A real-time bidding determination method based on user behavior data and computer device

Abstract

The present application relates to a method, device, computer equipment and storage medium for determining real-time bidding based on user behavior data, including: obtaining the current user behavior data of the target product in the media platform; calculating the behavior conversion data according to the current user behavior data and the pre-configured behavior conversion formula; determining the current real-time bidding strategy according to the behavior conversion data and the configured current behavior conditions; determining the real-time bidding of the target product based on the current real-time bidding strategy. The above method can adjust the real-time bidding strategy of RTA in real time according to the user performance in the media platform, without manual configuration, and automatically adjust the real-time bidding of the product.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, computer equipment and storage medium for determining real-time bidding based on user behavior data. Background Art

[0002] RTA (short for Realtime API) is used to meet advertisers' real-time personalized delivery needs. Its bidding principle is: each traffic request asks the advertiser for a bid through the API, the advertiser makes a decision after calculation, and then returns to the DSP (Demand Side Platform) for comparison. Finally, the DSP decides whether to bid, which ultimately improves the advertiser's advertising delivery effect. Traditional RTA relies on manual configuration, and requires manual observation and analysis of relevant data of products in the DSP platform, which consumes a lot of manpower and is inefficient. In addition, the RTA strategy involves too many subjective decisions, and it is impossible to modify the RTA strategy in a timely manner based on business needs. Summary of the invention

[0003] Based on this, it is necessary to provide a real-time bidding determination method, device, computer equipment and storage medium based on user behavior data to address the above technical problems, which can adjust the real-time bidding strategy of RTA in real time according to user performance in the media platform, without manual configuration, and automatically adjust the real-time bidding of products.

[0004] A method for determining real-time bidding based on user behavior data, comprising: obtaining current user behavior data of a target product in a media platform; calculating behavior conversion data based on the current user behavior data and a preconfigured behavior conversion formula; determining a current real-time bidding strategy based on the behavior conversion data and configured current behavior conditions; and determining the real-time bidding of the target product based on the current real-time bidding strategy.

[0005] In one of the embodiments, a real-time bidding determination method based on user behavior data also includes: dividing into multiple time periods, configuring corresponding behavior conditions for each time period; identifying the time period corresponding to the current time, and using the behavior conditions of the time period corresponding to the current time as the current behavior conditions.

[0006] In one of the embodiments, a method for determining a real-time bidding based on user behavior data also includes: configuring multiple real-time bidding strategies, each real-time bidding strategy is configured with a bid and one or more bidding conditions, and a real-time bidding strategy with a higher bid among the multiple real-time bidding strategies has fewer bidding conditions configured; determining the current real-time bidding strategy based on the behavior conversion data and the configured current behavior conditions, including: when the behavior conversion data meets the configured current behavior conditions, filtering out the current real-time bidding strategy from the multiple real-time bidding strategies.

[0007] In one of the embodiments, a method for determining a real-time bidding based on user behavior data further includes: when the behavior conversion data does not meet the configured current behavior condition, using a pre-configured default bidding strategy as the current real-time bidding strategy.

[0008] In one embodiment, the behavior conversion data includes the current exposure number of the target product, and the current behavior condition includes that the current exposure number is less than the historical exposure number, and the historical exposure number is determined based on the exposure number of the target product within a period of time from the current time, or based on the exposure number of the target product within a historical set time; the current real-time bidding strategy is screened out from multiple real-time bidding strategies according to the behavior conversion data and the configured current behavior condition, including: if the current exposure number of the target product is less than the historical exposure number, then the current real-time bidding strategy is screened out from multiple real-time bidding strategies, the bid of the current real-time bidding strategy is higher than the bid of the historical bidding strategy, and the bidding conditions of the current real-time bidding strategy are fewer than the bidding conditions of the historical bidding strategy, and the historical bidding strategy is any real-time bidding strategy among the multiple real-time bidding strategies adopted before the current time or a pre-configured default bidding strategy.

[0009] In one embodiment, obtaining current user behavior data of a target product in a media platform includes: identifying a user journey of the target product; obtaining current touch point data of any one or more touch points in the user journey; and using the current touch point data as current user behavior data of the target product.

[0010] In one of the embodiments, a method for determining a real-time bidding based on user behavior data also includes: upon receiving a real-time bidding request initiated by a media platform, executing the step of obtaining current user behavior data of a target product in the media platform; after the step of determining the real-time bidding of the target product based on the current real-time bidding strategy, it also includes: feeding back the real-time bidding of the target product and information representing the intention to participate in the bidding to the media platform.

[0011] A device for determining real-time bidding based on user behavior data, comprising: an acquisition module for acquiring current user behavior data of a target product in a media platform; a calculation module for calculating behavior conversion data based on the current user behavior data and a preconfigured behavior conversion formula; a first determination module for determining a current real-time bidding strategy based on the behavior conversion data and configured current behavior conditions; and a second determination module for determining the real-time bidding of the target product based on the current real-time bidding strategy.

[0012] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any of the above-mentioned embodiments are implemented.

[0013] A computer-readable storage medium stores a computer program, which implements the steps of any of the above-mentioned method embodiments when the computer program is executed by a processor.

[0014] The above-mentioned method, device, computer equipment and storage medium for determining real-time bidding based on user behavior data obtain the current user behavior data of the target product in the media platform, calculate the behavior conversion data based on the current user behavior data and the pre-configured behavior conversion formula, determine the current real-time bidding strategy based on the behavior conversion data and the configured current behavior conditions, and determine the real-time bidding of the target product based on the current real-time bidding strategy. Therefore, it is possible to automatically determine the current real-time bidding strategy that matches the current performance behavior of the user in the media platform, and the determined real-time bidding matches the user performance of the media platform and the business needs of the advertiser platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A diagram of an application environment of a method for determining a real-time bidding price based on user behavior data in one embodiment;

[0016] Figure 2 A flowchart of a method for determining a real-time bidding price based on user behavior data in one embodiment;

[0017] Figure 3 It is a configuration interface diagram of the calculation mode of the rta strategy in one embodiment;

[0018] Figure 4 A schematic diagram of the system architecture of a method for determining a real-time bidding price based on user behavior data in one embodiment;

[0019] Figure 5 It is a structural block diagram of a real-time bidding determination device based on user behavior data in one embodiment;

[0020] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0022] This application provides a real-time bidding determination method based on user behavior data, which is applied to Figure 1 In the application environment shown. Figure 1As shown, the advertiser platform 200 is used to execute a real-time bidding determination method based on user behavior data of the present application. Specifically, the user operates the target product in the advertising interface 103 provided by the media platform 104 through the terminal device 102 to generate user behavior data. The advertiser platform 200 obtains the current user behavior data of the target product in the media platform 104, calculates the behavior conversion data based on the current user behavior data and the pre-configured behavior conversion formula, determines the current real-time bidding strategy based on the behavior conversion data and the configured current behavior conditions, and determines the real-time bidding of the target product based on the current real-time bidding strategy.

[0023] In one embodiment, Figure 2 As shown, a real-time bidding determination method based on user behavior data is provided, and the method is applied to Figure 1 Taking the advertiser platform 200 in FIG. 1 as an example, the following steps are included:

[0024] S202, obtaining current user behavior data of the target product in the media platform.

[0025] In this embodiment, the target product may be an advertising product placed on a media platform, such as a credit product. The current user behavior data of the target product refers to the user behavior data generated by the user's real-time operation of the target product in the front-end advertising interface provided by the media platform. For example, the current user behavior data includes the behavior data of the user browsing the advertising space.

[0026] When the media platform sends a real-time bidding request to the advertiser platform, the advertiser platform obtains the current user behavior data of the target product in the media platform. It can be that the user behavior data within a short period of time from the current moment is read from the media platform as the current user behavior data. The short period of time is a manually configured time period.

[0027] In one example, the above-mentioned obtaining current user behavior data of the target product in the media platform includes: identifying the user journey of the target product; obtaining current touch point data of any one or more touch points in the user journey; and using the current touch point data as the current user behavior data of the target product.

[0028] Specifically, the user journey of the target product includes exposure, clicks, registrations and other events that occur on the media platform. Touch data refers to the device information, delivery account information, etc. returned by the media platform when the user is exposed, clicked, or registered on the media platform side, so that advertisers can perform data analysis. This example uses the current touch data of any one or more touch points in the user journey of the target product as the current user behavior data to calculate the user's touch data in real time to obtain the current user behavior data of the target product, so that the corresponding real-time bidding can be determined based on the user's touch data in the user journey without manual adjustment.

[0029] S204, calculating behavior conversion data according to the current user behavior data and a preconfigured behavior conversion formula.

[0030] In this embodiment, the behavior conversion formula may be any one or more of CPS (Cost per sale), CPL (Cost per lead), CPA (Cost per action), and CPC (Cost per click). The corresponding behavior conversion data is calculated by using the current user behavior data and the corresponding behavior conversion formula.

[0031] S206: Determine the current real-time bidding strategy according to the behavior conversion data and the configured current behavior conditions.

[0032] In this embodiment, each behavior conversion data configuration corresponds to a behavior condition. For example, the behavior condition corresponding to the CPA data is exceeding the set value N1, the behavior condition corresponding to the CPS is exceeding the set value N2, and so on. The behavior conditions are set based on business needs. The behavior conversion data is matched and identified with the current behavior conditions to determine the current real-time bidding strategy. For example, if the behavior conversion data is CPA data and the current behavior condition is exceeding the set value 8, the current real-time bidding strategy determined is an RTA strategy with fewer bidding conditions but higher bidding.

[0033] In one example, before determining the current real-time bidding strategy based on the behavior conversion data and the configured current behavior conditions, the above also includes: dividing into multiple time periods, configuring corresponding behavior conditions for each time period; identifying the time period corresponding to the current time, and using the behavior conditions of the time period corresponding to the current time as the current behavior conditions.

[0034] In this example, multiple time periods are divided and multiple behavior conditions are configured. Each time period corresponds to a configured behavior condition. The behavior condition of the time period corresponding to the current time is used as the current behavior condition.

[0035] For example, if the behavior conversion data is CPA data, between 8:00 and 9:00 in the morning, for the advertiser platform, a CPA data value of 8 is a normal state, and if it exceeds 8, the RTA strategy needs to be adjusted. Therefore, the behavior condition corresponding to the time period from 8:00 to 9:00 in the morning is configured as CPA data exceeding 8.

[0036] In one example, before determining the current real-time bidding strategy based on the behavior conversion data and the configured current behavior conditions, the method further includes: configuring multiple real-time bidding strategies, each real-time bidding strategy is configured with a bid and one or more bidding conditions, and the real-time bidding strategy with a higher bid among the multiple real-time bidding strategies has fewer bidding conditions configured; determining the current real-time bidding strategy based on the behavior conversion data and the configured current behavior conditions includes: when the behavior conversion data meets the configured current behavior conditions, filtering out the current real-time bidding strategy from the multiple real-time bidding strategies.

[0037] Specifically, configure multiple real-time bidding strategies, namely rta strategies. rta strategy: Real-Time API strategy, is an advertising delivery model. Its bidding principle is that each traffic request asks the advertiser for a bid through the API. The advertiser makes a decision after calculation, and then returns to the DSP (Demand Side Platform) for comparison. Finally, the DSP decides whether to bid, which ultimately improves the advertising delivery effect of the advertiser.

[0038] Each real-time bidding strategy is configured with a bid and one or more bidding conditions. The bidding conditions are used as reference conditions for the media platform to match target products. Among multiple real-time bidding strategies, the real-time bidding strategy with a higher bid has fewer bidding conditions configured. That is, among any two real-time bidding strategies, the number of bidding conditions in the real-time bidding strategy with a higher bid is less than the number of bidding conditions in the real-time bidding strategy with a lower bid. For example, the bid of real-time bidding strategy A is 3 yuan and the number of bidding conditions is N1, and the bid of real-time bidding strategy B is 5 yuan and the number of bidding conditions is N2, then N1 is greater than N2.

[0039] When the behavior conversion data corresponding to the target product in the media platform meets the configured current behavior conditions, the current real-time bidding strategy is selected from multiple real-time bidding strategies. When the behavior conversion data corresponding to the target product in the media platform does not meet the configured current behavior conditions, the pre-configured default bidding strategy is used as the current real-time bidding strategy. For example, the current real-time bidding strategy is the configured high bid high exclusion strategy, and the default bidding strategy is the normal strategy. The advertiser platform selects the corresponding bidding strategy such as Figure 3 As shown in the figure, the bidding strategy can be adjusted in real time based on user behavior data without manual configuration and modification.

[0040] In one example, the behavior conversion data includes the current exposure number of the target product, and the current behavior condition includes that the current exposure number is less than the historical exposure number, and the historical exposure number is determined based on the exposure number of the target product within a period of time from the current time, or based on the exposure number of the target product within a historical set time; the above-mentioned filtering out the current real-time bidding strategy from multiple real-time bidding strategies based on the behavior conversion data and the configured current behavior condition includes: if the current exposure number of the target product is less than the historical exposure number, then filtering out the current real-time bidding strategy from multiple real-time bidding strategies, the bid of the current real-time bidding strategy is higher than the bid of the historical bidding strategy, and the bidding conditions of the current real-time bidding strategy are fewer than the bidding conditions of the historical bidding strategy, and the historical bidding strategy is any real-time bidding strategy among the multiple real-time bidding strategies adopted before the current time or a pre-configured default bidding strategy.

[0041] In this example, the current behavior condition includes that the current exposure number is less than the historical exposure number. The historical exposure number can be set to 80% of the exposure number from yesterday to the current time. Or, 50% of the exposure number in any time period yesterday. If the current target product exposure number is less than the historical exposure number, the bid is increased, and the higher the bid, the fewer corresponding bidding conditions. For example, it may be necessary to meet conditions 1, 2, and 3 at the same time to be exposed, but it is found that the current target product has fewer exposures and needs to increase the exposure number. The real-time bidding strategy is adjusted to only require conditions 1 and 2 for exposure, and condition 3 is not required, and the condition restrictions are reduced.

[0042] Specifically, if the current target product's real-time exposure number is less than 80% of the exposure number from yesterday to the current time, the bid is increased and the RTA strategy selection conditions are fewer to increase the target product's exposure number. If the current target product's real-time exposure number is less than 50% of the exposure number from 5:00 to 9:00 yesterday, the bid is increased and the RTA strategy selection conditions are fewer to increase the number of exposures. By changing this condition, the target product's delivery strategy can be adjusted in real time to reduce delivery costs.

[0043] S208, determining the real-time bidding price of the target product based on the current real-time bidding strategy.

[0044] In this embodiment, the current real-time bidding strategy includes real-time bidding. When the current real-time bidding is determined, the real-time bidding of the current real-time bidding strategy is obtained, thereby determining the current real-time bidding of the target product.

[0045] The above-mentioned method for determining real-time bidding based on user behavior data obtains the current user behavior data of the target product in the media platform, calculates the behavior conversion data based on the current user behavior data and the pre-configured behavior conversion formula, determines the current real-time bidding strategy based on the behavior conversion data and the configured current behavior conditions, and determines the real-time bidding of the target product based on the current real-time bidding strategy. Therefore, it is possible to automatically determine the current real-time bidding strategy that matches the current performance behavior of the user in the media platform, and the determined real-time bidding matches the user performance of the media platform and the business needs of the advertiser platform.

[0046] In one embodiment, the above step of obtaining the current user behavior data of the target product in the media platform includes: upon receiving a real-time bidding request initiated by the media platform, executing to obtain the current user behavior data of the target product in the media platform; after the above step of determining the real-time bidding of the target product based on the current real-time bidding strategy, it also includes: feeding back the real-time bidding of the target product and information representing the intention to participate in the bidding to the media platform.

[0047] Specifically, Figure 4 As shown in , when the media platform confirms that the user browses the ad space, the media platform initiates an RTA request to the advertiser platform. The RTA request is a real-time bidding request. When the media platform receives the real-time bidding request, it obtains the current user behavior data of the target product in the media platform to calculate the real-time bidding of the target product. In addition, Figure 4 As shown, after the media platform determines the real-time bidding of the target product, it sends the bidding intention information and the real-time bidding result back to the media platform. Therefore, the real-time bidding of the target product on the media platform is realized.

[0048] For the above-mentioned real-time bidding determination method based on user behavior data, its implementation process and application system framework are as follows: Figure 4 First, call up the AI ​​process and configure the calculation mode. The implementation of the calculation mode can be found in Figure 3 As shown, select the RTA strategy. When the media platform initiates an RTA request, the advertiser platform determines whether the user participates in the competition based on the selected RTA strategy. The advertiser who successfully participates in the competition will launch an advertisement.

[0049] The above method for determining real-time bidding based on user behavior data can adjust the RTA strategy in real time according to the user's performance on the media platform. In addition, user data can be processed in time periods, and a specific RTA strategy can be set for a specific time period, so that the RTA strategy can be flexibly selected.

[0050] It should be understood that, although the steps in the flowchart are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0051] The present application also provides a real-time bidding determination device based on user behavior data. Figure 5 As shown, a real-time bidding determination device based on user behavior data includes an acquisition module 502, a calculation module 504, a first determination module 506, and a second determination module 508. The acquisition module 502 is used to acquire the current user behavior data of the target product in the media platform; the calculation module 504 is used to calculate the behavior conversion data according to the current user behavior data and the pre-configured behavior conversion formula; the first determination module 506 is used to determine the current real-time bidding strategy according to the behavior conversion data and the configured current behavior conditions; the second determination module 508 is used to determine the real-time bidding of the target product based on the current real-time bidding strategy.

[0052] In one of the embodiments, a real-time bidding determination device based on user behavior data also includes a first configuration module, which is used to divide a plurality of time periods, each time period is configured with a corresponding behavior condition; the time period corresponding to the current time is identified, and the behavior condition of the time period corresponding to the current time is used as the current behavior condition.

[0053] In one of the embodiments, a real-time bidding determination device based on user behavior data also includes a second configuration module, which is used to configure multiple real-time bidding strategies, each real-time bidding strategy is configured with a bid and one or more bidding conditions, and the real-time bidding strategy with a higher bid among the multiple real-time bidding strategies has fewer bidding conditions configured; determining the current real-time bidding strategy based on the behavior conversion data and the configured current behavior conditions, including: when the behavior conversion data meets the configured current behavior conditions, screening out the current real-time bidding strategy from the multiple real-time bidding strategies.

[0054] In one of the embodiments, a real-time bidding determination device based on user behavior data further includes a third determination module for using a preconfigured default bidding strategy as a current real-time bidding strategy when the behavior conversion data does not satisfy the configured current behavior condition.

[0055] In one embodiment, the behavior conversion data includes the current exposure number of the target product, and the current behavior condition includes that the current exposure number is less than the historical exposure number, and the historical exposure number is determined based on the exposure number of the target product within a period of time from the current time, or based on the exposure number of the target product within a historical set time; the current real-time bidding strategy is screened out from multiple real-time bidding strategies according to the behavior conversion data and the configured current behavior condition, including: if the current exposure number of the target product is less than the historical exposure number, then the current real-time bidding strategy is screened out from multiple real-time bidding strategies, the bid of the current real-time bidding strategy is higher than the bid of the historical bidding strategy, and the bidding conditions of the current real-time bidding strategy are fewer than the bidding conditions of the historical bidding strategy, and the historical bidding strategy is any real-time bidding strategy among the multiple real-time bidding strategies adopted before the current time or a pre-configured default bidding strategy.

[0056] In one embodiment, obtaining current user behavior data of a target product in a media platform includes: identifying a user journey of the target product; obtaining current touch point data of any one or more touch points in the user journey; and using the current touch point data as current user behavior data of the target product.

[0057] In one of the embodiments, a real-time bidding determination device based on user behavior data also includes a receiving module, which is used to execute the step of obtaining current user behavior data of a target product in a media platform when a real-time bidding request initiated by a media platform is received; after the step of determining the real-time bidding of the target product based on the current real-time bidding strategy, it also includes: feeding back the real-time bidding of the target product and information representing the intention to participate in the bidding to the media platform.

[0058] For the specific definition of a real-time bidding determination device based on user behavior data, please refer to the definition of a real-time bidding determination method based on user behavior data above, which will not be repeated here. Each module in the above-mentioned real-time bidding determination device based on user behavior data can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0059] In one embodiment, a computer device is provided. The computer device may be a server supporting the operation of an advertiser platform. The internal structure diagram thereof may be as follows: Figure 6As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to receive RTA requests initiated by a media platform, etc. When the computer program is executed by the processor, it implements the above-mentioned real-time bidding determination method based on user behavior data.

[0060] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0061] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: obtaining current user behavior data of a target product in a media platform; calculating behavior conversion data based on the current user behavior data and a preconfigured behavior conversion formula; determining a current real-time bidding strategy based on the behavior conversion data and configured current behavior conditions; and determining real-time bidding for the target product based on the current real-time bidding strategy.

[0062] In one of the embodiments, when the processor executes the computer program, the following steps are also implemented: dividing multiple time periods, configuring corresponding behavior conditions for each time period; identifying the time period corresponding to the current time, and using the behavior conditions of the time period corresponding to the current time as the current behavior conditions.

[0063] In one of the embodiments, when the processor executes the computer program, the following steps are further implemented: multiple real-time bidding strategies are configured, each real-time bidding strategy is configured with a bid and one or more bidding conditions, and a real-time bidding strategy with a higher bid among the multiple real-time bidding strategies has fewer bidding conditions configured; when the processor executes the computer program to implement the above-mentioned step of determining the current real-time bidding strategy based on the behavior conversion data and the configured current behavior conditions, the following steps are specifically implemented: when the behavior conversion data meets the configured current behavior conditions, the current real-time bidding strategy is screened out from the multiple real-time bidding strategies.

[0064] In one of the embodiments, when the processor executes the computer program, the following steps are also implemented: when the behavior conversion data does not meet the configured current behavior conditions, the preconfigured default bidding strategy is used as the current real-time bidding strategy.

[0065] In one embodiment, the behavior conversion data includes the current exposure number of the target product, and the current behavior condition includes that the current exposure number is less than the historical exposure number, and the historical exposure number is determined based on the exposure number of the target product within a period of time from the current time, or based on the exposure number of the target product within a historical set time; when the processor executes the computer program to implement the above-mentioned step of filtering out the current real-time bidding strategy from multiple real-time bidding strategies according to the behavior conversion data and the configured current behavior condition, the following steps are specifically implemented: if the current exposure number of the target product is less than the historical exposure number, the current real-time bidding strategy is filtered out from multiple real-time bidding strategies, the bid of the current real-time bidding strategy is higher than the bid of the historical bidding strategy, and the bidding conditions of the current real-time bidding strategy are fewer than the bidding conditions of the historical bidding strategy, and the historical bidding strategy is any real-time bidding strategy among the multiple real-time bidding strategies adopted before the current time or a pre-configured default bidding strategy.

[0066] In one of the embodiments, when the processor executes a computer program to implement the above-mentioned step of obtaining the current user behavior data of the target product in the media platform, the following steps are specifically implemented: identifying the user journey of the target product; obtaining the current touch point data of any one or more touch points in the user journey; and using the current touch point data as the current user behavior data of the target product.

[0067] In one of the embodiments, when the processor executes the computer program, it also implements the following steps: upon receiving a real-time bidding request initiated by a media platform, obtaining current user behavior data of a target product in the media platform; and, feeding back to the media platform the real-time bidding of the target product and information representing the intention to participate in the bidding.

[0068] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: obtaining current user behavior data of a target product in a media platform; calculating behavior conversion data based on the current user behavior data and a preconfigured behavior conversion formula; determining a current real-time bidding strategy based on the behavior conversion data and the configured current behavior conditions; and determining real-time bidding for the target product based on the current real-time bidding strategy.

[0069] In one of the embodiments, when the computer program is executed by the processor, the following steps are also implemented: dividing multiple time periods, configuring corresponding behavior conditions for each time period; identifying the time period corresponding to the current time, and using the behavior conditions of the time period corresponding to the current time as the current behavior conditions.

[0070] In one of the embodiments, when the computer program is executed by the processor, the following steps are further implemented: multiple real-time bidding strategies are configured, each real-time bidding strategy is configured with a bid and one or more bidding conditions, and a real-time bidding strategy with a higher bid among the multiple real-time bidding strategies has fewer bidding conditions configured; when the computer program is executed by the processor to implement the above-mentioned step of determining the current real-time bidding strategy based on the behavior conversion data and the configured current behavior conditions, the following steps are specifically implemented: when the behavior conversion data meets the configured current behavior conditions, the current real-time bidding strategy is screened out from the multiple real-time bidding strategies.

[0071] In one of the embodiments, when the computer program is executed by the processor, the following steps are also implemented: when the behavior conversion data does not meet the configured current behavior conditions, the preconfigured default bidding strategy is used as the current real-time bidding strategy.

[0072] In one of the embodiments, the behavior conversion data includes the current exposure number of the target product, and the current behavior condition includes that the current exposure number is less than the historical exposure number, and the historical exposure number is determined based on the exposure number of the target product within a period of time from the current time, or based on the exposure number of the target product within a historical set time; when the computer program is executed by the processor to implement the above-mentioned step of filtering out the current real-time bidding strategy from multiple real-time bidding strategies according to the behavior conversion data and the configured current behavior condition, the following steps are specifically implemented: if the current exposure number of the target product is less than the historical exposure number, the current real-time bidding strategy is filtered out from multiple real-time bidding strategies, the bid of the current real-time bidding strategy is higher than the bid of the historical bidding strategy, and the bidding conditions of the current real-time bidding strategy are fewer than the bidding conditions of the historical bidding strategy, and the historical bidding strategy is any real-time bidding strategy among the multiple real-time bidding strategies adopted before the current time or a pre-configured default bidding strategy.

[0073] In one of the embodiments, when the computer program is executed by the processor to implement the above-mentioned steps of obtaining the current user behavior data of the target product in the media platform, the following steps are specifically implemented: identifying the user journey of the target product; obtaining the current touch point data of any one or more touch points in the user journey; and using the current touch point data as the current user behavior data of the target product.

[0074] In one of the embodiments, when the computer program is executed by the processor, the following steps are also implemented: upon receiving a real-time bidding request initiated by a media platform, obtaining current user behavior data of a target product in the media platform; and, feeding back to the media platform the real-time bidding of the target product and information representing the intention to participate in the bidding.

[0075] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0076] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0077] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A real-time bidding determination method based on user behavior data, It is characterized in that The method comprises: Obtain current user behavior data of target products in media platforms; Behavior conversion data is calculated based on the current user behavior data and a preconfigured behavior conversion formula, wherein the behavior conversion formula includes any one or more of a calculation formula for charging per action, a calculation formula for charging per successful transaction, a calculation formula for charging per piece of data, and a calculation formula for charging per click; Divide into multiple time periods, configure corresponding behavior conditions for each time period, and the behavior conditions are exceeding set values ​​set based on business needs; Identify a time period corresponding to the current time, and use the behavior condition of the time period corresponding to the current time as the current behavior condition; Configure multiple real-time bidding strategies, each of which is configured with a bid and one or more bidding conditions. A real-time bidding strategy with a higher bid among the multiple real-time bidding strategies has fewer bidding conditions configured; Determining the current real-time bidding strategy according to the behavior conversion data and the configured current behavior conditions, wherein determining the current real-time bidding strategy according to the behavior conversion data and the configured current behavior conditions includes: when the behavior conversion data satisfies the configured current behavior conditions, selecting the current real-time bidding strategy from multiple real-time bidding strategies; Determining a real-time bidding price for the target product based on the current real-time bidding strategy; Before selecting the current real-time bidding strategy from multiple real-time bidding strategies according to the behavior conversion data and the configured current behavior condition, the method further includes: when the behavior conversion data does not meet the configured current behavior condition, using a pre-configured default bidding strategy as the current real-time bidding strategy; The behavior conversion data also includes the current exposure number of the target product, and the current behavior condition includes that the current exposure number is less than the historical exposure number, and the historical exposure number is determined based on the exposure number of the target product within a period of time from the current time, or based on the exposure number of the target product within a historical set time; the current real-time bidding strategy is screened out from multiple real-time bidding strategies according to the behavior conversion data and the configured current behavior condition, including: if the current exposure number of the target product is less than the historical exposure number, the current real-time bidding strategy is screened out from the multiple real-time bidding strategies, the bid of the current real-time bidding strategy is higher than the bid of the historical bidding strategy, and the bidding conditions of the current real-time bidding strategy are fewer than the bidding conditions of the historical bidding strategy, and the historical bidding strategy is any real-time bidding strategy among the multiple real-time bidding strategies adopted before the current time or the preconfigured default bidding strategy.

2. The method according to claim 1, It is characterized in that The obtaining of current user behavior data of the target product in the media platform includes: Identify the user journey for your target product; Obtain current touchpoint data of any one or more touchpoints in the user journey; The current contact data is used as the current user behavior data of the target product.

3. The method according to claim 1, It is characterized in that The method further comprises: Upon receiving the real-time bidding request initiated by the media platform, executing the step of obtaining current user behavior data of the target product in the media platform; After the step of determining the real-time bidding price of the target product based on the current real-time bidding strategy, the method further includes: The real-time bidding price of the target product and information indicating the intention to participate in the bidding are fed back to the media platform.

4. A real-time bidding determination device based on user behavior data, It is characterized in that The device comprises: An acquisition module is used to acquire current user behavior data of a target product in a media platform; A calculation module, configured to calculate behavior conversion data according to the current user behavior data and a preconfigured behavior conversion formula, wherein the behavior conversion formula includes any one or more of a calculation formula for charging per action, a calculation formula for charging per successful transaction, a calculation formula for charging per piece of data, and a calculation formula for charging per click; The first configuration module is used to divide a plurality of time periods, configure a corresponding behavior condition for each time period, and the behavior condition is a value exceeding a set value set based on business requirements; identify the time period corresponding to the current time, and use the behavior condition for the time period corresponding to the current time as the current behavior condition; The second configuration module is used to configure multiple real-time bidding strategies, each of which is configured with a bid and one or more bidding conditions, and a real-time bidding strategy with a higher bid among the multiple real-time bidding strategies is configured with fewer bidding conditions; A first determination module is used to determine the current real-time bidding strategy according to the behavior conversion data and the configured current behavior conditions, wherein the determining the current real-time bidding strategy according to the behavior conversion data and the configured current behavior conditions includes: when the behavior conversion data meets the configured current behavior conditions, selecting the current real-time bidding strategy from multiple real-time bidding strategies; A second determination module, configured to determine the real-time bidding price of the target product based on the current real-time bidding strategy; Before selecting the current real-time bidding strategy from multiple real-time bidding strategies according to the behavior conversion data and the configured current behavior condition, the method further includes: when the behavior conversion data does not meet the configured current behavior condition, using a pre-configured default bidding strategy as the current real-time bidding strategy; The behavior conversion data also includes the current exposure number of the target product, and the current behavior condition includes that the current exposure number is less than the historical exposure number, and the historical exposure number is determined based on the exposure number of the target product within a period of time from the current time, or based on the exposure number of the target product within a historical set time; the current real-time bidding strategy is screened out from multiple real-time bidding strategies according to the behavior conversion data and the configured current behavior condition, including: if the current exposure number of the target product is less than the historical exposure number, the current real-time bidding strategy is screened out from the multiple real-time bidding strategies, the bid of the current real-time bidding strategy is higher than the bid of the historical bidding strategy, and the bidding conditions of the current real-time bidding strategy are fewer than the bidding conditions of the historical bidding strategy, and the historical bidding strategy is any real-time bidding strategy among the multiple real-time bidding strategies adopted before the current time or the preconfigured default bidding strategy.

5. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images