step S201, receiving an advertisement putting request, acquiring a corresponding putting mark, and acquiring a corresponding user mark based on the putting mark.

Step S202, based on the user identification, acquiring the asset state distribution of each corresponding user, and based on the asset state distribution, determining each guest group category to which the user corresponding to the user identification belongs.

The asset state distribution specifically refers to the distribution of the cognitive state and the purchasing state of the user customer group on the brand commodities. And a guest group segmentation step: based on the initial passenger group package, carrying out asset state identification on users in the passenger group package, and clustering the passenger groups according to the asset state to finally form three subdivided passenger groups of hidden passengers, new passengers and old passengers; defining the subdivided guest group: the hidden customers are customers who do not know and purchase the commodities of the product; the new customers are a customer group which browses, clicks, pays attention to, purchases, searches, shares, meets or receives the coupons once or for multiple times, but does not purchase the goods of the product card; the old guests are the group of guests who have bought the product card for one or more times.

Step S203, obtaining historical advertisement putting data of users corresponding to each customer group, and calling an algorithm model output strategy to determine a serialized putting strategy corresponding to each customer group based on the historical advertisement putting data of users.

And step S204, respectively determining the serialized advertisement identifications corresponding to the serialized advertisement delivery strategies, and sending the serialized advertisement identifications to the playing ends of the advertisement service lines corresponding to the guest group classes so that the playing ends play the advertisements in order based on the serialized advertisement identifications.

Specifically, the playback control in the embodiment of the present application is specifically performed as follows:

and developing a real-time flow control system, accessing the serialized advertisement exposure data real-time flow and the serialized advertisement order following result quasi-real-time flow, receiving the serialized advertisement channel strategy information from a delivery end and the corresponding advertisement unit information, and judging the state of each user touched by the serialized advertisement so as to control the exposure frequency of the user on the serialized advertisement and judge the advertisement unit to be exposed. The above information is sent to the user server through the real-time flow control system, when each service line playing end requests the user server, the information is transmitted to each service line retleval, and the service line retleval develops the serialized advertisement filter to judge the advertisement unit to be played for each user under the serialized strategy. The serialized advertisement exposure data real-time stream and the serialized advertisement order following result quasi-real-time stream are received from the delivery end, and the serialized advertisement channel strategy information and the corresponding advertisement unit information come from a DataSource data layer. In the data source data layer, the execution body obtains the serialized advertisement unit information, the channel information of the serialized advertisement and the playing control information of each product line from a DSP (provider service platform) delivery end database by calling a cache service platform (such as JIMDB). The executing agent filters (filer) out orders to serialized ads by obtaining ad order data streams, such as order. The execution subject filters (filer) out the order following information of the serialized advertisement, such as imp.seq _ ad _ id, imp.device _ id, imp.user _ pin, imp.impress _ time, through the ad exposure data stream. And the executive body transmits the serialized advertisement order data and the total station data of the exposure data stream to a Service server through secondary processing through the filtered order following to the serialized advertisement order and the filtered order following information of the serialized advertisement.

Each playing end plays the advertisement in order based on each serialized advertisement identifier, specifically, it may call the advertisement playing service shown in fig. 5, so as to call the user service UserServer service based on the JDQ message received from the server, and call the advertisement server (Adserver) corresponding to the serialized advertisement identifier, so as to perform advertisement Retrieval (Retrieval) of recommending Adserver, searching Adserver, focusing Adserver, and off-site Adserver, for example, recommending Retrieval, searching Retrieval, focusing Retrieval, and off-site Retrieval, and perform advertisement arrangement on the advertisement display page based on the advertisement Retrieval result. The home focus, i.e., the home focus map, is where the first eye of the advertisement home page looks.

Fig. 3 is a schematic view of an application scenario of an advertisement delivery method according to a third embodiment of the present application. The advertisement delivery method can be applied to scenes in which advertisements are delivered according to the classification of the passenger groups. As shown in fig. 3, after the merchant completes the input entry filling required for creating the new policy, the system segments the initial guest group package into potentially new, new and old three segment guest group packages according to the guest group asset distribution state, the algorithm performs a series of data processing such as detailed channel policy calculation based on the segment guest group package, and finally generates a policy report.

The first step is as follows: and (5) establishing a new strategy. The policy report name is entered. The advertiser can customize the policy name when creating a new, such as: x is put in a serialization way, which is used as the identifier of the unique name of the strategy, and other strategies with the same name cannot be created under the same put account; of course, the policy is most often uniquely identified by a policy ID. The merchant inputs information such as brands, three-level categories, put commodities (SKUs), put total budget amount, put time periods, put periods, advertising line range, optimization targets and the like, wherein the optimization targets comprise GMVs (order amounts), conversion amounts (order lines) and the types of put customers are selected. Selecting a drop customer group type comprises: intelligent customer group (based on optimization target) selection, direct projection exposure re-marketing customer group selection, DMP self-defined customer group selection. Optimizing the target: namely, the impression effect index most concerned by the advertiser in the impression at this time supports the selection of two indexes of the order amount and the order line as the optimization target. The order line is the number of orders that produced the conversion, one SKU for each order line, and assuming there are 3 SKUs in an order, the order is split into 3 order lines.

Class III: that is, the finest granularity of the category to which each SKU belongs is divided, for example, if SKU is toner of brand X, the corresponding primary-secondary-tertiary categories are: make-up skin care-facial skin care-toner/lotion; advertisement service line range: namely, business lines such as XX express, shopping contact, XXX exhibition positions and the like are released; and (3) a release time period: the advertisement is the information input by the advertiser when the strategy is newly built, namely the specific time interval of the advertisement putting.

The intelligent customer group is an intelligent customer group label combination recommended by an algorithm side based on an optimization target selected by a merchant; after the initial passenger group package is selected, the system divides the associated passenger group assets into states and divides the initial passenger group package into the potential passengers, the new passengers and the old passengers. Performing intelligent guest group selection based on optimization targets (GMV, conversion amount and the like) or specific scenes (novelty, activity, update, membership and the like); considering the information of label CVR (conversion rate): conversion rate) is an index for measuring the effectiveness of CPA advertisement, in short, the conversion rate of a user clicking advertisement to become an effective activated or registered or even paying user, CVR (conversion amount/click amount) × 100%) and CTR (click rate), CTR is an important index for measuring the effectiveness of Internet advertisement, high CTR means that more users click on the landing page of the delivered product, if the landing page is not designed well, the user is not attracted quickly, the loss of the user is easily caused, the advertisement conversion rate is reduced, so that high CTR does not mean good delivery or good conversion rate, high CTR can provide more possibility for the advertisement effect conversion), etc., the combination of intelligent labels is carried out, and the targeted customer group conforming to the optimization target or the specific scene is screened out, wherein, the threshold value of the class level of the selected passenger group is output by the channel strategy side, and the intelligent passenger group selection needs to meet the class level of the threshold value. The intelligent guest group circle selection technical scheme is as follows: obtaining a label: screening tags from historical impressions of advertisers or categories; and (3) label roughing: roughly selecting labels according to the materials of the current advertiser and the information such as the estimated exposure and the estimated number of people of the passenger group package; tag selection: and (5) from the optimization target, selecting according to the CTR, CVR and other transformation indexes of the label.

In the embodiment of the application, the intelligent guest group: the algorithm optimizes and recommends high-quality user customers based on the relevant information such as categories, optimization targets and the like input by an advertiser; the estimated CVR, CTR and other information of each user is combined to carry out guest group selection or tag combination, and an optimal targeted guest group for the advertiser is selected; direct projection exposure re-marketing guest group: according to historical direct-casting delivery of an advertiser, performing circle selection of direct-casting exposure customer groups to perform in-station re-marketing on contact customer groups outside a historical station; DMP: the client group selection tool covers user data and CRM information owned by a client, and helps an advertiser to realize predictable and accurate targeted delivery; DMP self-defining guest group: a customer group classification in a source DMP tool, DMP self-building customer groups, refers to targeted customer groups created by advertisers through seed packets, labels and the like, and is used for advertisement delivery; such as browsing a certain brand of customer base in the last 30 days.

The second step is that: and (6) outputting the strategy. Based on the preposed input information and the segmented customer group package, the algorithm analyzes the historical delivery data based on the customer group and outputs a serialized delivery strategy which comprises information such as channel combination (for example, hidden customers: channel A-channel B-channel C; new customers: channel B-channel A-channel C; old customers: channel C-channel B-channel A), the reach order of the channels, budget allocation and bid suggestion, frequency control suggestion and the like; each subdivision passenger group of the hidden passenger, the new passenger and the old passenger corresponds to a strategy of channel sequential touch. And outputting the combination of channels, the reach sequence, the budget allocation and bid suggestion and the frequency control suggestion.

The third step: and (5) releasing the strategy. The executive agent can set associated delivery plans/units/creatives on each delivery service line for channel strategies corresponding to the hidden guests, the new guests and the old guests. And then, starting releasing and playing frequency control, and executing releasing end plan after releasing. Illustratively, a merchant can perform serialized delivery on subdivided customer groups according to a channel strategy, control the circulation sequence of the customer groups according to the channel reach sequence, perform real-time circulation and elimination of the customer groups according to exposure and conversion conditions, continue the mind of consumers in the whole advertisement reach process, promote final conversion layer by layer, and perform daily updating and adjustment of the channel strategy according to delivery data in the delivery process, wherein the information comprises budget, bid price and the like, so as to achieve the optimal delivery effect. And finally displaying the launch effect data representation of the strategy dimension for the merchant to view.

The advertisement delivery method is based on high-quality mass data, and based on the shopping decision path of the key user, the mental accumulation in the shopping decision process of the user is completed in a mode of combining accurate orientation and intelligent delivery, and finally the conversion of the maximum or optimal efficiency is promoted. Based on shopping path analysis, exploring multiple ordered interactions of a user on an advertisement path node, combining intelligent customer group mining, recommending a serialized delivery strategy based on a specific delivery customer group, and comprising channel combination, reach order, budget and bid suggestion, stream conversion frequency and the like; and a plan can be established for each service line in a unified way based on a channel strategy, in the releasing process, releasing customer groups are contacted layer by layer according to the sequence of the channel strategy, and real-time sequential funnel circulation is carried out on the customer groups by controlling the sequence and frequency of the serialized advertisement exposure of each user in a customer group package, so that the final conversion is realized, and the purposes of cost reduction and efficiency improvement are achieved.

The method and the device perform accurate recommendation of the passenger group reach paths based on the algorithm and data, and realize ordered delivery through passenger group directional circulation, channel order recommendation and exposure frequency control. Based on the user shopping path analysis, the shopping behaviors of the user and the advertisement path before placing an order are known, and the optimal channel combination and the reach sequence are recommended more scientifically. Based on scientific algorithm model and mass data support, the method is scientific and objective, saves labor cost, avoids human factor interference and achieves accurate recommendation; and the historical data can be utilized and optimized for multiple times, so that the recommendation has strong reusability. And (4) carrying out the circulation and elimination of the guest group according to the path strategy, solving the problems of advertisement marketing and user state splitting caused by random and disordered contact of the consumers by the advertisements and the advertisement cost waste caused by invalid exposure.

Fig. 6 is a schematic diagram of main units of an advertisement delivery device according to an embodiment of the present application. As shown in fig. 6, the advertisement delivery apparatus includes a receiving unit 601, a category determining unit 602, a policy determining unit 603, and an advertisement delivery unit 604.

A receiving unit 601 configured to receive an advertisement delivery request, obtain a corresponding delivery identifier, and obtain a corresponding user identifier based on the delivery identifier;

a category determining unit 602 configured to determine, based on the user identifier, each guest group category to which the user corresponding to the user identifier belongs;

a policy determining unit 603 configured to obtain historical advertisement delivery data of the user corresponding to each guest group category, and invoke an algorithm model output policy to determine a serialized delivery policy corresponding to each guest group category based on the historical advertisement delivery data of the user;

the advertisement delivering unit 604 is configured to determine serialized advertisement identifiers corresponding to the serialized delivering strategies respectively, and send the serialized advertisement identifiers to the playing ends of the advertisement service lines corresponding to the guest groups, so that the playing ends play the advertisements in order based on the serialized advertisement identifiers.

In some embodiments, the policy determination unit 603 is further configured to: determining sequential trigger information, exposure frequency and budget allocation information of channels corresponding to each customer group type according to historical advertisement delivery data of each user; and generating a serialized delivery strategy corresponding to each customer group type based on the sequential trigger information, the exposure frequency and the budget allocation information.

In some embodiments, the advertisement delivery device further comprises a correction unit, not shown in fig. 6, configured to: and obtaining advertisement playing feedback data and correcting a serialized delivery strategy.

In some embodiments, the advertisement delivery apparatus further comprises a circulation unit, not shown in fig. 6, configured to: determining channel exposure frequency and conversion state of users corresponding to each customer group type, determining users with channel exposure frequency reaching a preset threshold and without conversion, and transferring the users without conversion to the channels without exposure for exposure.

In some embodiments, the advertisement delivery device further comprises a culling unit, not shown in fig. 6, configured to: and removing the users exceeding the maximum exposure frequency and the converted users from the serialized delivery strategy, and not exposing the serialized advertisements.

In some embodiments, the advertisement delivery apparatus further comprises a status updating unit, not shown in fig. 6, configured to: serializing the advertisement exposure information; and discarding the advertisement exposure information which does not contain the user identification, and calculating and updating the conversion state of each corresponding user in real time.

In some embodiments, the advertisement delivery apparatus further comprises a status updating unit, not shown in fig. 6, configured to: serializing the advertisement order information, determining the converted user, and updating the conversion state of the user corresponding to the user identification.

In some embodiments, the category determination unit 602 is further configured to: and acquiring asset state distribution of each corresponding user, and determining each guest group category to which the user corresponding to the user identifier belongs based on each asset state distribution.

It should be noted that, in the present application, the advertisement delivery method and the advertisement delivery device have a corresponding relationship in the specific implementation content, so the repeated content is not described again.

Fig. 7 shows an exemplary system architecture 700 to which the advertisement delivery method or the advertisement delivery apparatus of the embodiments of the present application may be applied.

As shown in fig. 7, the system architecture 700 may include

terminal devices

701, 702, 703, a network 704, and a server 705. The network 704 serves to provide a medium for communication links between the

terminal devices

701, 702, 703 and the server 705. Network 704 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

A user may use the

terminal devices

701, 702, 703 to interact with a server 705 over a network 704, to receive or send messages or the like. The

terminal devices

701, 702, 703 may have installed thereon various communication client applications, such as a shopping-like application, a web browser application, a search-like application, an instant messaging tool, a mailbox client, social platform software, etc. (by way of example only).

The

terminal devices

701, 702, 703 may be various electronic devices having an advertisement delivery processing screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 705 may be a server providing various services, such as a background management server (for example only) supporting ad placement requests submitted by users using the

terminal devices

701, 702, 703. The background management server can receive the advertisement putting request, acquire a corresponding putting identification and acquire a corresponding user identification based on the putting identification; determining each passenger group category to which the user corresponding to the user identification belongs based on the user identification; acquiring historical advertisement putting data of users corresponding to each customer group type, and calling an algorithm model output strategy to determine a serialized putting strategy corresponding to each customer group type based on the historical advertisement putting data of the users; and respectively determining the serialized advertisement identifications corresponding to the serialized advertisement putting strategies, and sending the serialized advertisement identifications to the playing ends of the advertisement service lines corresponding to the guest group classes, so that the playing ends play the advertisements in order based on the serialized advertisement identifications. By classifying the users, correspondingly recommending an optimal serialized delivery strategy based on the user classification and delivering the advertisements according to the optimal serialized delivery strategy, the method has strong reusability, achieves the purposes of reducing the advertisement cost, increasing the advertisement effect and improving the advertisement conversion rate.

It should be noted that the advertisement delivery method provided in the embodiment of the present application is generally executed by the server 705, and accordingly, the advertisement delivery apparatus is generally disposed in the server 705.

It should be understood that the number of terminal devices, networks, and servers in fig. 7 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Referring now to FIG. 8, shown is a block diagram of a computer system 800 suitable for use in implementing a terminal device of an embodiment of the present application. The terminal device shown in fig. 8 is only an example, and should not bring any limitation to the functions and the use range of the embodiment of the present application.

As shown in fig. 8, the computer system 800 includes a Central Processing Unit (CPU)801 that can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)802 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 803. In the RAM803, various programs and data necessary for the operation of the computer system 800 are also stored. The CPU801, ROM802, and RAM803 are connected to each other via a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.

The following components are connected to the I/O interface 805: an input portion 806 including a keyboard, a mouse, and the like; an output section 807 including a signal such as a Cathode Ray Tube (CRT), a liquid crystal credit authorization query processor (LCD), and the like, and a speaker; a storage portion 808 including a hard disk and the like; and a communication section 809 including a network interface card such as a LAN card, a modem, or the like. The communication section 809 performs communication processing via a network such as the internet. A drive 810 is also connected to the I/O interface 805 as necessary. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 810 as necessary, so that a computer program read out therefrom is mounted on the storage section 808 as necessary.

In particular, according to embodiments disclosed herein, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments disclosed herein include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 809 and/or installed from the removable medium 811. The computer program executes the above-described functions defined in the system of the present application when executed by the Central Processing Unit (CPU) 801.

It should be noted that the computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes a receiving unit, a category determination unit, a policy determination unit, and an advertisement delivery unit. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.

As another aspect, the present application also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs, and when the one or more programs are executed by one of the devices, the device receives an advertisement placement request, acquires a corresponding placement identifier, and acquires a corresponding user identifier based on the placement identifier; determining each passenger group category to which the user corresponding to the user identification belongs based on the user identification; acquiring historical advertisement putting data of users corresponding to each customer group type, and calling an algorithm model output strategy to determine a serialized putting strategy corresponding to each customer group type based on the historical advertisement putting data of the users; and respectively determining the serialized advertisement identifications corresponding to the serialized advertisement putting strategies, and sending the serialized advertisement identifications to the playing ends of the advertisement service lines corresponding to the guest group classes, so that the playing ends play the advertisements in order based on the serialized advertisement identifications.

According to the technical scheme of the embodiment of the application, the advertisements are launched according to the optimal serialized launching strategy by classifying the users and correspondingly recommending the optimal serialized launching strategy based on the user classification, so that the reusability is strong, the advertisement cost is reduced, the advertisement effect is increased, and the advertisement conversion rate is improved.

The above-described embodiments should not be construed as limiting the scope of the present application. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An advertisement delivery method, comprising:

receiving an advertisement putting request, acquiring a corresponding putting identification, and acquiring a corresponding user identification based on the putting identification;

acquiring historical advertisement putting data of the user corresponding to each customer group type, and calling an algorithm model output strategy to determine a serialized putting strategy corresponding to each customer group type based on the historical advertisement putting data of the user;

2. The method according to claim 1, wherein the determining the serialized delivery strategy corresponding to each customer class comprises:

determining sequential trigger information, exposure frequency and budget allocation information of channels corresponding to the passenger group categories according to historical advertisement delivery data of the users;

and generating a serialized delivery strategy corresponding to each category based on the sequential trigger information, the exposure frequency and the budget allocation information.

3. The method of claim 2, wherein after sending each serialized advertisement identifier to a playout end of an advertisement service line corresponding to each guest group category, the method further comprises:

and acquiring advertisement playing feedback data and correcting the serialized delivery strategy.

4. The method of claim 2, wherein after the sending each serialized advertisement identifier to a playout end of an advertisement service line corresponding to each category of guest, the method further comprises:

determining channel exposure frequency and conversion state of users corresponding to each customer group category, determining users with channel exposure frequency reaching a preset threshold and without conversion, and transferring the users without conversion to the channels without exposure for exposure.

5. The method of claim 4, wherein after the sending each serialized advertisement identifier to a playout end of an advertisement service line corresponding to each category of guest, the method further comprises:

and determining the channel exposure frequency corresponding to each user, and removing the users corresponding to the channel exposure frequency exceeding the maximum exposure frequency and the converted users from the serialized delivery strategy.

6. The method of claim 4, wherein after sending each serialized advertisement identifier to a playout end of an advertisement service line corresponding to each guest group category, the method further comprises:

serializing the advertisement exposure information;

7. The method of claim 4, wherein after sending each serialized advertisement identifier to a playout end of an advertisement service line corresponding to each guest group category, the method further comprises:

serializing the advertisement order information, and determining the converted user so as to update the conversion state of the user corresponding to the user identification.

8. The method according to any one of claims 1 to 7, wherein the determining of each guest group class to which a user corresponding to the user identifier belongs comprises:

9. An advertisement delivery device, comprising:

the category determining unit is configured to determine each passenger group category to which the user corresponding to the user identification belongs based on the user identification;

the strategy determining unit is configured to acquire user historical advertisement delivery data corresponding to each customer class, and call an algorithm model output strategy to determine a serialized delivery strategy corresponding to each customer class based on the user historical advertisement delivery data;

and the advertisement putting unit is configured to respectively determine the serialized advertisement identifications corresponding to the serialized putting strategies, and send the serialized advertisement identifications to the playing ends of the advertisement service lines corresponding to the passenger groups, so that the playing ends play the advertisements in order based on the serialized advertisement identifications.

10. The apparatus of claim 9, wherein the policy determination unit is further configured to:

determining sequence reach information, exposure frequency and budget allocation information of channels corresponding to the customer classes according to historical advertisement delivery data of the users;

11. An advertisement delivery electronic device, comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-8.

12. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-8.