CN112001753A - Promotion information delivery method, device, equipment and storage medium - Google Patents
Promotion information delivery method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112001753A CN112001753A CN202010845372.XA CN202010845372A CN112001753A CN 112001753 A CN112001753 A CN 112001753A CN 202010845372 A CN202010845372 A CN 202010845372A CN 112001753 A CN112001753 A CN 112001753A
- Authority
- CN
- China
- Prior art keywords
- information
- promotion
- value
- feedback
- search request
- 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
Links
- 238000002716 delivery method Methods 0.000 title description 4
- 238000000034 method Methods 0.000 claims abstract description 46
- 230000004044 response Effects 0.000 claims abstract description 29
- 238000004590 computer program Methods 0.000 claims abstract description 10
- 230000001737 promoting effect Effects 0.000 claims description 56
- 238000006243 chemical reaction Methods 0.000 claims description 29
- 230000006399 behavior Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 abstract description 8
- 230000008901 benefit Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 230000002860 competitive effect Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 239000007787 solid Substances 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method, a device, equipment and a storage medium for putting promotion information, and belongs to the field of computer programs. The method comprises the steps of obtaining pending delivery value of each promotion information in at least two promotion information; calculating total promotion feedback obtained when at least two pieces of promotion information respond to the first search request based on the value to be released; determining the undetermined delivery value as a basic delivery value in response to the total promotion feedback meeting the feedback condition; and responding to a second search request sent by the terminal, and releasing first promotion information matched with the second search request based on the basic release value, namely in the process of releasing promotion information, and realizing accurate release of the promotion information by adopting the basic release value determined by the information promotion platform.
Description
Technical Field
The present application relates to the field of computer programs, and in particular, to a method, an apparatus, a device, and a storage medium for delivering promotional information.
Background
Promotion positions are set for all demanders on the information promotion platform, and due to the fact that the number of the promotion positions is limited, the promotion information of release needs to be determined based on release values given by the demanders.
Illustratively, taking the delivery of the alliance advertisements as an example, the information promotion platform maintains a set of demand parties, calculates an adjustment coefficient required by the delivery value of the promotion information according to the advertisement conversion rate of each demand party when delivering the promotion information, adjusts the delivery value corresponding to each promotion information for multiple times according to the adjustment coefficient when competing for promotion positions to obtain a final estimated delivery value, and determines the delivered promotion information according to the ranking of the estimated delivery value.
Since the initial delivery value (i.e., the basic delivery value) is often defined by each demand party without fully knowing the basic delivery values given by other demand parties, the delivery of the promotion information can be finally completed after multiple adjustments are required in the delivery process of the promotion information, and accurate delivery cannot be realized.
Disclosure of Invention
The embodiment of the application provides a method, a device, equipment and a storage medium for releasing promotion information, wherein the basic releasing value of the promotion information is more accurately determined by an information promotion platform on the premise that the basic releasing values of other demanders are known, so that the promotion information is accurately released by adopting the basic releasing value. The technical scheme is as follows:
according to one aspect of the application, a method for delivering promotion information is provided, which is applied to an information promotion platform, and comprises the following steps:
acquiring the pending delivery value of each piece of promotion information in at least two pieces of promotion information stored on an information promotion platform;
calculating total promotion feedback obtained when at least two pieces of promotion information respond to the first search request based on the value to be released;
determining the undetermined delivery value as a basic delivery value in response to the total promotion feedback meeting the feedback condition;
and in response to receiving a second search request sent by the terminal, delivering first promotion information matched with the second search request based on the basic delivery value.
According to another aspect of the present application, there is provided a device for delivering promotion information, the device including:
the acquisition module is used for acquiring the undetermined delivery value of each piece of promotion information in at least two pieces of promotion information;
the calculation module is used for calculating total promotion feedback obtained when at least two pieces of promotion information respond to the first search request based on the value to be released;
the determining module is used for responding to the fact that the total promotion feedback meets the feedback condition and determining the value to be determined as the basic value;
and the releasing module is used for responding to the received second search request sent by the terminal and releasing the first popularization information matched with the second search request based on the basic releasing value.
According to another aspect of the present application, there is provided a computer apparatus, including: the system comprises a processor and a memory, wherein the memory stores a computer program, and the computer program is loaded and executed by the processor to realize the promotion information release method.
According to another aspect of the present application, there is provided a computer-readable storage medium having stored therein a computer program, the computer program being loaded and executed by a processor to implement the method for delivering promotional information as described above.
According to another aspect of the present application, a computer program product is provided that includes computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method for delivering the promotion information.
The beneficial effects brought by the technical scheme provided by the embodiment of the application at least comprise:
on an information promotion platform, simulating a process of determining promotion information to be released from a plurality of promotion information in practice to simultaneously determine basic releasing values of at least two pieces of promotion information, wherein for one piece of promotion information, namely on the premise of knowing the basic releasing values of other promotion information having a competitive relationship with the promotion information, the basic releasing values of the promotion information are adjusted to finally obtain a more reasonable basic releasing value, and further, in the process of releasing the promotion information, the basic releasing values determined by the information promotion platform are adopted to realize accurate releasing of the promotion information; and the putting value does not need to be adjusted for many times, so that the putting efficiency of the popularization information is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 illustrates a block diagram of a computer system provided in an exemplary embodiment of the present application;
FIG. 2 is a flowchart illustrating a method for delivering promotional information according to an exemplary embodiment of the present application;
FIG. 3 is a flow chart illustrating a method for delivering promotional information provided by another exemplary embodiment of the present application;
FIG. 4 is a flowchart illustrating a method for delivering promotional information provided by another exemplary embodiment of the present application;
FIG. 5 is a flowchart illustrating a method for delivering promotional information provided by another exemplary embodiment of the present application;
FIG. 6 is a flow chart illustrating a method for placement of promotional information provided by another exemplary embodiment of the present application;
FIG. 7 is a schematic diagram illustrating a promotional information delivery apparatus provided by an exemplary embodiment of the present application;
fig. 8 shows a schematic structural diagram of a computer device provided in an exemplary embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
The terms referred to in this application are explained first as follows:
the search request is a request for searching for information related to search content. The search request is used for requesting promotion information related to search content; for example, the search content carried by the search request includes a keyword, and if the keyword "core network" is searched in the search engine, the promotion information related to the "core network" is displayed. The promotion information is information related to search content carried by the search request; the promotion information may be information providing answers to questions, information providing noun explanations, or information providing links for purchasing products, and may be, for example, terms, public welfare advertisements, commercials, papers, technical posts, and the like. Optionally, the search request further carries user information, and the user information is used for predicting click rate, conversion rate, and conversion feedback of the promotion information at a moment in combination with the search content.
The delivery value is a value that the promotion information has for delivery in a search request. For example, taking advertisement placement as an example, since advertisement placement brings promotion benefits, advertisements are given placement values to obtain placement opportunities, thereby creating promotion benefits. The promotion benefit refers to feedback brought by promotion information release. Illustratively, the promotional benefits may include at least one of economic benefits, environmental benefits, and social benefits. For example, the placement of commercial advertisements can provide an economic benefit to advertisers.
FIG. 1 shows a schematic structural diagram of a computer system 100 provided by an exemplary embodiment of the present application, where the computer system 100 includes a terminal 120 and a server cluster 140.
The terminal 120 is an electronic device held by a user, and a client operates on the terminal 120. Optionally, the client is a client corresponding to the information popularization platform, or an applet of the information popularization platform runs in the client, or the client is a browser in which a web page version of the information popularization platform runs. For example, the client may be at least one of a lifestyle client, a payment client, a finance client, a communication client, and a game client, and the type of the client is not limited in this application.
Illustratively, the terminal 120 may include at least one of a smart phone, a tablet computer, an e-book reader, a motion Picture Experts Group Audio Layer III (MP 3) player, a motion Picture Experts Group Audio Layer IV (MP 4) player, a laptop portable computer, a desktop computer, and a notebook computer.
The terminals 120 and the server clusters 140 are connected to each other through a wired or wireless network. The server cluster 140 is used to provide background services for clients on the terminal 120. The server cluster 140 is loaded with the information promotion platform, which is a platform for providing a push service of promotion information; optionally, the information promotion platform is further provided with an information search service. Illustratively, the server cluster 140 receives a search request for a keyword sent by the terminal 120, queries promotion information related to the keyword in response to the search request, and sends the queried promotion information to the terminal 120. Illustratively, the promotion information includes entries, public service advertisements, policy promotions, news, and the like.
Since one keyword corresponds to a plurality of pieces of promotional information, and the number of pieces of information that can be displayed on the display page of the promotional information in the client running on the terminal 120 is limited, the server cluster 140 further needs to determine a specified number of pieces of promotional information from the plurality of pieces of promotional information to deliver. Illustratively, the server cluster 140 executes the method for delivering the promotion information provided by the present application, so as to deliver the promotion information when receiving the search request sent by the terminal 120.
Illustratively, the terminal 120 sends a search request to the server cluster 140, where the search request carries search content; the server cluster 140 receives the search request sent by the terminal 120, responds to the search request, and determines at least two candidate promotion information corresponding to the search content; the server cluster 140 obtains target basic delivery values of at least two candidate promotional information, and also obtains a characteristic value of the candidate promotional information at a search time corresponding to the search request, wherein the characteristic value is used for reflecting a behavior characteristic of a user for viewing the promotional information at the search time; the server cluster 140 calculates the estimated delivery value of each candidate promotion information according to the target basic delivery value and the characteristic value; the server cluster 140 sorts the estimated delivery values in descending order, determines a specified number of target estimated delivery values arranged at the head, and determines promotion information corresponding to the target estimated delivery values as first promotion information; the server cluster 140 puts the first promotion information to the client on the terminal 120; after receiving the first promotion information, the terminal 120 displays the first promotion information on a display page of promotion information of the client.
Illustratively, the promotion information may be stored on a promotion information platform. Optionally, the promotion information is obtained by the promotion information platform from a third-party information platform. Illustratively, the promotion information platform is provided with release information of promotion information in a third-party information platform; the promotion information platform serves as an intermediate platform, after the promotion information platform receives the search request, first promotion information to be released is determined based on release information, an information identifier of the first promotion information is obtained, an Application Programming Interface (API) provided by a third-party information platform is called to obtain information content of the first promotion information corresponding to the information identifier from the third-party information platform, and the information content of the first promotion information is sent to the client.
The server cluster 140 may include at least one of a server, a plurality of servers, a cloud computing platform, and a virtualization center. Those skilled in the art will also appreciate that the number of terminals 120 described above may be greater or fewer. For example, the number of the terminals 120 may be only one, or the number of the terminals 120 may be tens or hundreds, or more, and the number of the terminals 120 and the type of the device are not limited in the embodiment of the present application.
Fig. 2 is a flowchart illustrating a method for delivering promotion information according to an exemplary embodiment of the present application, which is applied to an information promotion platform in a computer system shown in fig. 1 as an example, and includes:
The undetermined putting value refers to the basic putting value of the undetermined application. The method and the device are used for simultaneously determining the basic delivery value of each promotion information in one promotion information set. Optionally, the promotion information set includes at least two pieces of promotion information on the information promotion platform. Optionally, the promotional information set is divided according to search requests, for example, a search request with search content of "two-dimensional code" corresponds to the first promotional information set, and a search request with search content of "geographical positioning" corresponds to the second promotional information set. The information promotion platform acquires at least two pieces of promotion information in the promotion information set, and correspondingly acquires the value to be released of each piece of promotion information in the at least two pieces of promotion information.
Each piece of promotion information corresponds to a value to be determined for placement, and illustratively, the value to be determined for placement is preset on the information promotion platform, or the value to be determined for placement is determined by the information promotion platform. The value to be put in of the promotion information and the information identifier of the promotion information are correspondingly stored or cached; and the information promotion platform correspondingly obtains the value to be released of each promotion information according to the information identifier.
The first search request is a search request carrying first search content associated with at least two delivery values. Illustratively, d promotion positions are correspondingly arranged on the information promotion platform for the first search request, and the d promotion positions are used for releasing d promotion information related to the first search content carried by the first search request; the information promotion platform determines d promotion information released to d promotion positions from the at least two promotion information based on the value to be released; the information promotion platform calculates total promotion feedback obtained when the d promotion information is released at the d promotion positions; d is a positive integer.
And step 203, determining the undetermined delivery value as a basic delivery value in response to the fact that the total promotion feedback meets the feedback condition.
And the information promotion platform responds to the fact that the total promotion feedback accords with the feedback condition, the undetermined putting value is determined as the basic putting value, and the basic putting value of each promotion information is obtained. Illustratively, a feedback threshold is set on the information promotion platform, and the feedback condition includes that the total promotion feedback is greater than or equal to the feedback threshold; and the information promotion platform determines the undetermined delivery value as the basic delivery value in response to the fact that the total promotion feedback is larger than or equal to the feedback threshold value, and obtains the basic delivery value of each promotion message.
And 204, responding to the received second search request sent by the terminal, and delivering the first popularization information matched with the second search request based on the basic delivery value.
The information promotion platform receives a second search request sent by the terminal, wherein the second search request carries second search content; the information promotion platform acquires at least two candidate promotion information related to the second search content, and acquires the basic delivery value of each candidate promotion information in the at least two candidate promotion information; and the information promotion platform determines first promotion information from the at least two candidate promotion information based on the basic putting value, and puts the first promotion information to a promotion position corresponding to the second search request. Optionally, the second search content is the same as or different from the first search content.
It should be noted that, when acquiring at least two candidate pieces of promotion information related to the second search content, the information promotion platform first acquires promotion information related to the second search content and an investment budget corresponding to the promotion information, and determines promotion information whose investment budget is greater than or equal to a budget threshold as the candidate promotion information, where the budget threshold is a minimum investment budget required for investment of the promotion information.
It should be further noted that, if the information promotion platform does not find the promotion information related to the search content carried in the second search request, the information promotion platform does not promote the promotion information; if the information promotion platform only finds one promotion information related to the search content of the second search request, the release budget of the promotion information is obtained, and the promotion position of the promotion information is determined according to the release budget of the promotion information.
To sum up, in the popularization information delivery method provided in this embodiment, a process of determining popularization information to be delivered from a plurality of popularization information in practice is simulated on an information popularization platform to determine basic delivery values of at least two pieces of popularization information at the same time, for one piece of popularization information, that is, on the premise that the basic delivery values of other pieces of popularization information having a competitive relationship with the popularization information are known, the basic delivery value of the piece of popularization information is adjusted to finally obtain a more reasonable basic delivery value, and further, in the process of delivering the popularization information, accurate delivery of the piece of popularization information is achieved by using the basic delivery value determined by the information popularization platform; and the putting value does not need to be adjusted for many times, so that the putting efficiency of the popularization information is improved.
Based on fig. 2, the calculation of the total promotion feedback is explained in detail, and for example, as shown in fig. 3, step 202 may include steps 2021 to 2024, which are as follows:
The first characteristic value is obtained based on the first search request in a prediction mode, and the first characteristic value is used for reflecting behavior characteristics of viewing popularization information by a user at a search moment corresponding to the first search request. Exemplarily, the first search request carries first search content and first user information; the information promotion platform predicts click rate, conversion rate and conversion feedback of promotion information released at a search time corresponding to the first search request based on the first search content and the first user information, and calculates a first characteristic value according to the click rate, the conversion rate and the conversion feedback.
Illustratively, a prediction model is arranged on the information promotion platform, the information promotion platform takes the first search content and the first user information as input data, and the prediction model is called to predict click rate, conversion rate and conversion feedback when the promotion information is released at the search time corresponding to the first search request; illustratively, the predictive model is trained from a neural network model. The click rate refers to the ratio of the number of released times to the number of checked times of the promotion information; the conversion rate is the ratio of the participation times to the checked times, and the participation times are the times of the user participating in the content in the promotion information when the promotion information is checked; the conversion feedback refers to participation feedback obtained when the user participates in the content in the promotion information.
Illustratively, the information promotion platform calculates the first eigenvalue Value according to the following eigenvalue function:
Value＝pctr×pcvr×amount------(1)；
wherein, the click rate is used as the estimated real-time click rate (ctr), namely pctr; the conversion was taken as the estimated real-time conversion (cvr), i.e. pcvr; and taking the transformation feedback as estimated real-time transformation feedback, namely, amount.
Illustratively, the first search request is sent by the terminal to the information promotion platform, or is generated by the information promotion platform in a self-defined way; if the first search request is sent to the information promotion platform by the terminal, the first user information refers to user information corresponding to a user account sending the first search request; if the first search request is generated by the information popularization platform in a self-defined mode, the first user information is user information generated by simulating user information corresponding to a user account for comprehensively searching the first search content.
Illustratively, the information promotion platform calculates the first delivery value bid of the ith promotion information according to the following calculation formula of the delivery valuei：
bidi＝Value×base_bid------(2)；
Wherein, base _ bid is the pending value to be delivered (i.e. the basic value to be delivered), and i is a positive integer.
Illustratively, the information promotion platform sequences at least two first delivery values, and if the first delivery values are in the descending order, the information promotion platform determines promotion information corresponding to the first delivery value of the front d bits as second promotion information; and if the promotion information corresponding to the first d-position delivery value is determined as second promotion information by the information promotion platform according to the sequence from small to large.
Optionally, in consideration of the need to ensure promotion feedback on the information platform, the information promotion platform is further provided with an expected click rate of each promotion information; the information promotion platform calculates the expected delivery value of each promotion information according to the first delivery value and the expected click rate; second promotional information to be released in response to the first search request is determined from the at least two promotional information based on the at least two expected delivery values. For example, the expected delivery value rankScore of the ith promotion information is calculated as follows:
rankScore＝pcrt’×bidi------(3)；
where pcrt' refers to the expected click rate. The information promotion platform sequences at least two expected delivery values from large to small (from small to large), and determines promotion information corresponding to the expected delivery values positioned at the front d position (rear d position) as second promotion information.
Illustratively, the information promotion platform calculates promotion feedback when each piece of second promotion information is released at a promotion position under the first search request; for example, the information promotion platform calculates the promotion income when the product advertisement is released, calculates the promotion cost when the product advertisement is released, and subtracts the promotion cost from the promotion income to obtain the net promotion income when the product advertisement is released, that is, the promotion feedback. And then, the information promotion platform calculates the promotion feedback sum of the d pieces of second promotion information to obtain the total promotion feedback obtained by releasing the second promotion information when responding to the first search request.
In summary, in the method for delivering promotional information provided in this embodiment, the first feature value is used to calculate the first delivery value, and the first feature value reflects the behavior feature of the user viewing the promotional information at the search time corresponding to the first search request. Secondly, the expected click rate is used for calculating the expected delivery value when the second promotion information is determined, so that the promotion feedback on the information promotion platform can reach the target value.
In order to ensure the promotion feedback balance on the information promotion platform, the feedback condition may also be total promotion feedback convergence, and exemplarily, based on the embodiment shown in fig. 2, step 205 is added, as shown in fig. 4, and the steps are as follows:
and step 205, in response to that the total promotion feedback does not meet the feedback condition, restarting execution from the step of obtaining the pending delivery value of each promotion information in the at least two promotion information.
Wherein the feedback condition comprises total promotion feedback convergence; and in response to the non-convergence of the total promotion feedback, the information promotion platform restarts to execute from the step of acquiring the pending delivery value of each promotion information in the at least two promotion information, namely from step 201. It should be noted that the value to be delivered of the retrieved promotion information is the same as or different from the original value to be delivered.
Illustratively, the information promotion platform repeats the steps 201 and 202 x times to obtain x total promotion feedbacks, and determines whether the x total promotion feedbacks are converged; the information promotion platform responds to the convergence of the x total promotion feedbacks, executes step 203, and determines the undetermined delivery value corresponding to the x total promotion feedbacks as the basic delivery value; in response to x total generalized feedbacks not converging, perform step 205; wherein x is a positive integer greater than 1.
For example, the information promotion platform calculates the total promotion feedback for the first value to be released, determines the second value to be released when the total promotion feedback corresponding to the first value to be released is not converged, calculates the total promotion feedback for the second value to be released, and determines that the total promotion feedback is converged under the second value to be released when the difference between the total promotion feedback corresponding to the second value to be released and the total promotion feedback corresponding to the first value to be released is smaller than the difference threshold.
In summary, in the popularization information delivery method provided in this embodiment, the total popularization feedback convergence is used as a feedback condition, the value to be delivered is obtained again on the premise that the total popularization feedback does not converge, the total popularization feedback corresponding to the value to be delivered obtained again is calculated until the total popularization feedback converges, and the value to be delivered is determined as the basic delivery value, so that the popularization feedback balance between each piece of popularization information on the information popularization platform is ensured when the basic delivery value is applied.
Based on fig. 4, this alternative embodiment that the feedback to be placed is determined by the information promotion platform is explained in detail, for example, step 201 includes steps 2011 to step 2013, as shown in fig. 5, the steps are as follows:
in step 2011, historical promotion data of the ith promotion information in a historical time period is obtained from the database.
The history time period refers to a time period before the acquisition time of the history promotion data. Illustratively, the information promotion platform acquires historical promotion data of promotion information at 01:00, and determines a time period from 00:00 to 24:00 of the previous day as the historical time period. For example, the duration of the historical time period may be 1 day, 2 days, or 7 days, and the duration of the historical time period is not limited in this embodiment.
At least two candidate putting values are set in the information promotion platform; the information promotion platform adopts historical promotion data to calculate promotion feedback which can be obtained when the ith promotion information is released in a historical time period based on each candidate release value. Optionally, the historical delivery data includes a historical search request, a second feature value corresponding to the historical search request, and an actual delivery value corresponding to the historical search request; the promotion feedback for the ith promotion information may be calculated in the following manner:
1) and calculating a jth second delivery value corresponding to the jth candidate delivery value and the second characteristic value according to the ith popularization information.
Illustratively, for the ith promotion information, the information promotion platform determines the product of the jth candidate delivery price value and the second feature value as the jth second delivery value corresponding to the jth candidate delivery price value, wherein j is a positive integer.
2) And comparing the jth second putting value with the actual putting value, and determining n historical search requests responded by the ith popularization information in the historical time period.
Illustratively, the search content of the historical search request may be the same as or different from the search content of the first search request. Illustratively, for the h-th historical search request, the jth second delivery value is compared with the h-th actual delivery value corresponding to the h-th historical search request, and if the jth second delivery value is greater than or equal to the h-th actual delivery value, it indicates that the ith popularization information can respond to the h-th historical search request in the historical time period, and h is a positive integer.
Illustratively, a display page responding to the historical search request comprises y promotion positions, actual delivery values corresponding to each promotion position are different, correspondingly, the jth second delivery value is compared with y actual delivery values in the h group from large to small one by one, when the ith promotion information is determined to be delivered to the e promotion position, the comparison between the jth second delivery value and the actual delivery value is not continued, the ith promotion information is determined to be capable of responding to the h historical search request in the historical time period, and delivery is carried out on the e promotion position; e. y is a positive integer, and e is less than or equal to y. Finally, the information popularization platform determines n historical search requests which can be responded by the ith popularization information in a historical time period, wherein n is a positive integer.
3) And calculating the feedback sum of the ith promotion information released under the n historical search requests to obtain promotion feedback corresponding to the jth candidate release value.
Illustratively, the information promotion platform calculates a feedback sum of the ith promotion information released at n promotion positions to obtain a jth promotion feedback of the ith promotion information corresponding to a jth candidate release price value, and finally obtains at least two promotion feedbacks corresponding to at least two candidate release price values. Illustratively, the calculation formula of the jth promotion feedback is as follows:
reward＝∑n(GMVn)-α×∑n(costn)×(∑n(costn)/budget)β- - (4); wherein α and β are set feedback parameters, which are empirical values; sigman(GMVn) The feedback sum of non-net feedback when the ith promotion information is released at n promotion positions is referred to; sigman(costn) The total promotion cost of the ith promotion information released at the n promotion positions is referred to; the budget refers to the promotion budget of the ith promotion information, and the promotion budget is given by the provider of the promotion information in advance. For example, if the promotion information is a product advertisement, gmv (gross merchandisc volume) refers to a total amount of trades in a period of time.
And 2013, determining the candidate delivery value corresponding to the maximum promotion feedback as the pending delivery value of the ith promotion information, and correspondingly storing the pending delivery value and the ith promotion information, wherein i is a positive integer.
Illustratively, the information promotion platform determines a candidate delivery value corresponding to the largest promotion feedback in the at least two promotion feedbacks as an undetermined delivery value of the ith promotion information, and correspondingly stores the undetermined delivery value and the ith promotion information.
It should be further noted that, when the step 202 is executed to calculate the total promotion feedback obtained when the at least two pieces of promotion information respond to the first search request, the information promotion platform further updates promotion data of promotion information that is not released in the at least two pieces of promotion information to the historical promotion data, so as to recalculate the value of pending release.
For example, a program code is used to illustrate a determination method of the pending placement value of the ith promotion information in the steps 2011 to 2013, which is as follows:
FOR reach base _ bid (bd (1), bd (2),. d, bd (u),. d, bd (m))/FOR bd (1), bd (2),. d, bd (u),. d, bd (m)) these m candidate delivered values execute a FOR loop, m, u are positive integers, u is less than or equal to m;
calculating the u-th second delivery value corresponding to the u-th candidate delivery price value;
FOR each search request (r (1), r (2),. times, r (g),. times, r (v))/FOR the promotion data corresponding to the r (1), r (2),. times, r (g),. times, r (v)) of the v second search requests, g and v are positive integers, and g is less than or equal to v;
IF the IF bid > bid (r (g),1)// IF the u-th second delivery value is larger than the actual delivery value corresponding to the 1 st promotion position under the g-th historical search request, executing the following program statement;
GMV + ═ GMV (r (g),1)// accumulate promotion feedback when the ith promotion information is released at the 1 st promotion location under the g-th historical search request;
cost + ═ Cost (r (g),1)// accumulate the promotion Cost when the ith promotion information is released at the 1 st promotion position under the g th historical search request;
ELSE IF bid > bid (r (g),2)// IF the u-th second delivery value is greater than the actual delivery value corresponding to the 2 nd promotion position under the g-th historical search request, executing the following program statement;
GMV + ═ GMV (r (g),2)// accumulate promotion feedback when the ith promotion information is released at the 2 nd promotion position under the g th historical search request;
cost + ═ Cost (r (g),2)// accumulate the promotion Cost when the ith promotion information is released at the 2 nd promotion position under the g th historical search request;
reward(i)＝GMV-α*cost*(cost/budget)βcalculating the u popularization feedback when the ith popularization information is put in based on the u candidate putting value;
opt _ index ═ argmax (rewarded (i) | i in (1, m))// index number opt _ index that determines the candidate delivery value corresponding to the largest of the m promotional feedbacks;
return bd (opt _ index)// output index opt _ index is the value of the candidate placement.
In summary, according to the method for determining the undetermined delivery value provided by this embodiment, the comprehensive promotion data of the promotion information on the information promotion platform is used to calculate the promotion feedback that can be created by each candidate delivery value of the at least two candidate delivery values within a certain time period, and then the candidate delivery value corresponding to the maximum promotion feedback is determined as the undetermined delivery value, so that the determined basic delivery value can maximize the promotion feedback when the promotion information is delivered.
Based on fig. 4, the application of the basic value of the investment is explained in detail, for example, as shown in fig. 6, step 204 may include steps 2041 to 2044, which are as follows:
The second search request is sent to the information promotion platform by the terminal; illustratively, a client runs in a terminal, an information search page is displayed on the client, the terminal receives search operation for search content triggered on the information search page, and sends a second search request carrying the search content to an information popularization platform; the client also logs in a user account, and the terminal sends a second search request through the user account, wherein the second search request also comprises user information corresponding to the user account. For example, the user information may include information about a location of the user account, an interest of the user account holder, a viewing habit of the user account holder for the promotional information, and the like.
Optionally, the information promotion platform predicts click rate, conversion rate and conversion feedback when the candidate promotion information is released according to the search content and the user information; and determining a third characteristic value corresponding to the candidate promotion information based on the click rate, the conversion rate and the conversion feedback. Illustratively, the information promotion platform predicts real-time click rate, conversion rate and conversion feedback through the search content and the user information, and determines a product of the click rate, the conversion rate and the conversion feedback as a third characteristic value.
The information promotion platform finds out at least two candidate promotion information corresponding to the search content, and finds out target basic delivery values corresponding to the at least two promotion information respectively. Illustratively, the information identification of the promotion information and the basic delivery value are stored in a relation table correspondingly, and after determining the candidate promotion information corresponding to the search content, the information promotion platform queries the target basic delivery value corresponding to the candidate promotion information from the relation table.
It should be noted that, in the embodiment, the execution sequence of step 2041 and step 2042 is not limited, and the description is given only by taking the case where the promotion information platform executes step 2041 first and then step 2042 second as an example.
Illustratively, the information promotion platform determines the product of the target basic delivery value and the third characteristic value as the estimated delivery value. Optionally, the information promotion platform determines a product of the target basic delivery value, the third feature value and the expected click rate as the estimated delivery value.
Optionally, the release page of the promotion information includes c promotion positions, where c is a positive integer; correspondingly, the estimated delivery value of the promotion information is required to be positioned at the front c position. Illustratively, after the estimated delivery values of at least two pieces of popularization information are determined, the information popularization platform sequences the at least two estimated delivery values according to a sequence from large to small, determines the estimated delivery value at the front c position, determines the popularization information corresponding to the estimated delivery value at the front c position as first popularization information, and delivers the first popularization information to a popularization position.
In summary, according to the method for delivering promotional information provided in this embodiment, the estimated delivery value is calculated by using the third feature value that can truly and accurately reflect the behavior feature of the promotional information that the user views at a moment, the actual delivery value of a piece of promotional information is reflected on the side, and the accurate delivery value of the promotional information can be calculated once based on the basic delivery value and the third feature value.
Fig. 7 is a block diagram illustrating a device for delivering promotional information, which may be implemented by software, hardware or a combination thereof, to become part or all of a server, according to an exemplary embodiment of the present application, where the device includes:
an obtaining module 301, configured to obtain a value to be released of each piece of promotion information in at least two pieces of promotion information stored on an information promotion platform;
a calculating module 302, configured to calculate, based on the pending delivery value, total promotion feedback obtained when the at least two pieces of promotion information respond to the first search request;
a determining module 303, configured to determine a pending delivery value as a basic delivery value in response to the total promotion feedback meeting the feedback condition;
and the releasing module 304 is configured to, in response to receiving a second search request sent by the terminal, release first promotion information matched with the second search request based on the basic release value.
In some embodiments, the calculating module 302 is configured to obtain a first feature value, where the first feature value is predicted based on the first search request, and the first feature value is used to reflect a behavior feature that a user views the promotional information at a search time corresponding to the first search request; determining a first putting value of each piece of popularization information according to the value to be put and the first characteristic value;
a calculating module 302, configured to determine, based on the at least two first delivery values, second promotional information delivered in response to the first search request from the at least two promotional information; total promotional feedback obtained by delivering the second promotional information in response to the first search request is calculated.
In some embodiments, the expected click rate of each promotion information is set in the information promotion platform;
a calculating module 302, configured to calculate an expected delivery value of each piece of promotional information according to the first delivery value and the expected click rate; second promotional information to be released in response to the first search request is determined from the at least two promotional information based on the at least two expected delivery values.
In some embodiments, the determining module 303 is further configured to, in response to that the total promotion feedback does not meet the feedback condition, resume execution of the step of obtaining the value to be released of each promotion information of the at least two promotion information until the total promotion feedback meets the feedback condition; wherein the feedback condition comprises total generalized feedback convergence.
In some embodiments, at least two candidate delivery values are set in the information promotion platform;
an obtaining module 301, configured to obtain historical promotion data of the ith promotion information in a historical time period from a database; calculating promotion feedback which can be obtained when the ith promotion information is released in a historical time period based on each candidate release value by adopting historical promotion data; and determining the candidate delivery value corresponding to the maximum promotion feedback as the pending delivery value of the ith promotion information, and correspondingly storing the pending delivery value and the ith promotion information, wherein i is a positive integer.
In some embodiments, the historical delivery data includes a historical search request, a second feature value corresponding to the historical search request, and an actual delivery value corresponding to the historical search request;
an obtaining module 301, configured to calculate, for the ith popularization information, a jth second delivery value corresponding to the jth candidate delivery value and the second feature value; comparing the jth second delivery value with the actual delivery value, and determining n historical search requests responded by the ith popularization information in a historical time period; calculating the feedback sum of the ith promotion information released under the n historical search requests to obtain promotion feedback corresponding to the jth candidate release value; j. n is a positive integer.
In some embodiments, the second search request includes search content and user information;
the releasing module 304 is configured to obtain a third feature value corresponding to the search content and the user information; searching at least two candidate promotion information corresponding to the search content and target basic delivery values respectively corresponding to the at least two candidate promotion information;
the delivery module 304 is configured to calculate an estimated delivery value of each candidate promotion information according to the target basic delivery value and the third feature value; and in response to that the estimated delivery value of the first promotion information in the at least two candidate promotion information accords with the delivery requirement, delivering the first promotion information at the promotion position corresponding to the second search request.
In some embodiments, the delivery module 304 is configured to predict click rate, conversion rate, and conversion feedback when delivering the candidate promotion information according to the search content and the user information; and determining a third characteristic value corresponding to the candidate promotion information based on the click rate, the conversion rate and the conversion feedback.
To sum up, the put in device of the popularization information that this embodiment provided, the process of the popularization information that determines required input from a plurality of popularization information in the simulation reality on the information popularization platform, to determine the basic input value of two at least popularization information simultaneously, for a popularization information, namely on the premise of the basic input value of other popularization information that is known to have a competitive relationship with it, adjust the basic input value of this popularization information, finally obtain a more reasonable basic input value, and then in the process of popularization information input, the basic input value that adopts the information popularization platform to determine realizes the accurate input to the popularization information; and the putting value does not need to be adjusted for many times, so that the putting efficiency of the popularization information is improved.
Fig. 8 shows a schematic structural diagram of a computer device provided in an exemplary embodiment of the present application. The computer device may be a server that performs the method of delivery of promotional information as provided herein. Specifically, the method comprises the following steps:
the computer apparatus 400 includes a Central Processing Unit (CPU) 401, a system Memory 404 including a Random Access Memory (RAM) 402 and a Read Only Memory (ROM) 403, and a system bus 405 connecting the system Memory 404 and the Central Processing Unit 401. The computer device 400 also includes a basic Input/Output System (I/O System)406, which facilitates the transfer of information between devices within the computer, and a mass storage device 407 for storing an operating System 413, application programs 414, and other program modules 415.
The basic input/output system 406 includes a display 408 for displaying information and an input device 409 such as a mouse, keyboard, etc. for user input of information. Wherein a display 408 and an input device 409 are connected to the central processing unit 401 through an input output controller 410 connected to the system bus 405. The basic input/output system 406 may also include an input/output controller 410 for receiving and processing input from a number of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, input/output controller 410 may also provide output to a display screen, a printer, or other type of output device.
The mass storage device 407 is connected to the central processing unit 401 through a mass storage controller (not shown) connected to the system bus 405. The mass storage device 407 and its associated computer-readable media provide non-volatile storage for the computer device 400. That is, the mass storage device 407 may include a computer-readable medium (not shown) such as a hard disk or Compact disk Read Only Memory (CD-ROM) drive.
Computer-readable media may include computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), flash Memory or other Solid State Memory technology, CD-ROM, Digital Versatile Disks (DVD), or Solid State Drives (SSD), other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage, or other magnetic storage devices. The Random Access Memory may include a resistive Random Access Memory (ReRAM) and a Dynamic Random Access Memory (DRAM). Of course, those skilled in the art will appreciate that computer storage media is not limited to the foregoing. The system memory 404 and mass storage device 407 described above may be collectively referred to as memory.
According to various embodiments of the present application, the computer device 400 may also operate as a remote computer connected to a network through a network, such as the Internet. That is, the computer device 400 may be connected to the network 412 through the network interface unit 411 connected to the system bus 405, or may be connected to other types of networks or remote computer systems (not shown) using the network interface unit 411.
The memory further includes one or more programs, and the one or more programs are stored in the memory and configured to be executed by the CPU.
In an alternative embodiment, a computer device is provided that includes a processor and a memory, the memory having stored therein at least one instruction, at least one program, set of codes, or set of instructions, the at least one instruction, at least one program, set of codes, or set of instructions being loaded and executed by the processor to implement the method of delivering promotional information as described above.
In an alternative embodiment, a computer-readable storage medium is provided that has at least one instruction, at least one program, set of codes, or set of instructions stored therein, which is loaded and executed by a processor to implement the method of delivering promotional information as described above.
Optionally, the computer-readable storage medium may include: a Read Only Memory (ROM), a Random Access Memory (RAM), a Solid State Drive (SSD), or an optical disc. The Random Access Memory may include a resistive Random Access Memory (ReRAM) and a Dynamic Random Access Memory (DRAM). The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
The present application further provides a computer-readable storage medium, in which at least one instruction, at least one program, a code set, or a set of instructions is stored, and the at least one instruction, the at least one program, the code set, or the set of instructions is loaded and executed by a processor to implement the method for delivering promotional information provided by the above-mentioned method embodiments.
The present application further provides a computer program product comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method for delivering the promotion information.
It should be understood that reference to "a plurality" herein means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only exemplary of the present application and should not be taken as limiting, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (11)
1. A method for releasing promotion information is applied to an information promotion platform, and comprises the following steps:
acquiring the value to be released of each piece of promotion information in at least two pieces of promotion information stored on the information promotion platform;
calculating total promotion feedback obtained when the at least two promotion information respond to the first search request based on the value to be put;
determining the undetermined delivery value as a basic delivery value in response to the total promotion feedback meeting a feedback condition;
and responding to a second search request sent by a terminal, and delivering first promotion information matched with the second search request based on the basic delivery value.
2. The method of claim 1, wherein said calculating a total promotional feedback obtained when said at least two promotional information responses to a first search request based on said pending placement value comprises:
acquiring a first characteristic value, wherein the first characteristic value is obtained based on the prediction of the first search request, and the first characteristic value is used for reflecting the behavior characteristics of a user for viewing the popularization information at the search moment corresponding to the first search request;
determining a first putting value of each piece of popularization information according to the pending putting value and the first characteristic value;
determining second promotion information to be released in response to the first search request from the at least two promotion information based on at least two first release values;
calculating the total promotion feedback obtained by delivering the second promotion information in response to the first search request.
3. The method of claim 2, wherein the information promotion platform has a desired click through rate for each promotion information set therein;
the determining, from the at least two pieces of promotional information, second promotional information to be released in response to the first search request based on the at least two first release values includes:
calculating the expected delivery value of each promotion message according to the first delivery value and the expected click rate;
and determining the second promotion information to be released in response to the first search request from the at least two promotion information based on at least two expected release values.
4. The method of claim 1, further comprising:
in response to the fact that the total promotion feedback does not accord with the feedback condition, restarting execution from the step of obtaining the undetermined delivery value of each promotion information in the at least two promotion information until the total promotion feedback accords with the feedback condition;
wherein the feedback condition comprises the total generalized feedback convergence.
5. The method according to any one of claims 1 to 4, wherein at least two candidate delivery values are set in the information promotion platform;
the obtaining of the value to be released of each piece of promotion information in at least two pieces of promotion information stored on the information promotion platform includes:
acquiring historical popularization data of the ith popularization information in a historical time period from a database;
calculating promotion feedback which can be obtained when the ith promotion information is released in the historical time period based on each candidate release value by adopting the historical promotion data;
and determining the candidate delivery value corresponding to the maximum promotion feedback as the value to be delivered of the ith promotion information, and correspondingly storing the value to be delivered and the ith promotion information, wherein i is a positive integer.
6. The method according to claim 5, wherein the historical delivery data comprises a historical search request, a second feature value corresponding to the historical search request, and an actual delivery value corresponding to the historical search request;
the calculating, by using the historical promotional data, promotional feedback that can be obtained when the ith promotional information is released within the historical time period based on each candidate release value includes:
calculating a jth second delivery value corresponding to the jth candidate delivery value and the second characteristic value according to the ith popularization information;
comparing the jth second delivery value with the actual delivery value, and determining n historical search requests responded by the ith popularization information in the historical time period;
calculating the feedback sum when the ith popularization information is released under the n historical search requests to obtain the popularization feedback corresponding to the jth candidate release value; j. n is a positive integer.
7. The method according to any one of claims 1 to 4, wherein the second search request includes search content and user information;
the delivering of the first promotion information matched with the second search request based on the basic delivery value comprises:
acquiring a third characteristic value corresponding to the search content and the user information;
searching at least two candidate promotion information corresponding to the search content and target basic delivery values respectively corresponding to the at least two candidate promotion information;
calculating the estimated delivery value of each candidate promotion information according to the target basic delivery value and the third characteristic value;
and in response to that the estimated delivery value of the first promotion information in the at least two candidate promotion information accords with a delivery requirement, delivering the first promotion information at a promotion position corresponding to the second search request.
8. The method according to claim 7, wherein the obtaining a third feature value corresponding to the search content and the user information comprises:
predicting click rate, conversion rate and conversion feedback when the candidate promotion information is released according to the search content and the user information;
and determining the third characteristic value corresponding to the candidate promotion information based on the click rate, the conversion rate and the conversion feedback.
9. The utility model provides a put in device of popularization information which characterized in that, the device includes:
the acquisition module is used for acquiring the value to be released of each piece of promotion information in at least two pieces of promotion information stored on the information promotion platform;
the calculation module is used for calculating total promotion feedback obtained when the at least two pieces of promotion information respond to the first search request based on the value to be released;
the determining module is used for determining the undetermined delivery value as a basic delivery value in response to the fact that the total promotion feedback meets a feedback condition;
and the releasing module is used for responding to a second search request sent by the receiving terminal and releasing first promotion information matched with the second search request based on the basic releasing value.
10. A computer device, characterized in that the computer device comprises: a processor and a memory, the memory storing a computer program that is loaded and executed by the processor to implement the method of delivering promotional information according to any of claims 1 to 8.
11. A computer-readable storage medium, in which a computer program is stored, which is loaded and executed by a processor to implement the method for delivering promotional information according to any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010845372.XA CN112001753A (en) | 2020-08-20 | 2020-08-20 | Promotion information delivery method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010845372.XA CN112001753A (en) | 2020-08-20 | 2020-08-20 | Promotion information delivery method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112001753A true CN112001753A (en) | 2020-11-27 |
Family
ID=73472825
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010845372.XA Pending CN112001753A (en) | 2020-08-20 | 2020-08-20 | Promotion information delivery method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112001753A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113011927A (en) * | 2021-03-31 | 2021-06-22 | 北京奇艺世纪科技有限公司 | Information delivery method and device, electronic equipment and storage medium |
-
2020
- 2020-08-20 CN CN202010845372.XA patent/CN112001753A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113011927A (en) * | 2021-03-31 | 2021-06-22 | 北京奇艺世纪科技有限公司 | Information delivery method and device, electronic equipment and storage medium |
| CN113011927B (en) * | 2021-03-31 | 2023-10-13 | 北京奇艺世纪科技有限公司 | Information delivery method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2637431C2 (en) | Method and system of determining optimal value of auction parameter for digital object | |
| US8560293B2 (en) | Enhanced matching through explore/exploit schemes | |
| JP6427417B2 (en) | Multidimensional ad bidding | |
| US9460451B2 (en) | Quality scoring system for advertisements and content in an online system | |
| US20170098236A1 (en) | Exploration of real-time advertising decisions | |
| US20150235275A1 (en) | Cross-device profile data management and targeting | |
| US20150235258A1 (en) | Cross-device reporting and analytics | |
| US10262339B2 (en) | Externality-based advertisement bid and budget allocation adjustment | |
| US20140207564A1 (en) | System and method for serving electronic content | |
| US20110131093A1 (en) | System and method for optimizing selection of online advertisements | |
| CN112348592A (en) | Advertisement recommendation method and device, electronic equipment and medium | |
| US20100217668A1 (en) | Optimizing Delivery of Online Advertisements | |
| CN111932314A (en) | Method, device and equipment for pushing recommended content and readable storage medium | |
| US11188846B1 (en) | Determining a sequential order of types of events based on user actions associated with a third party system | |
| CN111813902B (en) | Intelligent response method, system and computing device | |
| CN114298728A (en) | Data processing method and related device | |
| CN113850416A (en) | Advertisement promotion cooperation object determining method and device | |
| CN112001753A (en) | Promotion information delivery method, device, equipment and storage medium | |
| US20230015413A1 (en) | Systems and methods for forecasting based on categorized user membership probability | |
| CN108959324B (en) | Method and device for estimating multimedia display resource inventory and storage medium | |
| CN113034188B (en) | Multimedia content delivery method and device and electronic equipment | |
| US20180211291A1 (en) | Generating Dynamic Computer Data Structures for Automatic Adjustment of Bids for Online Advertisements | |
| JP2022144320A (en) | Information processing apparatus, information processing method, and information processing program | |
| CN112785328A (en) | Content pushing method and device and computer storage medium | |
| US20190130437A1 (en) | Identifying actions to address performance issues in a content item delivery system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20201127 |