CN108428144B - Flow distribution method, service distribution method and device for push information order - Google Patents

Flow distribution method, service distribution method and device for push information order Download PDF

Info

Publication number
CN108428144B
CN108428144B CN201710080661.3A CN201710080661A CN108428144B CN 108428144 B CN108428144 B CN 108428144B CN 201710080661 A CN201710080661 A CN 201710080661A CN 108428144 B CN108428144 B CN 108428144B
Authority
CN
China
Prior art keywords
order
flow
supply node
flow distribution
orders
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.)
Active
Application number
CN201710080661.3A
Other languages
Chinese (zh)
Other versions
CN108428144A (en
Inventor
刘磊
陈戈
徐澜
江志
金伟
张弘
赵鹏昊
黄伟
黄东波
姜磊
朱思宇
谷俊青
游乐
魏望
洪福兴
陈怡然
李世强
江进
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 Beijing Co Ltd
Original Assignee
Tencent Technology Beijing 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 Beijing Co Ltd filed Critical Tencent Technology Beijing Co Ltd
Priority to CN201710080661.3A priority Critical patent/CN108428144B/en
Priority to PCT/CN2018/076226 priority patent/WO2018149371A1/en
Publication of CN108428144A publication Critical patent/CN108428144A/en
Application granted granted Critical
Publication of CN108428144B publication Critical patent/CN108428144B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • 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
    • 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
    • G06Q30/0277—Online advertisement

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

The application discloses a flow distribution method for pushing information orders, which comprises the following steps: acquiring information of each order, wherein the information comprises orientation information and frequency requirements of the order; for each order, determining supply nodes which are consistent with the directional information of the order, and determining the expected flow distribution proportion of each supply node to the order under the condition that the frequency requirement of the order is met; for any order, determining a flow distribution proportion of each corresponding supply node for the order for a push server menu under the condition that the frequency requirement and the flow supply and demand constraint condition of the order are met according to the expected flow distribution proportion of each corresponding supply node for the order, wherein the expected flow distribution proportion of each corresponding supply node corresponds to the directional information of the order. The application also discloses a service distribution method for pushing the information order and a corresponding device. By adopting the technical scheme, the information pushing is more reasonable.

Description

Flow distribution method, service distribution method and device for push information order
Technical Field
The present application relates to the field of internet technologies, and in particular, to a flow distribution method, a service distribution method, and an apparatus for pushing an information order.
Background
With the development of internet technology, more and more data (including text, pictures, audio, video, etc.) can be pushed to various users through the internet. Such as: when browsing a web page using a terminal device such as a mobile phone or a PC, a user may receive various data pushed by a network side, such as: advertisements in picture or video format, public service promotional information, news, etc. Thus, the user can know the time information, the interested contents and the like in time. Such data may be referred to as push information or push media content, etc.
Disclosure of Invention
The application provides a flow distribution method for pushing information orders, which comprises the following steps:
acquiring information of each order, wherein the information comprises orientation information and frequency requirements of the order;
for each order, determining supply nodes which are consistent with the directional information of the order, and determining the expected flow distribution proportion of each supply node to the order under the condition that the frequency requirement of the order is met;
for any order, determining a flow distribution proportion of each corresponding supply node for the order for a push server menu under the condition that the frequency requirement and the flow supply and demand constraint condition of the order are met according to the expected flow distribution proportion of each corresponding supply node for the order, wherein the expected flow distribution proportion of each corresponding supply node corresponds to the directional information of the order.
The application also provides a service distribution method for pushing the information order, which comprises the following steps:
receiving an information push request sent by a user,
determining a provisioning node matching the user;
determining a plurality of orders targeted for compliance with the supply node;
the receiving flow distribution unit obtains the flow distribution proportion of each order in the plurality of orders according to the flow distribution method;
and providing the flow distribution proportion to a push server so that the push server performs menu processing according to the flow distribution proportion.
The present application further provides a flow distribution device for pushing information orders, including:
the order information acquisition unit is used for acquiring information of each order, wherein the information comprises orientation information and frequency requirements of the order;
the expected flow distribution proportion determining unit is used for determining each supply node which accords with the directional information of each order and determining the expected flow distribution proportion of each supply node to the order under the condition that the frequency requirement of the order is met;
and a flow distribution proportion determining unit, configured to determine, for any order, a flow distribution proportion, for each supply node corresponding to the directional information of the order, to be used by a push server menu of the order, when the frequency requirement and a flow supply and demand constraint condition of the order are met, according to the expected flow distribution proportion, for the order, of each supply node corresponding to the directional information of the order.
The present application further provides a service distribution device for pushing information orders, including:
an information push request receiving unit, configured to receive an information push request sent by a user,
a provisioning node determination unit for determining a provisioning node matching the user;
an order determination unit for determining a plurality of orders oriented to coincide with the supply node;
a flow distribution proportion obtaining unit, configured to receive the flow distribution proportion of each of the plurality of orders obtained by the flow distribution unit according to the flow distribution method according to claim 1;
and the flow distribution proportion providing unit is used for providing the flow distribution proportion to the push server so that the push server performs menu processing according to the flow distribution proportion.
By adopting the scheme provided by the application, the flow distribution proportion under the frequency control condition is considered, and the method and the device can be suitable for pushing information orders with frequency requirements, so that the order delivery under the frequency control condition is more reasonable.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a system architecture diagram to which an example of the present application relates;
FIG. 2 illustrates the relationship between a supply node and a demand node;
FIG. 3 is a flow chart of a flow distribution method for push information orders according to an embodiment of the present application;
FIG. 4 is a flow chart illustrating a flow chart for obtaining an allocation ratio of an expected flow rate of an order according to an example of the present application;
FIG. 5 is a flow chart illustrating the determination of the flow distribution ratio according to an example of the present application;
FIG. 6 is a flow chart of a process for calculating a retention requirement constraint parameter according to an embodiment of the present application;
FIG. 7 is a flow chart illustrating a method for service distribution of push information orders according to an embodiment of the present application;
FIG. 8 is a flow chart illustrating an alternative order process for acquiring in an example of the present application;
FIG. 9 is a schematic diagram of a flow distribution device for push information orders according to an example of the present application;
FIG. 10 is a schematic diagram of a service distribution device for pushing information orders according to an example of the present application; and
FIG. 11 is a block diagram of a computing device in an example of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the internet-based information push technology, an online push information presentation service (such as presentation of online advertisements) can be implemented by a flow (i.e., exposure amount) guaranteed order. Among them, the media side (also called supplier) responsible for presenting push information guarantees a predetermined number of exposures to satisfy order targeting (targeting targets) to the demand side (e.g. Advertiser). Here, the orientation describes the target audience characteristics of the push information corresponding to the order, and one presentation of the push information to the user is called one exposure. In the information pushing phase, it is necessary to select an order for exposure preparation and determine how much exposure is allocated to each order for exposure preparation based on the current flow prediction result. For example: the most central problem in the Cost Per thousand (CPM) contract advertising system is how to allocate advertising exposure for sale, that is, allocating advertising traffic for a group of orders with a contracted amount and audience targeting constraints according to the audience targeting constraints and demand of each order under a given estimated traffic so that the lack or the overall lack of all orders is minimum.
Fig. 1 is a system architecture diagram according to an example of the present application. As shown in fig. 1, the system comprises at least: the system comprises a flow estimation module 101, a flow distribution module 102, a push server 103 and a data module 104.
In the internet, various users use clients to access websites such as: browsing web pages or viewing online videos, etc., the push server 103 (e.g., an advertisement server for delivering internet advertisements) may collect which users currently visit which pages (URLs) to determine which users need to be pushed with information and what information is pushed. The push server 103 generates information push requests (such as exposure requests) for users currently accessing the network, returns the information push requests to the clients of the corresponding users, transmits the information push requests to the data module 104 to be stored as historical exposure data, and also transmits the information push requests to the traffic distribution module 102, updates the current reserved volume of each order based on the information push requests, and transmits the latest predetermined volume of each order to the traffic distribution module 102.
The traffic estimation module 101 may estimate traffic according to historical exposure data acquired from the data module 104 to obtain estimated traffic, the traffic distribution module 102 may obtain a supply node oriented in accordance with the exposure request according to the received exposure request from the push server 103, further determine an order oriented in accordance with the supply node, receive the estimated traffic from the traffic estimation module 101, calculate a traffic distribution ratio of the order, and send the traffic distribution ratio to the push server 103, the push server 103 may perform menu processing on the orders according to the traffic distribution ratio, and may provide an information push service based on a menu result (for example, the advertisement server may push a corresponding advertisement to each user according to the menu result, or determine that no selected order is necessary to push an advertisement to the user).
In some examples, the traffic prediction module 101 and the traffic distribution module 102 predict traffic and complete traffic distribution based on an inventory model. The inventory model describes each supply node (supply node) and its corresponding estimated flow, wherein one supply node (also called a flow unit) can correspond to exposure under an orientation condition, the estimated flow corresponding to the supply node is the estimated exposure under the orientation condition corresponding to the supply node, and various information of the supply node is determined according to historical exposure data (can be obtained through statistics or estimated through an algorithm). In addition, an order can also be characterized by a demand node (demand node), which corresponds to the order's orientation and demand (i.e., the order's reservation).
FIG. 2 illustrates the relationship between a supply node and a demand node. Of these, there are 6 supply nodes with their respective targeting information and inventory (also known as forecasted flow) and N demand nodes with their respective targeting and demand (also known as flow reservations for orders). Such as: the orientation information (also referred to as user dimension information) of the provisioning node 1 is { beijing, sports }, which represents a user accessing a sports channel from beijing, and the corresponding estimated traffic is 8M, and represents that the number of times of user access (i.e., the number of exposure opportunities counted according to historical exposure data, also referred to as exposure number) with such orientation information { beijing, sports } is 8M. The orientation of the demand node 1 is { sports }, representing a user accessing a sports channel, with a corresponding subscription amount of 15M, representing a desire to ensure that the corresponding subscription has been exposed 15M times to users accessing a sports channel. As shown in fig. 2, for any pair of supply node and demand node having a connection line, the orientation information of the supply node corresponds to the orientation of the demand node, and it can be considered to expose the order corresponding to the demand node to the user corresponding to the supply node. The key problem in information push is how to distribute the traffic of each supply node to each demand node, and the directional constraint and the reservation quantity requirement of the demand node can be met.
In some examples, the flow distribution is performed by a flow distribution scheme based on an optimization model, but the flow distribution scheme does not consider frequency control and cannot be directly applied to the pushing of information pushing orders with frequency requirements. In other examples, the frequency ratio model is used for flow distribution, which is only applied to the heuristic HWM model, and the distribution result of flow distribution by the frequency ratio module is not optimal.
Based on the above technical problem, the present application provides a flow distribution method for pushing an information order, which can be applied to the flow distribution module 102. In one example, as shown in fig. 3, the method includes the steps of:
step 301: and acquiring information of each order, wherein the information comprises the orientation information and the frequency requirement of the order.
When a customer and a media provider (also called a supplier) enter an order, the order describes the characteristics of the target audience agreed by the media provider and the customer, i.e. the targeting information of the order. The requesting party and the media party contract the predetermined exposure amount of an order. For example, an order is oriented { sports }, representing a user accessing a sports channel with a corresponding subscription amount of 15M, representing a desire to ensure that the corresponding order is exposed 15M times to users accessing the sports channel. The information of the order also includes the frequency requirement of the order, i.e. the frequency that each user is required to view the order in a fixed time. The information of the order also includes the importance of the order and the unit price of the order for the penalty for the traffic that has failed to be exposed.
Step 302: for each order, determining supply nodes which are consistent with the directional information of the order, and determining the expected flow distribution proportion of each supply node to the order under the condition that the frequency requirement of the order is met.
For each order, determining a respective supply node that corresponds to the targeting information for that order. For example, in FIG. 2, for an order oriented { sports }, the supply nodes that match the orientation information for the order are supply nodes 1, 2, 3. And simultaneously calculating the expected flow distribution proportion of each supply node with the orientation information conforming to the order, wherein the expected flow distribution proportion is obtained by the flow reservation quantity of the order and the available flow of the order at each supply node. I.e. the predetermined amount of the order is evenly distributed over the available flow, whereas in the actual flow distribution, which differs from the desired flow distribution but for which a minimum deviation from the desired flow distribution is desired, each supply-and-demand node also fulfils some constraints. The available flow rate is the flow rate which can be used for showing the order at each supply node after the frequency requirement of the order is considered.
Step 303: for any order, determining a flow distribution proportion of each corresponding supply node for the order for a push server menu under the condition that the frequency requirement and the flow supply and demand constraint condition of the order are met according to the expected flow distribution proportion of each corresponding supply node for the order, wherein the expected flow distribution proportion of each corresponding supply node corresponds to the directional information of the order.
When determining the actual flow distribution proportion of the order, the demand constraint condition, the supply constraint condition, the frequency control constraint condition and the non-negative constraint condition need to be considered, and if the constraint conditions are met, the flow distribution proportion under the condition that the deviation from the expected flow distribution proportion is minimum is solved.
By adopting the flow distribution method for the push information orders, the flow distribution proportion under the condition of considering the frequency control is solved based on the estimated flow of the supply node, the method can be suitable for the push information orders with the frequency control requirement, the order release under the frequency control condition is more reasonable, and the supplement rate of the orders is reduced.
In some examples, the supply node corresponds to one user dimension or a combination of dimensions, or corresponds to one user, and when the supply node corresponds to one user, the determined traffic distribution proportion of the order is the traffic distribution proportion of one user to the order; when the supply node corresponds to one user dimension or one dimension combination, the determined flow distribution proportion of the order is the flow distribution proportion of the user dimension or the dimension combination to the order.
When the provisioning node corresponds to a user dimension or a combination of dimensions, the traffic at the provisioning node is the traffic of all users under the same orientation condition, so that all users under the same orientation condition use the same traffic distribution ratio regardless of the number of visits, and the obtained traffic distribution scheme has a problem, for example, the frequency limit of an order is 3, then for a user with 10 visits, the traffic distribution ratio should be 0.3 (i.e. 30% of the exposure can be used to show the order), while for a user with 3 or less visits, the frequency ratio should be 1, however, if the two users are under the same orientation condition, they use a common traffic distribution ratio, such as 0.5, which is obviously not suitable for both users. When the supply node corresponds to a user, the flow distribution can obtain a flow distribution proportion based on the user level, and the flow distribution proportion is more reasonable.
In some examples, in the step 302, when the determining is performed under the condition that the frequency requirement of the order is met, and the desired flow allocation proportion of each supply node to the order is distributed, as shown in fig. 4, the following steps may be included:
step 401: and determining the frequency ratio of each supply node to the order according to the frequency requirement of the order.
And obtaining the frequency ratio of each supply node which is oriented to be consistent with the order to the order according to the frequency requirement of the order, wherein the frequency ratio represents the flow rate ratio which can be used for the order in the flow rate provided by the corresponding supply node under the condition of meeting the frequency requirement.
Step 402: and determining the available flow provided by each supply node for the order according to the frequency ratio of each supply node to the order.
When an order is assigned a frequency limit, only a portion of the available traffic that satisfies its orientation is available. For example, if the demand of order j for frequency control is k times in n days, then for the users who have more accesses in n days, and more than k times, only the accesses within k times are the available flow of order j. And multiplying the estimated flow of each supply node by the corresponding frequency ratio to obtain the available flow at each supply node, and summing the available flows at each supply node to obtain the available flow of the order.
Step 403: and for each supply node, determining the expected flow distribution proportion of the supply node to the order according to the available flow, the frequency ratio, the flow reservation quantity of the order and the estimated flow of the supply node.
As discussed above, the desired flow allocation ratio is the desired average allocation of a predetermined amount of an order to available flow, which may be obtained by the ratio of the flow reservation amount for the order to the available flow for the order.
In some examples, the available flow S for order j corresponds toj' the available flow rate is determined by the following equation (1):
Sj'＝∑i∈Γ(j)min{si,si×fij} (1)
the desired flow allocation ratio t for order j for supply node iijDetermined by the following equation (2):
Figure BDA0001225784160000081
wherein s isiTo supply the estimated flow of node i, fijFor the frequency ratio of supply node i to order j, Γ (j) is the set of supply nodes corresponding to the orientation information of order j, djReserve volume for the flow of order j.
In some examples, in step 303, the flow distribution ratio x for order j for the provisioning node i to use for the push server menuijDetermined by a model represented by the following formula (3)
Figure BDA0001225784160000091
Namely, the actual flow distribution proportion under the condition that the actual flow distribution proportion deviates from the expected flow distribution proportion and the penalty of the order-off-the-flow is minimum is calculated.
Wherein the flow supply and demand constraint conditions are shown in the following formulas (4) to (6):
the requirement constraint condition is as follows:
Figure BDA0001225784160000092
supply constraint conditions:
Figure BDA0001225784160000093
frequency control constraint conditions:
Figure BDA0001225784160000094
wherein s isiTo supply the estimated flow, V, of node ijIs the importance of order j, tijTo supply node i's desired flow allocation proportion, μjFlow not placed for order j, pjPenalty unit price for non-delivered traffic, J order set, djBooking volume for flow of order j, fijThe order j is a frequency ratio of a supply node i to an order j, the frequency ratio represents a traffic ratio which can be used for the order j in traffic provided by the supply node i under the condition that a frequency requirement of the order j is met, Γ (j) is a set formed by all supply nodes conforming to the orientation information of the order j, and Γ (i) is a set formed by all orders conforming to the orientation information of the supply node i.
In addition, non-negative constraint conditions may be included in the flow distribution model, such as the following equations (7) and (8):
Figure BDA0001225784160000095
Figure BDA0001225784160000096
in some examples, the frequency ratio for an order by a supply node is determined by:
when the supply node corresponds to a user, the ratio of the frequency requirement of the order to the estimated flow of the supply node is used as the frequency ratio of the supply node to the order.
And when the supply node corresponds to a user dimension or a dimension combination, obtaining the frequency ratio of the supply node to the order according to the frequency requirement of the order and the historical exposure data statistics of the order.
In some examples, the flow allocation ratio x for order j for the provisioning node i to use for the push server menuijDetermined by the following equation (9):
Figure BDA0001225784160000101
wherein alpha isjConstraint parameter, β, corresponding to demand constraint for order jiFor supplying a constraint parameter of node i corresponding to a provisioning constraint, fijIs the frequency ratio, s, of supply node i to order jiEstimated flow, V, for the supply nodejIs the importance of order j, tijAllocating a proportion to the desired flow for order j for supply node i.
And obtaining a flow distribution proportion formula (9) of the calculated order through the flow distribution model (3) and the constraint conditions (4), (5) and (6). Specifically, let αjRepresenting a demand constraint parameter, also called demand-duality, betaiRepresenting feeding constraints, also called feeding couples, gammaijDenotes xijIs also called xijNon-negative duality of phijRepresents μjIs also called mujNon-negative dual of [, ]ijRepresenting a frequency-controlled constraint parameter, also called frequency-controlled dual, then x is determined according to the KKT (Karush-Kuhn-Tucker) conditionijThe corresponding stability condition (stability) is as the following equation (10):
Figure BDA0001225784160000102
γijand ηijThe corresponding complementary relaxation conditions are as in the following equations (11) and (12):
Figure BDA0001225784160000103
Figure BDA0001225784160000104
γijand ηijThe dual feasible condition of (a) is the following formula (13):
γij≥0,ηij≥0 (13)
according to xijThe corresponding stability condition, equation (10), yields the following equation (14):
Figure BDA0001225784160000105
further according to ηijThe corresponding complementary relaxation condition, equation (12), results in either compliance with equation (15) below or compliance with equation (16) below:
xij＝fij (15)
Figure BDA0001225784160000111
obtaining a formula (17) according to a frequency control constraint condition, namely a formula (6):
xij≤fij (17)
therefore, when the right side of formula (16) is larger than fijTime, etaijWill increase so that xij＝fijThus, equation (18) is obtained:
Figure BDA0001225784160000112
elimination of gamma by analogous methodsijTo obtain the above mentionedFormula (9):
Figure BDA0001225784160000113
order to
Figure BDA0001225784160000114
Equation (20) can be obtained
xij＝hij(αj-βi) (20)
Thereby obtaining the demand constraint parameter alphajAnd supply the constraint parameter betaiThen, the flow distribution ratio of the order can be calculated according to the formula (20).
Demand constraint parameter αjThe complementary relaxation condition of (a) is formula (21):
for all j, 0 ≦ αj≤pjAnd, either αj＝pjOr is sigmai∈Γ(j)sixij＝dj (21)
Supply of a constraint parameter betaiThe complementary relaxation condition of (a) is formula (22):
for all i, βiIs ≧ 0, and either βi0 or Σj∈Γ(i)xij＝1 (22)
In some examples, determining the flow rate distribution ratio x by the equation (20) is performedijAs shown in fig. 5, the method mainly comprises the following steps:
step 501: in the off-line phase, alpha of each order j is calculatedjAnd beta of each supply node iiAnd each alpha is storedj。
In the off-line stage, alpha of each order j is calculatedjAnd beta of each supply node iiBut only stores each alphajBecause of αjIs the same as the dimension of the order, betaiIs the same as the supply node, the order is typically thousands or tens of thousands of dimensions, and when a supply node characterizes a user, the supply node may be up toTo hundreds of millions or billions of dimensions, thereby preserving only each alphajAnd the storage space is saved.
Step 502: when the push server receives the information push request of the user, reading the stored alphajAnd based on each read αjCalculating beta for each supply nodei。
According to the above, in order to save storage space, only α is stored in the offline stagejWhen the push server receives the information push request of the user and the traffic distribution module 102 performs traffic distribution, the stored alpha is readjAnd based on the read αjAnd equation (22) calculates beta for each supply nodeiI.e. according toj∈Γ(i)hij(αj-βi) Calculate each β as 1i。
Step 503: according to each read alphajAnd each calculated betaiEach x is calculated by the formula (20)ij。
According to each alphajAnd betaiEach x is calculated by the formula (20)ij。
In some examples, the calculating α for each order j is performedjAnd when storing, as shown in fig. 6, mainly includes the following steps:
step 601: alpha for all ordersjAnd assigning an initial value.
αjAnd betaiIs convergent while being dependent on alphaj0 is less than or equal to alpha in the complementary relaxation conditionsj≤pjα for all ordersjA value close to 0 is assigned and may also be assigned 0.
Step 602: according to alphajConstraint of (2) and betaiConstraint of (2), iterative solution of each alphajAnd each betaiThe convergence solution of (1).
As described above, αjA constraint of (2), i.e. alphajThe complementary relaxation condition of (a) is formula (21):
for all j, 0 ≦ αj≤pjAnd, either αj＝pjOr is sigmai∈Γ(j)sixij＝dj (21)
βiA constraint of (i), i.e. betaiThe complementary relaxation condition of (a) is formula (22):
for all i, βiIs ≧ 0, and either βi0 or Σj∈Γ(i)xij＝1 (22)
Solving for alpha in an iterationjAnd betaiWhen solving for the solution:
first according to initialized alphaj0, according to βiThe constraint of (2), i.e. equation (22), calculates each betaiIn particular according to Σ in formula (22)j∈Γ(i)xij1, i.e. Σj∈Γ(i)hij(αj-βi) Calculate each β as 1iWhile in equation (22) βiIs ≧ 0, and possibly βi0, so when solving for βi<When 0 or no solution, let betai＝0。
When each beta is calculatediThen according to alphajThe constraint of (2), i.e. equation (21), calculates each αjIn particular according to the formula Σ in formula (21)i∈Γ(j)sixij＝djI.e. Σi∈Γ(j)sihij(αj-βi)＝djTo calculate each alphaj. While in the formula (21), 0. ltoreq. alphaj≤pjAnd may be alphaj＝pjThus when solving for alphaj>pjOr when there is no solution, let alphaj＝pj. Thus obtaining each alpha after iterative solution for a certain number of timesjThe convergence solution of (1).
Step 603: storing each alphajThe convergence solution of (1).
The present application further provides a service distribution method for pushing information orders, which can be applied to the traffic distribution module 102. In one example, as shown in fig. 7, the method includes the steps of:
step 701: and receiving an information push request sent by a user.
After receiving the exposure request from the push server 103, the traffic distribution module 102 obtains a supply node whose orientation corresponds to the exposure request.
Step 702: and determining a supply node matched with the user.
After receiving the exposure request, the traffic distribution module 102 determines a supply node corresponding to the exposure request according to the user information in the exposure request. For example, in fig. 2, a user who has access to a sports channel in shanghai would be matched to the provisioning node 2.
Step 703: determining to direct a plurality of orders that coincide with the supply node.
In a bipartite graph such as that shown in FIG. 2, a number of orders targeted for a supply node may be determined based on the targeting information for the supply node.
Step 704: receiving the flow distribution proportion of each order in the plurality of orders, which is obtained by the flow distribution unit 102 according to the flow distribution method described above.
For the plurality of orders determined in step 703, the flow distribution ratio for each order may be obtained according to the flow distribution method shown above.
Step 705: and providing the flow distribution proportion to a push server so that the push server performs menu processing according to the flow distribution proportion.
The flow distribution proportion of each order obtained in step 704 is provided to the push server, and the push server performs menu processing according to the flow distribution proportion of each order.
By the aid of the service distribution method for the pushed information orders, the flow distribution proportion under the condition of considering frequency control is solved based on the estimated flow of the supply node, the method can be suitable for the pushed information orders with the frequency control requirement, order putting under the condition of frequency control is more reasonable, and the supplement rate of the orders is reduced.
In some examples, all x's computed for one exposure (i.e., one supply node i)ijThe sum of (j e Γ (i)) may be different from 1. When x isijThe sum being less than 1, meaning thatAn appropriate order may not be selected for presentation, resulting in an empty order. When x isijIf the sum is greater than 1, a part of more important orders need to be selected first, and then put in. To this end, it is necessary to assign priorities to order definitions. Specifically, as shown in fig. 8, the method mainly includes the following steps:
step 801: when the sum of the flow rates of the orders is larger than 1, calculating the ratio of the flow rate reservation quantity to the available flow rate of each order.
In this example, the ratio of the predetermined volume of the order to the available flow rate under frequency controlled conditions is used as the assigned priority for the order.
Step 802: and sequencing the orders according to the ratio from large to small.
And sorting the corresponding orders according to the mode that the priority calculated by each order is from big to small. I.e. for all j e Γ (i) in accordance with
Figure BDA0001225784160000151
And sorting from large to small.
Step 803: selecting the first m orders from the ordered orders, so that the sum of the flow rates of the m orders is equal to 1; wherein m is an integer greater than 1. I.e. so that ∑mxij＝1。
Step 804: and providing the flow distribution proportion of the m selected orders to a push server so that the push server performs menu processing in the m orders according to the flow distribution proportion of the m orders.
The present application also proposes a flow distribution device 900 for pushing information orders, which can be applied to the flow distribution module 102. In one example, as shown in fig. 9, the apparatus includes:
the order information acquiring unit 901 is configured to acquire information of each order, where the information includes orientation information and frequency requirements of the order.
An expected flow distribution ratio determining unit 902 is configured to determine, for each order, each supply node that matches the targeting information of the order, and determine an expected flow distribution ratio of each supply node to the order if the frequency requirement of the order is met.
A flow distribution ratio determining unit 903, configured to determine, for any order, a flow distribution ratio for each supply node corresponding to the directional information of the order to be used by a push server menu of the order when the frequency requirement and a flow supply and demand constraint condition of the order are met according to the expected flow distribution ratio for the order of each supply node corresponding to the directional information of the order.
By adopting the flow distribution device for the pushed information orders, the flow distribution proportion under the condition of considering the frequency control is solved based on the estimated flow of the supply node, the flow distribution device can be suitable for the pushed information orders with the frequency control requirement, the orders under the frequency control condition are put more reasonably, and the supplement rate of the orders is reduced.
In some examples, the supply node corresponds to one user dimension or a combination of dimensions, or corresponds to one user, and when the supply node corresponds to one user, the determined traffic distribution proportion of the order is the traffic distribution proportion of one user to the order; when the supply node corresponds to one user dimension or one dimension combination, the determined flow distribution proportion of the order is the flow distribution proportion of the user dimension or the dimension combination to the order.
In some examples, the desired flow distribution ratio determining unit 902 is configured to:
determining the frequency ratio of each supply node to the order according to the frequency requirement of the order, wherein the frequency ratio represents the flow rate ratio which can be used for the order in the flow rate provided by the corresponding supply node under the condition of meeting the frequency requirement;
determining available flow provided by each supply node for the order according to the frequency ratio of each supply node to the order;
and for each supply node, determining the expected flow distribution proportion of the supply node to the order according to the available flow, the frequency ratio, the flow reservation quantity of the order and the estimated flow of the supply node.
The present application also proposes a service distribution device 1000 for pushing information orders, which can be applied to the traffic distribution module 102. In one example, as shown in fig. 10, the apparatus includes:
an information push request receiving unit 1001 for receiving an information push request sent by a user,
a provisioning node determination unit 1002, configured to determine a provisioning node matching the user;
an order determination unit 1003 for determining a plurality of orders oriented to coincide with the supply node;
a flow distribution ratio obtaining unit 1004, configured to receive the flow distribution ratio of each of the plurality of orders obtained by the flow distribution unit according to the flow distribution method of claim 1;
a flow distribution ratio providing unit 1005, configured to provide the flow distribution ratio to a push server, so that the push server performs menu processing according to the flow distribution ratio.
By adopting the service distribution device for the pushed information orders, the flow distribution proportion under the condition of considering the frequency control is solved based on the estimated flow of the supply node, the device can be suitable for the pushed information orders with the frequency control requirement, so that the orders under the frequency control condition are put more reasonably, and the supplement rate of the orders is reduced.
In some examples, the flow distribution ratio obtaining unit 1004 is configured to, when the sum of the flow ratios of the plurality of orders is greater than 1, further include: calculating the ratio of the flow booking quantity to the available flow of each order; sequencing the orders according to the ratio from large to small; selecting the first m orders from the ordered orders, so that the sum of the flow rates of the m orders is equal to 1; wherein m is an integer greater than 1; the flow distribution ratio providing unit 1005 provides the selected flow distribution ratios of the m orders to the push server, so that the push server performs menu processing on the m orders according to the flow distribution ratios of the m orders.
Fig. 11 is a block diagram showing a configuration of a computing device in which the flow distribution apparatus 900 for push information orders and the service distribution apparatus 1000 for push information orders are located. As shown in fig. 11, the computing device includes one or more processors (CPUs) 1102, a communications module 1104, a memory 1106, a user interface 1110, and a communications bus 1108 for interconnecting these components.
The processor 1102 may receive and transmit data via the communication module 1104 to enable network communications and/or local communications.
The user interface 1110 includes one or more output devices 1112, including one or more speakers and/or one or more visual displays. The user interface 1110 also includes one or more input devices 1114, including, for example, a keyboard, a mouse, a voice command input unit or microphone, a touch screen display, a touch-sensitive input pad, a gesture-capture camera or other input buttons or controls, and the like.
Memory 1106 may be high-speed random access memory such as DRAM, SRAM, DDR RAM, or other random access solid state memory devices; or non-volatile memory, such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid-state storage devices.
The memory 1106 stores a set of instructions executable by the processor 1102, including:
an operating system 1116, including programs for handling various basic system services and for performing hardware-related tasks;
the application 1118 includes various application programs for flow distribution and order service distribution, and such application programs can implement the processing flows in the above examples, such as some or all units in the flow distribution device 900 for push information orders shown in fig. 9 or some or all units in the service distribution device 1000 for push information orders shown in fig. 10. At least one of the units 901-903 may store machine executable instructions, and at least one of the units 1001-1005 may store machine executable instructions. The processor 1102 can further implement the function of at least one module in each of the units 901-903 or the function of at least one module in each of the units 1001-1005 by executing the machine executable instructions in each of the units 901-903 or in at least one of the units 1001-1005 in the memory 1106.
It should be noted that not all steps and modules in the above flows and structures are necessary, and some steps or modules may be omitted according to actual needs. The execution order of the steps is not fixed and can be adjusted as required. The division of each module is only for convenience of describing adopted functional division, and in actual implementation, one module may be divided into multiple modules, and the functions of multiple modules may also be implemented by the same module, and these modules may be located in the same device or in different devices.
The hardware modules in the embodiments may be implemented in hardware or a hardware platform plus software. The software includes machine-readable instructions stored on a non-volatile storage medium. Thus, embodiments may also be embodied as software products.
In various examples, the hardware may be implemented by specialized hardware or hardware executing machine-readable instructions. For example, the hardware may be specially designed permanent circuits or logic devices (e.g., special purpose processors, such as FPGAs or ASICs) for performing the specified operations. Hardware may also include programmable logic devices or circuits temporarily configured by software (e.g., including a general purpose processor or other programmable processor) to perform certain operations.
In addition, each example of the present application can be realized by a data processing program executed by a data processing apparatus such as a computer. It is clear that a data processing program constitutes the present application. Further, the data processing program, which is generally stored in one storage medium, is executed by directly reading the program out of the storage medium or by installing or copying the program into a storage device (such as a hard disk and/or a memory) of the data processing device. Such a storage medium therefore also constitutes the present application, which also provides a non-volatile storage medium in which a data processing program is stored, which data processing program can be used to carry out any one of the above-mentioned method examples of the present application.
The corresponding machine-readable instructions of the modules of fig. 11 may cause an operating system or the like operating on the computer to perform some or all of the operations described herein. The nonvolatile computer-readable storage medium may be a memory provided in an expansion board inserted into the computer or written to a memory provided in an expansion unit connected to the computer. A CPU or the like mounted on the expansion board or the expansion unit may perform part or all of the actual operations according to the instructions.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (19)

1. A flow distribution method for pushing information orders is characterized by comprising the following steps:
acquiring information of each order, wherein the information comprises orientation information and frequency requirements of the order;
for each order, determining each supply node which is consistent with the orientation information of the order, and determining the frequency ratio of each supply node to the order according to the frequency requirement of the order, wherein the frequency ratio represents the flow ratio which can be used for the order in the flows provided by the corresponding supply node under the condition of meeting the frequency requirement of the order; determining available flow provided by each supply node for the order according to the frequency ratio of each supply node to the order; for each supply node, determining the expected flow distribution proportion of the supply node to the order according to the available flow, the frequency ratio, the flow reservation quantity of the order and the estimated flow of the supply node;
for any order, determining a flow distribution proportion of each corresponding supply node for the order for a push server menu under the condition that the frequency requirement and the flow supply and demand constraint condition of the order are met according to the expected flow distribution proportion of each corresponding supply node for the order, wherein the expected flow distribution proportion of each corresponding supply node corresponds to the directional information of the order.
2. The method of claim 1, wherein a provisioning node corresponds to one user dimension or combination of dimensions, or to one user;
when the supply node corresponds to a user, the determined flow distribution proportion of the order is the flow distribution proportion of the user to the order;
when the supply node corresponds to one user dimension or dimension combination, the determined flow distribution proportion of the order is the flow distribution proportion of the user dimension or dimension combination to the order.
3. The method of claim 2, wherein said determining a frequency ratio for the order for each supply node based on the frequency requirement of the order comprises:
and when the supply node corresponds to a user, taking the ratio of the frequency requirement of the order to the estimated flow of the supply node as the frequency ratio of the supply node to the order.
4. The method of claim 1, wherein the available flow S for order jj' determined by the following formula (1):
Sj'＝∑i∈Γ(j)min{si,si×fij} (1)；
the desired flow allocation ratio t for order j for supply node iijDetermined by the following equation (2):
Figure FDA0003507043030000021
wherein s isiTo supply the estimated flow of node i, fijFor the frequency ratio of supply node i to order j, Γ (j) is the set of supply nodes corresponding to the orientation information of order j, djReserve volume for the flow of order j.
5. The method of claim 1, wherein the provisioning node i has a traffic distribution ratio x for order j for use by the push server menuijDetermined by a model represented by the following formula (3):
Figure FDA0003507043030000022
wherein the flow supply and demand constraint condition comprises:
the requirement constraint condition is as follows:
Figure FDA0003507043030000023
supply constraint conditions:
Figure FDA0003507043030000024
frequency control constraint conditions:
Figure FDA0003507043030000025
wherein s isiTo supply the estimated flow, V, of node ijIs the importance of order j, tijTo supply node i's desired flow allocation proportion, μjFlow not placed for order j, pjPenalty unit price for non-delivered traffic, J order set, djBooking volume for flow of order j, fijFor supplying the frequency ratio of node i to order j, the frequency ratio fijAnd representing the traffic ratio which can be used for the order j in the traffic provided by the supply node i when the frequency requirement of the order j is met, wherein Γ (j) is a set formed by all the supply nodes according with the orientation information of the order j, and Γ (i) is a set formed by all the orders according with the orientation information of the supply node i.
6. The method of claim 2, wherein said determining a frequency ratio for the order for each supply node based on the frequency requirement of the order comprises:
and when the supply node corresponds to one user dimension or dimension combination, counting to obtain the frequency ratio of the supply node to the order according to the frequency requirement of the order and historical exposure data of the order.
7. The method of claim 5, wherein the flow distribution ratio x for the order j for the provisioning node i to use by the push server menu is determined by a model of equation (3)ijExpressed by the following formula (9):
Figure FDA0003507043030000031
wherein alpha isjConstraint parameter, β, corresponding to demand constraint for order jiFor supplying a constraint parameter of node i corresponding to a provisioning constraint, fijIs the frequency ratio, s, of supply node i to order jiEstimated flow, V, for the supply nodejIs the importance of order j, tijAllocating a proportion to the desired flow for order j for supply node i.
8. The method of claim 7, further comprising:
in the off-line phase, alpha of each order j is calculatedjAnd beta of each supply node iiAnd each alpha is storedj；
When the push server receives the information push request of the user, reading the stored alphajAnd based on each read αjCalculating beta for each supply nodei；
According to each read alphajAnd each calculated betaiCalculating each x by said formula (9)ij。
9. The method of claim 8, wherein the calculating a for each order jjAnd each alpha is storedjThe method comprises the following steps:
alpha for all ordersjAssigning an initial value;
according to alphajConstraint of (2) and betaiConstraint of (2), iterative solution of each alphajAnd each betaiA converged solution of;
storing each alphajThe convergence solution of (1).
10. A service distribution method for pushing information orders is characterized by comprising the following steps:
receiving an information push request sent by a user, and determining a supply node matched with the user;
determining a plurality of orders targeted for compliance with the supply node;
the receiving flow distribution unit obtains the flow distribution proportion of each order in the plurality of orders according to the method of claim 1;
and providing the flow distribution proportion to a push server so that the push server performs menu processing according to the flow distribution proportion.
11. The method of claim 10, wherein when the sum of the flow proportions of the plurality of orders is greater than 1, the method further comprises:
calculating the ratio of the flow booking quantity to the available flow of each order;
sequencing the orders according to the ratio from large to small;
selecting the first m orders from the ordered orders, so that the sum of the flow rates of the m orders is equal to 1; wherein m is an integer greater than 1;
and providing the flow distribution proportion of the m selected orders to a push server so that the push server performs menu processing in the m orders according to the flow distribution proportion of the m orders.
12. A flow distribution device for pushing information orders, comprising:
the order information acquisition unit is used for acquiring information of each order, wherein the information comprises orientation information and frequency requirements of the order;
the expected flow distribution proportion determining unit is used for determining each supply node which is consistent with the directional information of each order according to each order, and determining the frequency ratio of each supply node to each order according to the frequency requirement of each order, wherein the frequency ratio represents the flow proportion which can be used for each order in the flows provided by the corresponding supply node under the condition that the frequency requirement of each order is met; determining available flow provided by each supply node for the order according to the frequency ratio of each supply node to the order; for each supply node, determining the expected flow distribution proportion of the supply node to the order according to the available flow, the frequency ratio, the flow reservation quantity of the order and the estimated flow of the supply node;
and a flow distribution proportion determining unit, configured to determine, for any order, a flow distribution proportion, for each supply node corresponding to the directional information of the order, to be used by a push server menu of the order, when the frequency requirement and a flow supply and demand constraint condition of the order are met, according to the expected flow distribution proportion, for the order, of each supply node corresponding to the directional information of the order.
13. The apparatus of claim 12, wherein a provisioning node corresponds to one user dimension or combination of dimensions, or to one user; when the supply node corresponds to a user, the determined flow distribution proportion of the order is the flow distribution proportion of the user to the order; when the supply node corresponds to one user dimension or dimension combination, the determined flow distribution proportion of the order is the flow distribution proportion of the user dimension or dimension combination to the order.
14. The apparatus according to claim 13, wherein the expected flow distribution ratio determining unit is configured to use a ratio of the frequency requirement of the order to the estimated flow of the supply node as the frequency ratio of the supply node to the order when the supply node corresponds to a user.
15. The apparatus according to claim 12, wherein the traffic distribution ratio determining unit determines the traffic distribution ratio x for the push server menu for order j of the provisioning node i by a model expressed by the following formulaij：
Figure FDA0003507043030000061
Wherein the flow supply and demand constraint condition comprises:
the requirement constraint condition is as follows:
Figure FDA0003507043030000062
supply constraint conditions:
Figure FDA0003507043030000063
frequency control constraint conditions:
Figure FDA0003507043030000064
wherein s isiTo supply the estimated flow, V, of node ijIs the importance of order j, tijTo supply node i's desired flow allocation proportion, μjFlow not placed for order j, pjPenalty unit price for non-delivered traffic, J order set, djBooking volume for flow of order j, fijFor supplying the frequency ratio of node i to order j, the frequency ratio fijAnd representing the traffic ratio which can be used for the order j in the traffic provided by the supply node i when the frequency requirement of the order j is met, wherein Γ (j) is a set formed by all the supply nodes according with the orientation information of the order j, and Γ (i) is a set formed by all the orders according with the orientation information of the supply node i.
16. A service distribution device for pushing information orders, comprising:
the information pushing request receiving unit is used for receiving an information pushing request sent by a user;
a provisioning node determination unit for determining a provisioning node matching the user;
an order determination unit for determining a plurality of orders oriented to coincide with the supply node;
a flow distribution proportion obtaining unit, configured to receive the flow distribution proportion of each of the plurality of orders obtained by the flow distribution unit according to the flow distribution method according to claim 1;
and the flow distribution proportion providing unit is used for providing the flow distribution proportion to the push server so that the push server performs menu processing according to the flow distribution proportion.
17. The apparatus according to claim 16, wherein the flow rate distribution ratio acquisition unit is further configured to,
when the sum of the flow rates of the plurality of orders is greater than 1,
calculating the ratio of the flow booking quantity to the available flow of each order;
sequencing the orders according to the ratio from large to small;
selecting the first m orders from the ordered orders, so that the sum of the flow rates of the m orders is equal to 1; wherein m is an integer greater than 1;
the flow distribution proportion providing unit provides the selected flow distribution proportion of the m orders to a push server, so that the push server performs menu processing in the m orders according to the flow distribution proportion of the m orders.
18. A computing device comprising a memory and a processor, the memory having stored therein computer-readable instructions that, when executed by the processor, implement the method of any of claims 1 to 11.
19. A computer-readable storage medium having computer-readable instructions stored thereon which, when executed by at least one processor, implement the method of any one of claims 1 to 11.
CN201710080661.3A 2017-02-15 2017-02-15 Flow distribution method, service distribution method and device for push information order Active CN108428144B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201710080661.3A CN108428144B (en) 2017-02-15 2017-02-15 Flow distribution method, service distribution method and device for push information order
PCT/CN2018/076226 WO2018149371A1 (en) 2017-02-15 2018-02-11 Flow and service allocation method and apparatus for push information order, and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710080661.3A CN108428144B (en) 2017-02-15 2017-02-15 Flow distribution method, service distribution method and device for push information order

Publications (2)

Publication Number Publication Date
CN108428144A CN108428144A (en) 2018-08-21
CN108428144B true CN108428144B (en) 2022-04-26

Family

ID=63155317

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710080661.3A Active CN108428144B (en) 2017-02-15 2017-02-15 Flow distribution method, service distribution method and device for push information order

Country Status (2)

Country Link
CN (1) CN108428144B (en)
WO (1) WO2018149371A1 (en)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109978221A (en) * 2019-01-02 2019-07-05 阿里巴巴集团控股有限公司 A kind of advertisement inventory method for pre-distributing and device
CN109829753B (en) * 2019-01-08 2023-04-14 聚好看科技股份有限公司 Method and equipment for distributing flow to advertisement orders
CN111047009B (en) * 2019-11-21 2023-05-23 腾讯科技（深圳）有限公司 Event trigger probability prediction model training method and event trigger probability prediction method
CN111523939B (en) * 2020-04-23 2023-11-28 腾讯科技（深圳）有限公司 Popularization content delivery method and device, storage medium and electronic equipment
CN113516495B (en) * 2020-09-30 2024-03-08 腾讯科技（深圳）有限公司 Information pushing method, device, electronic equipment and computer readable medium
CN112232878A (en) * 2020-10-19 2021-01-15 腾讯科技（深圳）有限公司 Virtual display resource processing method and device, computer equipment and storage medium
CN112435091B (en) * 2020-11-23 2024-03-29 百果园技术(新加坡)有限公司 Recommended content selection method, device, equipment and storage medium
CN112396474A (en) * 2020-12-23 2021-02-23 上海苍苔信息技术有限公司 System and method for allocating traffic according to advertiser budget
CN112598447B (en) * 2020-12-28 2023-10-10 加和（北京）信息科技有限公司 Order information processing method and device, electronic equipment and processor
CN113781090A (en) * 2021-02-24 2021-12-10 北京沃东天骏信息技术有限公司 Flow estimation method and device
CN114493726A (en) * 2022-04-06 2022-05-13 萨科(深圳)科技有限公司 Order monitoring method and monitoring platform

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103377309A (en) * 2012-04-13 2013-10-30 腾讯科技（北京）有限公司 Method and device for displaying released information
CN104751343A (en) * 2013-12-25 2015-07-01 北京思博途信息技术有限公司 Advertisement putting method and device and advertisement putting server
WO2015141931A1 (en) * 2014-03-19 2015-09-24 에스케이플래닛 주식회사 Apparatus and method for providing advertisement
CN105791157A (en) * 2016-04-20 2016-07-20 腾讯科技（深圳）有限公司 Flow distribution method, distribution system and server

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100318432A1 (en) * 2009-06-10 2010-12-16 Yahoo! Inc. Allocation of internet advertising inventory
CN105656964B (en) * 2014-11-10 2019-06-25 中国移动通信集团公司 The implementation method and device of data-pushing
CN104410714B (en) * 2014-12-16 2018-02-13 成都大学 Network information push method and network information push device
CN105491410B (en) * 2015-12-09 2018-10-23 优酷网络技术（北京）有限公司 A kind of distribution method and system that network video advertisement is launched

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103377309A (en) * 2012-04-13 2013-10-30 腾讯科技（北京）有限公司 Method and device for displaying released information
CN104751343A (en) * 2013-12-25 2015-07-01 北京思博途信息技术有限公司 Advertisement putting method and device and advertisement putting server
WO2015141931A1 (en) * 2014-03-19 2015-09-24 에스케이플래닛 주식회사 Apparatus and method for providing advertisement
CN105791157A (en) * 2016-04-20 2016-07-20 腾讯科技（深圳）有限公司 Flow distribution method, distribution system and server

Also Published As

Publication number Publication date
WO2018149371A1 (en) 2018-08-23
CN108428144A (en) 2018-08-21

Similar Documents

Publication Publication Date Title
CN108428144B (en) Flow distribution method, service distribution method and device for push information order
CN107767164B (en) Information processing method, distribution method and device for push information order
JP2020173778A (en) Method, apparatus, electronic facility, computer readable medium, and computer program for allocating resource
JPWO2002101587A1 (en) ADVERTISEMENT SELECTION DEVICE, ADVERTISEMENT SELECTION METHOD, AND STORAGE MEDIUM
JPWO2002101700A1 (en) Advertisement insertion device, advertisement insertion method, and storage medium
CN108389076B (en) Advertisement distribution method, device, server and computer readable storage medium
WO2011144560A1 (en) Message broadcasting in a clustered computing environment
US20140200995A1 (en) Temporal budget optimization in online advertising
US20230419369A1 (en) Cross-platform proposal creation, optimization, and deal management
CN110839069A (en) Node data deployment method, node data deployment system and medium
CN114175602A (en) Authority management of cloud resources
CN110570257B (en) Multimedia data delivery method, device and computer readable storage medium
CN108282418B (en) Media flow distribution method and device
CN107872483B (en) Media content pushing method, device and system
US20180027049A1 (en) Computing system and method of operating the computer system
WO2015096791A1 (en) Method and system for releasing media content
CN110914854A (en) Joint transmission commitment simulation
GB2552357A (en) Computing system and method of operating the computing system
KR102044259B1 (en) Advertisement delivery system and method thereof, and apparatus applied to the same
CN112860432A (en) Process management method, device and server
CN111275473A (en) Content item delivery method, device, server and storage medium
CN112491939A (en) Multimedia resource scheduling method and system
CN114282777A (en) Data delivery demand receiving control method and device
CN113722633B (en) Message release strategy determining method and device, electronic equipment and storage medium
CN113553485B (en) Method, device, equipment and storage medium for displaying multimedia resources

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
GR01 Patent grant
GR01 Patent grant