CN116797281A - Advertisement putting method, advertisement putting device, computer equipment and storage medium - Google Patents

Advertisement putting method, advertisement putting device, computer equipment and storage medium Download PDF

Info

Publication number
CN116797281A
CN116797281A CN202310551526.8A CN202310551526A CN116797281A CN 116797281 A CN116797281 A CN 116797281A CN 202310551526 A CN202310551526 A CN 202310551526A CN 116797281 A CN116797281 A CN 116797281A
Authority
CN
China
Prior art keywords
state
user
target
delivery
quality
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
CN202310551526.8A
Other languages
Chinese (zh)
Inventor
罗毅
李炜铭
金振保
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.)
Shenzhen Jiujiu Interactive Technology Co ltd
Original Assignee
Shenzhen Jiujiu Interactive Technology 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 Shenzhen Jiujiu Interactive Technology Co ltd filed Critical Shenzhen Jiujiu Interactive Technology Co ltd
Priority to CN202310551526.8A priority Critical patent/CN116797281A/en
Publication of CN116797281A publication Critical patent/CN116797281A/en
Pending legal-status Critical Current

Links

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
    • G06Q30/0251—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
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • G06Q30/0271—Personalized 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)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application relates to an advertisement putting method, an advertisement putting device, computer equipment and a storage medium. The method comprises the following steps: scoring the user based on the user behavior information and payment information to obtain a user quality score; predicting the state of the advertisement putting plan to obtain a target state; the target state comprises a put quality state and a flow state; determining a score threshold based on the user quality score and the target state, and determining a return condition according to the score threshold; screening the users according to the feedback conditions to obtain target users; and returning the target user so as to realize the advertisement delivery of the advertisement delivery platform according to the target user. By adopting the method, the accuracy of advertisement delivery can be improved.

Description

Advertisement putting method, advertisement putting device, computer equipment and storage medium
Technical Field
The present application relates to the field of internet technologies, and in particular, to an advertisement delivery method, an advertisement delivery device, a computer device, and a storage medium.
Background
The information flow advertisement refers to a process of realizing intelligent matching between a user and an advertisement by utilizing a big data technology based on browsing behaviors and personalized tags (age, gender, region, education, hobbies and the like) of the user.
According to the conversion targets of advertisement delivery, the current method is divided into two types, namely APP downloading types, wherein the conversion targets comprise conversion behaviors of installation completion, activation, registration, retention, payment and the like; the other type is a form class, and the conversion targets include form submission, payment, efficient acquisition, and the like. The advertiser may select any one of the conversion behaviors as a conversion target for the ad placement. The information feedback generally refers to a process of transmitting user information which is successfully converted to the advertisement delivery platform after a user completes a conversion action, so that the flow purchased from the advertisement delivery platform is guided to be close to the demand direction of an advertiser as soon as possible, and the aim of accurately delivering advertisements is fulfilled.
In the information feedback at present, the proper feedback condition is formulated to carry out the information feedback according to the daily operation of a delivery optimizer, the flow condition and the delivery quality of an advertisement delivery platform are continuously manually tested, obviously, the information feedback is carried out according to the feedback condition formulated by the manual experience to realize the advertisement delivery, and the problem of inaccurate advertisement delivery exists.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an advertisement delivery method, apparatus, computer device, computer-readable storage medium, and computer program product that can promote advertisement delivery inaccuracy.
In a first aspect, the present application provides a method of advertising. The method comprises the following steps:
scoring the user based on the user behavior information and payment information to obtain a user quality score;
predicting the state of the advertisement putting plan to obtain a target state; the target state comprises a put quality state and a flow state;
determining a score threshold based on the user quality score and the target state, and determining a return condition according to the score threshold;
screening the users according to the feedback conditions to obtain target users;
and returning the target user so as to realize the advertisement delivery of the advertisement delivery platform according to the target user.
In one embodiment, the method further comprises:
training the user quality model according to the historical user behavior information and the historical payment information to obtain a target user quality model; the target user quality model is used for predicting the payment condition of future users;
scoring the user based on the user behavior information and the payment information, and obtaining the user quality score comprises the following steps:
and inputting the user behavior information and payment information into the target user quality model to perform scoring calculation to obtain the user quality score of the user.
In one embodiment, the method further comprises:
training a delivery quality model and a delivery flow model according to historical delivery information and historical user information of a historical advertisement delivery plan to obtain a target delivery quality model and a target delivery flow model; the historical user information comprises the historical user behavior information and the historical payment information; the target delivery quality model is used for predicting the profit situation of the advertisement delivery plan; the target delivery flow model is used for predicting the quantity condition of the future users;
predicting the state of the advertisement putting plan to obtain a target state comprises the following steps:
inputting the delivery information of the advertisement delivery plan into the target delivery quality model for state prediction to obtain the delivery quality state;
inputting the delivery information of the advertisement delivery plan into the target delivery flow model for state prediction to obtain the flow state.
In one embodiment, the determining the backhaul condition according to the score threshold includes:
determining a current stage of the advertisement delivery plan; the current stage is an initial starting stage or a learning stage;
Adjusting the score threshold according to the current stage to obtain the adjusted score threshold; and determining a return condition according to the adjusted score threshold value.
In one embodiment, the filtering the user according to the backhaul condition to obtain the target user includes:
when the advertisement putting plan is in an initial starting stage, loose return conditions are obtained, and the users are screened according to the loose return conditions, so that loose target users are obtained;
and when the advertisement putting plan is in a learning stage, acquiring a tightening feedback condition, and screening the users according to the tightening feedback condition to obtain a tightening target user.
In one embodiment, the method further comprises:
if the delivery quality state is a high quality state and the flow state is a multi-flow state, maintaining budget consumption;
if the delivery quality state is a high quality state and the flow state is a low flow state, increasing the budget consumption;
if the delivery quality state is a low quality state and the flow state is a multi-flow state, reducing the budget consumption;
And if the delivery quality state is a low quality state and the flow state is a low flow state, stopping the budget consumption.
In a second aspect, the application also provides an advertisement putting device. The device comprises:
the scoring module is used for scoring the user based on the user behavior information and the payment information to obtain the user quality score;
the prediction module is used for predicting the state of the advertisement delivery plan to obtain a target state; the target state comprises a put quality state and a flow state;
the determining module is used for determining a score threshold value based on the user quality score and the target state and determining a return condition according to the score threshold value;
the screening module is used for screening the users according to the feedback conditions to obtain target users;
and the feedback module is used for returning the target user so as to realize that the advertisement delivery platform delivers advertisements according to the target user.
In one embodiment, the apparatus further comprises:
the training module is used for training the user quality model according to the historical user behavior information and the historical payment information to obtain a target user quality model; the target user quality model is used for predicting the payment condition of future users;
The scoring module is also used for inputting the user behavior information and the payment information into the target user quality model to perform scoring calculation so as to obtain the user quality score of the user.
In one embodiment, the training module is further configured to train the delivery quality model and the delivery flow model according to historical delivery information and historical user information of the historical advertisement delivery plan, so as to obtain a target delivery quality model and a target delivery flow model; the historical user information comprises the historical user behavior information and the historical payment information; the target delivery quality model is used for predicting the profit situation of the advertisement delivery plan; the target delivery flow model is used for predicting the quantity condition of the future users;
the prediction module is also used for inputting the delivery information of the advertisement delivery plan into the target delivery quality model to perform state prediction so as to obtain the delivery quality state; inputting the delivery information of the advertisement delivery plan into the target delivery flow model for state prediction to obtain the flow state.
In one embodiment, the determination module is further for determining a current stage of the advertising campaign; the current stage is an initial starting stage or a learning stage; adjusting the score threshold according to the current stage to obtain the adjusted score threshold; and determining a return condition according to the adjusted score threshold value.
In one embodiment, the screening module is further configured to obtain a loose backhaul condition when the advertisement delivery plan is in an initial start stage, and screen the user according to the loose backhaul condition to obtain a loose target user; and when the advertisement putting plan is in a learning stage, acquiring a tightening feedback condition, and screening the users according to the tightening feedback condition to obtain a tightening target user.
In one embodiment, the apparatus further comprises:
the budget determining module is used for maintaining budget consumption if the delivery quality state is a high quality state and the flow state is a multi-flow state; if the delivery quality state is a high quality state and the flow state is a low flow state, increasing the budget consumption; if the delivery quality state is a low quality state and the flow state is a multi-flow state, reducing the budget consumption; and if the delivery quality state is a low quality state and the flow state is a low flow state, stopping the budget consumption.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the steps of the above method when the processor executes the computer program.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the above method.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of the above method.
The advertisement putting method, the advertisement putting device, the computer equipment, the storage medium and the computer program product are used for scoring the users based on the user behavior information and the payment information to obtain the quality scores of the users; predicting the state of the advertisement putting plan to obtain a target state; the target state comprises a put quality state and a flow state; determining a score threshold based on the user quality score and the target state, and determining a return condition according to the score threshold; compared with the traditional mode of making the return condition according to the manual experience, the method greatly reduces the complexity of operation, determines the return condition by scoring the user and predicting the state of the advertisement delivery plan, has higher accuracy, and screens the user according to the return condition to obtain the target user; and returning the target user so as to realize the advertisement delivery of the advertisement delivery platform according to the target user, thereby effectively improving the accuracy of delivering advertisements.
Drawings
FIG. 1 is a diagram of an application environment for an advertisement delivery method in one embodiment;
FIG. 2 is a flow diagram of a method of advertising in one embodiment;
FIG. 3 is a flow diagram of the determine budget step in one embodiment;
FIG. 4 is a block diagram of an advertisement delivery method in one embodiment;
FIG. 5 is a block diagram of an advertisement delivery device in one embodiment;
FIG. 6 is a block diagram of an advertisement delivery device in one embodiment;
fig. 7 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The advertisement putting method provided by the embodiment of the application can be applied to an application environment shown in figure 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The present application may be executed by the terminal 102 or the server 104, and this embodiment is described by taking the terminal execution as an example.
The terminal 102 scores the user based on the user behavior information and payment information to obtain a user quality score; predicting the state of the advertisement putting plan to obtain a target state; the target state comprises a put quality state and a flow state; determining a score threshold based on the user quality score and the target state, and determining a return condition according to the score threshold; screening the users according to the feedback conditions to obtain target users; and returning the target user so as to realize the advertisement delivery of the advertisement delivery platform according to the target user.
The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In one embodiment, as shown in fig. 2, an advertisement delivery method is provided, and the method is applied to the terminal 102 in fig. 1 for illustration, and includes the following steps:
And S202, scoring the user based on the user behavior information and payment information to obtain the user quality score.
The user behavior information may refer to information related to operations of a user, and the user behavior includes, but is not limited to, operations such as browsing, downloading, logging, clicking, paying, and the like, and the user behavior information includes, but is not limited to, user behavior types, user behavior times, and user behavior frequencies. Payment information may refer to information related to a payment made by a user, including, but not limited to, the number of payments and the amount of payment. A user may refer to a user using a target product in this case, and the target product may refer to software that the user may use, for example, the target product may be game software, office software, shopping software, navigation software, and the like. The user quality score may refer to a score obtained based on user behavior information and payment information of a user in a target product, where the user quality score is used to measure user quality, in the present application, if the user quality of the user is higher, the greater the likelihood of payment or the greater the likelihood of payment amount in the future in the process of using the target product is indicated, and the more or less of payment amount is to be determined according to the actual situation, for example, when the total payment amount of the user in the target product exceeds a preset amount value in a predicted preset time period, the payment amount of the user may be taken as more; the preset monetary value may refer to a preset monetary value, for example, the preset monetary value may be 100 yuan, 500 yuan, 1000 yuan, or the like.
In one embodiment, before S202, training the user quality model according to the historical user behavior information and the historical payment information to obtain a target user quality model; the target user quality model is used to predict payment for future users. Wherein, the historical user behavior information may refer to user behavior information before the user quality model is trained. Historical payment information may refer to payment information prior to training of the user quality model. The user quality model may refer to a model used for training to generate a target user quality model. The target user quality model can be used for predicting the payment situation of future users, so that the user quality score is obtained according to the payment situation of the users.
In one embodiment, the user quality model is trained based on historical user base information, historical user behavior information, and historical payment information to obtain a target user quality model.
The historical user basic information can refer to user basic information before training the user quality model, wherein the user basic information comprises information related to a user such as a name, a communication, a head portrait, an age, a city and the like.
In one embodiment, S202 includes inputting user behavior information and payment information into a target user quality model for scoring calculation to obtain a user quality score for the user.
S204, predicting the state of the advertisement putting plan to obtain a target state; the target states include a put mass state and a flow state.
The advertisement delivery plan may refer to creative materials delivered on the advertisement delivery platform and related parameters for delivering the creative materials. An ad impression plan may refer to creative material corresponding to an impression made at an ad impression platform and related parameters for the impression of the creative material. The advertisement delivery platform may be used to deliver and manage advertisements. Ad delivery plans include, but are not limited to, promotional plans, ad details, ad creatives, and the like. The advertisement plan includes a plan type, a promotion goal, a plan daily budget, a plan total budget, and a delivery form. The advertisement details include targeting details, ad slots, targeting information, and scheduling and bidding. The ad creative includes a creative form and creative material.
Creative material refers to material having a creative, which may include multiple types of creative material, which refers to different types of material forms, such as one or more of video, text, picture, voice, etc. For example, the creative material may include at least one of video material, picture material, text material, voice material, and the like.
The target states include a put mass state and a flow state. The impression quality status may be used to measure revenue for an advertisement impression plan. The traffic status may be used to measure the number of users using the target product to which the advertising campaign corresponds.
In one embodiment, before S204, training a delivery quality model and a delivery flow model according to historical delivery information and historical user information of a historical advertisement delivery plan to obtain a target delivery quality model and a target delivery flow model; the historical user information comprises historical user behavior information and historical payment information; the target delivery quality model is used for predicting the profit situation of the advertisement delivery plan; the target delivery flow model is used for predicting the number of future users.
Wherein, the historical advertisement delivery plan may refer to the advertisement delivery plan prior to training the delivery quality model and the delivery flow model. Historical delivery information may refer to delivery information prior to training the delivery quality model and the delivery flow model. The delivery information may refer to delivery information related to an advertisement delivery plan, the delivery information including revenue information and user quantity information, and the revenue information may refer to revenue related information. The benefit in the case may refer to the benefit generated by the user using the corresponding target product through the advertisement delivery plan, and the calculation formula of the benefit may be: revenue = total amount paid-cost of delivery; the total amount paid refers to the total amount paid by the user during use of the target product. The placement cost refers to the cost of placing the advertisement, i.e., the funds consumed to run the advertisement placement program. The user quantity information may refer to information related to the number of users, which may be obtained by introducing a target product of the advertisement delivery plan.
The historical user information includes historical user behavior information and historical payment information. Historical user behavior information may refer to user behavior information prior to training the delivery quality model and the delivery flow model. Historical payment information may refer to payment information prior to training the quality of delivery model and the traffic of delivery model. The impression quality model may refer to a model used to generate the target impression quality model. The delivery flow model may refer to a model used to generate a target delivery flow model. The target delivery quality model is used for predicting the profit situation of the advertisement delivery plan. The target delivery flow model is used for predicting the number of future users.
In one embodiment, predicting the status of the advertising campaign, the target status comprises: inputting the delivery information of the advertisement delivery plan into a target delivery quality model for state prediction to obtain a delivery quality state; and inputting the delivery information of the advertisement delivery plan into a target delivery flow model for state prediction to obtain a flow state.
In one embodiment, inputting the delivery information of the advertisement delivery plan into the target delivery quality model for state prediction, and obtaining the delivery quality state includes: inputting the delivery information of the advertisement delivery plan into a target delivery quality model for state prediction, obtaining corresponding predicted benefits by the target delivery quality model according to the delivery information, and then carrying out state judgment on the predicted benefits to obtain the delivery quality state.
In one embodiment, inputting delivery information of an advertisement delivery plan into a target delivery flow model for state prediction, and obtaining a flow state includes: inputting the delivery information of the advertisement delivery plan into a target delivery flow model for state prediction, wherein the target delivery flow model obtains the corresponding predicted user quantity according to the delivery quality, and then carries out state judgment on the predicted user quantity to obtain a flow state.
S206, determining a score threshold value based on the user quality score and the target state, and determining a return condition according to the score threshold value.
Wherein the score threshold may refer to a threshold that screens for user quality scores. The backhaul condition may refer to a condition for filtering the user.
In one embodiment, determining a score threshold based on the user quality score and the target state includes determining the target state first, determining a first score threshold based on each user quality score if the put quality state is a high quality state and the traffic state is a multi-traffic state, and determining a backhaul condition based on the first score threshold; if the put quality state is a high quality state and the flow state is a low flow state, determining a second score threshold according to the quality scores of all users, and determining a return condition according to the second score threshold; if the put quality state is a low quality state and the flow state is a multi-flow state, determining a third score threshold according to the quality scores of all users, and determining a return condition according to the third score threshold; if the put quality state is a low quality state and the flow state is a low flow state, a fourth score threshold is determined according to the quality scores of the users, and a return condition is determined according to the fourth score threshold.
Wherein the high quality state may refer to a high revenue state and the low quality state may refer to a low revenue state, e.g., in a preset period, when revenue predicted for the advertisement placement plan is greater than a high revenue threshold, determining the placement quality state as a high quality state; and in the preset period, when the predicted benefit of the advertisement putting plan is smaller than the low benefit threshold, judging the putting quality state as a low quality state.
The preset period refers to a preset period, for example, the preset period may be 00 of 20xx year 5 month x day: 00 to 20xx year 5 month x day 24:00. the high benefit threshold may be used to measure whether the benefit is high or not, the low benefit threshold may be used to measure whether the benefit is low or not, the high benefit threshold is greater than or equal to the low benefit threshold, and the high benefit threshold and the low benefit threshold may be set according to the actual situation.
The multi-traffic state may refer to a multi-user number state, for example, when the number of users predicting the advertisement delivery plan is greater than a multi-user number threshold in a preset period, the traffic state is determined as the multi-traffic state. The low traffic state may refer to a state of a small number of users, for example, when the number of users predicting the advertisement delivery plan is less than a low number of users threshold for a preset period, the traffic state is determined as a low traffic state. The multi-user number threshold may be used to measure whether the number of users is multi-user number, the low-user number threshold may be used to measure whether the number of users is low, the multi-user number threshold is greater than or equal to the low-user number threshold, and the multi-user number threshold and the low-user number threshold may be set according to actual situations.
The first score threshold may refer to a score threshold determined when the delivery quality state is a high quality state and the flow state is a multi-flow state, the first score threshold being operable to maintain a backhaul condition. The second score threshold may refer to a score threshold determined when the delivery quality state is a high quality state and the flow state is a low flow state, the second score threshold being operable to relax the backhaul conditions. The third score threshold may refer to a score threshold determined when the put mass state is a low mass state and the flow state is a multi-flow state, the third score threshold being operable to cause the backhaul condition to become tightened. The fourth score threshold may refer to a score threshold determined when the put quality state is a low quality state and the flow state is a low flow state, and the fourth score threshold may be used to make the backhaul condition become the tightest, i.e. the screened target users are the least or not.
In one embodiment, determining the return condition based on the score threshold includes determining a current stage of the advertisement delivery plan; the current stage is an initial starting stage or a learning stage; adjusting the score threshold according to the current stage to obtain an adjusted score threshold; and determining a return condition according to the adjusted score threshold.
The current stage may refer to a stage in which advertisement delivery is currently performed through an advertisement delivery plan. The current stage is an initial start-up stage or a learning stage. The initial start-up phase may refer to an initial phase of obtaining the users pushed by the advertisement delivery platform, the initial start-up phase may be defined according to a user number range, and the user number range may be set according to actual conditions. The learning phase may refer to a phase other than the initial start-up phase, and may be defined according to the number of users. For example, the number of users in the initial start-up phase may range from 0 to 20, meaning that the current phase of the advertisement delivery plan is the initial start-up phase when the number of users acquired is between 0 and 20, and the number of users in the learning phase may range from 20 or more, meaning that the current phase of the advertisement delivery plan is the learning phase when the number of users acquired is 20 or more.
And S208, screening the users according to the feedback conditions to obtain target users.
Wherein the target user may refer to a user for information feedback.
Specifically, when the advertisement delivery plan is in an initial starting stage, loose return conditions are obtained, and users are screened according to the loose return conditions, so that loose target users are obtained; and when the advertisement putting plan is in the learning stage, acquiring tightening feedback conditions, and screening the users according to the tightening feedback conditions to obtain the tightening target users.
The loose backhaul condition may refer to a backhaul condition with a lower score threshold than a tight backhaul condition. The loose target user may refer to a target user obtained by screening the user according to the loose backhaul condition. Tightening the backhaul condition may refer to a backhaul condition with a higher score threshold than a looser backhaul condition. The tightening target user may refer to a target user obtained by screening the user according to a tightening return condition. For example, the score threshold corresponding to the loose backhaul condition is a loose score threshold, the score threshold corresponding to the tight backhaul condition is a tight score threshold, and the loose score threshold is less than or equal to the tight score threshold.
S210, returning the target user to realize that the advertisement delivery platform delivers advertisements according to the target user.
Specifically, the terminal can send the target related information of the target user to the advertisement delivery platform so as to realize that the advertisement delivery platform delivers advertisements according to the target related information of the target user.
The target related information may refer to related information of a target user, and the target related information includes, but is not limited to, user basic information, user behavior information, user quality scores, and the like.
The embodiment of the application relates to the acquisition, storage, use, processing and the like of data, which all meet the relevant regulations of national laws and regulations.
In the advertisement putting method, the user is scored based on the user behavior information and the payment information, so that the user quality score is obtained; predicting the state of the advertisement putting plan to obtain a target state; the target state comprises a put quality state and a flow state; determining a score threshold based on the user quality score and the target state, and determining a return condition according to the score threshold; compared with the traditional mode of making the return condition according to the manual experience, the method greatly reduces the complexity of operation, determines the return condition by scoring the user and predicting the state of the advertisement delivery plan, has higher accuracy, and screens the user according to the return condition to obtain the target user; and returning the target user so as to realize the advertisement delivery of the advertisement delivery platform according to the target user, thereby effectively improving the accuracy of delivering advertisements.
In one embodiment, as shown in FIG. 3, the step of determining the budget includes:
S302, if the delivery quality state is a high quality state and the flow state is a multi-flow state, the budget consumption is maintained.
Budget refers to digitally programming a plan for a period of the future, budget including, but not limited to, funds and manpower for a period of the future, etc., budget consumption including, in this case, primarily funds consumption and manpower consumption, etc.
In one embodiment, maintaining the budget consumption includes obtaining a historical budget consumption for a historical preset period, the historical budget consumption being taken as the budget consumption for a future preset period.
Wherein, the historical preset period may refer to a past preset period, the historical budget consumption may refer to a past budget consumption, and the future preset period may refer to a future preset period.
S304, if the putting quality state is a high quality state and the flow state is a low flow state, the budget consumption is increased.
In one embodiment, increasing the budget consumption includes obtaining a historical budget consumption for a historical preset period, and increasing the budget consumption for a future preset period based on the historical budget consumption.
S306, if the putting quality state is a low quality state and the flow state is a multi-flow state, budget consumption is reduced.
In one embodiment, reducing the budget consumption includes obtaining a historical budget consumption for a historical preset period, and reducing the budget consumption for a future preset period based on the historical budget consumption.
S308, if the delivery quality state is a low quality state and the flow rate state is a low flow rate state, stopping the budget consumption.
In one embodiment, stopping budget consumption includes reducing budget consumption for a future preset period to a budget consumption minimum. For example, the budget consumption minimum may be 0 fund and 0 manpower.
In this embodiment, by maintaining the budget consumption if the delivery quality state is a high quality state and the flow state is a multi-flow state, increasing the budget consumption if the delivery quality state is a high quality state and the flow state is a low flow state, decreasing the budget consumption if the delivery quality state is a low quality state and the flow state is a multi-flow state, and stopping the budget consumption if the delivery quality state is a low quality state and the flow state is a low flow state, the dynamic adjustment of the budget consumption according to the delivery quality state and the flow state is realized.
FIG. 4 is a diagram of an architecture of an advertising method in one embodiment, as one example; according to the architecture shown in fig. 4, the present embodiment is as follows:
1. Modeling
1. And establishing a target user quality model for evaluating the user quality according to the user basic information and the user behavior information deposited by the advertiser terminal (terminal).
2. And establishing a target delivery quality model and a target delivery flow model for future advertisement delivery according to the historical delivery information of the advertisement delivery plan and the historical user information.
2. Advertisement delivery
1. And scoring the users according to the target user quality model to obtain user quality scores, and controlling the feedback of the users according to the user quality scores. If a looser backhaul condition is desired, a lower score threshold is taken for user quality score. If a more severe backhaul condition is desired, a higher score threshold is scored for user quality.
2. The states of the advertisement delivery plans are described according to the established target delivery quality model and the target delivery flow model, and the states are mainly divided into four large directions: high mass state + multi-flow state, high mass state + low flow state, low mass state + multi-flow state, low mass state + low flow state.
3. According to the current stage of the advertisement delivery plan and the future state prediction of the advertisement delivery plan, the feedback condition is dynamically adjusted, so that the requirements of the advertisement delivery platform on feedback flow (the number of users) can be continuously activated, and the quality requirements of the advertiser on the buying users can be achieved by controlling the quality of the feedback condition.
3.1, in the initial starting stage of the advertisement delivery plan, the random initial flow distributed by the advertisement delivery platform is faced, loose return conditions are adopted, the random flow stage of the advertisement delivery platform is ended as soon as possible, the flow purchased from the advertisement delivery platform is guided to be close to the demand direction of an advertiser as soon as possible, and the consumption of the advertiser is reduced.
3.2 in the subsequent learning stage of the advertisement delivery plan, the feedback conditions need to be gradually tightened as the advertisement delivery platform continuously learns the users required by the advertisers, so that the advertisement delivery platform is guided to learn the users more beneficial to the advertisers.
3.3 when the return condition is tightened, if the future traffic of the advertisement is predicted to be reduced, the traffic of the advertisement delivery platform is activated by properly loosening the return condition under the condition that the future quality of the advertisement is predicted to be allowed, so that the situation that the traffic cannot be bought due to high quality requirement is avoided.
4. According to the prediction condition of the future quality and flow of the advertisement delivery plan, the control of the advertisement delivery plan investment budget can be further carried out.
5.1 if it is predicted that the advertisement delivery plan will be of high future quality and high traffic, the budget consumption can be kept on.
5.2 if the advertisement delivery plan future is predicted to be of high quality but low traffic, the budget consumption is increased.
5.3 if the advertisement placement plan is predicted to be of low future quality and high traffic, the budget consumption is reduced.
5.4 if it is predicted that the advertisement delivery plan will be low in future quality and low in traffic, budget consumption is stopped (delivery is stopped).
It should be understood that, although the steps in the flowcharts related to the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides an advertisement delivery device for realizing the above related advertisement delivery method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation of one or more embodiments of the advertisement delivery device provided below may refer to the limitation of the advertisement delivery method hereinabove, and will not be repeated here.
In one embodiment, as shown in FIG. 5, there is provided an advertisement delivery device comprising: a scoring module 502, a prediction module 504, a determination module 506, a screening module 508, and a backhaul module 510, wherein:
the scoring module 502 is configured to score the user based on the user behavior information and the payment information, so as to obtain a user quality score;
the prediction module 504 is configured to predict a status of the advertisement delivery plan to obtain a target status; the target state comprises a put quality state and a flow state;
a determining module 506, configured to determine a score threshold based on the user quality score and the target state, and determine a backhaul condition according to the score threshold;
a screening module 508, configured to screen the user according to the backhaul condition to obtain a target user;
And the feedback module 510 is configured to feedback the target user, so that the advertisement delivery platform delivers advertisements according to the target user.
In one embodiment, the scoring module 502 is further configured to input the user behavior information and the payment information into the target user quality model for scoring calculation, so as to obtain the user quality score of the user.
In one embodiment, the prediction module 504 is further configured to input the delivery information of the advertisement delivery plan into the target delivery quality model for performing state prediction, so as to obtain a delivery quality state; and inputting the delivery information of the advertisement delivery plan into a target delivery flow model for state prediction to obtain a flow state.
In one embodiment, determination module 506 is also used to determine the current stage of the advertising campaign; the current stage is an initial starting stage or a learning stage; adjusting the score threshold according to the current stage to obtain an adjusted score threshold; and determining a return condition according to the adjusted score threshold.
In one embodiment, the screening module 508 is further configured to obtain a loose backhaul condition when the advertisement delivery plan is in the initial start-up phase, and screen the user according to the loose backhaul condition to obtain a loose target user; and when the advertisement putting plan is in the learning stage, acquiring tightening feedback conditions, and screening the users according to the tightening feedback conditions to obtain the tightening target users.
In one embodiment, as shown in FIG. 6, the advertising device further comprises: a training module 512 and a determine budget module 514, wherein:
the training module 512 is configured to train the user quality model according to the historical user behavior information and the historical payment information to obtain a target user quality model; the target user quality model is used to predict payment for future users.
A determine budget module 514 for maintaining budget consumption if the delivery quality status is a high quality status and the traffic status is a multi-traffic status; if the putting quality state is a high quality state and the flow state is a low flow state, increasing budget consumption; if the putting quality state is a low quality state and the flow state is a multi-flow state, budget consumption is reduced; if the delivery quality state is a low quality state and the flow state is a low flow state, stopping budget consumption.
In one embodiment, the training module 512 is further configured to train the delivery quality model and the delivery flow model according to the historical delivery information and the historical user information of the historical advertisement delivery plan, so as to obtain a target delivery quality model and a target delivery flow model; the historical user information comprises historical user behavior information and historical payment information; the target delivery quality model is used for predicting the profit situation of the advertisement delivery plan; the target delivery flow model is used for predicting the number of future users.
In the embodiment, the user quality score is obtained by scoring the user based on the user behavior information and the payment information; predicting the state of the advertisement putting plan to obtain a target state; the target state comprises a put quality state and a flow state; determining a score threshold based on the user quality score and the target state, and determining a return condition according to the score threshold; compared with the traditional mode of making the return condition according to the manual experience, the method greatly reduces the complexity of operation, determines the return condition by scoring the user and predicting the state of the advertisement delivery plan, has higher accuracy, and screens the user according to the return condition to obtain the target user; and returning the target user so as to realize the advertisement delivery of the advertisement delivery platform according to the target user, thereby effectively improving the accuracy of delivering advertisements.
The various modules in the advertising device described above may be implemented in whole or in part in software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a method of advertising. The display unit of the computer equipment is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device, wherein the display screen can be a liquid crystal display screen or an electronic ink display screen, the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on a shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in FIG. 7 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided that includes a memory having a computer program stored therein and a processor that implements the above embodiments when the processor executes the computer program.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the above embodiments.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, implements the embodiments described above.
It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims (10)

1. A method of advertising, the method comprising:
scoring the user based on the user behavior information and payment information to obtain a user quality score;
predicting the state of the advertisement putting plan to obtain a target state; the target state comprises a put quality state and a flow state;
determining a score threshold based on the user quality score and the target state, and determining a return condition according to the score threshold;
Screening the users according to the feedback conditions to obtain target users;
and returning the target user so as to realize the advertisement delivery of the advertisement delivery platform according to the target user.
2. The method according to claim 1, wherein the method further comprises:
training the user quality model according to the historical user behavior information and the historical payment information to obtain a target user quality model; the target user quality model is used for predicting the payment condition of future users;
scoring the user based on the user behavior information and the payment information, and obtaining the user quality score comprises the following steps:
and inputting the user behavior information and payment information into the target user quality model to perform scoring calculation to obtain the user quality score of the user.
3. The method according to claim 2, wherein the method further comprises:
training a delivery quality model and a delivery flow model according to historical delivery information and historical user information of a historical advertisement delivery plan to obtain a target delivery quality model and a target delivery flow model; the historical user information comprises the historical user behavior information and the historical payment information; the target delivery quality model is used for predicting the profit situation of the advertisement delivery plan; the target delivery flow model is used for predicting the quantity condition of the future users;
Predicting the state of the advertisement putting plan to obtain a target state comprises the following steps:
inputting the delivery information of the advertisement delivery plan into the target delivery quality model for state prediction to obtain the delivery quality state;
inputting the delivery information of the advertisement delivery plan into the target delivery flow model for state prediction to obtain the flow state.
4. The method of claim 1, wherein said determining a backhaul condition in accordance with the score threshold comprises:
determining a current stage of the advertisement delivery plan; the current stage is an initial starting stage or a learning stage;
adjusting the score threshold according to the current stage to obtain the adjusted score threshold; and determining a return condition according to the adjusted score threshold value.
5. The method of claim 1, wherein the filtering the user according to the backhaul condition to obtain a target user comprises:
when the advertisement putting plan is in an initial starting stage, loose return conditions are obtained, and the users are screened according to the loose return conditions, so that loose target users are obtained;
And when the advertisement putting plan is in a learning stage, acquiring a tightening feedback condition, and screening the users according to the tightening feedback condition to obtain a tightening target user.
6. The method according to claim 1, wherein the method further comprises:
if the delivery quality state is a high quality state and the flow state is a multi-flow state, maintaining budget consumption;
if the delivery quality state is a high quality state and the flow state is a low flow state, increasing the budget consumption;
if the delivery quality state is a low quality state and the flow state is a multi-flow state, reducing the budget consumption;
and if the delivery quality state is a low quality state and the flow state is a low flow state, stopping the budget consumption.
7. An advertising device, the device comprising:
the scoring module is used for scoring the user based on the user behavior information and the payment information to obtain the user quality score;
the prediction module is used for predicting the state of the advertisement delivery plan to obtain a target state; the target state comprises a put quality state and a flow state;
The determining module is used for determining a score threshold value based on the user quality score and the target state and determining a return condition according to the score threshold value;
the screening module is used for screening the users according to the feedback conditions to obtain target users;
and the feedback module is used for returning the target user so as to realize that the advertisement delivery platform delivers advertisements according to the target user.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
CN202310551526.8A 2023-05-16 2023-05-16 Advertisement putting method, advertisement putting device, computer equipment and storage medium Pending CN116797281A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310551526.8A CN116797281A (en) 2023-05-16 2023-05-16 Advertisement putting method, advertisement putting device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310551526.8A CN116797281A (en) 2023-05-16 2023-05-16 Advertisement putting method, advertisement putting device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN116797281A true CN116797281A (en) 2023-09-22

Family

ID=88038906

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310551526.8A Pending CN116797281A (en) 2023-05-16 2023-05-16 Advertisement putting method, advertisement putting device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116797281A (en)

Similar Documents

Publication Publication Date Title
US11210690B2 (en) Deep reinforcement learning methods and apparatuses for referral marketing
US10692117B2 (en) Systems and methods for autonomous bids of advertisement inventory
US20200090230A1 (en) Systems and methods for suggesting creative types for online content items to an advertiser
US8666809B2 (en) Advertisement campaign simulator
US20100268731A1 (en) Touchpoint customization system
US20150095166A1 (en) System, method and computer program for providing qualitative ad bidding
US20120259711A1 (en) Methods and systems for merchant-centric promotion generation and targeted publishing
Goodwin et al. The challenges of pre-launch forecasting of adoption time series for new durable products
CN110956505B (en) Advertisement inventory estimation method and related device
JP2013137759A (en) System and method for generating marketing mix solution
US10650404B2 (en) Real-time bidding through placebo-based experimentation
CN111222902B (en) Advertisement putting method, device, system, computing equipment and storage medium
JP2009205683A (en) Incentive mechanism for developing activity-based trigger of advertisement presentation
JP2011048831A (en) System and method for supporting consumer aggregation procedure in electronic network
US20160140577A1 (en) Unified marketing model based on conduit variables
CN110992190A (en) Asset configuration method and device based on user portrait
CN110580632B (en) Advertisement putting method and device
CN107507023B (en) Information delivery method and device
CN114298728A (en) Data processing method and related device
CN117112942A (en) User interface adjustment method, device, computer equipment and storage medium
US20140188611A1 (en) Combination of multiple advertisements in an ad slot on a network accessible device
US20120053999A1 (en) Delivering Highly Targeted Advertisements Based on a Coupon-Exchanging System
CN116797281A (en) Advertisement putting method, advertisement putting device, computer equipment and storage medium
US20150227953A1 (en) Holding access price constant for selected time when access prices change dynamically in an automates system for delivering reasonably priced access to content
EP3743873B1 (en) Modeling distribution of digital components over a network

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