CN111899041A - Information delivery processing method, information delivery device, information delivery equipment and storage medium - Google Patents

Information delivery processing method, information delivery device, information delivery equipment and storage medium Download PDF

Info

Publication number
CN111899041A
CN111899041A CN201910370831.0A CN201910370831A CN111899041A CN 111899041 A CN111899041 A CN 111899041A CN 201910370831 A CN201910370831 A CN 201910370831A CN 111899041 A CN111899041 A CN 111899041A
Authority
CN
China
Prior art keywords
flow
cost
information
target
delivery
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910370831.0A
Other languages
Chinese (zh)
Inventor
陈琼
王流斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to CN201910370831.0A priority Critical patent/CN111899041A/en
Publication of CN111899041A publication Critical patent/CN111899041A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0242—Determining effectiveness of advertisements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0247—Calculate past, present or future revenues
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0254—Targeted advertisements based on statistics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/08—Auctions

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Theoretical Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The embodiment of the invention provides a processing method and a device for information delivery, an information delivery method and a device, computer equipment and a storage medium, wherein the method comprises the following steps: obtaining historical releasing data of releasing information, and determining expected conversion cost of flow used in the historical releasing of the releasing information according to the historical releasing data; selecting a target flow from the candidate flows to form a flow set according to the expected conversion cost of the flow; and when the difference value between the conversion cost of the target flow and the target cost in the flow set accords with a set relationship, determining the consumption cost of the flow in the current release of the release information according to the expected conversion cost corresponding to the target flow in the flow set. In this manner, maximum conversion is achieved while ensuring that the placement of the placement information approaches the target cost.

Description

Information delivery processing method, information delivery device, information delivery equipment and storage medium
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a method and an apparatus for processing information delivery, a method and an apparatus for information delivery, a computer device, and a storage medium.
Background
With the development of information technology, in order to make more people know and purchase the products or services produced by the people, media information for promoting the products or services is generally made and displayed on a display position of a display platform known to the public, such as a webpage, a social network, and the like, wherein a process of displaying the media information on the display platform may be referred to as information delivery, and the displayed media information may be referred to as delivery information.
The cost and the information conversion amount of information release on a display platform are different due to different display positions, release time periods and user groups, so that the problem that the success rate and the conversion amount of releasing bidding cannot be effectively controlled exists in the existing information release scheme.
Disclosure of Invention
The embodiment of the invention provides a processing method and device for information delivery, an information delivery method and device, computer equipment and a storage medium, which can effectively give consideration to both stale power for information delivery and conversion quantity obtained after delivery.
The technical scheme of the embodiment of the invention is realized as follows:
a processing method for information delivery comprises the following steps: obtaining historical releasing data of releasing information, and determining expected conversion cost of flow used in the historical releasing of the releasing information according to the historical releasing data; selecting a target flow from the candidate flows to form a flow set according to the expected conversion cost of the flow; and when the difference value between the conversion cost of the target flow and the target cost in the flow set accords with a set relationship, determining the consumption cost of the flow in the current release of the release information according to the expected conversion cost corresponding to the target flow in the flow set.
An information delivery method, comprising: acquiring a releasing request sent by the flow for releasing the information; determining expected conversion cost of flow used in historical putting based on historical putting data of putting information, and selecting target flow to form a flow set according to the expected conversion cost of the flow; when the difference value between the conversion cost of the target flow and the target cost in the flow set accords with a set relationship, determining the consumption cost of the flow in the current delivery based on the expected conversion cost corresponding to the target flow, and participating in the bidding ranking of the information to be delivered in the current delivery according to the consumption cost, the estimated conversion rate and the estimated click rate; and selecting information to be delivered of the target according to the bidding ranking, and delivering the information to be delivered of the target at a corresponding display position of corresponding flow.
A computer device comprising a processor and a memory for storing a computer program operable on the processor; the processor is configured to implement the information delivery processing method or the information delivery method according to the embodiment of the present invention when the computer program is run.
A storage medium on which a computer program is stored, the computer program, when executed by a processor, implementing an information delivery processing method or an information delivery method according to an embodiment of the present invention.
In the embodiment of the invention, the expected conversion cost of the used flow in the historical putting data of the putting information is used as a reference, the target flow is selected according to the expected conversion cost of the flow, and the consumption cost of the flow in the current putting of the putting information is determined according to the expected conversion cost of the target flow in a flow set formed by the selected target flow.
Drawings
Fig. 1 is an application architecture diagram for implementing a processing method for information delivery provided in an embodiment of the present invention;
fig. 2 is a flowchart of a processing method for information delivery in an embodiment of the present invention;
fig. 3 is a system framework diagram of a processing method for information delivery in an embodiment of the present invention;
fig. 4 is a flowchart of a processing method for information delivery according to an embodiment of the present invention;
FIG. 5 is a flow chart illustrating the process of selecting target flows to form a flow set according to an embodiment of the present invention;
FIG. 6 is a diagram illustrating an architecture of a method for implementing data weighting according to an embodiment of the present invention;
fig. 7 is a flowchart of a processing method for information delivery according to an alternative embodiment of the present invention;
figure 8 is a diagram comparing the cpa advertisement delivery mode with other advertisement delivery modes provided by the embodiments of the present invention;
fig. 9 is a schematic structural diagram of a processing apparatus for information delivery according to an embodiment of the present invention;
fig. 10 is a flowchart of an information delivery method according to an embodiment of the present invention;
fig. 11 is a schematic structural diagram of an information delivery apparatus according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
Before further detailed description of the present invention, terms and expressions referred to in the embodiments of the present invention are described, and the terms and expressions referred to in the embodiments of the present invention are applicable to the following explanations.
1) The information delivery refers to a process in which a provider of a product or service makes information recommended for the product or server and displays the information on a display site of a display platform known to the public, such as a web page, a social network, and the like, and for example, the information delivery may refer to advertisement delivery.
2) The placement information refers to information that is displayed on a display position of a display platform in information placement, and the information is used for recommendation and may be referred to as media information or recommendation information, for example, the placement information may refer to an advertisement in advertisement placement.
3) The estimated click rate (pCTR) is the probability of being clicked by the user after exposure of the placement information. Taking the advertisement serving as the advertisement example, the advertisement is the probability that one advertisement is clicked by the user after being exposed.
4) The estimated conversion ratio (pCVR) is the probability that the delivery information will generate a conversion after being clicked. Taking the advertisement serving as the advertisement example, the advertisement is the probability that one advertisement is clicked by the user after being exposed. The recognition that the Conversion is generated after clicking is determined according to the type (Conversion/Action) of the Conversion behavior expected by the information publisher corresponding to the delivery information, for example, the Conversion behavior expected by an Advertiser (Advertiser) for advertisement delivery may be a downloading behavior, an installing behavior, a behavior of adding goods into a shopping cart, and the like, and each time the corresponding behavior occurs, the corresponding behavior is regarded as one Conversion. If the conversion behavior expected by the advertiser includes a click, the one-click behavior may also be considered as one conversion.
5) The expected revenue (eCPM) refers to the expected revenue of the placement information per thousand exposures, taking the placement information as an advertisement as an example, the eCPM refers to the expected revenue of the advertisement per thousand exposures, and the advertisement with the largest eCPM on the line competes for the opportunity of current exposure, that is, wins the opportunity of advertisement placement in real-time bidding.
6) The automatic bid mode (oCPA) refers to a new advertisement putting mode provided by the embodiment of the invention, and the automatic bid is carried out according to the conversion cost and the click charging is carried out.
Other known ad delivery modes include CPM, CPC, CPA, wherein the CPM ad delivery mode refers to bid-on-exposure, charge-on-exposure; the CPC advertisement delivery mode refers to bidding according to clicking and charging according to clicking; the CPA advertisement putting mode refers to bidding according to conversion and charging according to conversion.
7) Smart bid (SmartCPA): a Demand Platform Side (DSP) selects a consumption cost of traffic calculated from delivery information delivered using the cpa advertisement delivery mode for an information delivery person.
Taking the advertisement serving as an example, SmartCPA refers to the consumption cost of the traffic calculated by selecting the advertisement serving in the oCPA advertisement serving mode for the Advertiser by the DSP, and is also called the traffic bid; and determining an intelligent Bid, calculating a click Bid of each flow in real time according to the intelligent Bid according to the Bid and the Bid price, and participating bidding ranking on a real-time bidding line according to the eCPM (SamrtCPA) pCVR pCTR.
8) A Demand Platform Side (DSP) can be regarded as a set of information publishers, and provides bidding or billing strategies in different publishing modes for the information publishers, so as to facilitate the information publishers to achieve maximum conversion while publishing information under the premise of controlling costs.
Taking the advertisement serving information as an example, the DSP is a party providing different bidding and billing strategies under different advertisement serving modes for the advertiser, so as to enable the advertiser to obtain the maximum conversion amount while performing advertisement serving under the premise of controlling the cost.
9) Target conversion cost (TargetCPA): the average cost of conversion after the information publisher desires to deliver the information, taking the delivery information as an advertisement as an example, TargetCPA refers to the average cost of conversion after the advertiser desires to deliver the advertisement.
10) Expected conversion cost (eCPA): and (4) estimating the average conversion cost of the delivered information, taking the delivered information as an advertisement as an example, wherein eCPA refers to the estimated average conversion cost of the advertisement.
11) In a traffic transaction mode in real-time bidding (RTB) and internet information delivery, when a user just opens a traffic carrier (such as APP or Wap site), what the display position needs to display is not determined, and when bidding is finished, the actually displayed content (Creative) is determined, and the bidding time is usually within 100 milliseconds;
taking the advertisement serving as the advertisement, the advertisement slot refers to an advertisement slot, that is, the RTB mechanism is equivalent to real-time auction purchasing resources, and an auction is performed on the basis of each advertisement display exposure, that is, each PV (pageview) performs one-time display bidding, and the advertisement with a high bid is displayed by the PV. The DSP is used as a party for providing bidding and charging strategies under different advertisement putting modes for the advertiser, namely, the DSP serves for the advertiser to determine bidding (bid), helps the advertiser to obtain display opportunities on the premise of being closest to the budget putting cost of the advertiser for carrying out advertisement putting, and simultaneously obtains the maximum conversion amount.
12) Traffic is a carrier of presentation positions, such as web pages of websites, public numbers of social networks, and the like.
Embodiments of the present invention provide an information delivery processing method, an information delivery processing device implementing the information delivery processing method, an information delivery device implementing the information delivery method, a computer device, and a storage medium storing an executable computer program for implementing the information delivery processing method or the information delivery method. The information delivery processing method and the information delivery method in the embodiment of the present invention are implemented in the same environment, and as for implementation of the information delivery processing method and the information delivery method, the embodiment of the present invention provides a scheme implemented on a terminal side and/or a server side, and an exemplary implementation scenario of the information delivery processing method is described.
As shown in fig. 1, in order to implement the processing method for information delivery according to the embodiment of the present invention, an optional application scenario is schematically illustrated, and an architecture of the application scenario includes a first terminal 100, a second terminal 200, a server 300, and a database 400 based on a network communication connection. In the following embodiments of the present invention, the advertisement serving as the advertisement is described, and it should be noted that the advertisement in the following description may be replaced by the advertisement serving as the advertisement.
The first terminal 100 is a user terminal corresponding to an advertiser, that is, an advertiser terminal, and the second terminal 200 is a terminal corresponding to a user, that is, an advertising user terminal, that receives an advertisement displayed on an advertisement display platform, and performs actions of clicking, browsing, downloading, adding a commodity to a shopping cart, and the like, according to a preference of the user for the displayed advertisement. The actions of clicking, browsing, downloading, adding goods to the shopping cart, etc. may be referred to as conversion of the advertisement. The server 300 is a platform that provides bidding and billing policies under various advertisement delivery modes for advertisers, that is, a platform on a demand side that implements the processing method for information delivery provided by the embodiment of the present invention. The database 400 is used for storing historical advertisement delivery data for advertisement delivery in corresponding advertisement delivery modes, and the historical advertisement delivery data mainly includes traffic information, user information and advertisement information of advertisements delivered in different advertisement slots on different advertisement display platforms. Wherein, the advertisement information includes but is not limited to image data, text data or data combining image and text related to the product subject; the user information refers to user-related data of actions of clicking, browsing, downloading, adding commodities into a shopping cart and the like after receiving the advertisement through the advertisement display platform; the flow information refers to the flow rate of advertisement delivery through each advertisement bidding ranking, the actual conversion amount corresponding to the flow rate, the cost, the expense and other related data.
Referring to fig. 2, a flowchart of implementing an opca advertisement delivery mode according to an embodiment of the present invention is shown, where the implementing of the opca advertisement delivery mode includes the following steps: step S1, the advertiser selects an oCPA advertisement delivery mode through the first terminal 100, and sets a target cost; step S2, the server 300 obtains historical placement data from the database 400 based on the placement request of the advertiser; step S3, the server 300 determines the expected conversion cost of each flow according to the historical delivery data; step S4, the server 300 selects a flow to form an optimal flow set based on the expected conversion cost of each flow; step S5, the server 300 determines the consumption cost of the traffic according to the target cost and the selected traffic set; the server 300 calculates a click bid per traffic and a rank bid to participate in advertisement delivery in real time according to the consumption cost of the traffic at step S6. And step S7, the advertisement display platform selects the advertisement for obtaining the exposure display opportunity based on the real-time bidding mechanism and puts the advertisement to the second terminal corresponding to the advertisement user. And step S8, the advertisement user receives the advertisement delivered by the corresponding page of the advertisement display platform through the second terminal, and clicks (downloads, installs, joins in a shopping cart) the advertisement of interest. In step S9, the database 400 obtains data related to advertisement placement, and forms and stores historical placement data.
Referring to fig. 3, an overall system framework diagram for determining consumption cost of traffic in the cpap advertisement delivery mode is shown, the system framework is located at the server 300 side shown in fig. 1, and includes a basic data module 31, a vocabulary loading module 32, and a task processing module 33. The basic data module 31 is mainly used for acquiring historical advertisement delivery data obtained by a specified channel, summarizing actual cost and conversion information of each advertisement according to the historical advertisement delivery data, analyzing and storing click information of each advertisement according to a specified format. The vocabulary loading module 32 mainly comprises an activating reflux vocabulary unit, a real-time adjusting vocabulary unit, an experimental configuration vocabulary unit, a pCVR offline estimation vocabulary unit, an advertisement forward arrangement vocabulary unit, a charging ratio vocabulary unit, an abnormal information vocabulary unit and a SmartCPA vocabulary unit. The activation reflux word list unit is used for recording data reporting channels, judging whether the specified data reporting channels are stable or not, and judging whether the specified channels are stable or not according to the reporting records of the specified channels of the historical advertisement delivery data. The real-time adjusting word list unit is used for storing a rule for adjusting the real-time calculation result of the consumption cost of the flow, such as a rule for correcting the current calculation result according to the difference between the real-time calculation result of the consumption cost of the flow and the historical calculation result in the similar time period. The experiment configuration word list unit is used for realizing strategy release or upgrading, such as upgrading and adjusting the strategy for obtaining historical advertisement delivery data. The pCVR offline estimated word list unit is used for recording the rule for adjusting the estimated conversion rate of the advertisement, such as adjusting the current estimated conversion rate according to the difference between the estimated conversion rates of the advertisement in two adjacent time periods. And the advertisement forward word list unit is used for recording the sorted related data of the online advertisements. The charging ratio word table unit is used for providing or updating an initialized charging ratio, the charging ratio refers to the ratio of the consumption cost of the flow to the actual bid, and the advertisement without historical delivery records can be applied to a strategy for determining the consumption cost of the flow by adopting the initialized charging ratio. And the abnormal information word list unit is used for filtering and screening abnormal records in the historical advertisement delivery data. And the SmartCPA word list unit is used for recording or storing the historical consumption cost calculation result of the flow.
The task processing module 33 comprises a periodic task unit, a real-time task unit and a SmartCPA linkage task unit. The regular task unit mainly comprises a charging ratio word list updating unit and a SmartCPA parallel computing unit. The charging ratio vocabulary updating unit is configured to update the charging ratio vocabulary in the vocabulary loading module according to a set period, and may specifically include updating an initialized charging ratio according to a preset policy. The SmartCPA parallel computing unit is used for implementing the processing method for information delivery provided by the embodiment of the invention according to a set period to compute the consumption cost of the flow, and can also be used for intelligently adjusting the SmartCPA computed parallel quantity according to the quantity change condition of delivery requests counted in the set period. The real-time task unit is mainly used for updating the running state of the advertisement according to the real-time change of the advertisement delivery, such as processing new delivery, suspension, off-shelf and the like of the advertisement, and can also comprise updating the experimental configuration vocabulary in the vocabulary loading module, and specifically can comprise updating the advertisement release strategy according to the real-time change of the advertisement delivery. And the SmartCPA linkage task unit is used for adjusting the value of historical advertisement delivery data on which a processing method for realizing information delivery depends according to the pCVR obtained by calculation of the pre-estimated conversion rate model and a set data processing strategy. The SmartCPA in each advertisement delivery calculated by the task processing module 33 is recorded in the SmartCPA vocabulary.
Referring to fig. 4, a flowchart of a processing method for information delivery according to an embodiment of the present invention is applicable to the server shown in fig. 1, where it should be noted that the server may also be other computer devices such as a terminal, and the following steps will be described.
Step 101, obtaining historical releasing data of releasing information, and determining expected conversion cost of flow used in the historical releasing of the releasing information according to the historical releasing data.
The historical release data of the release information is related data formed according to the historical release record of the release information. Taking the advertisement serving as the advertisement as an example, the historical advertisement delivery data of the advertisement serving information refers to related data formed according to historical advertisement delivery records, and the delivery record corresponding to the historical advertisement delivery of each advertisement item may include information of three aspects, namely traffic information, user information and advertisement information. The advertisement information includes but is not limited to image data, text data or data of combination of image and text related to the product subject related to the advertisement; the user information refers to the relevant data of the user who clicks, browses, downloads, adds commodities into a shopping cart and the like after receiving the advertisement through the advertisement display platform; the flow information refers to the actual conversion amount, cost, expense and other related data after the advertisement is put through each advertisement bidding ranking.
The delivery record of an advertisement may include relevant data of exposure, click and the like of the advertisement, and the index corresponding to each flow of the advertisement may include click rate, conversion rate and expected revenue. The flow rates respectively correspond to the behaviors of the user for opening the advertisement display platform, that is, the user correspondingly regards as one flow rate when opening the page capable of receiving the displayed advertisement once. As an alternative embodiment, the total historical placement data for an advertisement may be represented by the data set T, and the click rate, conversion rate, and expected revenue per traffic corresponding to the advertisement may be indicated by pCTRt,pCVRt,eCPMnextCharacterisation, i.e. the data set T for an advertisement has a per-traffic indicator of (pCTR)t,pCVRt,eCPMnext). The expected conversion cost of the flow may be in eCPAtThe desired conversion cost may be determined based on the actual cost of the ad versus the amount of conversion, as indicated.
Step 103, selecting a target flow rate from the candidate flow rates to form a flow rate set according to the expected conversion cost of the flow rate.
Here, the target flow is selected according to the expected conversion cost corresponding to the flow, the target flow with the expected conversion cost meeting the requirement is selected to form a flow set, and the current bid for delivering the corresponding flow is determined according to the target flow contained in the flow set as a reference. The candidate flows may be one or more flows, and the flow set of the target flows for which the conversion cost is expected to meet the requirement is the set of the flows with the largest conversion amount on the premise that the delivery cost meets the target cost. The expected conversion cost corresponding to each flow contained in the historical advertisement putting record is screened based on the target cost of the advertiser, the target flow with the flow conversion amount as much as possible and the conversion cost close to the target cost is searched, and the consumption cost of the flow is determined through the target flow index selected in the flow set, so that the advertiser can bid according to the conversion cost. The flow bid can be further used for conducting bidding sorting according to the estimated conversion rate and the estimated click rate of the advertisement and releasing according to the bidding result, so that the bid and the charge in the advertisement releasing process can be decoupled, the average conversion cost of the advertisement is close to the target cost, and the conversion amount is obtained as much as possible.
And 105, when the difference between the conversion cost of the target traffic and the target cost in the traffic set meets a set relationship, determining the consumption cost of the traffic in the current delivery of the delivery information according to the expected conversion cost corresponding to the target traffic in the traffic set.
Here, the conversion cost of the target flow rate in the flow rate set may be an average conversion cost determined by conversion costs corresponding to the target flow rates in the flow rate set, or may be an average conversion cost determined by removing a part of the target flow rates from the flow rate set based on a set rule. In an alternative embodiment, the conversion cost of the target traffic in the traffic set is determined according to the ratio of the total actual bid to the total conversion number of all target traffic in the traffic set, as shown in the following equation 1:
Figure BDA0002049881900000101
wherein Ts is a flow set, CPA is the average conversion cost of the target flow in the flow set, and Σ T is an epsilon TscosttMeans the total actual bid for all target flows in the set of flows, Σ T ∈ TsconversiontRefers to the total number of conversions for all target flows in the set of flows. The difference between the conversion cost of the target flow and the target cost in the flow set meets a set relationship, which means that the conversion cost of the target flow in the flow set is equal to the target cost, or the difference between the conversion cost of the target flow in the flow set and the target cost is relatively minimum in the process of sequentially selecting and forming the flow set.
In the above embodiment of the present invention, by using the expected conversion cost of the traffic used in the historical delivery data of the delivery information as a reference, selecting the target traffic according to the expected conversion cost of the traffic in the historical delivery, and when the difference between the conversion cost of the target traffic and the target cost in the traffic set formed by sequentially selecting the target traffic meets a set relationship, determining the consumption cost of the traffic in the current delivery of the delivery information according to the expected conversion cost of the target traffic in the traffic set formed by the selected target traffic, so that the consumption cost of the traffic determined according to the historical delivery data of the delivery information can accurately reflect the actual value of the traffic, thereby facilitating the delivery control of the delivery information according to the actual value of the traffic reflected by the consumption cost of the traffic, and improving the success rate of the information to be delivered participating in the current delivery on the premise of meeting the target cost, the maximum conversion can be obtained.
Taking the advertisement serving as an example, the target traffic is selected according to the expected conversion cost of each traffic in the historical advertisement serving data as a reference, the traffic bid is determined according to the expected conversion cost of the target traffic in the traffic set formed by the selected traffic, and the actual value of the traffic can be accurately reflected through the traffic bid determined according to the historical advertisement serving data, so that the purpose of obtaining the maximum conversion while ensuring that the advertisement serving is close to the target cost of an advertiser is achieved.
In some embodiments, said selecting a target flow among said candidate flows according to a desired conversion cost of said flow forms a flow set, comprising:
ranking the candidate flows according to their expected conversion costs;
and sequentially selecting target flow and adding the flow set according to the sequencing result until the difference value between the conversion cost of the target flow and the target cost in the flow set accords with the setting relation.
Here, the expected conversion cost corresponding to the flow rate may be determined according to a ratio of the cost corresponding to the flow rate to the conversion number, and as an alternative embodiment, the expected conversion cost corresponding to the flow rate is shown in the following formula 2:
Figure BDA0002049881900000111
wherein, eCPAtMeans the expected conversion cost, corresponding to the flowtMeans the cost corresponding to the flow, pCVRtIs the number of conversions, eCPM, corresponding to the flownextRefers to the expected yield, pCTR, corresponding to the flowtThe click rate is the amount of click corresponding to the flow rate. When the expected conversion cost corresponding to the traffic is determined, the calculation amount of the corresponding cost in the index corresponding to each traffic determined according to the historical advertisement delivery data is large, so that the cost corresponding to the traffic is converted according to the relation between the expected income of the traffic and the number of clicks, and the expected conversion cost corresponding to the traffic is determined according to the ratio of the expected income of the traffic to the number of clicks and the number of conversions corresponding to the traffic.
In the embodiment of the invention, expected conversion cost corresponding to traffic used in historical delivery is calculated according to historical delivery data of advertisements, sequencing is performed according to the expected conversion cost of the traffic, when a plurality of candidate traffic is provided, a target traffic is selected according to the sequenced candidate traffic and added into a traffic set, so that the traffic set is determined by sequentially selecting the target traffic with relatively low expected conversion cost directly according to the sequencing result, and the conversion cost of the target traffic in the traffic set is enabled to be closest to the target cost to ensure that the advertisement delivery can be close to the main target cost of the advertisements.
In some embodiments, the sequentially selecting a target flow and adding the target flow into a flow set according to the sorting result until a difference between a conversion cost of the target flow and a target cost in the flow set meets the setting relationship includes: adding a target flow with a minimum expected conversion cost to the flow set; when the difference value between the conversion cost of the target flow and the target cost in the flow set does not accord with a set relation, selecting the target flow from the candidate flows according to the ascending order of the expected conversion cost to add into the flow set until the difference value between the conversion cost of the target flow and the target cost in the flow set accords with the set relation.
Here, the target cost refers to a budget placement cost of an advertiser for advertisement placement. Sorting the flow according to the expected conversion cost corresponding to the flow from small to large, firstly selecting the flow with the minimum expected conversion cost in the candidate flows as a target flow addition flow set, judging whether the conversion cost of the target flow in the flow set meets a set relation with the target cost, if not, sequentially selecting the flow with the relatively minimum next expected conversion cost in the candidate residual flows as the target flow addition flow set, and judging whether the conversion cost of the target flow in the flow set meets the set relation with the target cost again, and repeating the steps until the conversion cost of the target flow in the flow set meets the set relation with the target cost, so that the final flow set is obtained.
In an alternative embodiment, the entire historical placement data for an advertisement is represented by data set T, and the advertisement is represented by a (pCTR) per traffic T includedt,pCVRt,eCPMnext) Showing that the target flow is selected to form an optimal flow set T according to the expected conversion cost corresponding to the flowsSo that the flow set contains the maximum number of conversions
Figure BDA0002049881900000121
And the conversion cost of the flow set is equal to the target cost
Figure BDA0002049881900000122
The target flow rate of (1). The selected target flow forms an optimal flow set TsReferring to fig. 5, the method includes the following steps:
step S11, calculating the expected conversion cost of each flow T in the data set T; as shown in equation 2;
step S12, sorting the flow T in the data set T from small to large according to the expected conversion cost;
step S13, selecting the flow T with the minimum expected conversion cost from the data set T, adding the flow T into the flow set TsDeleting the flow T from the data set T, and calculating the flow set TsThe conversion cost of (a);
step S14, judging flow set TsWhether the conversion cost of (a) is equal to the target cost; if yes, executing step S15, otherwise, returning to step S13;
step S15, according to the flow set TsThe maximum expected conversion cost in the flow t, the flow bid is determined. That is, SmartCPA ═ Max (eCPA)t,t∈Ts) Adding the last to TseCPA corresponding to medium flow ttAs a traffic bid.
In the above embodiment of the present invention, the flows are sorted from small to large according to the corresponding expected conversion costs, the flow update flow sets are sequentially selected from small to small, and the relationship between the conversion cost of the corresponding flow set and the target cost is calculated every time a new flow is added, so that the target flow with relatively small expected conversion cost is sequentially selected according to the sorting to determine the flow set, and the conversion cost in the flow set is closest to the target cost to ensure that the advertisement delivery can approach the advertiser target cost.
In some embodiments, after sequentially selecting the target traffic to add into the traffic set according to the sorting result, the method further includes: and determining the conversion cost of the target flow in the flow set according to the ratio of the total actual consumption cost of the target flow to the total conversion number contained in the flow set.
Here, the conversion cost of the target flow rate in the flow rate set may be an average conversion cost determined from an average value of conversion costs corresponding to the target flow rates in the flow rate set, or may be an average conversion cost determined from an average value of conversion costs of remaining target flow rates after a part of the target flow rates in the flow rate set are removed based on a set rule, or the like. Wherein the total actual consumption cost of the target traffic may be determined from a sum of the actual bids of said target traffic.
In the above embodiment of the present invention, in the process of sequentially selecting the target flow to form the flow set according to the expected conversion cost corresponding to the flow, the conversion cost of the flow set is calculated in real time according to the added flow, so that the flow set with the conversion cost closest to the target cost can be obtained.
In some embodiments, the obtaining historical placement data for placement information includes: acquiring historical release data of release information in a set time period; when the data volume of the historical release data is determined to be larger than a threshold value, respectively determining weights corresponding to a plurality of time periods according to confidence degrees of data in the time periods contained in the set time period; weighting historical impression data for each of the time periods based on the weights.
Here, the setting time period may be predetermined according to actual conditions, such as a week, a set number of days, a set number of hours, and the like. The time period is that the set time period is further divided into a plurality of periods, when the data volume of the historical release data is larger than a threshold value, the weight corresponding to the time period is determined according to the confidence of the data in each period, and the historical release data in each time period is weighted based on the corresponding weight. In an optional embodiment, the set time period may be one week, the set time period may be one day, the delivery information is an advertisement, when the data amount of the historical delivery data of the advertisement in one week is greater than a threshold, the weight corresponding to the data of the day is adjusted according to the confidence of the data of each day in the week, and the data of the days in the week is weighted according to the determined weight, so as to improve the weight of the data of the latest date, and to compatibly calculate the timeliness of the historical delivery data of the consumption cost of traffic.
In the embodiment of the invention, through the division of the set time period and the set period, for the advertisement with sufficient historical delivery data, the data weight of the latest date can be increased in a weight adjusting mode, so that the sufficiency and timeliness of the historical delivery data for calculating the consumption cost of the traffic are compatible.
In some embodiments, the obtaining historical delivery data of delivery information further includes: when the data volume of the historical release data is determined to be smaller than the data volume threshold value, increasing the duration of the set time period; and acquiring the historical release data within the increased duration until the data volume of the release information is greater than the data volume threshold.
Here, the setting time period may be predetermined according to actual conditions, such as a week, a set number of days, a set number of hours, and the like. In order to obtain enough data and ensure the sufficiency of the data, when the data volume of the historical release data in a set time period is determined to be smaller than the threshold value, the time length of the set time period is increased according to a set rule and the historical release data in the increased time length is obtained until the data volume of the release information is larger than the threshold value. In an optional embodiment, the set time period may be one week, the delivery information is an advertisement, the time lengths of the set time period increased according to the set rule may be sequentially increased by one day, and when it is determined that the data amount in one week is smaller than the threshold, the historical delivery data of the advertisement in one day is increased and whether the data amount meets the requirement is determined again.
It should be noted that, after obtaining the historical delivery data in the increased duration until the data size of the historical delivery data of the delivery information is greater than the threshold, determining weights respectively corresponding to the time periods according to confidence degrees of data in a plurality of time periods in the set time period, and weighting the historical delivery data in each time period based on the weights, so as to compatibly calculate the sufficiency and timeliness of the historical delivery data of the consumption cost of the traffic by increasing the weight of the data on the latest date.
In some embodiments, the determining, according to the confidence degrees of the data in the plurality of time periods included in the set time period, weights corresponding to the time periods respectively includes: and respectively determining the weights corresponding to the time periods according to the direct proportion relation between the weight corresponding to each time period in the set time period and the confidence coefficient of the data in the time period and the inverse proportion relation between the weight corresponding to each time period and the confidence coefficient of the data in the previous time period.
The confidence of the data in the corresponding time period can be determined according to at least one of sufficiency of the data in the corresponding time period, similarity with the data in the adjacent time period and stability. The sufficiency of the amount may be determined according to the size of the data amount. The similarity to the data in adjacent time periods may be based on corresponding indicators of flow in adjacent time periods, such as number of hits, number of conversions, and expected revenue (pCTR)t,pCVRt,eCPMnext) A determination is made. The stability can be determined according to the stability of the reporting channel of the advertisement delivery data. Here, the reporting channel of the advertisement delivery data may refer to a platform that generates or stores the advertisement delivery data.
Referring to fig. 6, in an architecture diagram for implementing data weighting according to an embodiment of the present invention, determining weights respectively corresponding to time periods according to confidence levels of data in a plurality of time periods in the set time period, and weighting historical advertisement delivery data in each time period based on the weights includes: determining the confidence corresponding to the data in each time period according to the sufficiency, similarity and stability of the data in each time period; between two adjacent time periods, the weight of the data in each time period is in a direct proportion relation with the confidence coefficient of the data in the time period and in an inverse proportion relation with the confidence coefficient of the data in the adjacent previous time period. Here, the time period is in days, the time period includes day1, day2 and day3 whose dates are sequentially from near to far in the set time period, taking day1 as an example, the confidence of day1 is determined according to the sufficiency, similarity and stability of the advertisement delivery data in day1, and the data weight of day1 is in a direct proportion to the confidence of day1 and in an inverse proportion to the confidence of day 2.
Through the data weighting method provided by the embodiment of the invention, the timeliness of the historical delivery data of the latest date can be improved while the historical delivery data with sufficient data volume is acquired, so that the following two goals are realized: for advertisements with insufficient data, historical advertisement putting data of a longer time period can be used, and the sufficiency requirement of historical data on which flow bidding depends is compatibly calculated; and secondly, for advertisements with insufficient data, the weight of the latest date can be increased, and the timeliness requirement of the historical data on which the flow bid depends is compatible to be calculated.
In some embodiments, the determining an expected conversion cost of traffic used in the historical impressions of the impression information from the historical impression data includes: according to the historical putting data, determining the click number, the conversion number and the expected profit corresponding to each flow used in the historical putting of the putting information, determining the product of the click rate and the conversion rate, and determining the expected conversion cost of each flow according to the ratio of the expected profit corresponding to the flow to the product.
Here, taking the delivery information as an example of the advertisement, the delivery data of a piece of advertisement may include related data such as bid-engaging ranking, exposure, click and the like of the advertisement, and the index corresponding to each flow of the piece of advertisement may include click rate, conversion rate and expected revenue. Each flow rate corresponds to a behavior of opening the advertisement display platform by the user, that is, a page which can receive the displayed advertisement and is opened by the user once can be regarded as a flow rate.
In the above embodiment of the present invention, by obtaining historical advertisement delivery data, according to traffic information included in the historical advertisement delivery data, determining click rate, conversion rate, and expected revenue corresponding to each traffic for representing the traffic, determining a product of the click rate and the conversion rate, and determining an expected conversion cost of the corresponding traffic according to a ratio of the expected revenue of the traffic to the product, a traffic set is formed by selecting a target traffic according to the expected conversion cost, so as to achieve a purpose of selecting the target traffic closest to a target cost of an advertiser and having a maximum conversion rate according to the traffic set.
In some embodiments, after determining the consumption cost of the traffic in the current delivery of the delivery information according to the expected conversion cost corresponding to the target traffic in the traffic set, the method further includes: and adjusting the consumption cost of the flow in the current advertisement delivery according to a set proportion according to the deviation between the consumption cost of the flow obtained by the previous calculation and the actual cost of the flow for advertisement delivery.
Here, the actual cost of advertisement delivery may refer to an advertisement cost determined according to an actual conversion amount of an advertisement after advertisement delivery. The deviation between the consumption cost of the flow obtained by the previous calculation and the actual cost of the flow for advertisement putting is used as feedback, and the calculation result of the consumption cost of the flow in the current advertisement putting is adjusted according to the set proportion based on the feedback, so that the flow bid can be further optimized to be close to the actual cost, and the cost achievement rate is guaranteed on the premise that the conversion cost of the advertisement is effectively controlled to be close to the budget putting cost of an advertiser.
In some embodiments, the method further comprises: determining the transaction data of single click of the flow in the current delivery of the delivery information according to the consumption cost of the flow and the estimated conversion rate of the delivery information; and/or determining a bidding result of the to-be-released releasing information participating in the current releasing according to the consumption cost of the flow, the estimated click rate and the estimated conversion rate of the releasing information, and sending the to-be-released releasing information to a display position corresponding to the corresponding flow for displaying according to the bidding result.
Here, the transaction data of a single click of traffic may refer to a single click bid of traffic. The single click bid of the traffic in the current delivery of the delivery information is determined according to the product of the consumption cost of the traffic and the estimated conversion rate of the delivery information, and the payment of the advertisement can be determined according to the product of the single click bid and the conversion amount. The bidding result of the information to be released participating in the current releasing can be a releasing request sent according to the flow of the releasing information of the user, the bidding ranking of the information to be released participating in the current releasing is determined according to the consumption cost of the flow, the estimated click rate and the estimated conversion rate of the releasing information on a releasing request line, and the information to be released of the target is selected according to the bidding result of the bidding ranking and displayed on the corresponding display position.
In order to make the implementation flow of the processing method for information delivery provided by the embodiment of the present invention more clearly understood, please refer to fig. 7, a flow of the processing method for information delivery is described below by taking an optional specific example as an example, where the delivery information refers to an advertisement, and the calculation of the traffic bid mainly includes three task branches: the first task branch is used for regularly and routinely calculating SmartCPA, the second task branch is used for updating the advertisement state on line in real time, and the third task branch is used for updating the SmartCPA in a linkage mode according to the updating of the conversion rate calculation model; the periodically and routinely calculating SmartCPA comprises the following steps:
s21, acquiring all historical delivery data of corresponding advertisements on an advertisement slot in a set time period, and expressing the data by a data set T; wherein, the characterization index of the flow corresponding to each advertisement display exposure of the advertisement position is (pCTR)t,pCVRt,eCPMnext)；
S22, judging whether the data of the historical advertisement putting data is sufficient;
s23, when the historical advertisement delivery data are not sufficient, increasing the time length of the set time period according to a set rule and acquiring the historical advertisement delivery data within the increased time length until the data volume of the advertisement meets the requirement of sufficiency; the sufficiency of the data can be determined according to the data quantity;
s24, when the historical advertisement delivery data are sufficient, determining weights corresponding to the time periods according to the confidence degrees of the data in the time periods in the set time period, and weighting the historical advertisement delivery data in the time periods based on the weights;
the set time period is divided into a plurality of time periods to respectively determine the corresponding weights, the weight of the number of the latest dates can be increased, and the sufficiency and timeliness of historical release data depended by SmartCPA can be further calculated in a compatible mode;
s25, calculating a corresponding expected conversion cost for each flow T in the data set T, and selecting target flows in sequence from small to large according to the expected conversion cost to form the flow set TsUp to the flow set TsThe conversion cost of (a) is equal to the target cost;
wherein the flow is integrated TsThe conversion cost of (a) can be shown in equation 1, the calculation of the expected conversion cost per traffic t can be shown in equation 2, and the target cost refers to the expected delivery cost of the advertiser to deliver the advertisement.
S26, collecting T according to the flowsDetermining SmartCPA corresponding to the advertisement slot according to the maximum expected conversion cost in the medium flow t;
wherein the flow set TsThe expected conversion cost of the traffic t with the maximum expected conversion cost is the traffic value corresponding to the advertisement showing exposure with the maximum conversion amount and the conversion cost of the corresponding advertisement slot is closest to the expected putting cost of the advertiser, and SmartCPA is determined according to the traffic value.
S27, in the process of online advertisement putting through real-time bidding, determining the single click bidding of the flow according to the product of the SmartCPA and the estimated conversion rate, and participating in the bidding sorting of the current putting according to the product of the SmartCPA, the estimated click rate and the estimated conversion rate; the bidding method comprises the steps of calculating SmartCPA, calculating the real-time bidding price according to the SmartCPA when online advertising is carried out through real-time bidding, and equivalently calculating the bidding price according to the flow value, so that the participation or the advance specification of an advertiser is not needed, and the bidding price can be adjusted in real time according to the conversion rate, and the bidding price in the real-time bidding can be determined by combining the target cost of the advertiser.
And updating the advertisement state on line in real time, wherein the updating mainly comprises processing new advertisement delivery, suspension and the like in real time. And updating SmartCPA according to the updating linkage of the conversion rate calculation model, and mainly comprises recalculating the conversion rate obtained after updating and upgrading the conversion rate calculation model and updating the SmartCPA.
In the above embodiment of the present invention, by taking the expected conversion cost of traffic in the historical advertisement delivery data as a reference, selecting traffic according to the expected conversion cost corresponding to each traffic, and when it is determined that the conversion cost of the target traffic in the traffic set and the target cost meet the set relationship, determining SmartCPA according to the expected conversion cost corresponding to the target traffic in the traffic set, so that the conversion cost of the target traffic in the traffic set formed by the selected traffic meets the target cost of the advertiser and can obtain the maximum conversion, thereby achieving the purpose of obtaining the maximum conversion while ensuring that the advertisement delivery is close to the target cost of the advertiser.
The mode for advertising by adopting the processing method for information delivery provided by the embodiment of the invention is an oCPA advertising mode, and when an advertiser delivers the advertisement, the advertiser only needs to select the oCPA advertising mode and input budget delivery cost. Determining SmartCPA by taking the budget delivery cost as a target cost and taking the expected conversion cost of the flow in the historical delivery data of the advertisement as a reference, and participating in the ranking bidding according to the SmartCPA, the estimated conversion rate and the estimated click rate on line as shown in formula 3:
eCPM ═ SamrtCPA ═ pCVR ═ pCTR (formula 3)
And intelligently adjusting the click Bid Bid of each flow during real-time bidding according to the SmartCPA obtained by calculation, as shown in a formula 4:
bid ═ SmartCPA × pCVR (formula 4)
Equivalently, the bid price and the charging price are decoupled, the advertiser can obtain the maximum conversion amount while achieving the effect that the actual cost is close to the budget release cost of the advertiser according to the conversion bid price and click-on fee deduction, and meanwhile, the income of a traffic party is guaranteed. Please refer to fig. 8, which is a comparison diagram of an opca advertisement delivery mode for advertisement delivery by using the information delivery processing method according to the embodiment of the present invention and several known advertisement delivery modes. Fig. 8A is a profit risk comparison of the advertisement delivery mode, where the CPC advertisement delivery mode/CPM advertisement delivery mode cannot guarantee the advertisement delivery effect; while the revenue risk of the traffic party is too large in the CPA advertisement delivery mode, the opca advertisement delivery mode proposed by the present invention can guarantee the revenue risk of both the advertiser and the traffic party, fig. 8B is a comparison of the bidding and billing logics of the advertisement delivery mode, and the advantages of the opca advertisement delivery mode at least include: 1) the straight-face target is controllable in cost according to the conversion bid price; 2) the bidding and the charging are decoupled, and the income of a traffic party is guaranteed; 3) and the intelligent bidding is carried out in consideration of the flow conversion value, so that the system efficiency is improved.
An embodiment of the present invention further provides an embodiment in which a processing apparatus for information delivery can be implemented by using a terminal or a server, and regarding a hardware structure of the processing apparatus for information delivery implementing the processing method for information delivery, please refer to fig. 9, which is a schematic diagram of an optional hardware structure of the processing apparatus for information delivery provided in the embodiment of the present invention, and the exemplary embodiment includes: at least one first processor 901, a first memory 902, at least one network interface 904, and a user interface 906. The various components of the processing means for information delivery are coupled together by a bus system 905. As will be appreciated, the bus system 905 is used to enable communications among the components. The bus system 905 includes a power bus, a control bus, and a status signal bus, in addition to a data bus. For clarity of illustration, the various buses are labeled as a bus system in FIG. 9.
User interface 906 may include, among other things, a display, a keyboard, a mouse, a trackball, a click wheel, keys, buttons, a touch pad, or a touch screen.
It will be appreciated that the first memory 902 can be either volatile memory or nonvolatile memory, and can include both volatile and nonvolatile memory. Among them, the nonvolatile Memory may be a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), which serves as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM). The described memory for embodiments of the present invention is intended to comprise, without being limited to, these and any other suitable types of memory.
The first memory 902 in the embodiment of the present invention is used for storing various kinds of data to inform the operation of the processing device for delivery. Examples of such data include: any executable program for operating on a processing device for information delivery, such as operating systems and application programs; historical delivery data of advertisements; a flow set formed by the selected target flow, and the like; the operating system includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, and is used for implementing various basic services and processing hardware-based tasks. The application programs may include various application programs such as a target application, a Media Player (Media Player), a Browser (Browser), etc. for implementing various application services. The information delivery processing device for implementing the information delivery processing method provided by the embodiment of the invention can be included in an application program.
The method disclosed in the above embodiments of the present invention may be applied to the first processor 901, or implemented by the first processor 901. The first processor 901 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be implemented by an integrated logic circuit of hardware or an instruction in the form of software in the first processor 901. The first processor 901 may be a general-purpose processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, or the like. The first processor 901 may implement or perform the methods, steps and logic blocks disclosed in the embodiments of the present invention. The general purpose first processor 901 may be a microprocessor or any conventional processor or the like. The implementation steps of the information delivery processing method provided by the embodiment of the invention can be directly embodied as the execution of a hardware decoding processor, or the combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium having a memory and a processor reading the information in the memory and combining the hardware to perform the steps of the method.
In an exemplary embodiment, the processing Device for information delivery may be implemented by one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs), for performing the aforementioned methods.
In an exemplary embodiment, with continuing reference to fig. 9, an information delivery processing apparatus according to an embodiment of the present invention includes: the device comprises an acquisition module 11, a selection module 12 and a determination module 13. The obtaining module 11 is configured to obtain historical delivery data of delivery information, and determine an expected conversion cost of a flow used in the historical delivery of the delivery information according to the historical delivery data; the selecting module 12 is configured to select a target flow from the candidate flows to form a flow set according to the expected conversion cost of the flow; the determining module 13 is configured to determine, when a difference between the conversion cost of the target traffic in the traffic set and the target cost meets a set relationship, a consumption cost of the traffic in the current delivery of the delivery information according to the expected conversion cost corresponding to the target traffic in the traffic set.
In some embodiments, the selecting module 12 is further configured to rank the candidate flows according to expected conversion costs of the flows; and sequentially selecting target flow and adding the flow set according to the sequencing result until the difference value between the conversion cost of the target flow and the target cost in the flow set accords with the setting relation.
In some embodiments, the selecting module 12 is further configured to add the target traffic with the minimum expected conversion cost to the traffic set; when the difference value between the conversion cost of the target flow and the target cost in the flow set does not accord with a set relation, selecting the target flow from the candidate flows according to the ascending order of the expected conversion cost to add into the flow set until the difference value between the conversion cost of the target flow and the target cost in the flow set accords with the set relation.
In some embodiments, the selecting module 12 is further configured to determine the conversion cost of the target flow in the flow set according to a ratio of a total actual consumption cost of the target flow to a total conversion number included in the flow set.
In some embodiments, the obtaining module 11 is further configured to obtain historical delivery data of delivery information within a set time period; when the data volume of the historical release data is determined to be larger than a threshold value, respectively determining weights corresponding to a plurality of time periods according to confidence degrees of data in the time periods contained in the set time period; weighting historical impression data for each of the time periods based on the weights.
In some embodiments, the obtaining module 11 is further configured to increase the duration of the set time period when it is determined that the data amount of the historical delivery data is smaller than the data amount threshold; and acquiring the historical release data within the increased duration until the data volume of the release information is greater than the data volume threshold.
In some embodiments, the obtaining module 11 is further configured to determine the weights corresponding to the time periods respectively according to a direct relationship between the weight corresponding to each time period in the set time period and the confidence level of the data in the time period, and an inverse relationship between the weight corresponding to each time period and the confidence level of the data in the previous time period.
In some embodiments, the obtaining module 11 is further configured to determine, according to the historical placement data, a number of clicks, a number of conversions, and an expected revenue corresponding to each traffic used in the historical placement of the placement information, determine a product of the click rate and the conversion rate, and determine an expected conversion cost for each traffic according to a ratio of the expected revenue corresponding to the traffic to the product.
In some embodiments, the system further comprises a delivery module, configured to determine, according to the consumption cost of the traffic and the estimated conversion rate of the delivery information, single-click transaction data of the traffic in a current delivery of the delivery information; and/or determining a bidding result of the information to be released participating in the current release according to the consumption cost of the flow, the estimated click rate and the estimated conversion rate of the release information, and sending the information to be released to a display position corresponding to the corresponding flow for display according to the bidding result.
It should be noted that: in the information delivery processing device provided in the above embodiment, when implementing the information delivery processing method in the embodiment of the present invention, only the division of each program module is described as an example, and in practical applications, the processing may be distributed to different program modules according to needs, that is, the internal structure of the device may be divided into different program modules to complete all or part of the processing described above. In addition, the information delivery processing device provided in the above embodiment and the information delivery processing method embodiment in the embodiment of the present invention belong to the same concept, and specific implementation processes thereof are described in detail in the method embodiment and are not described herein again.
In another aspect of the embodiments of the present invention, please refer to fig. 10, which further provides an information delivery method, including the following steps:
step 201, obtaining a delivery request for sending the traffic of the delivery information.
The traffic corresponds to the delivery request for delivery information, that is, the exposure opportunity of one advertisement delivery corresponds to one traffic. For example, a user opens a specified page of an advertisement display platform to obtain delivery information displayed in the specified page, that is, a flow rate is corresponding to the delivery information, after a click operation of opening the specified page of the advertisement display platform by the user, a delivery request sent by the flow rate for the delivery information is obtained, and a real-time bidding is performed before the delivery information displayed on the specified page is returned to achieve advertisement delivery based on the delivery request, wherein the bidding time is usually within 100 milliseconds.
Step 203, determining an expected conversion cost of the traffic used in the historical delivery based on the historical delivery data of the delivery information, and selecting a target traffic according to the expected conversion cost of the traffic to form a traffic set.
The historical delivery data refers to relevant data formed according to historical delivery information delivery records, and by taking delivery information as an advertisement as an example, the delivery records correspondingly contained in the historical delivery of each advertisement can include traffic information, user information and advertisement information. The advertisement information includes but is not limited to image data, text data or data of combination of image and text related to the product subject related to the advertisement; the user information refers to the relevant data of the user who clicks, browses, downloads, adds commodities into a shopping cart and the like after receiving the advertisement through the advertisement display platform; the flow information refers to the actual conversion amount, cost, expense and other related data after the advertisement is put through each advertisement bidding ranking.
Step 205, when the difference between the conversion cost of the target traffic and the target cost in the traffic set conforms to a set relationship, participating in a bidding ranking of currently released information to be released according to the consumption cost, an estimated conversion rate and an estimated click rate, based on the consumption cost of the traffic in the current release determined by the expected conversion cost corresponding to the target traffic;
here, the target cost refers to a budget placement cost when an advertiser places an advertisement. Determining consumption cost of the flow, namely flow bid, based on the maximum value of the expected conversion costs of the target flow in the flow set according to the relationship between the conversion costs of the target flow in the flow set and the target cost, that is, calculating average conversion costs according to the target flow added to the flow set, obtaining a final flow set when the average conversion costs are equal to the target cost, and determining the flow bid according to the maximum expected conversion costs of the flow in the final flow set.
It should be noted that, the selecting a target flow according to the expected conversion cost corresponding to the flow to form a flow set, and determining a flow bid based on the maximum value of the expected conversion cost of the target flow in the flow set according to the relationship between the conversion cost of the target flow in the flow set and the target cost may be the consumption cost of the flow obtained by using the processing method for information delivery provided by any embodiment of the present invention.
The traffic bid is determined by the expected conversion of the selected target traffic into costs, with the traffic bid as a reference for the traffic value, so that advertisers can bid at the actual conversion cost of the traffic.
And step 207, selecting information to be released of the target according to the bidding ranking, and releasing the information to be released of the target at a corresponding display position of corresponding flow.
And further determining the bidding ranking of the traffic of which the information to be delivered participates in the current delivery according to the consumption cost of the traffic, so as to ensure that the maximum conversion amount is obtained while the advertiser can deliver the advertisement with the bid closest to the budget delivery cost.
In the above embodiment of the present invention, in real-time bidding of advertisement delivery, by using the expected conversion cost of traffic used in the historical delivery data of the delivery information as a reference, target traffic is selected according to the expected conversion cost of traffic in historical delivery, and when a difference between the conversion cost of the target traffic and the target cost in the traffic set formed by sequentially selecting target traffic meets a set relationship, the consumption cost of traffic in the current delivery of the delivery information is determined according to the expected conversion cost of the target traffic in the traffic set formed by the selected target traffic, so that the consumption cost of traffic determined according to the historical delivery data of the delivery information can accurately reflect the actual value of traffic, thereby facilitating the delivery control of the delivery information according to the actual value of traffic reflected by the consumption cost of the traffic, on the premise of meeting the target cost, the success rate of the information to be released participating in the current release is improved, and meanwhile, the maximum conversion amount can be obtained.
In some embodiments, the information delivery method further includes: and determining the transaction data of single click of the flow in the current delivery of the delivery information according to the consumption cost of the flow and the estimated conversion rate of the delivery information.
Here, the transaction data of a single click of traffic may refer to a single click bid of traffic. The single click bid of the traffic in the current delivery of the delivery information is determined according to the product of the consumption cost of the traffic and the estimated conversion rate of the delivery information, and the payment of the advertisement can be determined according to the product of the single click bid and the conversion amount.
In the above embodiment of the present invention, the estimated delivery cost of the advertiser for delivering the advertisement is used as the target cost, the SmartCPA is determined by using the expected conversion cost of the traffic in the historical delivery data of the advertisement as the reference, and the bid participating in the current delivery can be determined on line according to the product of the SmartCPA and the estimated conversion rate and the estimated click rate to participate in the bidding ranking, as shown in the foregoing formula 3, the information to be delivered of the target is selected according to the bidding result of the bidding ranking, and is displayed on the corresponding display position; and the click Bid of each flow during real-time bidding can be intelligently adjusted according to the SmartCPA, as shown in the formula 4, the charging can be determined according to the product of the click Bid and the actual conversion amount, so that the Bid and the charging are equivalently decoupled, an advertiser can obtain the maximum conversion amount while the actual cost is close to the budget release cost of the advertiser according to the conversion Bid and the click deduction fee, and the income of a flow party is guaranteed.
An embodiment of the present invention further provides an information delivery device for implementing the information delivery method, where an implementation side of the information delivery method may be the same as an implementation side of the information delivery processing method, and the implementation side is the same as the implementation side of the information delivery processing method, and is the server shown in fig. 1. Referring to fig. 11, an optional hardware structure diagram of an information delivery apparatus according to an embodiment of the present invention is shown, including: at least one second processor 801, a second memory 802, at least one network interface 804 and a user interface 806. The various components of the information delivery device are coupled together by a bus system 805. As will be appreciated, the bus system 805 is used to enable communications among the components. The bus system 805 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as a bus system in fig. 11.
The user interface 806 may include, among other things, a display, a keyboard, a mouse, a trackball, a click wheel, keys, buttons, a touch pad, or a touch screen.
It will be appreciated that the second memory 802 can be either volatile memory or nonvolatile memory, and can include both volatile and nonvolatile memory. Among them, the nonvolatile Memory may be a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), which serves as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM). The second memory 802 described in connection with the embodiments of the invention is intended to comprise, without being limited to, these and any other suitable types of memory.
The second memory 802 in the embodiment of the present invention is used for storing various kinds of data to support the operation of the information delivery apparatus. Examples of such data include: any executable program for operating on the information delivery device, such as an operating system and application programs; historical delivery data, traffic bids, etc.; the operating system includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, and is used for implementing various basic services and processing hardware-based tasks. The application programs may include various application programs such as a target application, a Media Player (Media Player), a Browser (Browser), etc. for implementing various application services. The information delivery device for implementing the information delivery method provided by the embodiment of the invention can be contained in an application program.
The method disclosed in the above embodiments of the present invention may be applied to the second processor 801, or implemented by the second processor 801. The second processor 801 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be implemented by integrated logic circuits of hardware or instructions in the form of software in the second processor 801. The second processor 801 may be a general purpose processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. The second processor 801 may implement or perform the methods, steps and logic blocks disclosed in embodiments of the present invention. The general purpose second processor 801 may be a microprocessor or any conventional processor or the like. The implementation steps of the information delivery method provided by the embodiment of the invention can be directly embodied as the execution of a hardware decoding processor, or the combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium having a memory and a processor reading the information in the memory and combining the hardware to perform the steps of the method.
In an exemplary embodiment, the information delivery Device may be used by one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs) to perform the aforementioned methods.
In an exemplary embodiment, with continuing reference to fig. 11, an information delivery apparatus provided by an embodiment of the present invention includes a request module 21, an aggregation forming module 22, a bid sorting module 23, and a delivery module 24. The request module 21 is configured to obtain a delivery request sent by a traffic for delivering information; the set forming module 22 is configured to determine an expected conversion cost of traffic used in historical delivery based on historical delivery data of delivery information, and select a target traffic according to the expected conversion cost of the traffic to form a traffic set; the bidding sorting module 23 is configured to, when a difference between a conversion cost of the target traffic and a target cost in the traffic set meets a set relationship, participate in bidding sorting of currently released information to be released according to the consumption cost, an estimated conversion rate and an estimated click rate, based on the consumption cost of the traffic in the current release determined by the expected conversion cost corresponding to the target traffic; the releasing module 24 is configured to select information to be released of the target according to the bidding ranking, and release the information to be released of the target at a corresponding display position of the corresponding flow.
The system further comprises a data determining module, wherein the data determining module is used for determining the transaction data of single click of the flow in the current delivery of the delivery information according to the consumption cost of the flow and the estimated conversion rate of the delivery information.
It should be noted that: in the information delivery device provided in the above embodiment, when implementing the information delivery method, only the division of each program module is taken as an example, and in practical applications, the processing distribution may be completed by different program modules according to needs, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the information delivery device and the information delivery method provided by the above embodiments belong to the same concept, and specific implementation processes thereof are detailed in the method embodiments and are not described herein again.
An embodiment of the present invention further provides a storage medium, such as the first memory 902 shown in fig. 9 and including an executable computer program, or the second memory 802 shown in fig. 11 and including an executable computer program, where the computer program is executable by a processor to perform the method for processing information delivery or the steps of the method for processing information delivery provided by the embodiment of the present invention. The readable storage medium can be a Memory such as a magnetic random access Memory (FRAM), a read-only Memory (ROM), a programmable read-only Memory (PROM), a nonvolatile read-only Memory (EPROM), a charged pluggable programmable read-only Memory (EEPROM), a Flash Memory (Flash Memory), a magnetic surface Memory, an optical disk, or a compact disk read-only Memory (CD-ROM); or may be various devices, such as computer devices, including one or any combination of the above-described memories.
In summary, by taking the expected conversion cost of the traffic in the historical delivery data of the information delivery as a reference, performing traffic selection according to the expected conversion cost of each traffic, determining that the conversion cost of the target traffic in the traffic set is equal to or nearly equal to the target cost, and determining the maximum expected conversion cost in the traffic set as SmartCPA according to the expected conversion cost corresponding to the target traffic in the traffic set, so that the traffic set formed by the selected traffic contains the target traffic with the conversion cost that meets the target cost of the advertiser and can obtain the most conversion, so that the consumption cost of the traffic in the current delivery determined according to the target traffic can more accurately reflect the actual cost of the traffic, and online determining the bidding ranking of the information to be delivered participating in the current delivery according to the consumption cost of the traffic, the estimated click rate of the delivery information and the estimated conversion rate, and selecting target information to be released according to the bidding results of the bidding ranking and displaying the target information to be released at the corresponding display position, so that the maximum conversion amount can be obtained while ensuring that the advertisement release is close to the target cost of the advertiser.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention 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 invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.

Claims (15)

1. A method for processing information delivery, comprising:
obtaining historical releasing data of releasing information, and determining expected conversion cost of flow used in the historical releasing of the releasing information according to the historical releasing data;
selecting a target flow from the candidate flows to form a flow set according to the expected conversion cost of the flow;
when the difference between the conversion cost of the target flow and the target cost in the flow set meets a set relationship,
and determining the consumption cost of the flow in the current delivery of the delivery information according to the expected conversion cost corresponding to the target flow in the flow set.
2. The method of claim 1, wherein said selecting a target flow among said candidate flows to form a set of flows based on a desired conversion cost of said flows comprises:
ranking the candidate flows according to their expected conversion costs;
and sequentially selecting target flow and adding the flow set according to the sequencing result until the difference value between the conversion cost of the target flow and the target cost in the flow set accords with the setting relation.
3. The method of claim 2, wherein the sequentially selecting target flows to be added to the flow set according to the sorting result until a difference between a conversion cost and a target cost of the target flows in the flow set meets the setting relationship comprises:
adding a target flow with a minimum expected conversion cost to the flow set;
when the difference value between the conversion cost of the target flow and the target cost in the flow set does not accord with a set relation, selecting the target flow from the candidate flows according to the ascending order of the expected conversion cost to add the target flow into the flow set until the target flow is added into the flow set
And the difference value between the conversion cost of the target flow in the flow set and the target cost accords with the setting relation.
4. The method of claim 2, wherein after sequentially selecting the target traffic to add to the traffic set according to the sorting result, further comprising:
and determining the conversion cost of the target flow in the flow set according to the ratio of the total actual consumption cost of the target flow to the total conversion number contained in the flow set.
5. The method of claim 1, wherein said obtaining historical placement data for placement information comprises:
acquiring historical release data of release information in a set time period;
when the data volume of the historical release data is determined to be larger than a threshold value, respectively determining weights corresponding to a plurality of time periods according to confidence degrees of data in the time periods contained in the set time period;
weighting historical impression data for each of the time periods based on the weights.
6. The method of claim 5, further comprising:
when the data volume of the historical release data is determined to be smaller than the data volume threshold value, increasing the duration of the set time period;
and acquiring the historical release data within the increased duration until the data volume of the release information is greater than the data volume threshold.
7. The method according to claim 5, wherein the determining weights corresponding to the time periods according to the confidences of the data in the plurality of time periods included in the set time period respectively comprises:
and respectively determining the weights corresponding to the time periods according to the direct proportion relation between the weight corresponding to each time period in the set time period and the confidence coefficient of the data in the time period and the inverse proportion relation between the weight corresponding to each time period and the confidence coefficient of the data in the previous time period.
8. The method according to any one of claims 1 to 7, wherein said determining from said historical placement data an expected conversion cost for traffic used in historical placements of said placement information comprises:
according to the historical putting data, determining the click number, the conversion number and the expected profit corresponding to each flow used in the historical putting of the putting information, determining the product of the click rate and the conversion rate, and determining the expected conversion cost of each flow according to the ratio of the expected profit corresponding to the flow to the product.
9. The method of any one of claims 1 to 7, further comprising:
determining the transaction data of single click of the flow in the current delivery of the delivery information according to the consumption cost of the flow and the estimated conversion rate of the delivery information; and/or
And determining a bidding result of the information to be released participating in the current release according to the consumption cost of the flow, the estimated click rate and the estimated conversion rate of the releasing information, and sending the information to be released to a display position corresponding to the corresponding flow for displaying according to the bidding result.
10. An information delivery method, comprising:
acquiring a releasing request sent by the flow for releasing the information;
determining expected conversion cost of flow used in historical putting based on historical putting data of putting information, and selecting target flow to form a flow set according to the expected conversion cost of the flow;
when the difference value between the conversion cost of the target flow and the target cost in the flow set accords with a set relationship, determining the consumption cost of the flow in the current delivery based on the expected conversion cost corresponding to the target flow, and participating in the bidding ranking of the information to be delivered in the current delivery according to the consumption cost, the estimated conversion rate and the estimated click rate;
and selecting information to be delivered of the target according to the bidding ranking, and delivering the information to be delivered of the target at a corresponding display position of corresponding flow.
11. The method of claim 10, further comprising:
and determining the transaction data of single click of the flow in the current delivery of the delivery information according to the consumption cost of the flow and the estimated conversion rate of the delivery information.
12. A processing apparatus for information delivery, comprising:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring historical release data of release information and determining expected conversion cost of flow used in the historical release of the release information according to the historical release data;
a selecting module for selecting a target flow from the candidate flows to form a flow set according to the expected conversion cost of the flow;
and the determining module is used for determining the consumption cost of the flow in the current release of the release information according to the expected conversion cost corresponding to the target flow in the flow set when the difference value between the conversion cost of the target flow and the target cost in the flow set meets a set relationship.
13. An information delivery apparatus, comprising:
the request module is used for acquiring a releasing request sent by the flow of releasing information;
the system comprises a set forming module, a flow set generating module and a flow distribution module, wherein the set forming module is used for determining expected conversion cost of used flow in historical putting based on historical putting data of putting information, and selecting target flow according to the expected conversion cost of the flow to form a flow set;
a bidding sequencing module, configured to, when a difference between a conversion cost of the target traffic and a target cost in the traffic set meets a set relationship, determine a consumption cost of the traffic in the current delivery based on the expected conversion cost corresponding to the target traffic, and participate in bidding sequencing of the currently delivered information to be delivered according to the consumption cost, an estimated conversion rate and an estimated click rate;
and the releasing module is used for selecting the information to be released of the target according to the bidding ranking and releasing the information to be released of the target at the corresponding display position of the corresponding flow.
14. A computer device, comprising: a processor and a memory for storing a computer program capable of running on the processor;
wherein the processor is configured to implement the processing method for information delivery according to any one of claims 1 to 9 or the method for information delivery according to any one of claims 10 to 11 when the computer program is executed.
15. A storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method for processing information delivery according to any one of claims 1 to 9 or implements the method for information delivery according to any one of claims 10 to 11.
CN201910370831.0A 2019-05-06 2019-05-06 Information delivery processing method, information delivery device, information delivery equipment and storage medium Pending CN111899041A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910370831.0A CN111899041A (en) 2019-05-06 2019-05-06 Information delivery processing method, information delivery device, information delivery equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910370831.0A CN111899041A (en) 2019-05-06 2019-05-06 Information delivery processing method, information delivery device, information delivery equipment and storage medium

Publications (1)

Publication Number Publication Date
CN111899041A true CN111899041A (en) 2020-11-06

Family

ID=73169430

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910370831.0A Pending CN111899041A (en) 2019-05-06 2019-05-06 Information delivery processing method, information delivery device, information delivery equipment and storage medium

Country Status (1)

Country Link
CN (1) CN111899041A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112700282A (en) * 2021-01-06 2021-04-23 中国银联股份有限公司 Method and device for screening advertisement delivery sites and storage medium
CN113011911A (en) * 2021-01-21 2021-06-22 腾讯科技（深圳）有限公司 Data prediction method, device, medium and electronic equipment based on artificial intelligence
CN113793181A (en) * 2021-09-15 2021-12-14 北京奇艺世纪科技有限公司 Method, system and device for bidding advertising spots
CN114971734A (en) * 2022-06-07 2022-08-30 北京奇艺世纪科技有限公司 Information generation method and device for advertisement, electronic equipment and storage medium
CN115082133A (en) * 2022-08-19 2022-09-20 深圳云威网络科技有限公司 Target page flow analysis management system and management method
CN116739643A (en) * 2023-06-29 2023-09-12 杭州面朝信息科技有限公司 Data processing method, device, electronic equipment and readable storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150134463A1 (en) * 2013-11-08 2015-05-14 Turn Inc. Performance metric based bid placement
CN107153970A (en) * 2017-04-24 2017-09-12 郑州埃文计算机科技有限公司 A kind of bid and budget method of estimation towards real time bid advertisement
CN108280684A (en) * 2018-01-19 2018-07-13 北京达佳互联信息技术有限公司 Advertisement price competing method, system and server
CN108335136A (en) * 2018-01-30 2018-07-27 易玩（上海）网络科技有限公司 A kind of advertisement pricing method and computing device
CN108876472A (en) * 2018-07-02 2018-11-23 微梦创科网络科技（中国）有限公司 A kind of information distribution method and device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150134463A1 (en) * 2013-11-08 2015-05-14 Turn Inc. Performance metric based bid placement
CN107153970A (en) * 2017-04-24 2017-09-12 郑州埃文计算机科技有限公司 A kind of bid and budget method of estimation towards real time bid advertisement
CN108280684A (en) * 2018-01-19 2018-07-13 北京达佳互联信息技术有限公司 Advertisement price competing method, system and server
CN108335136A (en) * 2018-01-30 2018-07-27 易玩（上海）网络科技有限公司 A kind of advertisement pricing method and computing device
CN108876472A (en) * 2018-07-02 2018-11-23 微梦创科网络科技（中国）有限公司 A kind of information distribution method and device

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112700282A (en) * 2021-01-06 2021-04-23 中国银联股份有限公司 Method and device for screening advertisement delivery sites and storage medium
CN112700282B (en) * 2021-01-06 2024-04-30 中国银联股份有限公司 Screening method, device and storage medium of advertisement putting site
CN113011911A (en) * 2021-01-21 2021-06-22 腾讯科技（深圳）有限公司 Data prediction method, device, medium and electronic equipment based on artificial intelligence
CN113793181A (en) * 2021-09-15 2021-12-14 北京奇艺世纪科技有限公司 Method, system and device for bidding advertising spots
CN113793181B (en) * 2021-09-15 2023-10-13 北京奇艺世纪科技有限公司 Bid method, system and device for advertisement space
CN114971734A (en) * 2022-06-07 2022-08-30 北京奇艺世纪科技有限公司 Information generation method and device for advertisement, electronic equipment and storage medium
CN115082133A (en) * 2022-08-19 2022-09-20 深圳云威网络科技有限公司 Target page flow analysis management system and management method
CN115082133B (en) * 2022-08-19 2022-11-18 深圳云威网络科技有限公司 Target page flow analysis management system and method
CN116739643A (en) * 2023-06-29 2023-09-12 杭州面朝信息科技有限公司 Data processing method, device, electronic equipment and readable storage medium

Similar Documents

Publication Publication Date Title
CN111899041A (en) Information delivery processing method, information delivery device, information delivery equipment and storage medium
US8473339B1 (en) Automatically switching between pricing models for services
JP5695655B2 (en) Online advertising selection and prioritization based on user feedback
JP5801425B2 (en) Ad progressive pricing method
JP5656632B2 (en) Content item pricing
US8666809B2 (en) Advertisement campaign simulator
US20070260515A1 (en) Method and system for pacing online advertisement deliveries
CN110796477A (en) Advertisement display method and device, electronic equipment and readable storage medium
US20050171844A1 (en) Apparatus and methods for streamlined term adjustment
US20130097028A1 (en) Dynamic Floor Pricing for Managing Exchange Monetization
US20120130798A1 (en) Model sequencing for managing advertising pricing
JP2012502388A (en) Method, system and computer-readable recording medium for auction and billing for search advertisements
WO2008055217A2 (en) Selecting advertisements based on consumer transactions
US20130006758A1 (en) User feedback-based selection of online advertisements using normalized cost modifiers
US10318985B2 (en) Determining bidding strategies
AU2010358588B2 (en) Managing revenue sharing bids
US20130346218A1 (en) Bidding on Impression Opportunities Using Confidence Indicators
JP5703213B2 (en) Advertisement providing method and advertisement providing system
US20120130828A1 (en) Source of decision considerations for managing advertising pricing
US20150081422A1 (en) Service providing apparatus and service providing method
US20210382952A1 (en) Web content organization and presentation techniques
CN103593788A (en) Expressive bidding in online advertising auctions
US20120054027A1 (en) Network based advertisement system
CN116151894A (en) Real-time bidding global optimization method and system for multi-channel search advertisement
CN116051206A (en) Advertisement delivery request sending method, device, equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination