Advertising Bidding Method, Device, Electronic Device and Computer Readable Medium

Abstract

The present disclosure relates to an advertisement bidding method, apparatus, electronic device, and computer-readable medium. The method includes: determining a plurality of areas to be analyzed according to the geographical location of a target advertiser; determining a plurality of advertiser queues corresponding to the plurality of areas to be analyzed; predicting a plurality of competitive bids of the target advertiser according to the click-through rates of the plurality of advertiser queues; and determining a target bid of the advertiser according to the plurality of competitive bids. The advertisement bidding method, apparatus, electronic device, and computer-readable medium according to the present disclosure can center around merchants, accurately simulate user search requests in actual scenarios, and thus provide reasonable advertisement recommended bids for merchants.

Description

Technical Field

[0001] The present disclosure relates to the field of computer information processing, and more particularly, to an advertising bidding method, apparatus, electronic device, and computer-readable medium. Background Art

[0002] Advertising is one of the most common ways for Internet companies to monetize traffic. In a typical advertising product ecosystem, there are three main participants: advertisers, advertising platforms, and users. The goal of advertisers is to obtain more traffic by placing advertisements, while the goal of advertising platforms is to balance the relationship between short-term value (advertising revenue) and long-term value (user stickiness).

[0003] In the Internet industry, common advertising placement forms include display billing CPM (Cost Per Mille), click billing CPC (Cost Per Click), and conversion billing CPA (Cost Per Action), etc. Regardless of which placement form, advertisers need to set corresponding bidding units (CPM: per thousand impressions, CPC: per single click, CPA: per single conversion). For advertisers, when setting bidding units, they will face a difficulty: how much to bid when expecting the advertisement to appear at or before a certain position.

[0004] To help advertisers solve such problems, in the search effect advertising bidding system, the advertising platform provides a bidding suggestion service tool, which mainly solves the following requirements: the advertiser gives the expected position of the advertisement placement, and the advertising platform estimates the optimal bid for the advertisement to be ranked at the expected position. Its basic principle is to simulate the competition scenario among advertisers to achieve bid estimation. From the perspectives of accuracy, usability, and traffic segmentation, the existing methods for assisting advertisers in bid estimation have many defects.

[0005] Therefore, a new advertising bidding method, apparatus, electronic device, and computer-readable medium are needed.

[0006] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0007] In view of this, the present disclosure provides an advertising bidding method, apparatus, electronic device, and computer-readable medium, which can center around merchants, accurately simulate user search requests in the actual scenario, and thus provide reasonable advertising suggested bids for merchants.

[0008] Other features and advantages of the present disclosure will become apparent through the following detailed description, or be learned in part through the practice of the present disclosure.

[0009] According to one aspect of the present disclosure, an advertisement bidding method is provided. The method includes: determining a plurality of areas to be analyzed according to the geographical location of a target advertiser; determining a plurality of advertiser queues corresponding to the plurality of areas to be analyzed; estimating a plurality of competitive bids of the target advertiser according to the click-through rates of the plurality of advertiser queues; and determining a target bid of the advertiser according to the plurality of competitive bids.

[0010] In an exemplary embodiment of the present disclosure, determining a plurality of areas to be analyzed according to the geographical location of a target advertiser includes: determining a plurality of target points within a predetermined distance of the geographical location of the target advertiser; determining a regional radius; and determining the plurality of areas to be analyzed with the plurality of target points as the centers and based on the regional radius.

[0011] In an exemplary embodiment of the present disclosure, determining a plurality of advertiser queues corresponding to the plurality of areas to be analyzed includes: determining the advertisers in each of the plurality of areas to be analyzed; obtaining the advertisement display costs corresponding to the advertisers; and ranking the advertisers in each of the areas to be analyzed according to the advertisement display costs to generate an advertiser queue.

[0012] In an exemplary embodiment of the present disclosure, estimating a plurality of competitive bids of the target advertiser according to the click-through rates of the plurality of advertiser queues includes: estimating a plurality of competitive bids of the target advertiser according to the real-time click-through rates of the plurality of advertiser queues; and / or estimating a plurality of competitive bids of the target advertiser according to the average click-through rates of the plurality of advertiser queues.

[0013] In an exemplary embodiment of the present disclosure, estimating a plurality of competitive bids of the target advertiser according to the real-time click-through rates of the plurality of advertiser queues includes: obtaining the advertisement display costs corresponding to each advertiser in the advertiser queue; obtaining the real-time click-through rates corresponding to each advertiser in the advertiser queue; obtaining the advertisement display coefficients corresponding to each advertiser in the advertiser queue; and estimating a plurality of competitive bids of the target advertiser through the advertisement display costs, real-time click-through rates, and advertisement display coefficients corresponding to each advertiser.

[0014] In an exemplary embodiment of the present disclosure, the advertisement display costs, average click-through rates, and advertisement display coefficients are obtained through a search recall request.

[0015] In an exemplary embodiment of the present disclosure, estimating multiple competitive bids of the target advertiser according to the average click-through rate of the multiple advertiser queues includes: obtaining the advertising display cost corresponding to each advertiser in the advertiser queue; obtaining the average click-through rate corresponding to each advertiser in the advertiser queue; obtaining the advertising display coefficient corresponding to each advertiser in the advertiser queue; and estimating multiple competitive bids of the target advertiser through the advertising display cost, average click-through rate, and advertising display coefficient corresponding to each advertiser.

[0016] In an exemplary embodiment of the present disclosure, the advertising display cost and advertising display coefficient are obtained through a search recall request; the average click-through rate is determined through historical data.

[0017] In an exemplary embodiment of the present disclosure, estimating multiple competitive bids of the target advertiser according to the click-through rate of the multiple advertiser queues includes: estimating multiple competitive bids corresponding to multiple rankings of the target advertiser in each area to be analyzed through the advertising display cost, advertising display coefficient, real-time click-through rate, and / or average click-through rate corresponding to each advertiser.

[0018] In an exemplary embodiment of the present disclosure, determining the target bid of the advertiser according to the multiple competitive bids includes: merging the multiple competitive bids in the multiple areas to be analyzed according to the ranking; determining the largest competitive bid in each ranking as a sub-target bid; and generating the target bid through the multiple rankings and their corresponding sub-target bids.

[0019] According to an aspect of the present disclosure, an advertising bidding device is provided, and the device includes: a region module for determining multiple areas to be analyzed according to the geographical location of the target advertiser; a queue module for determining multiple advertiser queues corresponding to the multiple areas to be analyzed; an estimation module for estimating multiple competitive bids of the target advertiser according to the click-through rate of the multiple advertiser queues; and a bidding module for determining the target bid of the advertiser according to the multiple competitive bids.

[0020] In an exemplary embodiment of the present disclosure, the estimation module includes: a real-time estimation unit for estimating multiple competitive bids of the target advertiser according to the real-time click-through rate of the multiple advertiser queues; and / or an average estimation unit for estimating multiple competitive bids of the target advertiser according to the average click-through rate of the multiple advertiser queues.

[0021] According to an aspect of the present disclosure, an electronic device is provided, and the electronic device includes: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.

[0022] According to one aspect of the present disclosure, a computer-readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the above-described method is implemented.

[0023] According to the advertising bidding method, device, electronic device and computer-readable medium of the present disclosure, it is possible to accurately simulate user search requests in an actual scenario centered around merchants, so as to provide reasonable advertising suggested bids for merchants.

[0024] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] By referring to the accompanying drawings and describing its exemplary embodiments in detail, the above and other objectives, features and advantages of the present disclosure will become more apparent. The following described drawings are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0026] Figure 1 is a system block diagram of an advertising bidding method and device shown according to an exemplary embodiment.

[0027] Figure 2 is an application scenario diagram of an advertising bidding method and device shown according to an exemplary embodiment.

[0028] Figure 3 is a flowchart of an advertising bidding method shown according to another exemplary embodiment.

[0029] Figure 4 is a schematic diagram of an advertising bidding method shown according to another exemplary embodiment.

[0030] Figure 5 is a schematic diagram of an advertising bidding method shown according to another exemplary embodiment.

[0031] Figure 6 is a schematic diagram of an advertising bidding method shown according to another exemplary embodiment.

[0032] Figure 7 is a flowchart of an advertising bidding method shown according to another exemplary embodiment.

[0033] Figure 8 is a flowchart of an advertising bidding method shown according to another exemplary embodiment.

[0034] Figure 9 is a block diagram of an advertising bidding device shown according to an exemplary embodiment.

[0035] Figure 10 is a block diagram of an electronic device shown according to an exemplary embodiment.

[0036] Figure 11 is a schematic diagram of a computer-readable storage medium shown according to an exemplary embodiment. Detailed implementation manners

[0037] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. Like reference numerals in the figures denote like or similar parts, and thus their repetitive description will be omitted.

[0038] In addition, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of the embodiments of the present disclosure. However, those skilled in the art will realize that the technical solutions of the present disclosure can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be used. In other cases, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the present disclosure.

[0039] The block diagrams shown in the drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0040] The flowcharts shown in the drawings are only illustrative and do not necessarily include all the contents and operations / steps, nor do they necessarily have to be executed in the described order. For example, some operations / steps can be decomposed, while some operations / steps can be combined or partially combined, so the actual execution order may change according to the actual situation.

[0041] It should be understood that although terms such as first, second, and third may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another. Thus, the first component discussed below may be referred to as the second component without departing from the teachings of the concept of the present disclosure. As used herein, the term "and / or" includes any one and all combinations of one or more of the associated listed items.

[0042] Those skilled in the art can understand that the accompanying drawings are only schematic diagrams of exemplary embodiments, and the modules or processes in the drawings are not necessarily essential for implementing the present disclosure. Therefore, they cannot be used to limit the protection scope of the present disclosure.

[0043] The inventors of the present application found that for advertisers, when setting a bid unit, they will face a difficulty: how much should be bid to expect the advertisement to appear at or before a certain position.

[0044] To help advertisers solve such problems, in the search result advertising bidding system, the advertising platform provides a bidding suggestion service as a tool, which mainly solves the following requirements: the advertiser gives the expected position of the advertisement placement, and the advertising platform estimates the optimal bid for the advertisement to be ranked at the expected position. Its basic principle is to simulate the competition scenario among advertisers to achieve bid estimation.

[0045] In the traditional result advertising model, the competition among advertisers is global; but in the O2O industry based on geographical location information, the relationship among advertisers is local competition. For example, when a user near Zhongshan Park in Shanghai searches for the keyword "hot pot" on the Dianping app, the advertisers participating in the auction for this advertisement position are only those within a small area where the current user is located. At this time, the influence of location information on the competition among advertisers plays a key role. Specifically, it includes the influence on click-through rate estimation and the constraint on the admission threshold of advertisement positions, etc. Therefore, the bidding suggestion strategy of traditional search result advertising cannot be directly applied to the O2O industry in the LBS scenario, and a bidding suggestion scheme for this scenario should be designed and implemented according to the actual traffic characteristics.

[0046] For this scenario, there is a bid estimation method based on offline calculation in the prior art. The brief process is as follows:

[0047] 1. Divide the cellular area: The cellular area is formed by clustering a large amount of user location information using a clustering algorithm to aggregate user or advertiser aggregation areas. The division steps include replaying user logs and delineating potential traffic. After division, the competition scope among advertisers is limited within the same cell.

[0048] 2. Simulate the bid range: Assume that the bids of other advertisers remain unchanged, adjust the bid of the current advertiser, and calculate the change in the traffic it can obtain according to the change in the bid.

[0049] 3. Online traffic test. Apply the offline simulation results obtained in step 2 to the online environment, and observe the traffic situation that the advertiser can obtain in the actual production environment.

[0050] 4. Evaluation of effectiveness indicators. When evaluating the effectiveness of advertising placement, in addition to presenting absolute quantity indicators such as the number of impressions, clicks, conversions, etc., indicators such as traffic recall rate, exposure rate, click-through rate, order placement rate, etc. can be given in combination with the honeycombs.

[0051] From the perspectives of accuracy, usability, and traffic segmentation, the existing offline bid estimation methods have the following problems:

[0052] 1. The honeycomb division obtained through offline data modeling is difficult to be accurate in reflecting the online real-time competition environment. This is mainly because the competition environment in the LBS placement scenario changes constantly and unpredictably. The specific manifestations are as follows:

[0053] a) The competition queue in the same LBS scenario changes frequently, specifically manifested as changes in advertisers' enabling / suspending of placement, time targeting factors, budget depletion, etc., which are unpredictable.

[0054] b) The competition environment is greatly affected by real-time traffic changes, and the honeycomb areas divided according to historical data are likely to be inapplicable to the current competition environment.

[0055] 2. Poor verifiability and interpretability, which are not easily understood by advertisers: Advertisers' most direct requirement for the bid suggestion tool is to be able to know the bid they need to give to compete for a certain ad position. However, the results given by the existing offline bid suggestion schemes are based on the traffic that advertisers can actually obtain, making it difficult for advertisers to understand and even more difficult to verify.

[0056] 3. The offline estimation is independent of the real-time search ad recall process and cannot be iteratively changed in a timely manner when changes occur in the online business process and strategy, resulting in problems of insufficient accuracy.

[0057] 4. The offline bid suggestion only gives bid suggestions in one scenario and cannot achieve further traffic segmentation.

[0058] In view of the technical defects existing in the prior art, the present application proposes an advertising bid method, which can improve the applicability of information placement data analysis and obtain analysis results that are instructive for the placement of information placement data in the O2O mode, thereby facilitating the optimization of the placement structure of information placement data.

[0059] POI: point of interest, that is, the advertiser in the LBS placement scenario, generally referring to the placement store.

[0060] Competitive queue, target POI, competitor: The set of advertising POIs competing in the same LBS scenario (such as the same business district) is hereinafter referred to as the competitive queue; when making a bid estimate for a certain POI, that POI is called the target POI, and the other POIs in its competitive queue are called competitors.

[0061] eCPM: effective cost per mille, the estimated cost per thousand impressions, which is one of the main evaluation indicators for the revenue of performance advertising. In the bidding and ranking system for search list ad slots, eCPM is generally used as the basis for list sorting.

[0062] LBS: Location Based Service, location-based service, which refers to an added-value service that obtains the location information of mobile terminal users through the radio communication network of a telecommunications mobile operator or external positioning methods, and provides corresponding services to users with the support of a GIS platform.

[0063] The following uses specific embodiments to introduce the detailed content of the present disclosure:

[0064] Figure 1 It is a system block diagram of an advertising bidding method and device shown according to an exemplary embodiment.

[0065] As Figure 1 shown, the system architecture 100 may include user terminal devices 101, 102, merchant terminal device 103, network 104, and server 105. The network 104 is used to provide a medium for communication links between the user terminal devices 101, 102, merchant terminal device 103, and server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0066] Ordinary users can interact with the server 105 through the user terminal devices 101, 102 via the network 104 to receive or send messages, etc. Advertiser users can interact with the server 105 via the merchant terminal device 103 and the network 104 to receive or send messages, etc. Various communication client applications may be installed on the user terminal devices 101, 102, and merchant terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0067] The terminal devices 101, 102, 103 may be various electronic devices with a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop portable computers, and desktop computers, etc.

[0068] Server 105 may be a server that provides various services. For example, it is a background server that supports search websites browsed by users using terminal devices 101 and 102. Server 105 can process the received user query information and feedback search results (such as multiple ads to be recommended) to terminal devices 101 and 102. Server 105 can also, for example, receive a bid assistance request from merchant terminal device 103 to assist merchant terminal 103 in making bids when providing ad recommendations for terminal devices 101 and 102.

[0069] Server 105 can, for example, determine multiple areas to be analyzed based on the geographical location of the target advertiser; Server 105 can, for example, determine multiple advertiser queues corresponding to the multiple areas to be analyzed; Server 105 can, for example, estimate multiple competitive bids of the target advertiser based on the click-through rates of the multiple advertiser queues; Server 105 can, for example, determine the target bid of the advertiser based on the multiple competitive bids.

[0070] Server 105 can be a physical server or, for example, composed of multiple servers. It should be noted that the ad bidding method provided in the embodiments of the present disclosure can be executed by Server 105. Correspondingly, the ad bidding device can be set in Server 105. The web page end for users to browse products and the request end for merchant queries are generally located in terminal devices 101 and 102.

[0071] According to the ad bidding method of the present disclosure, a real-time bidding suggestion method based on traffic segmentation in O2O industry ad placement is proposed. This method basically includes: obtaining positioning points of multiple users, determining multiple areas to be analyzed based on the multiple positioning points; determining traffic sets corresponding to each information placement data when it is placed in each of the areas to be analyzed; analyzing the relationship between the traffic of each information placement data in each area to be analyzed and the corresponding placement cost based on each traffic set. The technical solution implemented in the present invention improves the applicability of information placement data analysis and can obtain analysis results that are instructive for the placement of information placement data in the O2O mode, thereby facilitating the optimization of the placement structure of information placement data.

[0072] Figure 2 It is an application scenario diagram of an ad bidding method and device shown according to an exemplary embodiment.

[0073] Such as Figure 2As described above, a user makes a search request on a website being browsed, and the search target may be, for example, a nearby restaurant. A website first sorts the merchants near the user by category, which may be, for example, divided into major categories such as food, leisure and entertainment, and then extracts and sorts the restaurant merchants under the food category. The restaurant merchant list may be, for example, restaurant A, restaurant B, restaurant C, restaurant D, etc. Restaurant A, restaurant B, restaurant C, and restaurant D may compete for a position displayed on the user side by conducting a bidding ranking in the background of the website.

[0074] Restaurant A, restaurant B, restaurant C, and restaurant D can bid, for example, through a fixed bidding method or a real-time estimated bidding method. Based on the bids of each restaurant, the network backend server ranks each restaurant. Generally, the restaurant with the highest bid is ranked higher. The final bidding result shows the ranking of each different restaurant displayed on the user side.

[0075] Figure 3 is a flow chart of an advertisement bidding method according to another exemplary embodiment. The advertisement bidding method 30 at least includes steps S302 to S308.

[0076] like Figure 3 As shown, in S302, multiple areas to be analyzed are determined according to the geographic location of the target advertiser. For example, multiple target points are determined within a predetermined distance of the geographic location of the target advertiser; a region radius is determined; and the multiple areas to be analyzed are determined based on the region radius with the multiple target points as the center of the circle.

[0077] Figure 4 FIG. 1 is a schematic diagram of an advertisement bidding method according to another exemplary embodiment. Figure 4 As shown, in one embodiment, a multi-point LBS search advertisement request can be simulated: a circle is drawn with a target POI as the center and a certain distance as the radius, and multiple target points are selected. Specifically, for example, the circle can be divided into 60 degrees, and six points are selected as coordinates for simulating LBS search.

[0078] The reason why six requests are used instead of a single request is that in actual user search scenarios, searches are usually initiated not at the store location, but at a location nearby, so multiple requests are needed to simulate the results. The six-point solution was determined based on the experimental results and after comprehensively considering the balance between accuracy and performance.

[0079] By simulating online real-time search requests, a target POI with a suggested bid is given, and its nearby + advertising POIs of the same category are used as the competitive candidate set queue. Among them, the screening range of "nearby" is calculated by statistics and clustering of specific business scenarios (such as food, leisure and entertainment, etc.), and is divided into two cases according to the advertiser density in the business scenario. Figure 5It is a schematic diagram of an advertising bidding method shown according to another exemplary embodiment. As Figure 5 shown, in a search request, the determination of the "predetermined distance value" and the "area radius" is calculated based on the main category to which the POI belongs and the merchant density of the city, and can also be adjusted according to experimental results. The higher the merchant density, the more intense the competition. At this time, the "predetermined distance value" and the "area radius" are smaller; in the case of a small advertiser density, the simulated distance of the user from the merchant is slightly less than or equal to the radius of the advertisement recall. At this time, the nearby distance value should not be too small, otherwise the competition is insufficient and the estimated bid price is lower than the actual price; on the contrary, in the case of a large advertiser density, the simulated distance of the user from the merchant is much less than the radius of the advertisement recall. At this time, the nearby distance value should not be too large, otherwise the result will be too high.

[0080] In S304, determine a plurality of advertiser queues corresponding to the plurality of areas to be analyzed. The method includes: determining advertisers in each of the plurality of areas to be analyzed; obtaining advertising display costs corresponding to the advertisers; and ranking the advertisers in each area to be analyzed according to the advertising display costs to generate an advertiser queue.

[0081] Simulate search request recall at multiple points. The advertising lists recalled by each request are sorted from high to low according to eCPM, and the result list is the competition queue. To quantitatively describe the relevant parameters of bid price estimation, the form of the advertising eCPM formula is transformed as follows:

[0082]

[0083] where bid is the advertising bid, that is, eCPM is a polynomial of the advertising bid, and ak is the coefficient of each term of bid. This generalized form is basically applicable to the CTR estimation model in various business scenarios of LBS advertising. In the existing LBS business scenario, ak = 0 (k>1), and the formula is simplified to:

[0084] eCPM = q * bid + p

[0085] q = a0, that is, the first term of bid, and p = a1 is a constant term independent of the bid. q is the click-through rate, corresponding to CTR in the original formula, and is the main factor affecting eCPM.

[0086] For the generalized second-price auction (GSP) mode in search advertising bidding, the basis for competitive ranking can be quantified by eCPM, that is, the search result list is sorted from high to low according to the eCPM of the advertisement. eCPM can be expressed by the following formula:

[0087] eCPM = CTR * bid

[0088] Among them, CTR is the predicted click-through rate, and bid is the bid of the advertiser. Given a batch of CTRs and bids of other POIs in the competition, the bid required for the target POI to compete for a certain ranking can be deduced backwards.

[0089] In S306, the multiple competitive bids of the target advertiser are predicted according to the click-through rates of the multiple advertiser queues. This includes: predicting the multiple competitive bids of the target advertiser according to the real-time click-through rates of the multiple advertiser queues; and / or predicting the multiple competitive bids of the target advertiser according to the average click-through rates of the multiple advertiser queues.

[0090] In one embodiment, predicting the multiple competitive bids of the target advertiser according to the real-time click-through rates of the multiple advertiser queues includes: obtaining the advertising display fees corresponding to each advertiser in the advertiser queue; obtaining the real-time click-through rates corresponding to each advertiser in the advertiser queue; obtaining the advertising display coefficients corresponding to each advertiser in the advertiser queue; and predicting the multiple competitive bids of the target advertiser through the advertising display fees, real-time click-through rates, and advertising display coefficients corresponding to each advertiser. Specifically, for example, the advertising display fees, average click-through rates, and advertising display coefficients can be obtained through a search recall request. In the present disclosure, this method of predicting the multiple competitive bids of the target advertiser through the real-time click-through rates of the multiple advertiser queues can be referred to as "ordinary real-time bid suggestion".

[0091] In one embodiment, predicting the multiple competitive bids of the target advertiser according to the average click-through rates of the multiple advertiser queues includes: obtaining the advertising display fees corresponding to each advertiser in the advertiser queue; obtaining the average click-through rates corresponding to each advertiser in the advertiser queue; obtaining the advertising display coefficients corresponding to each advertiser in the advertiser queue; and predicting the multiple competitive bids of the target advertiser through the advertising display fees, average click-through rates, and advertising display coefficients corresponding to each advertiser. Specifically, for example, the advertising display fees and advertising display coefficients can be obtained through a search recall request; the average click-through rate can be determined through historical data. In the present disclosure, this method of predicting the multiple competitive bids of the target advertiser through the average click-through rates of the multiple advertiser queues can be referred to as "non-real-time bid suggestion". More specifically, through offline data, the historical average CTR of all POIs year-on-year (T-7 days) last week can be counted as the average click-through rate in the present disclosure.

[0092] In one embodiment, estimating multiple competitive bids of the target advertiser based on the click-through rates of the multiple advertiser queues includes: estimating multiple competitive bids corresponding to multiple rankings of the target advertiser in each area to be analyzed through the corresponding advertising display fee, advertising display coefficient, real-time click-through rate and / or average click-through rate of each advertiser.

[0093] In S308, the advertiser's target bid is determined according to the multiple competitive bids, including: merging the multiple competitive bids in the multiple areas to be analyzed according to their rankings; determining the largest competitive bid in each ranking as a sub-target bid; and generating the target bid through the multiple rankings and their corresponding sub-target bids.

[0094] Figure 6 FIG. 1 is a schematic diagram of an advertisement bidding method according to another exemplary embodiment. Figure 6 As shown in the figure, taking 6 areas to be analyzed as an example, the bid suggestion requests of 6 requests can be merged first, and the final bid suggestion result calculated for each position takes the largest value among the 6 request results of that position. The largest value among the 6 results is used because from the perspective of easy verification, the given suggestion result should more accurately reflect the actual ranking result, while the statistical mean or median result is not consistent with the actual bidding ranking effect, which leads to obstacles for advertisers to understand and verify.

[0095] According to the advertising bidding method disclosed in the present invention, multiple advertiser queues corresponding to multiple areas to be analyzed are determined according to the geographic locations of the target advertisers; competitive bidding is simulated according to the bidding information related to the multiple advertiser queues; and the target bid of the advertiser is determined according to the multiple competitive bids. This method can be merchant-centric and accurately simulate user search requests in actual scenarios, thereby providing merchants with reasonable advertising recommended bids.

[0096] It should be clearly understood that the present disclosure describes how to form and use specific examples, but the principles of the present disclosure are not limited to any details of these examples. On the contrary, based on the teachings of the contents disclosed in the present disclosure, these principles can be applied to many other embodiments.

[0097] Figure 7 FIG. 1 is a flow chart of an advertisement bidding method according to another exemplary embodiment. Figure 7 The advertisement bidding method 70 shown exemplarily describes the whole process of the server platform assisting the advertiser in bidding.

[0098] In S702, the POI information is requested.

[0099] In S704, it is determined whether the POI information is complete.

[0100] In S706, it is determined whether the current moment belongs to the placement moment.

[0101] In S708, the placement time period is supplemented.

[0102] In S710, a search is requested.

[0103] In S712, whether there are competitors;

[0104] In S714, a request is made to bid at the lowest price.

[0105] In S716, the recommended bid is calculated;

[0106] In S718, the bid rule is checked;

[0107] In S720, a bid is made.

[0108] According to the business rule restrictions, the admission threshold for the sorting position of the POI advertisement list is represented as maxPosition, that is, the highest advertisement position that the POI can compete for. The result of a single real-time recall contains the q, p, and maxPosition values of each POI in the competition queue. According to these parameters, the bid values corresponding to different positions of the target POI in the competition queue are calculated, which are the bid suggestions for the advertiser.

[0109] Subject to business rule restrictions, the sorting position of the advertisement list is also related to the highest admission ranking position of each POI; in different LBS scenarios, the rankings that advertisements can compete for will change dynamically. Therefore, it is necessary to obtain the admission positions of each competing POI in real time during estimation.

[0110] The information required for real-time bid estimation can be obtained in the following ways: from the POI location information system and placement data, obtain the competition queue and its bids around the location of the target POI; obtain the CTR of the competing POIs through real-time estimation; by importing the bid threshold judgment rules in each business scenario and substituting them into the eCPM calculation process, obtain the bid of the target POI.

[0111] Figure 8 It is a flowchart of an advertisement bidding method shown according to another exemplary embodiment. As Figure 8 shown, the advertisement bidding method 80 exemplarily describes the whole process of the server platform assisting the advertisement to monitor traffic and bids in real time. In the advertisement bidding method 80, taking a specific application scenario as an example, the process of advertising bidding is described respectively through two methods of "ordinary real-time bid suggestion" and "non-real-time bid suggestion". In actual application scenarios, for example, bidding can also be carried out through other bid suggestion methods, and all can be selected through a judgment step similar to that in S810, which will not be elaborated again in this application.

[0112] Among them, in S802, complete the POI information.

[0113] In S804, perform target determination.

[0114] In S806, perform search scenario determination.

[0115] In S808, construct a search request.

[0116] In S810, determine whether it is non-real-time bid recommendation traffic.

[0117] In S812, recall general real-time bid ads.

[0118] In S814, recall non-real-time bid ads.

[0119] In S816, calculate the bid.

[0120] In S818, perform data verification.

[0121] In S820, place the bid.

[0122] It is worth mentioning that the general real-time bid recommendation method cannot guarantee that the results of each recommendation are consistent with the actual traffic situation. The main reasons are: (1) The click-through rate (corresponding to the estimated CTR) recalled by each LBS search will change dynamically, and the q of the simulated recall request cannot correspond to the actual request CTR every time; (2) The method of taking 6 points around the target POI does not necessarily guarantee the same as all user online requests (including requests during advertiser verification), and the LBS location may have a great impact on eCPM. The accumulation of these perturbations may have a greater impact on the accuracy of the final bid recommendation.

[0123] For traffic that needs to ensure consistency between online and recommended results, "non-real-time bid recommendation" can be adopted, aiming to enable merchants and sales to easily verify the accuracy of bid recommendations through real requests.

[0124] More specifically, in actual application scenarios, bid recommendations are divided into two categories: "general real-time bid recommendation" and "non-real-time bid recommendation" according to different traffic. Among them, "general real-time bid recommendation" is mainly for traffic with low requirements for the accuracy of recommended bids, while "non-real-time bid recommendation" is mainly for traffic with extremely high requirements for the accuracy of bid recommendations. After obtaining competitive bids through "general real-time bid recommendation" or "non-real-time bid recommendation", the calculation and ranking of eCPM are then performed.

[0125] Among them, the "non-real-time bid recommendation" method can make the online real request results correspond to the simulated estimated requests, and will not affect the overall online CTR and revenue due to only using static click-through rates.

[0126] In the present disclosure, through two flexibly selectable bidding methods, namely "ordinary real-time bidding suggestions" and "non-real-time bidding suggestions", the way to obtain bidding suggestions can be flexibly adjusted to meet the needs of different advertisers. Moreover, the effect of the bidding suggestions can be accurately verified by the advertisers, which can truly reflect the effect of the advertisers' bids in the main traffic.

[0127] According to the advertising bidding method of the present disclosure, a bidding suggestion method based on the actual ranking of advertisements in the O2O industry is proposed. It can center around merchants, simulate user requests, and then calculate the suggested bid of the advertisement in real time.

[0128] According to the advertising bidding method of the present disclosure, a specific advertising real-time bidding suggestion method in the O2O industry can meet the accuracy of the suggested bid on special traffic.

[0129] Those skilled in the art can understand that all or part of the steps of implementing the above embodiments are realized as a computer program executed by a CPU. When the computer program is executed by the CPU, it executes the above functions defined by the above method provided by the present disclosure. The program can be stored in a computer-readable storage medium, which can be a read-only memory, a magnetic disk, an optical disk, etc.

[0130] In addition, it should be noted that the above drawings are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, rather than for limiting purposes. It is easy to understand that the processes shown in the above drawings do not indicate or limit the time sequence of these processes. Additionally, it is also easy to understand that these processes can be executed synchronously or asynchronously in, for example, multiple modules.

[0131] The following is an embodiment of the device of the present disclosure, which can be used to execute the embodiment of the method of the present disclosure. For the details not disclosed in the embodiment of the device of the present disclosure, please refer to the embodiment of the method of the present disclosure.

[0132] Figure 9 It is a block diagram of an advertising bidding device shown according to an exemplary embodiment. The advertising bidding device 90 includes: a region module 902, a queue module 904, an estimation module 906, and a bidding module 908.

[0133] The region module 902 is used to determine a plurality of regions to be analyzed according to the geographical location of the target advertiser. For example: determine a plurality of target points within a predetermined distance of the geographical location of the target advertiser; determine the region radius; and with the plurality of target points as the centers, determine the plurality of regions to be analyzed based on the region radius.

[0134] The queue module 904 is used to determine multiple advertiser queues corresponding to the multiple regions to be analyzed, including: determining the advertisers in each region to be analyzed among the multiple regions to be analyzed; obtaining the advertising display costs corresponding to the advertisers; and ranking the advertisers in each region to be analyzed according to the advertising display costs to generate an advertiser queue.

[0135] The estimation module 906 is used to estimate multiple competitive bids of the target advertiser according to the click-through rates of the multiple advertiser queues, including: estimating multiple competitive bids of the target advertiser according to the real-time click-through rates of the multiple advertiser queues; and / or estimating multiple competitive bids of the target advertiser according to the average click-through rates of the multiple advertiser queues.

[0136] Among them, the estimation module 906 includes:

[0137] The real-time estimation unit 9062 is used to estimate multiple competitive bids of the target advertiser according to the real-time click-through rates of the multiple advertiser queues. Specifically, for example: obtaining the advertising display costs corresponding to each advertiser in the advertiser queue; obtaining the real-time click-through rates corresponding to each advertiser in the advertiser queue; obtaining the advertising display coefficients corresponding to each advertiser in the advertiser queue; and estimating multiple competitive bids of the target advertiser through the advertising display costs, real-time click-through rates, and advertising display coefficients corresponding to each advertiser. Specifically, for example, obtaining the advertising display costs, average click-through rates, and advertising display coefficients through a search and recall request.

[0138] The average estimation unit 9064 estimates multiple competitive bids of the target advertiser according to the average click-through rates of the multiple advertiser queues. Specifically, for example: obtaining the advertising display costs corresponding to each advertiser in the advertiser queue; obtaining the average click-through rates corresponding to each advertiser in the advertiser queue; obtaining the advertising display coefficients corresponding to each advertiser in the advertiser queue; and estimating multiple competitive bids of the target advertiser through the advertising display costs, average click-through rates, and advertising display coefficients corresponding to each advertiser. Specifically, for example, obtaining the advertising display costs and advertising display coefficients through a search and recall request; determining the average click-through rate through historical data.

[0139] The bid module 908 is used to determine the target bid of the advertiser according to the multiple competitive bids. Combining the multiple competitive bids in the multiple regions to be analyzed according to the ranking; determining the largest competitive bid in each ranking as a sub-target bid; and generating the target bid through multiple rankings and their corresponding sub-target bids.

[0140] According to the advertising bidding device of the present disclosure, multiple advertiser queues corresponding to multiple areas to be analyzed are determined according to the geographical location of the target advertiser; competitive bidding is simulated according to the relevant bidding information of the multiple advertiser queues; and the target bid of the advertiser is determined according to the multiple competitive bids. In this way, it is possible to accurately simulate the user search requests in the actual scenario centered around the merchant, so as to provide reasonable advertising recommended bids for the merchant.

[0141] Figure 10 It is a block diagram of an electronic device shown according to an exemplary embodiment.

[0142] The following refers to Figure 10 to describe the electronic device 200 according to this embodiment of the present disclosure. Figure 10 The shown electronic device 200 is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present disclosure.

[0143] As Figure 10 shown, the electronic device 200 is presented in the form of a general-purpose computing device. The components of the electronic device 200 may include but are not limited to: at least one processing unit 210, at least one storage unit 220, a bus 230 connecting different system components (including the storage unit 220 and the processing unit 210), a display unit 240, etc.

[0144] Among them, the storage unit stores program codes, and the program codes can be executed by the processing unit 210, so that the processing unit 210 executes the steps according to various exemplary embodiments of the present disclosure described in the above part of the electronic prescription transfer processing method of this specification. For example, the processing unit 210 can execute as Figure 3 , Figure 7 , Figure 8 the steps shown in.

[0145] The storage unit 220 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 2201 and / or a cache storage unit 2202, and may further include a read-only storage unit (ROM) 2203.

[0146] The storage unit 220 may further include a program / utility 2204 having a set (at least one) of program modules 2205. Such program modules 2205 include but are not limited to: an operating system, one or more application programs, other program modules, and program data. The implementation of the network environment may be included in each or some combination of these examples.

[0147] The bus 230 may represent one or more of several types of bus structures, including a memory unit bus or a memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of the various bus structures.

[0148] The electronic device 200 may also communicate with one or more external devices 300 (such as a keyboard, a pointing device, a Bluetooth device, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 200, and / or may communicate with any device that enables the electronic device 200 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication may be performed through the input / output (I / O) interface 250. Moreover, the electronic device 200 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 260. The network adapter 260 may communicate with other modules of the electronic device 200 through the bus 230. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0149] Through the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software, or can be implemented by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the above methods according to the embodiments of the present disclosure.

[0150] Figure 8 Schematically shows a schematic diagram of a computer-readable storage medium in an exemplary embodiment of the present disclosure.

[0151] Refer to Figure 8 As shown, a program product 400 for implementing the above method according to an embodiment of the present disclosure is described. It may adopt a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, the readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.

[0152] The program product may employ any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, 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.

[0153] The computer-readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable medium may also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0154] The program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, executed as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0155] The above computer-readable medium carries one or more programs, and when the one or more programs are executed by a device, the computer-readable medium realizes the following functions: determining a plurality of areas to be analyzed according to the geographical location of the target advertiser; determining a plurality of advertiser queues corresponding to the plurality of areas to be analyzed; predicting a plurality of competitive bids of the target advertiser according to the click-through rates of the plurality of advertiser queues; and determining the target bid of the advertiser according to the plurality of competitive bids.

[0156] Those skilled in the art can understand that the above-mentioned modules can be distributed in the device according to the description of the embodiments, or can be correspondingly changed and distributed in one or more devices that are only different from this embodiment. The modules of the above embodiments can be combined into one module, or can be further split into multiple sub-modules.

[0157] Through the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software, or can be implemented by a combination of software and necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0158] The above specifically shows and describes the exemplary embodiments of the present disclosure. It should be understood that the present disclosure is not limited to the detailed structures, settings, or implementation methods described herein; on the contrary, the present disclosure is intended to cover various modifications and equivalent settings included within the spirit and scope of the appended claims.

[0159] In addition, the structures, ratios, sizes, etc. shown in the drawings of this specification are only used to cooperate with the content disclosed in the specification for those skilled in the art to understand and read, and are not used to limit the limiting conditions under which the present disclosure can be implemented. Therefore, they do not have technical substance. Any modification of the structure, change of the proportional relationship, or adjustment of the size, without affecting the technical effects that the present disclosure can produce and the purposes that can be achieved, should still fall within the scope that the technical content disclosed by the present disclosure can cover. At the same time, the terms such as "upper", "first", "second", and "one" cited in this specification are only for the convenience of clear narration, and are not used to limit the scope that the present disclosure can be implemented. The change or adjustment of their relative relationships, without substantial change in the technical content, should also be regarded as the scope that the present disclosure can be implemented.

Claims

1. An advertising bidding method, characterized in that, including: determining a plurality of areas to be analyzed according to the geographical location of the target advertiser; determining a plurality of advertiser queues corresponding to the plurality of areas to be analyzed; estimating a plurality of competitive bids of the target advertiser according to the click-through rates of the plurality of advertiser queues; and determining the target bid of the advertiser according to the plurality of competitive bids; wherein, determining a plurality of areas to be analyzed according to the geographical location of the target advertiser includes: determining a plurality of target points within a predetermined distance of the geographical location of the target advertiser; determining the area radius; and determining the plurality of areas to be analyzed with the plurality of target points as the centers and based on the area radius.

2. The method according to claim 1, wherein Determining a plurality of advertiser queues corresponding to the plurality of areas to be analyzed includes: determining the advertisers in each area to be analyzed among the plurality of areas to be analyzed; obtaining the advertising display costs corresponding to the advertisers; and ranking the advertisers in each area to be analyzed according to the advertising display costs to generate an advertiser queue.

3. The method according to claim 1, characterized in that Estimating a plurality of competitive bids of the target advertiser according to the click-through rates of the plurality of advertiser queues includes: estimating a plurality of competitive bids of the target advertiser according to the real-time click-through rates of the plurality of advertiser queues; and / or estimating a plurality of competitive bids of the target advertiser according to the average click-through rates of the plurality of advertiser queues.

4. The method according to claim 3, wherein Estimating a plurality of competitive bids of the target advertiser according to the real-time click-through rates of the plurality of advertiser queues includes: obtaining the advertising display costs corresponding to each advertiser in the advertiser queue; obtaining the real-time click-through rates corresponding to each advertiser in the advertiser queue; obtaining the advertising display coefficients corresponding to each advertiser in the advertiser queue; and estimating a plurality of competitive bids of the target advertiser through the advertising display costs, real-time click-through rates, and advertising display coefficients corresponding to each advertiser.

5. The method according to claim 4, characterized in that, Obtaining the advertising display costs, average click-through rates, and advertising display coefficients through a search and recall request.

6. The method according to claim 3, wherein Estimating a plurality of competitive bids of the target advertiser according to the average click-through rates of the plurality of advertiser queues includes: obtaining the advertising display costs corresponding to each advertiser in the advertiser queue; obtaining the average click-through rates corresponding to each advertiser in the advertiser queue; obtaining the advertising display coefficients corresponding to each advertiser in the advertiser queue; and estimating a plurality of competitive bids of the target advertiser through the advertising display costs, average click-through rates, and advertising display coefficients corresponding to each advertiser.

7. The method according to claim 5, characterized in that, Obtaining the advertising display costs and advertising display coefficients through a search and recall request; determining the average click-through rate through historical data.

8. The method according to claim 4 or 5, characterized in that, Estimating a plurality of competitive bids of the target advertiser according to the click-through rates of the plurality of advertiser queues includes: estimating a plurality of competitive bids corresponding to multiple rankings of the target advertiser in each area to be analyzed through the advertising display costs, advertising display coefficients, real-time click-through rates, and / or average click-through rates corresponding to each advertiser.

9. The method according to claim 8, wherein Determining the target bid of the advertiser according to the plurality of competitive bids includes: merging the plurality of competitive bids in the plurality of areas to be analyzed according to the rankings; determining the largest competitive bid in each ranking as a sub-target bid; and The target bid is generated through multiple rankings and their corresponding sub-target bids.

10. An advertising bid device, characterized in that, It includes: A region module for determining multiple regions to be analyzed according to the geographical location of the target advertiser; A queue module for determining multiple advertiser queues corresponding to the multiple regions to be analyzed; An estimation module for estimating multiple competitive bids of the target advertiser according to the click-through rates of the multiple advertiser queues; And A bid module for determining the target bid of the advertiser according to the multiple competitive bids; Wherein, the region module is set to: Determine multiple target points within a predetermined distance of the geographical location of the target advertiser; Determine the region radius; and With the multiple target points as the centers, determine the multiple regions to be analyzed based on the region radius.

11. The device according to claim 10, wherein The estimation module includes: A real-time estimation unit for estimating multiple competitive bids of the target advertiser according to the real-time click-through rates of the multiple advertiser queues; and / or An average estimation unit for estimating multiple competitive bids of the target advertiser according to the average click-through rates of the multiple advertiser queues.

12. An electronic device, characterized in that, It includes: One or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-9.

13. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, the method according to any one of claims 1-9 is implemented.

Images