CN115730972A

CN115730972A - Method, device and equipment for dynamically setting guaranteed price

Info

Publication number: CN115730972A
Application number: CN202211528792.0A
Authority: CN
Inventors: 何旭锋; 韩宗阳; 徐可; 郑玮; 邵鸽; 蒋能学
Original assignee: Hangzhou Netease Cloud Music Technology Co Ltd
Current assignee: Hangzhou Netease Cloud Music Technology Co Ltd
Priority date: 2022-11-30
Filing date: 2022-11-30
Publication date: 2023-03-03

Abstract

The application discloses a method, a device and equipment for dynamically setting a guaranteed price, wherein the method comprises the following steps: responding to an advertisement filling request initiated by a target object, acquiring a first historical bidding set of the plurality of demander platforms for the corresponding traffic of the target object, wherein the first historical bidding set comprises a plurality of bidding records of the plurality of demander platforms for the corresponding traffic of the target object within a first preset time period; determining a bidding mean value of the target object corresponding flow according to a plurality of bidding records of the plurality of demander platforms on the target object corresponding flow within a first preset time period; and determining the target reserve price of the target object corresponding to the flow according to the bid mean value, thereby improving the reasonability and reliability of the reserve price setting and realizing lean operation on the flow.

Description

Method, device and equipment for dynamically setting guaranteed price

Technical Field

The application relates to the technical field of computers, in particular to a method, a device and equipment for dynamically setting a guaranteed price.

Background

With the development of internet technology, more and more merchants choose to place advertisements on terminal software to improve exposure rate. At present, media and demand parties are mainly connected through a programmed advertisement trading platform, an advertisement position is provided by the media party, and the advertisement trading platform converges flow provided by the media for the demand parties to conduct bidding trading and provide advertisement materials. Usually, in order to guarantee the value of own traffic, the media party will agree on a guaranteed price for each ad slot when accessing the programmed trading platform.

However, currently the setting of the reserve price per ad slot mainly relies on the operator to manually set the base reserve price, and all traffic for that ad slot shares the same reserve price. However, operators manually set the basic reserve price all depend on operation experience, so that the current setting mode of the reserve price has the problem of low reliability. In addition, the effective range of the current quotation is an advertisement space, and the fine operation of the flow cannot be realized.

Disclosure of Invention

The embodiment of the application provides a method, a device and equipment for dynamically setting the guaranteed price, which can improve the reliability of setting the guaranteed price of an advertisement space and can finely operate the flow.

In a first aspect, a method for dynamically setting a reserve price is provided, the method comprising:

in response to an advertisement filling request initiated by a target object, acquiring a first historical bidding set of a plurality of demander platforms for the corresponding traffic of the target object, wherein the first historical bidding set comprises a plurality of bidding records of the plurality of demander platforms for the corresponding traffic of the target object within a first preset time period;

determining a bidding mean value of the flow corresponding to the target object according to a plurality of bidding records of the flow corresponding to the target object within a first preset time period by the plurality of demander platforms;

and determining a target reserve price of the flow corresponding to the target object according to the bid mean value.

Optionally, the determining a target reserve price of the flow corresponding to the target object according to the bid mean value includes:

determining a target value level to which the flow corresponding to the target object belongs according to the bid mean value;

and determining a target reserve price of the flow corresponding to the target object according to a plurality of bid records of the flow corresponding to all the objects in the target value hierarchy within a first preset time period by the plurality of demander platforms.

Optionally, the determining, according to the bid mean, a target value level to which the flow corresponding to the target object belongs includes:

respectively acquiring second historical bidding sets of the demanding party platform on a plurality of objects including the target object, wherein each second historical bidding set comprises a plurality of bidding records of the demanding party platform on the corresponding flow of the corresponding object in the plurality of objects within a first preset time period;

determining a bid mean value of flow corresponding to each object according to a second historical bid set corresponding to each object in the plurality of objects;

sorting each object according to the bid average value of the corresponding flow of each object;

dividing the plurality of objects into a plurality of object sets according to the sorting order, wherein each object set comprises at least one object, and each object set corresponds to a different value level;

and determining the value level corresponding to the object set to which the target object belongs as the target value level.

Optionally, the determining, according to a plurality of bid records of traffic corresponding to all objects in the target value hierarchy within a first preset time period, a target reserve price of the traffic corresponding to the target object further includes:

determining the overall value mean value of all objects in the target value level according to a third history bidding set of all objects in the target value level within the first preset time period by the demander platform, wherein the third history bidding set comprises a plurality of bidding records of corresponding flow of all objects in the target value level within the first preset time period by the demander platform;

and determining the target reserve price of the flow corresponding to the target object according to the overall value mean value.

Optionally, the determining the target reserve price of the flow corresponding to the target object according to the overall value mean includes:

determining the value standard deviation of all objects in the target value level according to the overall value mean value and the third history bidding set;

and determining the target reserve price of the corresponding flow of the target object according to the overall value mean and the value standard deviation.

Optionally, the determining a target reserve price of the target object corresponding to the flow according to the overall value mean and the value standard deviation includes:

acquiring flow performance data of the target object in a second preset time period;

determining a first target adjustment coefficient according to the flow performance data;

calculating a first product between the first target adjustment factor and the value standard deviation;

and calculating a first difference value between the overall value mean value and the first product, and determining the first difference value as a target reserve price of the flow corresponding to the target object.

acquiring object portrait data of the target object;

determining a second target adjustment coefficient according to the object portrait data;

calculating a second difference between the overall value mean and the value standard deviation;

and calculating a second product between the second target adjusting coefficient and the second difference value, and determining the second product as a target reserve price of the flow corresponding to the target object.

In a second aspect, there is provided a device for dynamically setting a guaranteed price, the device comprising:

the system comprises an obtaining module, a sending module and a receiving module, wherein the obtaining module is used for responding to an advertisement filling request initiated by a target object, and obtaining a first historical bidding set of a plurality of demander platforms for the corresponding traffic of the target object, and the first historical bidding set comprises a plurality of bidding records of the plurality of demander platforms for the corresponding traffic of the target object within a first preset time period;

the first determining module is used for determining a bid mean value of the flow corresponding to the target object according to a plurality of bid records of the flow corresponding to the target object within a first preset time period by the plurality of demander platforms;

and the second determination module is used for determining the target reserve price of the flow corresponding to the target object according to the bid mean value.

Optionally, the second determining module may be configured to: determining a target value level to which the flow corresponding to the target object belongs according to the bid mean value; and determining a target reserve price of the flow corresponding to the target object according to a plurality of bid records of the flow corresponding to all the objects in the target value hierarchy within a first preset time period by the plurality of demander platforms.

Optionally, the second determining module may be specifically configured to: respectively acquiring second historical bidding sets of the demanding party platform on a plurality of objects including the target object, wherein each second historical bidding set comprises a plurality of bidding records of the demanding party platform on the corresponding flow of the corresponding object in the plurality of objects within a first preset time period; determining a bid mean value of flow corresponding to each object according to a second historical bid set corresponding to each object in the plurality of objects; sorting each object according to the bid average value of the corresponding flow of each object; dividing the plurality of objects into a plurality of object sets according to the sorting order, wherein each object set comprises at least one object, and each object set corresponds to a different value level; and determining a value level corresponding to the object set to which the target object belongs as the target value level.

Optionally, the second determining module may be further specifically configured to: determining the overall value mean value of all objects in the target value level according to a third history bidding set of all objects in the target value level within the first preset time period by the demander platform, wherein the third history bidding set comprises a plurality of bidding records of corresponding flow of all objects in the target value level within the first preset time period by the demander platform; and determining the target reserve price of the flow corresponding to the target object according to the overall value mean value.

Optionally, the second determining module may be specifically configured to: determining the value standard deviation of all objects in the target value level according to the overall value mean value and the third history bidding set; and determining the target reserve price of the corresponding flow of the target object according to the overall value mean and the value standard deviation.

Optionally, the second determining module may be specifically configured to: acquiring flow performance data of the target object in a second preset time period; determining a first target adjustment coefficient according to the flow performance data; calculating a first product between the first target adjustment factor and the value standard deviation; and calculating a first difference value between the overall value mean value and the first product, and determining the first difference value as a target reserve price of the flow corresponding to the target object.

Optionally, the second determining module may be specifically configured to: acquiring object portrait data of the target object; determining a second target adjustment factor from the object portrait data; calculating a second difference between the overall value mean and the value standard deviation; and calculating a second product between the second target adjusting coefficient and the second difference value, and determining the second product as a target reserve price of the flow corresponding to the target object.

In a third aspect, a computer-readable storage medium is provided, in which a computer program is stored, the computer program being adapted to be loaded by a processor to perform the steps of the dynamic setting method of a reserve price according to the first aspect.

In a fourth aspect, a computer device is provided, the computer device includes a processor and a memory, the memory stores a computer program, and the processor is used for executing the steps in the dynamic setting method of the reserve price according to the first aspect by calling the computer program stored in the memory.

In a fifth aspect, there is provided a computer program product comprising computer instructions which, when executed by a processor, implement the steps in the dynamic setting method of a reserve price according to the first aspect.

The method and the device for achieving the bidding of the target object have the advantages that the first historical bidding set of the target object corresponding flow of the multiple demander platforms is obtained through responding to the advertisement filling request initiated by the target object, the first historical bidding set comprises multiple bidding records of the multiple demander platforms for the target object corresponding flow in the first preset time period, then the bidding mean value of the target object corresponding flow is determined according to the multiple bidding records of the multiple demander platforms for the target object corresponding flow in the first preset time period, and the target reserve price of the target object corresponding flow is determined according to the bidding mean value. According to the method and the device for determining the value measurement of the target object corresponding flow rate, the average value of the target object corresponding flow rate of a plurality of demand side platforms in a first preset time period is determined. And then, determining the target reserve price of the target object corresponding to the flow according to the bid mean value, improving the reasonability and reliability of reserve price setting, and overcoming the subjectivity caused by the fact that the basic reserve price is manually set by operators in the conventional reserve price setting method. In addition, the guarantee base price is set in the flow dimension instead of the advertisement space dimension, so that different flows under a specific advertisement space can be set with different guarantee base prices, and lean operation of the flows is realized.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic view of a first application scenario of a reserve price setting method in the related art according to an embodiment of the present application.

Fig. 2 is a schematic view of a second application scenario of the reserve price setting method in the related art according to the embodiment of the present application.

Fig. 3 is a schematic flow chart of a method for dynamically setting a reserve price according to an embodiment of the present application.

Fig. 4 is another schematic flow chart of a method for dynamically setting a reserve price according to an embodiment of the present application.

Fig. 5 is an application scenario diagram of the method for dynamically setting the reserve price according to the embodiment of the present application.

Fig. 6 is a schematic diagram of an experimental effect of the method for dynamically setting the reserve price according to the embodiment of the present application.

Fig. 7 is a schematic structural diagram of a device for dynamically setting a guaranteed price according to an embodiment of the present application.

Fig. 8 is a schematic structural diagram of a computer device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The embodiment of the application provides a method and a device for dynamically setting a guaranteed price, computer equipment and a storage medium. Specifically, the method for dynamically setting the reserve price according to the embodiment of the present application may be executed by a computer device.

First, some terms or expressions appearing in the course of describing the embodiments of the present application are explained as follows:

ADX (ad exchange, programmatic ad exchange) sells ad resources through different trading modes, supporting multiple trading modes such as programmatic direct acquisition, preferred purchase, open bidding, and the like.

The DSP (Demand-Side Platform) serves an advertiser and helps the advertiser to carry out advertisement putting on the Internet or the mobile Internet, and the DSP can enable the advertiser to simply and conveniently follow a uniform bidding and feedback mode and buy high-quality advertisement inventory in real time at a reasonable price for online advertisements positioned on a plurality of advertisement trading platforms. The advertisement exposure opportunity is obtained from an advertisement trading platform in a real-time bidding mode, and the DSP purchases each exposure independently in a bidding participation mode and generally settles the exposure multiplying unit price with the ADX.

Media, i.e., traffic owner. The media sends the flow of the advertisement request to the ADX, the ADX sends the advertisement request to each DSP, the DSP responds the advertisement and the bid in real time, bid trading is carried out on the ADX, and the winning advertisement is returned to the media exposure.

An ad slot is a location where media is used to fill in an ad. Different locations will have different total amounts of traffic (inventory) and different values. The same location may also have different values at different times. In order to guarantee the value of the flow of the media party, the guaranteed price of each position is appointed when the media party accesses the ADX, the ADX brings the guaranteed price when requesting the advertisement from the DSP, and the bidding price which is told to be lower than the guaranteed price by the DSP is filtered before bidding, so that the opportunity of participating in bidding is avoided.

eCPM (effective Cost Per Mille, thousands of exposures are all priced), and bidding advertisements are usually settled by exposure, and because the price of a single exposure is very low, which is not beneficial to intuitive communication and related operations, people are usually used as pricing units in various scenes, such as advertiser ordering, purchase settlement, sale negotiation and other scenes, at the price of thousands of exposures in the advertisement industry.

RTB (real time Bidding) is a Bidding technique that evaluates and bids on the display behavior of each user on millions of websites using third party techniques.

Currently, in the internet advertising industry, two methods are generally adopted for configuring the guaranteed price of an advertisement space. The first is that the operator configures according to the operation experience and the historical eCPM corresponding to the ad slot. However, in such a manner that the operator manually sets the reserve price, the manual configuration efficiency is low as the number of the advertisement slots increases, and whether the manually configured reserve price is reasonable and completely empirical or not, if the reserve price is too high, the willingness of the DSP to participate in bidding is reduced, which reduces the filling rate of the advertisement slots, and if the reserve price is too low, the value of the advertisement slots is reduced, which deteriorates the benefit of the media player. The second is a mode of manually setting the basic reserve price, and then feeding back and adjusting the basic reserve price according to the results of the display rate, the winning rate and the like during the operation of the system to obtain the final reserve price. The following formula can be referred to:

floor_price＝α×bid_price _base

α＝m×a+n×b

wherein, the floor _ price is the final reserve price, bid _ price _base The base price is the standard base price, m and n are regulating coefficients, a is the display rate, and b is the winning rate. In the mode, when the display rate and the winning rate are high, the base-guaranteeing price is high, and more advertisements are filtered out, so that the display rate and the winning rate are reduced; when the display rate and the winning rate are reduced, the reserve price is reduced, and the display rate and the winning rate are increased. The essence of this approach is to implement dynamic adjustment of the warranty price by applying negative feedback to the calculation process according to the result. However, this approach still requires manual determination of bid _ price _base Therefore, the problems of inefficiency and doubt in rationality that require manual setting of the advertisement space warranty price are not solved. In addition, the method excessively simplifies the relation between the reserve price and the display rate and the winning rate, and ignores other influence factors of the display rate and the winning rate of the advertisement in the advertisement system, such as flow distribution, bidding environment anduser profile, etc. Therefore, the effect and the theoretical reliability of this method are reduced by simplifying the cause and effect relationship.

In addition, the effective guarantee price range of the current advertisement space is the advertisement space, namely the guarantee prices of all traffic under the advertisement space are the same. As shown in fig. 2, when a user a and a user B open an APP (software application) through a terminal, assuming that an advertisement slot is provided on a start page of the APP, an advertisement filling request is initiated and sent to an ADX (advertisement trading platform), and then the ADX sends a user portrait, a guaranteed price, and the like to each Demand Side Platform (DSP) to bid on each DSP. As shown in fig. 2, user a's user representation tag data is 25 years old, female, fashion and travel, and user B's user representation tag data is 40 years old, male and dad. It can be determined from the user images of user a and user B that user a is more likely to be a high consumption crowd, and the traffic value when user a initiates an ad fill request should be higher and the bid threshold should be higher than the traffic value when user B opens the software application to initiate an ad fill request, and the bid threshold corresponds to the reserve price of the ad slot. However, since the media ad slot reserve price is set uniformly at present, the reserve price is the same when the user a initiates the ad filling request and when the user B initiates the ad filling request. It can be seen that the current way of setting the reserve price of the media advertisement space cannot set different reserve prices for the single requested flow, that is, cannot set the bidding threshold according to the flow value, and cannot perform fine operation of the flow.

The embodiment of the application provides a method for dynamically setting the guaranteed base price, which can determine the value measurement of a plurality of demander platforms on the corresponding flow of a target object, and determine the target guaranteed base price of the corresponding flow of the target object according to the value measurement of the plurality of demander platforms on the corresponding flow of the target object, thereby improving the reasonability and reliability of the setting of the guaranteed base price, and overcoming the subjectivity caused by the fact that the basic guaranteed base price is manually set by operators in the conventional method for setting the guaranteed base price. In addition, the guarantee base price is set in the flow dimension instead of the advertisement space dimension, so that different flows under a specific advertisement space can be set with different guarantee base prices, and lean operation of the flows is realized.

The following are detailed below. It should be noted that the description sequence of the following embodiments is not intended to limit the priority sequence of the embodiments.

Please refer to fig. 3 to 6, fig. 3 and 4 are schematic flow diagrams of a dynamic setting method of a reserve price according to an embodiment of the present application, fig. 5 is a schematic application scenario diagram of the dynamic setting method of a reserve price according to the embodiment of the present application, and fig. 6 is a schematic experimental effect diagram of the dynamic setting method of a reserve price according to the embodiment of the present application. The method comprises the following steps:

step 101, in response to an advertisement filling request initiated by a target object, obtaining a first historical bid set of multiple demander platforms for the corresponding traffic of the target object, where the first historical bid set includes multiple bid records of the multiple demander platforms for the corresponding traffic of the target object within a first preset time period.

The target object is a target user for single traffic targeting of the media advertisement space, for example, if the media requests to perform advertisement filling on the user a corresponding to the advertisement space, the target object is the user a. Specifically, the ADX may be connected to multiple media terminals directly or indirectly, where different media correspond to different media IDs (unique identifiers), and each media includes multiple advertisement slots, which represent locations that can be used to fill advertisements. Wherein, when the target object accesses the website, page or interface where the advertisement position is located, an advertisement filling request can be generated.

In particular, with the development of internet advertising, many internet products, such as social media software, multimedia software, game software, etc., are provided with advertising spots. For example, when user A accesses multimedia software and enters an ad page, user A initiates an ad fill request, which may include information such as a user unique identifier and a user representation. The media party may then send the ad filling request to the ad exchange platform.

In the embodiment, in order to better measure the value of the flow rate corresponding to the target object, the scheme obtains a plurality of bid records of the flow rate corresponding to the target object in a first preset time period by a plurality of demand side platforms, and then determines the reserve price of the flow rate corresponding to the target object according to the bid records.

Specifically, a plurality of bid records of the target object corresponding to traffic of a plurality of demand side platforms in a first preset time period may be stored in a preset database, and the preset database may be maintained by the ADX.

For example, the predetermined database may store a bid record for each DSP for each object, e.g., an ID for each object and a plurality of bid records for each ID for different DSPs for the object during a first predetermined time period. The ADX can request the reserve price configuration center for the reserve price of the target object corresponding to the flow in response to an advertisement filling request initiated by the target object, and carries a plurality of bid records of the target object on different DSPs in a first preset time period while initiating the reserve price request.

Step 102, determining a bid mean value of the target object corresponding flow according to a plurality of bid records of the plurality of demand side platforms on the target object corresponding flow within a first preset time period.

The first preset time period may be customized to a past time period, and may be set to seven days, fifteen days, or thirty days.

For example, assume a0_ price ₀ 、a0_price ₁ …a0_price _n When the representative target object a0 initiates an advertisement filling request in a past period of time, the bids of the DSPs for the target object a0 are recorded, and then the average bid value of the corresponding traffic of the target object a0 can be determined as:

wherein, val _a0 The bidding average value of the corresponding flow of the target object a0 is shown, and n is the total number of the bidding records of each DSP to the target object a 0.

And 103, determining a target reserve price of the flow corresponding to the target object according to the bid mean value.

It is easily understood that the average value of the bids of the plurality of demand parties for the target object corresponding traffic in the past period of time can be considered as the value evaluation of the target object corresponding traffic, and therefore, the target reserve price of the target object corresponding traffic can be determined according to the average value of the bids. For example, the bid mean may be directly determined as the target reserve price for the target object corresponding to the traffic. Therefore, the reasonability and the reliability of the corresponding flow of the target object are improved. In addition, the guaranteed base price is determined according to the single flow, so that the problem that the guaranteed base price can only be set according to the advertisement space and the flow under the advertisement space cannot be finely operated at present is solved.

Specifically, the bid mean value is determined according to a plurality of bid records of the corresponding flow of the target object in a first preset time period by a plurality of demand side platforms. Because the determination of the bid mean value does not depend on a certain specific demand party platform, the flow value reflected by the bid mean value does not depend on a certain specific demand party platform, the accuracy of flow value measurement is improved, and the accuracy of the flow reserve price is further improved. Moreover, a higher high value traffic reserve price will increase the bid on the demander platform, while a lower low value traffic reserve price will increase the fill rate of the ad spots. Therefore, the dynamic method for guaranteeing the base price can improve the yield of the flow and the filling rate of the advertisement space.

In some embodiments, determining a target reserve price for the target object corresponding to the traffic based on the bid mean comprises: determining a target value level to which the flow corresponding to the target object belongs according to the bid mean value; and determining a target reserve price of the flow corresponding to the target object according to a plurality of bid records of the flow corresponding to all the objects in the target value hierarchy within a first preset time period by a plurality of demand side platforms.

In this embodiment, a plurality of value hierarchies may be set in advance, each of which represents a high to low of the user's value within a value hierarchy. The value level to which each object belongs may be determined according to the bid mean value corresponding to each object, for example, each value level corresponds to one price interval, and the value level to which each object belongs may be determined by determining which price interval the bid mean value corresponding to each object belongs to. For another example, the target value level to which the target object belongs may be determined by sorting all objects according to their bid mean, and then performing bucket sorting to determine which bucket each object belongs to.

Specifically, the reserve price corresponding to each value level may be determined according to a plurality of bid records of traffic corresponding to all objects in each value level within a first preset time period by a plurality of demander platforms, and then the reserve price corresponding to each value level may be determined as the shared reserve price of traffic corresponding to all objects in the value level. For example, the overall value mean of all users in each value level may be calculated according to bid records of all objects corresponding to traffic in each value level within a first preset time period by a plurality of demander platforms, and then the overall value mean may be determined as the reserve price corresponding to the value level. Therefore, the problem that the demand side platform bids sparsely on the flow corresponding to the individual user can be solved, and the accuracy of determining the reserve price is improved.

In this embodiment, determining a target value level to which a flow corresponding to a target object belongs according to the bid mean includes: respectively acquiring second historical bidding sets of a plurality of objects including target objects by a demander platform, wherein each second historical bidding set comprises a plurality of bidding records of flow corresponding to the corresponding object in the plurality of objects by the demander platform within a first preset time period; determining a bid mean value of flow corresponding to each object according to a second historical bid set corresponding to each object in the plurality of objects; sequencing each object according to the bid mean value of the flow corresponding to each object; dividing the plurality of objects into a plurality of object sets according to the sorting order, wherein each object set comprises at least one object and corresponds to different value levels; and determining the value level corresponding to the object set to which the target object belongs as a target value level.

Wherein the plurality of objects may include all users to which all traffic of the plurality of media parties of the ADX docking is directed. Specifically, the average value of the bids corresponding to the traffic of each object can be determined according to the historical bid records of the platform on the demand side for all the objects, and the average value of the bids can be used for measuring the traffic value of each object. All objects may then be binned according to the traffic value of each object, thereby separating all objects into different value tiers. Specifically, the bid means and the objects are in a one-to-one correspondence relationship, so that the bid means can be sorted and then partitioned into buckets, the bid means can be partitioned into different value levels, and then the target value level of the target object can be determined by determining which value level the bid means corresponding to the target object belongs to.

For example, assume that there are m objects, denoted by a0, a1 \8230am, respectively. Firstly, n bid records of multiple corresponding flows of the m objects within a first preset time period are respectively obtained by multiple demand side platforms, wherein am is taken as an example, am _ price ₀ 、am_price ₁ 、am_price ₂ …am_price _n Respectively representing n bid records for object am. Specifically, it can be obtained that, in a first preset time period, the average value of bids of the DSP on the corresponding flow of each object is:

where val represents the bid mean, and m and n are both positive integers.

Then, the above bid means may be sorted from small to large, so as to obtain the following sorting order: val _a0 ＜val _a1 ＜val _a2 ＜…＜val _am 。

Then, due to val _a0 、val _a1 、…val _am The values of the objects a0 to am are represented by the average value of the bids of the DSPs on the objects a0 to am in the first preset time period, and the average value of the bids on all the objects a0 to am can be represented by the value acceptance of the DSPs, namely the value of the object is considered by the DSPs. Because the bid mean values correspond to the objects one to one, the bid mean values can be sorted and then subjected to bucket partitioning, that is, the bucket partitioning of a plurality of objects can be represented, and each bucket represents a value level. For example, can be based onThe number of the objects, which is to divide all the bid means equally into a plurality of buckets, each bucket may include k bid means, that is, a plurality of objects are divided equally into a plurality of buckets, each bucket includes k objects.

The target value level for the target object may then be determined by determining which bucket the target object belongs to.

In this embodiment, determining a target reserve price of a flow corresponding to a target object according to a plurality of bid records of the flow corresponding to all objects in a target value hierarchy within a first preset time period by a demander platform further includes: determining the overall value mean value of all objects in the target value level according to a third history bid set of all objects in the target value level within a first preset time period by a demand side platform, wherein the third history bid set comprises a plurality of bid records of corresponding flow of all objects in the target value level within the first preset time period by the demand side platform; and determining the target reserve price of the target object corresponding to the flow according to the overall value mean.

Specifically, each value level may include a plurality of objects, and taking the example that each value level includes k objects, an average value of bids of the plurality of demanding platforms on the k objects in each value level in the first preset time period may be calculated according to bid records of the plurality of demanding platforms on the k objects in each value level in the first preset time period, where the average value of the bids may be used to represent the value acceptance, i.e. the value level, of the DSP on the k objects in the value level. Therefore, the reserve price shared by all the objects in the target value hierarchy can be determined according to the overall value mean value of all the objects in the target value hierarchy, and then the shared reserve price of the value hierarchy to which the target object belongs is determined as the reserve price of the corresponding traffic of the target object. Therefore, even under the condition that the bids of a plurality of demand side platforms on the corresponding flow of the target object are sparse, the flow value of the corresponding flow of the target object can be well measured, and the accuracy of determining the reserve price of the corresponding flow of the target object is improved.

For example, for each value level, assuming that all objects in the target value level form a set { slotA }, the overall value mean of all objects in the value level can be determined according to the following formula:

wherein, slot _ avg _ price is the average value of the whole value, bid _ price _user For each bid record, slotA is the object set corresponding to the value level, and n is the sum of the number of bids of each demand side platform on all objects in the slotA.

Specifically, determining a target reserve price of the target object corresponding to the flow according to the overall value mean value comprises the following steps: determining the value standard deviation of all objects in the target value level according to the overall value mean value and the third history bidding set; and determining the target reserve price of the flow corresponding to the target object according to the overall value mean and the value standard deviation.

It is readily understood that the standard deviation is a measure of the degree of dispersion of a set of data from the mean. A larger standard deviation indicates that most of the data is more similar to the mean of the data, and a smaller standard deviation indicates that most of the data is closer to the mean of the data. In order to avoid that the bid mean value of most objects in the target value level is greatly different from the overall value mean value, an error exists when the overall value mean value is directly used as the shared reserve price of all the objects in the target value level, and therefore after the overall value mean value is calculated, the value standard deviation of all the objects in the target value level can be calculated. The value standard deviation is used for representing the value difference of all the objects in the value level, and then the target reserve price is determined according to the value standard deviation and the overall value mean value, so that the accuracy of reserve price determination can be further improved.

Specifically, the standard deviation of value and the target reserve price for all objects in the target value hierarchy can be determined by the following formulas:

floor_price＝slot_avg_price-N*slot_std_price

the slot _ std _ price is the value standard deviation of all objects in the target value level, the slot _ avg _ price is the overall value mean value of all the objects in the target value level, the floor _ price is the target reserve price, N is the sum of the times that all the objects in the target value level are bid by all the demand party platforms within the first preset time period, and N is an adjusting coefficient. Generally, the initial value of N is 1, and the value of N may be subsequently adjusted according to the advertisement delivery effect of the target object corresponding to the traffic.

Specifically, determining a target reserve price of the target object corresponding to the flow according to the overall value mean and the value standard deviation comprises the following steps: acquiring flow performance data of the target object in a second preset time period; determining a first target adjustment coefficient according to the flow performance data; calculating a first product between the first target adjustment factor and the value standard deviation; and calculating a first difference value between the overall value mean value and the first product, and determining the first difference value as a target reserve price of the flow corresponding to the target object.

The traffic performance data may include, among other things, revenue data, fill rate data, and the like. Wherein the target reserve price may be adjusted based on the flow performance data. For example, the default value of the adjustment factor is 1, and then, based on the flow performance data, for example, the flow performance data is poor, the adjustment factor may be increased to obtain the first target adjustment factor, so that the reserve price is lowered. If the flow rate performance data is excellent, the first target turndown coefficient can be reduced, and the reserve price can be increased.

Specifically, determining a target reserve price of the target object corresponding to the flow according to the overall value mean and the value standard deviation comprises the following steps: acquiring object portrait data of a target object; determining a second target adjustment factor from the object portrait data; calculating a second difference value between the overall value mean and the value standard deviation; and calculating a second product between the second target adjusting coefficient and the second difference value, and determining the second product as a target reserve price of the flow corresponding to the target object.

The subject representation data may include, among other things, age data, gender data, consumption ability data, etc. of the target subject.

For example, the default value of the adjustment coefficient is 1, and if the age data of the target object indicates that the age of the target object is not within the preset age range, the adjustment coefficient is increased; and if the consumption capacity data of the target object indicates that the consumption capacity of the target object is lower, increasing the adjustment coefficient, and finally obtaining a second target adjustment coefficient to reduce the base price.

Specifically, after determining the target reserve price of the traffic corresponding to the target object, the ADX may send an advertisement request carrying the target reserve price to each DSP, so that each DSP can auction the traffic corresponding to the target object. Wherein, the advertisement request can also carry the portrait information of the target object. After receiving the advertisement request, the DSP determines whether to participate in bidding according to information such as target reserve price, image data and the like. If the DSP decides to participate in the bidding, the DSP responds to the advertisement materials and the bidding, and otherwise, the DSP does not respond or responds to an agreed code to indicate that participation in the bidding is abandoned. And then, after receiving the advertisement materials responded by each DSP, ADX firstly filters the base price, namely filters the materials with the price lower than the target reserve price, and finally carries out bidding sorting to obtain the high price. It will be readily appreciated that as each DSP responds to advertising material and bids, the bids for each DSP are saved to a predetermined database.

To better explain the dynamic setting method of the reserve price provided in the embodiment of the present application, please refer to fig. 4, the flow of the dynamic setting method of the reserve price provided in the embodiment of the present application can be summarized as the following steps 201 to 209, which are described as follows:

step 201, in response to an advertisement filling request initiated by a target object, obtaining a first historical bid set of multiple demander platforms for corresponding traffic of the target object, where the first historical bid set includes multiple bid records of the multiple demander platforms for corresponding traffic of the target object within a first preset time period.

For example, referring to fig. 5, taking the target object as user a as an example, the advertisement trading platform responds to the advertisement filling request initiated by user a, and requests the guaranteed price of the traffic corresponding to user a from the traffic value calculation module of the configuration center. At the moment, the flow value calculation module acquires a plurality of bid records of a plurality of demand side platforms (DSP 1-DSPn) for the corresponding flow of the user A in a first preset time period from the big data module.

Step 202, determining a bid mean value of the target object corresponding flow according to a plurality of bid records of the plurality of demand side platforms for the target object corresponding flow within a first preset time period.

Referring to fig. 5, after the traffic value calculation module obtains a plurality of bid records of the traffic corresponding to the user a in the first preset time period by the plurality of demand side platforms, the traffic value calculation module may determine a bid mean value val of the traffic corresponding to the target object according to the following formula _A ：

Wherein, A _ price _n And an nth bid record of the corresponding flow of the user A for the platform of the demand side, wherein n is the total number of the bid records, and n is a positive integer.

And step 203, determining a target value level to which the flow corresponding to the target object belongs according to the bid mean value.

Wherein, the average value of the bids of the plurality of demanders on the target object corresponding traffic in the past period can be considered as the value evaluation on the target object corresponding traffic. It is readily understood that the bid mean is determined from a plurality of bid records for a plurality of demand side platforms for corresponding traffic to the target object over a first preset time period. Because the determination of the bid mean value does not depend on a certain specific demand party platform, the flow value reflected by the bid mean value does not depend on a certain specific demand party platform, the accuracy of flow value measurement is improved, and the accuracy of the flow reserve price is further improved. Moreover, a higher high value traffic reserve price will increase the bid on the demander platform, while a lower low value traffic reserve price will increase the fill rate of the ad spots. Therefore, the dynamic method for guaranteeing the base price provided by the embodiment of the application can improve the yield of the flow and the filling rate of the advertisement space.

Specifically, the value average of the traffic corresponding to a plurality of objects including the target object may be determined, and then, each object may be ranked according to the bid average of the traffic corresponding to each object; dividing the plurality of objects into a plurality of object sets according to the sorting order, wherein each object set comprises at least one object, and each object set corresponds to a different value level; and determining the value level corresponding to the object set to which the target object belongs as a target value level.

Wherein the plurality of objects may include all users to which all traffic of the plurality of media parties of the ADX docking is directed. Specifically, the average bid value of the corresponding traffic of each object can be determined according to the historical bid records of the demand side platform on all the objects, and the average bid value can be used for measuring the traffic value of each object. All objects may then be binned according to the traffic value of each object, thereby separating all objects into different value tiers. Specifically, the bid mean values and the objects are in one-to-one correspondence, so that the bid mean values can be sorted and then partitioned into buckets, the bid mean values are partitioned into different value levels, and then the target value level of the target object is determined by determining which value level the bid mean value corresponding to the target object belongs to.

Step 204, determining the overall value mean value of all the objects in the target value level according to a third history bidding set of all the objects in the target value level within the first preset time period by the demander platform, wherein the third history bidding set comprises a plurality of bidding records of corresponding flow of all the objects in the target value level within the first preset time period by the demander platform.

Specifically, each value level may include a plurality of objects, and taking the example that the target value level includes k objects, a mean value of bids of the plurality of demanding platforms on the k objects in the target value level in a first preset time period may be calculated according to bid records of the plurality of demanding platforms on the k objects in the target value level in the first preset time period, where the mean value of bids may be used to represent the value acceptance, i.e. the value height, of the DSP on the k objects in the value level.

For example, assuming that all objects in the target value hierarchy constitute the set { slotA }, the overall value mean of all objects in the value hierarchy can be determined according to the following formula:

Step 205, determining the standard deviation of the value of all the objects in the target value level according to the overall value mean and the third history bid set.

For example, the standard deviation of value for all objects in the target value hierarchy can be determined by the following formula:

the slot _ std _ price is a value standard deviation of all objects in the target value level, the slot _ avg _ price is an overall value mean value of all objects in the target value level, and n is the sum of the times of bidding of all the objects in the target value level by all the demand party platforms within a first preset time period.

And step 206, acquiring flow performance data of the target object in a second preset time period.

The traffic performance data may include, among other things, revenue data, fill rate data, and the like.

Step 207, determining a first target adjustment coefficient according to the flow performance data.

For example, the default value of the adjustment factor is 1, and then, based on the flow performance data, for example, the flow performance data is poor, the adjustment factor may be increased to obtain the first target adjustment factor, so that the reserve price is lowered. If the flow rate performance data is excellent, the first target turndown coefficient can be reduced, and the reserve price can be increased.

At step 208, a first product between the first target adjustment factor and the value standard deviation is calculated.

And 209, calculating a first difference value between the overall value mean value and the first product, and determining the first difference value as a target reserve price of the flow corresponding to the target object.

Specifically, the target reserve price may be determined according to the following formula:

floor_price＝slot_avg_price-N*slot_std_price

the slot _ std _ price is the value standard deviation of all objects in the target value level, the slot _ avg _ price is the overall value mean value of all the objects in the target value level, the floor _ price is the target reserve price, and N is a first target adjustment coefficient.

Specifically, please continue to refer to fig. 5, after the flow value calculation module determines the target reserve price of the flow corresponding to the target object, the target reserve price is issued to the advertisement trading platform. Then, the advertisement trading platform can send an advertisement request carrying the target reserve price to each DSP. In addition, the advertisement request can also carry object image data of the target object, so that each DSP can determine whether to participate in bidding according to the target reserve price and the object image data of the target object. For example, as shown in fig. 5, DSP1 relinquishes participation in bidding, and DSP1 through DSPn participate in bidding and respond to material. After the advertisement trading platform obtains the bids and response materials of the DSPn from the DSP1, the price base filtering is firstly carried out, namely the bids and the response materials corresponding to the bids which are lower than the target reserve price are filtered. Then, the bids which are not lower than the target reserve price are sequenced, and the higher price is obtained, namely, the response material with the highest bid is subjected to advertisement filling.

It should be noted that after each DSP participates in bidding, the bidding will be sent to the advertisement trading platform, and the bidding records will be saved, for example, in a preset database. For example, continuing with FIG. 5, DSP1 through DSPn participate in bidding, and send bids to the ad exchange platform and, at the same time, send bids to the big data module for storage.

As can be seen from the above, in the embodiment of the present application, according to a plurality of bid records of a plurality of demander platforms for a target object corresponding to a flow rate within a first preset time period, a bid mean value of the target object corresponding to the flow rate is determined, so as to evaluate a value of the target object corresponding to the flow rate. And then, the flow values corresponding to all the objects are subjected to bucket separation, so that the flow values corresponding to all the objects are layered from low to high, and the problem that the flow corresponding to an individual object is bid sparsely is solved. In addition, in the embodiment, the problem of accuracy of the evaluation of the traffic value is considered, and since the evaluation process does not depend on a specific DSP completely, the traffic value does not depend on any specific DSP, in other words, the traffic value is not defined by a specific DSP. Conversely, high value traffic floor price boosting stimulates the DSP to raise bids, while low value traffic floor price lowering promotes ad filling, with traffic value fully dominated by the ad exchange platform.

Specifically, referring to fig. 6, fig. 6 shows the effect of performing a real-time bidding (RTB) experiment using the dynamic setting method for the reserve price provided by the embodiment of the present application. As shown in fig. 6, in the android system, the change of filling rate and the change of income both show a significant trend of increasing after being put into use for 3 months and one month in 2022, and in the iOS system, the change of filling rate and the change of income both show a significant trend of increasing after being put into use for 3 months and one month in 2022.

All the above technical solutions can be combined arbitrarily to form the optional embodiments of the present application, and are not described herein again.

According to the method and the device, a first historical bidding set of the multiple demander platforms for the corresponding flow of the target object is obtained by responding to an advertisement filling request initiated by the target object, the first historical bidding set comprises multiple bidding records of the multiple demander platforms for the corresponding flow of the target object in a first preset time period, then, a bidding mean value of the corresponding flow of the target object is determined according to the multiple bidding records of the multiple demander platforms for the corresponding flow of the target object in the first preset time period, and a target reserve price of the corresponding flow of the target object is determined according to the bidding mean value. According to the method and the device for determining the value measurement of the target object corresponding flow rate, the average value of the target object corresponding flow rate of a plurality of demand side platforms in a first preset time period is determined. And then, determining the target reserve price of the target object corresponding to the flow according to the bid mean value, improving the reasonability and reliability of reserve price setting, and overcoming the subjectivity caused by the fact that the basic reserve price is manually set by operators in the conventional reserve price setting method. In addition, the guarantee base price is set in the flow dimension instead of the advertisement space dimension, so that different flows under a specific advertisement space can be set with different guarantee base prices, and lean operation of the flows is realized.

In order to better implement the method for dynamically setting the guaranteed price in the embodiment of the present application, an embodiment of the present application further provides a device for dynamically setting the guaranteed price. Referring to fig. 7, fig. 7 is a schematic structural diagram of a device for dynamically setting a guaranteed price according to an embodiment of the present application. The device 10 for dynamically setting a guaranteed price may include:

an obtaining module 11, configured to obtain, in response to an advertisement filling request initiated by a target object, a first historical bid set of multiple demander platforms for corresponding traffic of the target object, where the first historical bid set includes multiple bid records of the multiple demander platforms for corresponding traffic of the target object within a first preset time period;

the first determining module 12 is configured to determine a bid mean value of a target object corresponding to a flow rate according to a plurality of bid records of a plurality of demander platforms for the target object corresponding to the flow rate within a first preset time period;

and a second determining module 13, configured to determine a target reserve price of the flow corresponding to the target object according to the bid mean value.

Optionally, the second determining module 13 may be configured to: determining a target value level to which the flow corresponding to the target object belongs according to the bid mean value; and determining a target reserve price of the flow corresponding to the target object according to a plurality of bid records of the flow corresponding to all the objects in the target value hierarchy within a first preset time period by a plurality of demander platforms.

Optionally, the second determining module 13 may be specifically configured to: respectively acquiring second historical bidding sets of a plurality of objects including target objects by a demander platform, wherein each second historical bidding set comprises a plurality of bidding records of the flow corresponding to the corresponding object in the plurality of objects by the demander platform in a first preset time period; determining a bid mean value of flow corresponding to each object according to a second historical bid set corresponding to each object in the plurality of objects; sequencing each object according to the bid mean value of the flow corresponding to each object; dividing the plurality of objects into a plurality of object sets according to the sorting order, wherein each object set comprises at least one object, and each object set corresponds to a different value level; and determining the value level corresponding to the object set to which the target object belongs as a target value level.

Optionally, the second determining module 13 may be further configured to: determining the overall value mean value of all objects in the target value level according to a third history bid set of all objects in the target value level within a first preset time period by the demander platform, wherein the third history bid set comprises a plurality of bid records of corresponding flow of all objects in the target value level within the first preset time period by the demander platform; and determining the target reserve price of the target object corresponding to the flow according to the overall value mean value.

Optionally, the second determining module 13 may be specifically configured to: determining the value standard deviation of all objects in the target value level according to the overall value mean value and the third history bidding set; and determining the target reserve price of the flow corresponding to the target object according to the overall value mean and the value standard deviation.

Optionally, the second determining module 13 may be specifically configured to: acquiring flow performance data of the target object in a second preset time period; determining a first target adjustment coefficient according to the flow performance data; calculating a first product between the first target adjustment factor and the value standard deviation; and calculating a first difference value between the overall value mean value and the first product, and determining the first difference value as a target reserve price of the flow corresponding to the target object.

Optionally, the second determining module 13 may be specifically configured to: acquiring object portrait data of a target object; determining a second target adjustment coefficient according to the object portrait data; calculating a second difference value between the overall value mean and the value standard deviation; and calculating a second product between the second target adjusting coefficient and the second difference value, and determining the second product as a target reserve price of the corresponding flow of the target object.

Each unit in the above-mentioned guaranteed price dynamic setting device can be wholly or partially realized by software, hardware and a combination thereof. The units may be embedded in hardware or independent from a processor in the computer device, or may be stored in a memory in the computer device in software, so that the processor can call and execute operations corresponding to the units.

The dynamic reserve price setting device 10 may be integrated into a terminal or a server having a memory and a processor and having an arithmetic capability, or the dynamic reserve price setting device 10 may be the terminal or the server.

The device 10 for dynamically setting a reserve price provided in the embodiment of the present application, in response to an advertisement filling request initiated by a target object, obtains a first historical bid collection of flows corresponding to the target object by a plurality of demander platforms through an obtaining module 11, where the first historical bid collection includes a plurality of bid records of flows corresponding to the target object by the plurality of demander platforms within a first preset time period, and then a first determining module 12 determines a bid mean value of flows corresponding to the target object according to the plurality of bid records of flows corresponding to the target object by the plurality of demander platforms within the first preset time period, and then a second determining module 13 determines the target reserve price of flows corresponding to the target object according to the bid mean value. According to the method and the device for determining the value measurement of the target object corresponding flow rate, the average value of the target object corresponding flow rate of a plurality of demand side platforms in a first preset time period is determined. And then, determining the target reserve price of the target object corresponding to the flow according to the bid mean value, improving the reasonability and reliability of reserve price setting, and overcoming the subjectivity caused by the fact that the basic reserve price is manually set by operators in the conventional reserve price setting method. In addition, the guarantee base price is set in the flow dimension instead of the advertisement space dimension, so that different flows under a specific advertisement space can be set with different guarantee base prices, and lean operation of the flows is realized.

Optionally, the present application further provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps in the foregoing method embodiments when executing the computer program.

Fig. 8 is a schematic structural diagram of a computer device according to an embodiment of the present application, and as shown in fig. 8, the computer device 800 may include: a communication interface 801, a memory 802, a processor 803, and a communication bus 804. The communication interface 801, the memory 802, and the processor 803 communicate with each other via a communication bus 804. The communication interface 801 is used for data communication between the computer apparatus 800 and external apparatuses. The memory 802 may be used to store software programs and modules, and the processor 803 may operate the software programs and modules stored in the memory 802, such as the software programs of the corresponding operations in the foregoing method embodiments.

Alternatively, the processor 803 may invoke the software programs and modules stored in the memory 802 to perform the following operations: responding to an advertisement filling request initiated by a target object, acquiring a first historical bidding set of a plurality of demander platforms for the corresponding traffic of the target object, wherein the first historical bidding set comprises a plurality of bidding records of the plurality of demander platforms for the corresponding traffic of the target object within a first preset time period; determining a bidding mean value of the target object corresponding flow according to a plurality of bidding records of the plurality of demander platforms on the target object corresponding flow within a first preset time period; and determining a target reserve price of the corresponding flow of the target object according to the bid mean value.

The present application also provides a computer-readable storage medium for storing a computer program. The computer-readable storage medium can be applied to a computer device, and the computer program enables the computer device to execute the corresponding process in the method for dynamically setting the reserve price in the embodiment of the present application, which is not described herein again for brevity.

The present application also provides a computer program product comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and executes the computer instruction, so that the computer device executes the corresponding process in the method for dynamically setting the reserve price in the embodiment of the present application, which is not described herein again for brevity.

The present application also provides a computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and executes the computer instruction, so that the computer device executes the corresponding process in the method for dynamically setting the reserve price in the embodiment of the present application, which is not described herein again for brevity.

It should be understood that the processor of the embodiments of the present application may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method embodiments may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.

It will be appreciated that the memory in the embodiments of the subject application can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. The non-volatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. The volatile Memory may be a Random Access Memory (RAM) which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), double Data Rate Synchronous Dynamic random access memory (DDR SDRAM), enhanced Synchronous SDRAM (ESDRAM), synchronous link SDRAM (SLDRAM), and Direct Rambus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer or a server) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for dynamically setting a reserve price, the method comprising:

2. The method for dynamically setting the reserve price according to claim 1, wherein the determining the target reserve price of the target object corresponding to the traffic according to the bid mean value comprises:

3. The method for dynamically setting the reserve price according to claim 2, wherein the determining the target value level to which the corresponding traffic of the target object belongs according to the bid mean value comprises:

4. The method according to claim 3, wherein the determining the target reserve price for the traffic corresponding to the target object according to the plurality of bid records for the traffic corresponding to all the objects in the target value hierarchy within the first preset time period by the demander platform further comprises:

5. The method for dynamically setting the reserve price according to claim 4, wherein the determining the target reserve price of the target object corresponding to the flow according to the overall value mean value comprises:

6. The method for dynamically setting the reserve price according to claim 5, wherein the determining the target reserve price of the target object corresponding to the traffic according to the overall value mean and the value standard deviation comprises:

7. A device for dynamically setting a guaranteed price, the device comprising:

8. A computer-readable storage medium, characterized in that it stores a computer program adapted to be loaded by a processor to execute the dynamic setting method of a reserve price according to any one of claims 1 to 6.

9. A computer device, characterized in that the computer device comprises a processor and a memory, wherein the memory stores a computer program, and the processor is used for executing the dynamic setting method of the reserve price according to any one of claims 1 to 6 by calling the computer program stored in the memory.

10. A computer program product comprising computer instructions, wherein the computer instructions, when executed by a processor, implement the dynamic reserve price setting method of any of claims 1-6.