Posting of recommendation content item
By adjusting posting costs based on conversion metrics for both initial and subsequent events, the method optimizes lead quality and reduces costs, addressing inefficiencies in existing content posting methods.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- BEIJING YOUZHUJU NETWORK TECH CO LTD
- Filing Date
- 2025-01-06
- Publication Date
- 2026-07-09
AI Technical Summary
Existing methods for posting recommendation content items focus solely on achieving a first conversion event, neglecting the impact of subsequent conversion events, leading to inefficiencies and higher costs per qualified lead due to insufficient data for training models.
Adjust posting costs based on adjustment parameters derived from conversion metrics associated with both the first and second conversion events, determining a target content item that optimizes both conversion rates while minimizing costs.
Improves the quality of leads and reduces cost per qualified lead by balancing conversion rates across multiple events, requiring less data for effective model training.
Smart Images

Figure CN2025070844_09072026_PF_FP_ABST
Abstract
Description
POSTING OF A RECOMMENDATION CONTENT ITEMFIELD
[0001] Example embodiments of the present disclosure generally relate to the field of computer technology, and more particularly, to posting of a recommendation content item.BACKGROUND
[0002] In recent years, the Internet has provided accesses to a variety of resources. For example, various applications, products, audio and video content, etc., may be accessed through the Internet. In addition, the accessible content also includes specific recommendation content items related to the various resources. Resource providers with resources may post their recommendation content items through content delivery system to attract potential buyers (a.k.a., leads) . However, the path that a potential buyer takes before making a purchase may consist of several stages and involves many activities. As such, it is generally expected to improve the quality of leads obtained through posting the recommendation content item.SUMMARY
[0003] In a first aspect of the present disclosure, a method for posting a recommendation content item is provided. The method comprises: obtaining a plurality of posting costs corresponding to a plurality of recommendation content items, each of the plurality of posting costs indicating a cost of posting a corresponding recommendation content item at an exposure opportunity for accomplishing a first conversion event of the corresponding recommendation content item; determining a plurality of adjustment parameters corresponding to the plurality of recommendation content items based on values of at least one conversion metric for the plurality of recommendation content items, the at least one conversion metric being associated with accomplishing a second conversion event of the corresponding recommendation content item that follows the first conversion event; adjusting the plurality of posting costs based on the plurality of adjustment parameters; and determining, from the plurality of recommendation content items and based on the plurality of adjusted posting costs, a target recommendation content item to be posted at the exposure opportunity.
[0004] In a second aspect of the present disclosure, an apparatus for posting a recommendation content item is provided. The apparatus comprises: an obtaining module, configured to obtain a plurality of posting costs corresponding to a plurality of recommendation content items, each of the plurality of posting costs indicating a cost of posting a corresponding recommendation content item at an exposure opportunity for accomplishing a first conversion event of the corresponding recommendation content item; a first determining module, configured to determine a plurality of adjustment parameters corresponding to the plurality of recommendation content items based on values of at least one conversion metric for the plurality of recommendation content items, the at least one conversion metric being associated with accomplishing a second conversion event of the corresponding recommendation content item that follows the first conversion event; an adjusting module, configured to adjust the plurality of posting costs based on the plurality of adjustment parameters; and a second determining module, configured to determine, from the plurality of recommendation content items and based on the plurality of adjusted posting costs, a target recommendation content item to be posted at the exposure opportunity.
[0005] In a third aspect of the present disclosure, an electronic device is provided. The electronic device comprises: at least one processor; and at least one memory coupled to the at least one processor and storing instructions executable by the at least one processor, the instructions, upon execution by the at least one processor, causing the electronic device to perform the method according to the first aspect of the present disclosure.
[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium has a computer program stored thereon which, upon execution by an electronic device, causes the electronic device to perform the method according to the first aspect of the present disclosure.
[0007] In a fifth aspect of the present disclosure, a computer program product is provided. The computer program product is embodied on a computer-readable medium and comprising computer-executable instructions which are executed by a processor to perform the method according to the first aspect of the present disclosure.
[0008] It should be understood that the content described in this Summary section is not intended to limit the key features or important features of the embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the present disclosure will be readily envisaged through the following description.BRIEF DESCRIPTION OF THE DRAWINGS
[0009] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent in combination with the accompanying drawings and with reference to the following detailed description. In the drawings, the same or similar reference symbols refer to the same or similar elements, where:
[0010] FIG. 1 illustrates a block diagram of an example environment in which various embodiments of the present disclosure may be implemented;
[0011] FIG. 2 illustrates a flowchart of a method for posting a recommendation content item according to some example embodiments of the present disclosure;
[0012] FIG. 3 illustrates an example interface for configurating a posting policy of recommendation content items according to some example embodiments of the present disclosure;
[0013] FIG. 4 illustrates a block diagram of an apparatus for posting a recommendation content item according to some example embodiments of the present disclosure; and
[0014] FIG. 5 illustrates a block diagram of an electronic device in which one or more embodiments of the present disclosure can be implemented.DETAILED DESCRIPTION
[0015] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some example embodiments of the present disclosure are shown in the drawings, it would be appreciated that the present disclosure may be implemented in various forms and should not be interpreted as limited to the embodiments described herein. On the contrary, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It would be appreciated that the drawings and embodiments of the present disclosure are only for the purpose of illustration and are not intended to limit the scope of protection of the present disclosure.
[0016] In the description of the embodiments of the present disclosure, the term "including" and similar terms would be appreciated as open inclusion, that is, "including but not limited to" . The term "based on" would be appreciated as "at least partially based on" . The term "one embodiment" or "the embodiment" would be appreciated as "at least one embodiment" . The term "some example embodiments" would be appreciated as "at least some example embodiments" . Other explicit and implicit definitions may also be included below. As used herein, the term "model" can represent the matching degree between various data. For example, the above matching degree can be obtained based on various technical solutions currently available and / or to be developed in the future.
[0017] It will be appreciated that the data involved in this technical proposal (including but not limited to the data itself, data acquisition or use) shall comply with the requirements of corresponding laws, regulations and relevant provisions.
[0018] It will be appreciated that before using the technical solution disclosed in each embodiment of the present disclosure, users should be informed of the type, the scope of use, the use scenario, etc. of the personal information involved in the present disclosure in an appropriate manner in accordance with relevant laws and regulations, and the user’s authorization should be obtained.
[0019] For example, in response to receiving an active request from a user, a prompt message is sent to the user to explicitly prompt the user that the operation requested operation by the user will need to obtain and use the user's personal information. Thus, users may select whether to provide personal information to the software or the hardware such as an electronic device, an application, a server or a storage medium that perform the operation of the technical solution of the present disclosure according to the prompt information.
[0020] As an optional but non-restrictive implementation, in response to receiving the user's active request, the method of sending prompt information to the user may be, for example, a pop-up window in which prompt information may be presented in text. In addition, pop-up windows may also contain selection controls for users to choose “agree” or “disagree” to provide personal information to electronic devices.
[0021] It will be appreciated that the above notification and acquisition of user authorization process are only schematic and do not limit the implementations of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.
[0022] As used herein, the term “model” may learn a correlation between respective inputs and outputs from training data, so that a corresponding output can be generated for a given input after training is completed. The generation of the model can be based on machine learning techniques. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multiple layers of processing units. A neural networks model is an example of a deep learning-based model. As used herein, “model” may also be referred to as “machine learning model” , “learning model” , “machine learning network” , “learning network” , or the like, and these terms are used interchangeably herein.
[0023] “Neural networks” are a type of machine learning network based on deep learning. Neural networks are capable of processing inputs and providing corresponding outputs, typically comprising input and output layers and one or more hidden layers between the input and output layers. Neural networks used in deep learning applications typically comprise many hidden layers, thereby increasing the depth of the network. The layers of neural networks are sequentially connected so that the output of the previous layer is provided as input to the latter layer, where the input layer receives the input of the neural network and the output of the output layer serves as the final output of the neural network. Each layer of a neural network comprises one or more nodes (also known as processing nodes or neurons) , each of which processes input from the previous layer.
[0024] Usually, machine learning may roughly comprise three stages, namely training stage, test stage, and application stage (also known as inference stage) . During the training stage, a given model can be trained using a large scale of training data, iteratively updating parameter values until the model can obtain consistent inference from the training data that meets the expected objective. Through the training, the model can be considered to learn the correlation between input and output (also known as input-to-output mapping) from the training data. The parameter values of the trained model are determined. In the test stage, test inputs are applied to the trained model to test whether the model can provide correct outputs, thereby determining the performance of the model. In the application stage, the model can be used to process actual inputs and determine corresponding outputs based on the parameter values obtained from training.
[0025] FIG. 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. As shown in FIG. 1, the example environment 100 generally involves a content posting platform 110, a content management system 120, one or more terminal devices 130-1, 130-2, …130-L, one or more audience members 132-1, 132-2, …, 132-N, a content database 140, and one or more resource providers 150-1, 150-2, …, 150-K, where each of K, L and N is an integer, such as 1, 3, 10 or the like. For ease of discussion, the one or more terminal devices 130-1, 130-2, …130-L may be collectively or individually referred to as a terminal device 130 hereinafter, the one or more audience member 132-1, 132-2, …, 132-N may be collectively or individually referred to as a terminal device 130 hereinafter, and the one or more resource providers 150-1, 150-2, …, 150-K may be collectively or individually referred to as a terminal device 130 hereinafter.
[0026] One or more content providers (not shown in FIG. 1) may use the content management system 120 to manage and post content on the content posting platform 110. The terminal device 130 is communicatively coupled with the content posting platform 110 and may access various types of content provided by the content posting platform 110, for example, based on an operation (s) of the corresponding audience member 132. By way of example, the content posting platform 110 may be an application, a website, a webpage, or any other accessible platform. The terminal device 130 may be installed with applications for accessing the content posting platform 110, or may access the content posting platform 110 in any suitable manner.
[0027] The content management system 120 may be configured to deliver one or more specific recommendation content items related to one or more resources to the audience member 132 based on corresponding posting policies, e.g., through presenting on the terminal device 130. For example, the recommendation content items to be delivered may include recommendation content items 142-1, 142-2, …, 142-M in the content database 140, where M is an integer. For ease of discussion, the recommendation content items 142-1, 142-2, …, 142-M may be collectively or individually referred to as a recommendation content item 142.
[0028] For example, resources may include various recommendation objects, such as applications, physical goods, virtual goods, audio and video content, services and so on. As used herein, “recommendation content item” refers to content to be presented for recommending corresponding resource. Example implementations of a recommendation content item 142 may include an advertisement, a brochure, or the like. An audience group of a recommendation content item may include one or more audience members 132. As used herein, “audience member” may refer to any potential consumer of resources, such as a user, a group, an organization, an entity, a corporation, and so on.
[0029] In some example embodiments, the content management system 120 may distribute corresponding recommendation content items 142 on the content posting platform 110 based on requests from resource providers 150. For example, the content management system 120 may deliver a recommendation content item 142 to corresponding audience member 132 by posting the recommendation content item 142 on the content posting platform 110 at least based on requests from the resource provider 150. In an advertisement delivery scenario, the resource provider 150 may also be referred to an advertiser. In some example embodiments, the resource provider 150 may also pay the content provider for the presentation of recommendation content items 142 and subsequent conversions.
[0030] In some example embodiments, the content management system 120 may select a recommendation content item (s) for presentation to a specific terminal device 130 at an exposure opportunity (e.g., at a specific time and / or a specific position) of the content posting platform 110, e.g., based on bidding results. For example, the content management system 120 may receive bids from the resource providers 150. In some example embodiments, the content management system 120 may allocate the exposure opportunity to the highest bidder, which means that the corresponding recommendation content item 142 may be successfully posted at the exposure opportunity. As used herein, “bid” may refer to the cost of contending for posting a certain recommendation content item 142 at a certain exposure opportunity.
[0031] In the example environment 100, the terminal device 130 may be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDA) , audio / video Player, digital cameras / video cameras, positioning devices, television receivers, radio broadcast receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some example embodiments, the terminal device 130 may also support any type of user-specific interface (such as “wearable” circuits, etc. ) . In the example environment 100, the content posting platform 110 and / or the content management system 120 may be various types of computing systems / servers that may provide computing capability, including but not limited to mainframes edge computing nodes, data centers, cloud computing environments, etc.
[0032] It should be understood that the structure and function of each element in the example environment 100 is described for illustrative purposes only and does not imply any limitations on the scope of the present disclosure. In one example embodiment, although shown as separate, the content posting platform 110 and the content management system 120 may also be integrated into a same system or device. The implementation of solutions disclosed herein is not limited in this regard.
[0033] As briefly mentioned above, the path that a potential buyer takes before making a purchase consists of several stages and involves many activities. By way of example, a typical sales funnel may comprise an awareness stage, an interest stage, a consideration stage, an intent stage, and a purchase stage. Generally, the sales funnel may also be divided into an upper funnel (a.k.a., top-of-funnel) and a deep funnel (a.k.a., bottom of funnel) . The upper funnel focuses on building awareness and attracting leads through informative content, while the deep funnel focuses on conversion and closing deals with qualified leads. For example, the upper funnel may comprise posting recommendation content item on the content posting platform to attract leads to filling out a form, and the deep funnel may comprise various events following the upper funnel, such as offline activities to close deals with these leads, and / or the like.
[0034] It is seen that lead generation typically has a relative longer sales funnel and involves several offline activities after an onsite conversion event being triggered on the content posting platform. In addition to ensuring the conversion rate regarding onsite conversion event, the resource provider also desires to improve the conversion rate regarding the deep funnel event. In an existing design, a new conversion rate (CVR) model may be directly trained from scratch based on information regarding the deep funnel event. In this case, a large amount of data related to the deep funnel event is essential to ensure the accuracy of the trained model. However, it is still challenging to obtain such a large amount of data related to the deep funnel event. A CVR model trained with insufficient deep funnel event data may be ineffective and may even be detrimental to the resulting conversion rate. On the other hand, training a new CVR model from scratch will also leads to a tedious training process and a massive consumption of computing resources.
[0035] According to embodiments of the present disclosure, an improved solution for posting a recommendation content item is proposed. In a solution according to embodiments of the present disclosure, a plurality of posting costs corresponding to a plurality of recommendation content items are obtained. Each of the plurality of posting costs indicates a cost of posting a corresponding recommendation content item at an exposure opportunity for accomplishing a first conversion event of the corresponding recommendation content item. Furthermore, a plurality of adjustment parameters corresponding to the plurality of recommendation content items are determined based on values of at least one conversion metric for the plurality of recommendation content items. The at least one conversion metric is associated with accomplishing a second conversion event of the corresponding recommendation content item that follows the first conversion event. Moreover, the plurality of posting costs are adjusted based on the plurality of adjustment parameters; and a target recommendation content item to be posted at the exposure opportunity is determined from the plurality of recommendation content items based on the plurality of adjusted posting costs.
[0036] Based on the solution according to embodiments of the present disclosure, the posting costs for accomplishing a first conversion event are adjusted with adjustment parameters determined based on values of at least one conversion metric associated with accomplishing a second conversion event following the first conversion event, and then the target recommendation content item to be posted at the exposure opportunity is determined based on the adjusted posting costs. Thereby, instead of merely focusing on the accomplishment of the first conversion event, the adjusted posting costs can further reflect the influence of the at least one conversion metric associated with accomplishing the second conversion event, and thus the target recommendation content item determined based on the adjusted posting costs can advantageously benefit the accomplishment rate of second conversion event while ensuring the accomplishment rate of the first conversion event. Thereby, the quality of leads obtained through posting the target recommendation content item can be improved, and the cost per qualified lead (CPQL) can be reduced. On the other hand, compared with the above-mentioned existing design, the proposed solution requires only a relatively small amount of data associated with accomplishing the second conversion event, and thus the effectiveness of the proposed solution can be ensured with little hindrance.
[0037] Example embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.
[0038] FIG. 2 illustrates a flowchart of a method 200 for posting a recommendation content item according to some example embodiments of the present disclosure. For example, the method 200 may be performed by the content posting platform 110 and / or the content management system 120 as shown in FIG. 1. It should be understood that the method 200 may also include additional blocks not shown, and / or blocks shown may be omitted. The scope of the present disclosure is not limited in this respect.
[0039] At 210, a plurality of posting costs corresponding to a plurality of recommendation content items 142 are obtained. Each of the plurality of posting costs indicates a cost of posting a corresponding recommendation content item 142 at an exposure opportunity for accomplishing a first conversion event of the corresponding recommendation content item 142. For example, the first conversion event may be an upper funnel online event, such as filling out a form, making an appointment with the corresponding resource provider 150, completing a registration, or the like. In one example embodiment, the plurality of recommendation content items 142 may share the same first conversion event. Alternatively, different first conversion events may be specified for different recommendation content items 142. It should be understood that the possible implementations of the first conversion event described here are merely illustrative and the first conversion event may be any other suitable event, such as an offline event or the like. The scope of the present disclosure is not limited in this respect.
[0040] In some example embodiments, each of the plurality of posting costs may be determined based on an effective cost per mille (eCPM) for accomplishing the first conversion event of the corresponding recommendation content item 142. By way of example rather than limitation, an eCPM corresponding to a recommendation content item 142 may be determined based on following Equation (1) : eCPM = CT×CV×B (1) where CT represents a click-through rate of the recommendation content item, CV represents a conversion rate of the recommendation content item 142 related to accomplishing the first conversion event, and B represents a bid amount with the target of having the first conversion event accomplished by one audience member. For example, the click-through rate may indicate the ratio of the number of audience members who view and then click the recommendation content item 142 to the number of audience members who view the recommendation content item 142. Since the conversion rate is related to accomplishing the first conversion event, the conversion rate may indicate the ratio of the number of audience members who click the recommendation content item 142 and then accomplished the first conversion event to the number of audience members who click the recommendation content item 142.
[0041] For example, the posting cost of a specific recommendation content item 142 may be set equal to a value of the eCPM determined according to Equation (1) . In aid of the eCPM, the posting costs can more accurately measure the cost of posting the corresponding recommendation content item at an exposure opportunity for accomplishing a first conversion event, which is beneficial to improving the effectiveness of the finally determined target recommendation content item.
[0042] In some example embodiments, the plurality of posting costs may be obtained from a pre-trained model. The model may be trained with historical conversion data related to the first conversion event. At the inference stage, characteristics (such as commodity type, price and / or the like) related to each of the plurality of recommendation content items 142 may be input to the pre-trained model and the pre-trained model may output a posting cost corresponding to each of the plurality of recommendation content items 142.
[0043] It should be understood that the above examples are described merely for purpose of description, and the plurality of posting costs may also be determined in any other suitable manner, such as based on a cost per action (CPA) for accomplishing the first conversion event, a CPQL for accomplishing the first conversion event, and / or the like. The scope of the present disclosure is not limited in this respect.
[0044] At 220, a plurality of adjustment parameters corresponding to the plurality of recommendation content items 142 are determined based on values of at least one conversion metric for the plurality of recommendation content items 142. The at least one conversion metric is associated with accomplishing a second conversion event of the corresponding recommendation content item 142 that follows the first conversion event. For example, the second conversion event may comprise a deep funnel offline event, such as going to a brick-and-mortar store of the resource provider 150, querying detail information of the resource from the resource provider 150, or the like. It should be understood that the possible implementations of the second conversion event described here are merely illustrative and the second conversion event may be any other suitable event, such as an onsite event or the like. The scope of the present disclosure is not limited in this respect.
[0045] In some example embodiments, the plurality of recommendation content items 142 may comprise a recommendation content item 142 configured to recommend a resource from a specific resource provider 150. In this case, the second conversion event of this recommendation content item 142 may be determined by the specific resource provider 150. In one example embodiment, the plurality of recommendation content items 142 may share the same second conversion event. Alternatively, different second conversion events may be specified for different recommendation content items 142. Moreover, the above-mentioned first conversion event of this recommendation content item 142 may also be determined by the resource provider 150.
[0046] FIG. 3 illustrates an example interface 300 for configurating the posting policy of recommendation content items 142 according to some example embodiments of the present disclosure. The example interface 300 may be presented by a client device to a resource provider 150, and the client device may be communicatively coupled with the content management system 120 in FIG. 1. As shown in FIG. 3, in aid of a selection control 320, the resource provider 150 may select an optimization event of the posting policy, which may correspond to the above-mentioned first conversion event. In addition, through the selection control 310, the resource provider 150 may select a data source for the postback of data related to the selected optimization event, so as to improve the quality of the posting costs obtained at 210.
[0047] Furthermore, the resource provider 150 may enable or disable the proposed solution with an on-off control 330. In the example shown in FIG. 3, the proposed solution is enabled and thus the example interface 300 further comprises two selection controls 340 and 350. In aid of the selection control 350, the resource provider 150 may select a deep funnel event, which may be the target of the deep funnel optimization and may correspond to the above-mentioned second conversion event. Thereby, the first conversion event and / or the second conversion event can be configured by the resource provider 150 based on his / her individual needs. Thereby, the posting policy can advantageously be adapted to a personalized demand, and the user experience of the resource provider can be improved.
[0048] In addition, by using the selection control 340, the resource provider 150 may select a data source for the postback of data related to the selected deep funnel event. Since information regarding a deep funnel event is usually unavailable to the content posting platform 110 and the content management system 120, in aid of this deep funnel information postback mechanism, the real deep funnel information may be utilized for determining the target recommendation content item to be posted at the exposure opportunity. Thereby, the effectiveness of the target recommendation content item can be enhanced, and thus the leads quality can be improved.
[0049] It is seen that in aid of the proposed solution, the optimization event will not be changed, the target for the initial CVR model and system bidding will also not be changed, and the client-side target event for conversion and CPA will not be changed. Thereby, the potential risks of higher-than-expected CPA and CPA fluctuation can be avoided.
[0050] It should be understood that the layout of the example interface 300 shown in FIG. 3 is merely illustrative, and the example interface 300 may also include additional elements not shown, and / or element shown may be omitted. By way of example, in a case where the deep funnel optimization is disabled with the on-off control 330, the selection controls 340 and 350 may also fade out. The scope of the present disclosure is not limited in this respect.
[0051] In some example embodiments, the at least one conversion metric may comprise a first conversion metric indicating a probability that a target object of the exposure opportunity proceeds from accomplishing the first conversion event to accomplish the second conversion event. For example, the target object of the exposure opportunity may be an audience member 132 of the exposure opportunity, and the first conversion metric may be a deep conversion rate which models the probability that the audience member 132, who has already finished the first conversion event, further completes the second conversion event. By way of example rather than limitation, a value of the first conversion metric may be determined in aid of a model trained with the data postbacked by the resource providers.
[0052] Additionally or alternatively, the at least one conversion metric may comprise a second conversion metric indicating an average probability that a set of objects proceed from accomplishing the first conversion event to accomplish the second conversion event. For example, the set of objects may be a set of audience members 132, and the second conversion metric may be an average deep conversion rate.
[0053] In some example embodiments, a value of the at least one conversion metric for a recommendation content item 142 may be determined based on historical conversion data for the recommendation content item 142 that is provided by the resource provider 150. By way of example, the resource provider 150 corresponding to the recommendation content item 142 may postback historical conversion data related to accomplishing the second conversion event by configuring the policy via the example interface 300 shown in FIG. 3. The historical conversion data may comprise the number of customers who have accomplished the second conversion event, the time point when a customer finished the second conversion event, and / or the like. In this case, the second conversion metric (e.g., the average deep conversion rate) may be determined based on the historical conversion data related to accomplishing the second conversion event.
[0054] It should be understood that the possible implementations of the at least one conversion metric described above are merely illustrative and therefore should not be construed as limiting the present disclosure in any way. The at least one conversion metric may also comprise any other suitable metric. It should be noted that compared with training a new model from scratch, the data volume needed for determining the value of the at least one conversion metric is quite small, and thus the proposed solution makes lower demands on data volume regarding accomplishing the second conversion event.
[0055] The detail of determining the plurality of adjustment parameters is to be described below. For ease of description, a first adjustment parameter among the plurality of adjustment parameters will be taken as an example. This first adjustment parameter may correspond to a first recommendation content item 142 among the plurality of recommendation content items 142. For example, a ratio between values of the first and second conversion metrics for the first recommendation content item 142 may be determined. In one example embodiment, the ratio may be determined to be a result of dividing the value of the first conversion metric by the value of the second conversion metric. In addition, the first adjustment parameter may be determined based on the ratio. In one example embodiment, the first adjustment parameter may be directly set equal to the ratio.
[0056] In an alternative example embodiment, a weighted sum of the ratio and a predetermined value (such as 1, or the like) may be determined and further used to determine the first adjustment parameter. By way of example rather than limitation, the first adjustment parameter may be determined based on the following Equation (2) : where coef represents an adjustment parameter, α represents a weight, deep_CV represents the value of the first conversion metric, and avg_deep_CV represents the value of the second conversion metric. In aid of the weight α, the influence of the conversion metric related to accomplishing the second conversion event can be controlled easily. Thereby, the adjusted posting cost determined with the adjustment parameter can achieve a good balance between the conversion rate for accomplishing the first conversion event and the conversion rate for accomplishing the second conversion event. In this event, the leads quality can be improved, and the resulting CPQL decreases.
[0057] In addition, the rest of the plurality of the adjustment parameters may be determined in a manner similar to the above-described first adjustment parameter. It should be understood that the plurality of the adjustment parameters may also be determined in any other suitable manner. The scope of the present disclosure is not limited in this respect.
[0058] Referring back to FIG. 2, at 230, the plurality of posting costs are adjusted based on the plurality of adjustment parameters. In one example embodiment, each of the plurality of posting costs may be scaled with the corresponding adjustment parameter. By way of example rather than limitation, each of the plurality of posting costs may be adjusted based on the following Equation (3) : P_adj=P×coef (3) wherein P represents an original posting cost corresponding to a recommendation content item, P_adj represents the adjusted posting cost, and coef represents an adjustment parameter corresponding to the recommendation content item 142.
[0059] It should be noted that in a case where the original posting cost P is set equal to the eCPM determined based on the above Equation (1) and the adjustment parameter coef is determined based on the above Equation (2), Equation (3) may be equivalent to the following Equation: P_adj= (1-α) ×eCPM+α×deep_eCPM (4) where deep_eCPM represents the approximated eCPM for accomplishing the second conversion event of the corresponding recommendation content item, and deep_eCPM is calculated as follows: where the term represents an approximation of a bid amount with the target of having the second conversion event accomplished by one audience member. It is observed that if the term avg_deep_CV is accurate, the term may be exactly the bid amount with the target of having the second conversion event accomplished by one audience member.
[0060] In aid of the above-described adjustment process, the original posting costs, which are obtained at 210 and focused on accomplishing the first conversion event, are disturbed with the at least one conversion metric regarding accomplishing the second conversion event following the first conversion event. In other words, the adjusted posting costs are determined by considering both the conversion rate for accomplishing the first conversion event and the conversion rate for accomplishing the second conversion event. Compared with conventional posting costs merely focused on ensuring either the conversion rate for accomplishing the first conversion event or the conversion rate for accomplishing the second conversion event, the adjusted posting costs can achieve a good balance between the conversion rate for accomplishing the first conversion event and the conversion rate for accomplishing the second conversion event. Thereby, the target recommendation content item determined based on the adjusted posting costs can advantageously benefit the accomplishment rate of second conversion event while ensuring the accomplishment rate of the first conversion event. Thereby, the quality of leads obtained through posting the target recommendation content item can be improved, and the resulting CPQL is relatively low.
[0061] It should be understood that the possible implementations of the adjustment process described above are merely illustrative, the plurality of posting costs may also be adjusted based on the plurality of adjustment parameters in any other suitable manner. The scope of the present disclosure is not limited in this respect.
[0062] At 240, a target recommendation content item to be posted at the exposure opportunity is determined from the plurality of recommendation content items 142 based on the plurality of adjusted posting costs. In some example embodiments, the plurality of recommendation content items 142 may be ranked based on the plurality of adjusted posting costs. In one example embodiment, the plurality of recommendation content items 142 may be ranked in a descending order by the adjusted posting costs. Alternatively, the plurality of recommendation content items 142 may be ranked in an ascending order by the adjusted posting costs. Furthermore, the target recommendation content item may be selected from the plurality of recommendation content based on a result of the ranking. By way of example rather than limitation, one of the plurality of recommendation content items 142 that is of the maximum adjusted posting cost is determined as the target recommendation content item. It should be understood that the target recommendation content item may also be determined in any other suitable manner, and the scope of the present disclosure is not limited in this respect.
[0063] In view of the above, the posting costs for accomplishing a first conversion event are adjusted with adjustment parameters determined based on values of at least one conversion metric associated with accomplishing a second conversion event following the first conversion event, and then the target recommendation content item to be posted at the exposure opportunity is determined based on the adjusted posting costs. Thereby, instead of merely focusing on the accomplishment of the first conversion event, the adjusted posting costs can further reflect the influence of the at least one conversion metric associated with accomplishing the second conversion event, and thus the target recommendation content item determined based on the adjusted posting costs can advantageously benefit the accomplishment rate of second conversion event while ensuring the accomplishment rate of the first conversion event. Thereby, the quality of leads obtained through posting the target recommendation content item can be improved, and the cost per qualified lead (CPQL) can be reduced. On the other hand, compared with the existing design, the proposed solution requires only a relatively small amount of data associated with accomplishing the second conversion event, and thus the effectiveness of the proposed solution can be ensured with little hindrance.
[0064] It should be understood by those of ordinary skill in the art that the operations of the methods disclosed herein are not necessarily presented in any particular order and that performance of some or all of the operations in an alternative order (s) is possible and is contemplated. The operations have been presented in the demonstrated order for ease of description and illustration. Operations may be added, omitted, performed together, and / or performed simultaneously, without departing from the scope of the appended claims. It should also be understood that the illustrated methods may end at any time and need not be performed in their entireties.
[0065] FIG. 4 illustrates a block diagram of an apparatus 400 for posting a recommendation content item according to some example embodiments of the present disclosure. The apparatus 400 may be implemented, for example, or included at the content posting platform 110 and / or the content management system 120 as shown in FIG. 1. Various modules / components in the apparatus 400 may be implemented by hardware, software, firmware, or any combination thereof.
[0066] As shown in FIG. 4, the apparatus 400 comprises an obtaining module 410, a first determining module 420, an adjusting module 430 and a second determining module 430. The obtaining module 410 is configured to obtain a plurality of posting costs corresponding to a plurality of recommendation content items. Each of the plurality of posting costs indicates a cost of posting a corresponding recommendation content item at an exposure opportunity for accomplishing a first conversion event of the corresponding recommendation content item. The first determining module 420 is configured to determine a plurality of adjustment parameters corresponding to the plurality of recommendation content items based on values of at least one conversion metric for the plurality of recommendation content items. The at least one conversion metric is associated with accomplishing a second conversion event of the corresponding recommendation content item that follows the first conversion event. The adjusting module 430 is configured to adjust the plurality of posting costs based on the plurality of adjustment parameters. The second determining module 440 is configured to determine, from the plurality of recommendation content items and based on the plurality of adjusted posting costs, a target recommendation content item to be posted at the exposure opportunity.
[0067] In some example embodiments, the at least one conversion metric comprises at last one of the following: a first conversion metric indicating a probability that a target object of the exposure opportunity proceeds from accomplishing the first conversion event to accomplish the second conversion event, or a second conversion metric indicating an average probability that a set of objects proceed from accomplishing the first conversion event to accomplish the second conversion event.
[0068] In some example embodiments, the plurality of adjustment parameters comprises a first adjustment parameter corresponding to a first recommendation content item among the plurality of recommendation content items, and the first determining module is further configured to: determine a ratio between values of the first and second conversion metrics for the first recommendation content item; and determine the first adjustment parameter based on the ratio.
[0069] In some example embodiments, determining the first adjustment parameter comprises: determining a weighted sum of the ratio and a predetermined value; and determining the first adjustment parameter based on the weighted sum.
[0070] In some example embodiments, the plurality of recommendation content items comprises a second recommendation content item configured to recommend a resource from a resource provider, and the second conversion event of the second recommendation content item is determined by the resource provider.
[0071] In some example embodiments, a value of the at least one conversion metric for the second recommendation content item is determined based on historical conversion data for the second recommendation content item that is provided by the resource provider.
[0072] In some example embodiments, the adjusting module is further configured to scale each of the plurality of posting costs with the corresponding adjustment parameter.
[0073] In some example embodiments, the second determining module is further configured to: rank the plurality of recommendation content items based on the plurality of adjusted posting costs; and select the target recommendation content item from the plurality of recommendation content based on a result of the ranking.
[0074] In some example embodiments, one of the plurality of recommendation content items that is of the maximum adjusted posting cost is determined as the target recommendation content item.
[0075] In some example embodiments, the first conversion event comprises an online event, and the second conversion event comprises an offline event.
[0076] In some example embodiments, each of the plurality of posting costs is determined based on an effective cost per mille (eCPM) for accomplishing the first conversion event of the corresponding recommendation content item.
[0077] The units and / or modules included in the apparatus 400 may be implemented in various forms, including software, hardware, firmware, or any combination thereof. In some example embodiments, one or more units and / or modules may be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units and / or modules in the apparatus 400 may be implemented, at least in part, by one or more hardware logic components. By way of example and not limitation, example types of hardware logic components that may be used include field programmable gate arrays (FPGAs) , application specific integrated circuits (ASICs) , application specific standards (ASSPs) , system-on-a-chip (SOCs) , complex programmable logic devices (CPLDs) , and the like.
[0078] FIG. 5 illustrates a block diagram of an electronic device 500 in which one or more embodiments of the present disclosure can be implemented. It would be appreciated that the electronic device 500 shown in FIG. 5 is only an example and should not constitute any restriction on the function and scope of the embodiments described herein. The electronic device 500 may be used, for example, to implement the content posting platform 110 and / or the content management system 120 as shown in FIG. 1.
[0079] As shown in FIG. 5, the electronic device 500 is in the form of a general computing device. The components of the electronic device 500 may include, but are not limited to, one or more processors or processing units 510, a memory 520, a storage device 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. The processing unit 510 may be an actual or virtual processor and can execute various processes according to the programs stored in the memory 520. In a multiprocessor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 500.
[0080] The electronic device 500 typically includes a variety of computer storage medium. Such medium may be any available medium that is accessible to the electronic device 500, including but not limited to volatile and non-volatile medium, removable and non-removable medium. The memory 520 may be volatile memory (for example, a register, cache, a random access memory (RAM) ) , a non-volatile memory (for example, a read-only memory (ROM) , an electrically erasable programmable read-only memory (EEPROM) , a flash memory) or any combination thereof. The storage device 530 may be any removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which can be used to store information and / or data (such as training data for training) and can be accessed within the electronic device 500.
[0081] The electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage medium. Although not shown in FIG. 5, a disk driver for reading from or writing to a removable, non-volatile disk (such as a "floppy disk" ) , and an optical disk driver for reading from or writing to a removable, non-volatile optical disk can be provided. In these cases, each driver may be connected to the bus (not shown) by one or more data medium interfaces. The memory 520 may include a computer program product 525, which has one or more program modules configured to perform various methods or acts of various embodiments of the present disclosure.
[0082] The communication unit 540 communicates with a further computing device through the communication medium. In addition, functions of components in the electronic device 500 may be implemented by a single computing cluster or multiple computing machines, which can communicate through a communication connection. Therefore, the electronic device 500 may be operated in a networking environment using a logical connection with one or more other servers, a network personal computer (PC) , or another network node.
[0083] The input device 550 may be one or more input devices, such as a mouse, a keyboard, a trackball, etc. The output device 560 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 500 may also communicate with one or more external devices (not shown) through the communication unit 540 as required. The external device, such as a storage device, a display device, etc., communicate with one or more devices that enable users to interact with the electronic device 500, or communicate with any device (for example, a network card, a modem, etc. ) that makes the electronic device 500 communicate with one or more other computing devices. Such communication may be executed via an input / output (I / O) interface (not shown) .
[0084] According to example implementation of the present disclosure, a computer-readable storage medium is provided, on which a computer-executable instruction or computer program is stored, where the computer-executable instructions or the computer program is executed by the processor to implement the method described above. According to example implementation of the present disclosure, a computer program product is also provided. The computer program product is physically stored on a non-transient computer-readable medium and includes computer-executable instructions, which are executed by the processor to implement the method described above.
[0085] Various aspects of the present disclosure are described herein with reference to the flow chart and / or the block diagram of the method, the device, the equipment and the computer program product implemented in accordance with the present disclosure. It would be appreciated that each block of the flowchart and / or the block diagram and the combination of each block in the flowchart and / or the block diagram may be implemented by computer-readable program instructions.
[0086] These computer-readable program instructions may be provided to the processing units of general-purpose computers, special computers or other programmable data processing devices to produce a machine that generates a device to implement the functions / acts specified in one or more blocks in the flow chart and / or the block diagram when these instructions are executed through the processing units of the computer or other programmable data processing devices. These computer-readable program instructions may also be stored in a computer-readable storage medium. These instructions enable a computer, a programmable data processing device and / or other devices to work in a specific way. Therefore, the computer-readable medium containing the instructions includes a product, which includes instructions to implement various aspects of the functions / acts specified in one or more blocks in the flowchart and / or the block diagram.
[0087] The computer-readable program instructions may be loaded onto a computer, other programmable data processing apparatus, or other devices, so that a series of operational steps can be performed on a computer, other programmable data processing apparatus, or other devices, to generate a computer-implemented process, such that the instructions which execute on a computer, other programmable data processing apparatus, or other devices implement the functions / acts specified in one or more blocks in the flowchart and / or the block diagram.
[0088] The flowchart and the block diagram in the drawings show the possible architecture, functions and operations of the system, the method and the computer program product implemented in accordance with the present disclosure. In this regard, each block in the flowchart or the block diagram may represent a part of a module, a program segment or instructions, which contains one or more executable instructions for implementing the specified logic function. In some alternative implementations, the functions marked in the block may also occur in a different order from those marked in the drawings. For example, two consecutive blocks may actually be executed in parallel, and sometimes can also be executed in a reverse order, depending on the function involved. It should also be noted that each block in the block diagram and / or the flowchart, and combinations of blocks in the block diagram and / or the flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or acts, or by the combination of dedicated hardware and computer instructions.
[0089] Each implementation of the present disclosure has been described above. The above description is example, not exhaustive, and is not limited to the disclosed implementations. Without departing from the scope and spirit of the described implementations, many modifications and changes are obvious to ordinary skill in the art. The selection of terms used in this article aims to best explain the principles, practical application or improvement of technology in the market of each implementation, or to enable other ordinary skill in the art to understand the various embodiments disclosed herein.
Claims
A method for posting a recommendation content item, comprising:obtaining a plurality of posting costs corresponding to a plurality of recommendation content items, each of the plurality of posting costs indicating a cost of posting a corresponding recommendation content item at an exposure opportunity for accomplishing a first conversion event of the corresponding recommendation content item;determining a plurality of adjustment parameters corresponding to the plurality of recommendation content items based on values of at least one conversion metric for the plurality of recommendation content items, the at least one conversion metric being associated with accomplishing a second conversion event of the corresponding recommendation content item that follows the first conversion event;adjusting the plurality of posting costs based on the plurality of adjustment parameters; anddetermining, from the plurality of recommendation content items and based on the plurality of adjusted posting costs, a target recommendation content item to be posted at the exposure opportunity.The method of claim 1, wherein the at least one conversion metric comprises at last one of the following:a first conversion metric indicating a probability that a target object of the exposure opportunity proceeds from accomplishing the first conversion event to accomplish the second conversion event, ora second conversion metric indicating an average probability that a set of objects proceed from accomplishing the first conversion event to accomplish the second conversion event.The method of claim 2, wherein the plurality of adjustment parameters comprises a first adjustment parameter corresponding to a first recommendation content item among the plurality of recommendation content items, and wherein determining the plurality of adjustment parameters comprises:determining a ratio between values of the first and second conversion metrics for the first recommendation content item; anddetermining the first adjustment parameter based on the ratio.The method of claim 3, wherein determining the first adjustment parameter comprises:determining a weighted sum of the ratio and a predetermined value; anddetermining the first adjustment parameter based on the weighted sum.The method of any of claims 1-4, wherein the plurality of recommendation content items comprises a second recommendation content item configured to recommend a resource from a resource provider, and the second conversion event of the second recommendation content item is determined by the resource provider.The method of claim 5, wherein a value of the at least one conversion metric for the second recommendation content item is determined based on historical conversion data for the second recommendation content item that is provided by the resource provider.The method of any of claims 1-6, wherein adjusting the plurality of posting costs comprises:scaling each of the plurality of posting costs with the corresponding adjustment parameter.The method of any of claims 1-7, wherein determining the target recommendation content item comprises:ranking the plurality of recommendation content items based on the plurality of adjusted posting costs; andselecting the target recommendation content item from the plurality of recommendation content based on a result of the ranking.The method of any of claims 1-8, wherein one of the plurality of recommendation content items that is of the maximum adjusted posting cost is determined as the target recommendation content item.The method of any of claims 1-9, wherein the first conversion event comprises an online event, and the second conversion event comprises an offline event.The method of any of claims 1-10, wherein each of the plurality of posting costs is determined based on an effective cost per mille (eCPM) for accomplishing the first conversion event of the corresponding recommendation content item.An apparatus for posting a recommendation content item, comprising:an obtaining module, configured to obtain a plurality of posting costs corresponding to a plurality of recommendation content items, each of the plurality of posting costs indicating a cost of posting a corresponding recommendation content item at an exposure opportunity for accomplishing a first conversion event of the corresponding recommendation content item;a first determining module, configured to determine a plurality of adjustment parameters corresponding to the plurality of recommendation content items based on values of at least one conversion metric for the plurality of recommendation content items, the at least one conversion metric being associated with accomplishing a second conversion event of the corresponding recommendation content item that follows the first conversion event;an adjusting module, configured to adjust the plurality of posting costs based on the plurality of adjustment parameters; anda second determining module, configured to determine, from the plurality of recommendation content items and based on the plurality of adjusted posting costs, a target recommendation content item to be posted at the exposure opportunity.An electronic device, comprising:at least one processor; andat least one memory coupled to the at least one processor and storing instructions executable by the at least one processor, the instructions, upon execution by the at least one processor, causing the electronic device to perform the method according to any of claims 1 to 11.A computer-readable storage medium, having a computer program stored thereon which, upon execution by an electronic device, causes the electronic device to perform the method according to any of claims 1 to 11.A computer program product being embodied on a computer-readable medium and comprising computer-executable instructions which are executed by a processor to perform the method according to any of claims 1 to 11.