Methods for determining funding, equipment, and storage media for multimedia content distribution.

Abstract

This invention relates to a method, apparatus, and storage medium for determining the investment for multimedia content delivery. The method includes: acquiring expected resource consumption information for multimedia content within a target time period; determining investment adjustment parameters for the multimedia content in the i-th time window based on expected and actual resource consumption information within time windows preceding the i-th time window out of n time windows; and determining the actual investment for the multimedia content in the i-th time window based on the initial investment and the investment adjustment parameters. Because this invention considers factors such as actual and expected resource consumption information during the determination of actual investment, the actual investment is set more accurately, reducing the probability of incomplete consumption and exceeding limits, thus improving the accuracy of budget control.

Description

Technical Field

[0001] This invention relates to the field of Internet technology, and in particular to a method, device, and storage medium for determining the investment in the delivery of multimedia content. Background Technology

[0002] Currently, more and more advertisers are choosing to place ads on internet platforms. When placing ads, in order to maximize the advertiser's return on investment (ROI), it is necessary to set reasonable prices for the ads.

[0003] In related technologies, advertisers set the placement price for their ads, which is then sent to the ad delivery system. The ad delivery system sorts the ads in the ad pool, taking placement price as a factor in the sorting process, and selects the ads with the highest potential revenue for placement.

[0004] Setting a fixed price for an ad before it is actually run is inaccurate and can affect the accuracy of budget control. Summary of the Invention

[0005] This invention provides a method, device, and storage medium for determining the investment in multimedia content delivery, which can be used to solve the problem that the method of setting advertising delivery prices in related technologies is not accurate enough, thus affecting the accuracy of budget control.

[0006] On one hand, embodiments of the present invention provide a method for determining the investment in multimedia content delivery, applied in a computer device, the method comprising:

[0007] Obtain the expected resource consumption information of multimedia content within a target time period. The expected resource consumption information is used to indicate the resource consumption situation obtained according to the expected delivery plan of the multimedia content. The target time period includes n time windows, where n is an integer greater than 1.

[0008] Based on the expected and actual resource consumption information of the multimedia content within the time window preceding the i-th time window in the n time windows, the investment adjustment parameters of the multimedia content within the i-th time window are determined; wherein, the actual resource consumption information is used to indicate the resource consumption situation statistically calculated based on the actual deployment of the multimedia content, and i is an integer greater than 1 and less than or equal to n;

[0009] Based on the initial investment in the multimedia content and the investment adjustment parameters of the multimedia content within the i-th time window, the actual investment in the multimedia content within the i-th time window is determined.

[0010] On the other hand, embodiments of the present invention provide a device for determining the investment in the delivery of multimedia content, applied in a computer device, the device comprising:

[0011] The information acquisition module is used to acquire the expected resource consumption information of multimedia content within a target time period. The expected resource consumption information is used to indicate the resource consumption situation obtained according to the expected delivery plan of the multimedia content. The target time period includes n time windows, where n is an integer greater than 1.

[0012] The parameter determination module is used to determine the investment adjustment parameters of the multimedia content in the i-th time window based on the expected resource consumption information and the actual resource consumption information of the multimedia content in the time window before the i-th time window in the n time windows; wherein, the actual resource consumption information is used to indicate the resource consumption situation statistically calculated based on the actual deployment of the multimedia content, and i is an integer greater than 1 and less than or equal to n;

[0013] The investment determination module is used to determine the actual investment of the multimedia content in the i-th time window based on the initial investment of the multimedia content and the investment adjustment parameters of the multimedia content in the i-th time window.

[0014] In another aspect, embodiments of the present invention provide a computer device, the computer device including a processor and a memory, the memory storing at least one instruction, at least one program, code set or instruction set, the at least one instruction, the at least one program, the code set or instruction set being loaded and executed by the processor to implement the method for determining the delivery investment of multimedia content as described above.

[0015] In another aspect, embodiments of the present invention provide a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the method for determining the delivery funding of multimedia content as described above.

[0016] In another aspect, a computer program product is provided, which, when executed, is used to determine the method for investing in the delivery of multimedia content as described above.

[0017] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0018] By analyzing the expected resource consumption information of multimedia content during its delivery period and the actual resource consumption information from the start of delivery to the present, the actual delivery investment for the multimedia content in the next time window is determined. Because the determination of the actual delivery investment considers factors such as actual and expected resource consumption information, the set actual delivery investment is more accurate. Furthermore, this method of determining the actual delivery investment ensures that the total budget for the multimedia content during the aforementioned delivery period is as close as possible to the actual expenditure, reducing the probability of unused resources and exceeding budget limits, thereby improving the accuracy of budget control. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of an implementation environment provided in one embodiment of the present invention;

[0020] Figure 2 This is a schematic diagram illustrating a method for determining the investment in multimedia content delivery according to an embodiment of the present invention;

[0021] Figure 3 This is a flowchart of a method for determining the investment in multimedia content delivery according to an embodiment of the present invention;

[0022] Figure 4 This is a schematic diagram of the delivery interface provided in one embodiment of the present invention;

[0023] Figure 5 This is a schematic diagram of the expected resource consumption curve provided in one embodiment of the present invention;

[0024] Figure 6 This is a schematic diagram illustrating the delivery of multimedia content according to an embodiment of the present invention;

[0025] Figure 7 This is a block diagram of a multimedia content delivery funding determination device provided in an embodiment of the present invention;

[0026] Figure 8 This is a block diagram of a multimedia content delivery funding determination device provided in another embodiment of the present invention;

[0027] Figure 9 This is a schematic diagram of a computer device provided in one embodiment of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0029] Before describing the embodiments of the present invention, the relevant terms involved in the embodiments of the present invention will be introduced.

[0030] Budget control: By controlling the spending parameters of advertising, the spending rate of the budget can be controlled to reduce the probability of exceeding the limit and to achieve the goal of smooth playback.

[0031] Inexhaustible: The total budget is not fully spent due to budget control, but could be spent if budget control were not implemented.

[0032] Real cost: The actual amount deducted, which is the amount actually deducted by the billing side.

[0033] Discount cost: The expected deduction amount, specifically the amount to be deducted after the initial pricing during the fine-tuning stage, and then discounted according to business logic.

[0034] Exceeding the limit: The difference between the amount deducted and the amount actually deducted, representing the loss incurred due to the exhaustion of the available budget without timely cessation of playback.

[0035] Pctr: The probability of an ad being clicked after it has been displayed, based on factors such as the ad's characteristics, user characteristics, and context.

[0036] Please refer to Figure 1 The diagram illustrates an implementation environment provided by an embodiment of the present invention. This implementation environment may include: a server 11, at least one first terminal 12, and at least one second terminal 13.

[0037] Server 11 has the function of determining the investment for multimedia content delivery. Optionally, server 11 is a server in an advertising delivery system. Optionally, server 11 also has the function of data interaction with other devices, for example, server 11 delivers multimedia content to second terminal 13, or server 11 receives information from first terminal 12 regarding the expected resource consumption of multimedia content within a target time period. Optionally, server 11 also has the function of sorting multimedia content.

[0038] Server 11 can be a single server, a server cluster consisting of multiple servers, or a cloud computing service center. In a specific example, when server 11 is in a cluster architecture, server 11 includes a budget control server, a sorting server, a first interaction server, and a second interaction server. The budget control server is used to determine the funding for multimedia content delivery; the sorting server is used to sort the multimedia content; the first interaction server is used to implement data interaction with the first terminal 12; and the second interaction server is used to implement data interaction with the second terminal 13.

[0039] The first terminal 12 has the function of interacting with the server 11, for example, sending information about the expected resource consumption of multimedia content within a target time period to the server 11. Optionally, the first terminal 12 is a terminal belonging to the provider of the multimedia content. In one possible implementation, the first terminal 12 has a browser installed, through which the multimedia content provider accesses the server 11; in another possible implementation, the first terminal 12 runs a first application for providing multimedia content delivery services, through which the multimedia content provider accesses the server 11. The first terminal 12 can be an electronic device such as a mobile phone, tablet computer, e-book reader, multimedia playback device, wearable device, or laptop computer.

[0040] The second terminal 13 also has the function of interacting with the server 11, for example, receiving multimedia content delivered by the server 11. Optionally, the second terminal 13 also has a multimedia content display function. Optionally, the second terminal 13 has a second application installed, which is used to implement the multimedia content display function. The second application can be a social application, a video application, etc. The second terminal 13 can be an electronic device such as a mobile phone, tablet computer, e-book reader, multimedia playback device, wearable device, or laptop computer.

[0041] A communication connection is established between the first terminal 12 and the server 11, and a communication connection is also established between the second terminal 13 and the server 11. The above communication connections can be established based on a wired network or a wireless network.

[0042] The technical solution provided by this invention determines the actual investment for multimedia content in the next time window by considering the expected resource consumption information during the delivery period and the actual resource consumption information from the start of delivery to the present. Because the determination of actual investment considers factors such as actual and expected resource consumption information, the set actual investment is more accurate. Furthermore, the above method for determining actual investment can make the total budget and actual expenditure of multimedia content during the delivery period as close as possible, reducing the probability of incomplete consumption and exceeding budget limits, thereby improving the accuracy of budget control.

[0043] The technical solution provided by this invention can be applied to advertising placement tasks. The following explanation uses the application of this technical solution to placing advertisements on video playback websites as an example.

[0044] Each advertiser submits their total budget for the advertising campaign to the ad delivery system before the campaign period begins. The ad delivery system first sets the budget for the first time window based on this total budget and the historical performance of the ad. Then, at the end of the first time window, the system updates the budget for the next time window based on the previous actual spending and the total budget. When a user triggers an ad display request from their device (e.g., clicking to enter a video playback website or clicking to play a video), the ad delivery system sorts the ads in the ad pool and pushes the top-ranked ad (or the top m ads) to the user's device. The ad delivery budget is one of the factors that the ad delivery system considers when sorting ads.

[0045] In a specific example, referring to the reference Figure 2 The advertiser's terminal sends an ad delivery request to the first interaction server in the advertising system. This request carries relevant information about the ad to be delivered, such as ad content, delivery time, total budget, and delivery mode. The first interaction server forwards this information to the budget control server, which calculates the actual delivery cost of the ad using the technical solution provided in this invention. The budget control server then stores the calculated actual delivery cost in the ad pool. When the user terminal sends an ad display request to the second interaction server, the second interaction server forwards the request to the sorting server. The sorting server retrieves the actual delivery cost of each ad from the ad pool and sorts them using the PCTR and the user terminal's corresponding personal information to obtain the ads to be displayed. The sorting server then sends the ads to be displayed to the second interaction server, which returns the ads to be displayed to the user terminal. The second interaction server can also return the delivery results to the budget control server so that the budget control server can adjust the actual delivery cost of each ad. These delivery results may include whether the user viewed the ad, the viewing duration, and whether the user clicked the ad.

[0046] Please refer to Figure 3 It illustrates a flowchart of a method for determining the investment in multimedia content delivery according to an embodiment of the present invention. This method can be applied to computer devices, for example... Figure 1 In the server of the implementation environment shown, the method may include the following steps:

[0047] Step 301: Obtain information on the expected resource consumption of multimedia content within the target time period.

[0048] In this embodiment of the invention, multimedia content can be multimedia information such as video, audio, and images. In a typical application scenario, the multimedia content is an advertisement. The advertisement is content that promotes a product or service. The advertisement can be in the form of text, images, audio, video, etc., and this embodiment of the invention does not limit the form.

[0049] The target time period includes n time windows, where n is an integer greater than 1. The target time period is the time period during which multimedia content is delivered. If the current time falls within the target time period, the user has a certain probability of watching the multimedia content through a certain channel, such as watching it on a multimedia content display platform on a second terminal. The target time period can be one day, one week, one month, etc., and this embodiment of the invention does not limit this. In this embodiment, only a one-day target time period is used as an example for explanation.

[0050] The n time windows are obtained by dividing the target time period. The length of each time window can be the same or different. In this embodiment of the invention, only the example of all time windows having the same length is described. In addition, the length of a time window can be set according to the actual needs of controlling the investment in the distribution of multimedia content; for example, the length of a time window is 5 minutes.

[0051] The anticipated resource consumption information is used to indicate the resource consumption based on the anticipated delivery plan of the multimedia content. The anticipated delivery plan refers to the expected delivery situation of the multimedia content provider. For example, the anticipated delivery plan could mean that the resources consumed by the multimedia content during the target time period are smoothly distributed throughout the target time period; another example is that the anticipated delivery plan could mean that the total budget of the multimedia content during the target time period is consumed as quickly as possible, but the value indicated by the actual resource consumption information of the multimedia content during the target time period should not exceed the aforementioned total budget. Furthermore, in this embodiment of the invention, the consumed resources can be virtual items, monetary amounts, etc., and this embodiment of the invention does not limit this.

[0052] Optionally, step 301 may include the following two sub-steps:

[0053] Step 301a: Obtain the multimedia content delivery pattern within the target time period;

[0054] The aforementioned delivery modes are used to indicate the overall trend of multimedia content delivery within a target time period. Delivery modes include a uniform delivery mode and a rapid delivery mode. When the expected delivery plan is that the resources consumed by multimedia content within the target time period can be smoothly distributed throughout the entire target time period, the multimedia content provider can choose the uniform delivery mode; when the expected delivery plan is that the total budget for multimedia content within the target time period can be consumed as quickly as possible, but the actual resource consumption information of the multimedia content within the target time period does not exceed the aforementioned total budget, the multimedia content provider can choose the rapid delivery mode.

[0055] Optionally, the first terminal displays a delivery interface, which includes two options: a uniform delivery mode and a fast delivery mode. The first terminal receives a selection signal corresponding to any option, and after receiving a confirmation instruction, sends the selected option to the server. The selected option is the delivery mode of the multimedia content during the target time period.

[0056] Reference Figure 4 The diagram illustrates a delivery interface 41 provided in an exemplary embodiment of the present invention. The delivery interface 41 includes a constant speed delivery mode option 411, an accelerated delivery mode option 412, and a confirmation button 413.

[0057] In addition, the server can obtain the multimedia content delivery pattern during the target time period before the target time period, or it can obtain the multimedia content delivery pattern during the target time period during the target time period. This embodiment of the invention does not limit the timing of obtaining the multimedia content delivery pattern during the target time period.

[0058] Step 301b: Determine the expected delivery plan for multimedia content during the target time period based on the delivery mode.

[0059] The expected delivery plan is determined based on at least one of the following: traffic, conversion rate, and time. The expected delivery plan can be determined by the server based on previously statistically derived delivery demands. For example, when the goal is for multimedia content to be viewed by more users, the expected delivery plan can be determined based on traffic; similarly, when the goal is for multimedia content to achieve better conversion rates, the expected delivery plan can be determined based on actual conversion results. In other possible implementations, the expected delivery plan can also be determined by the multimedia content provider.

[0060] When the expected delivery plan is determined based on traffic, the server can directly determine the traffic distribution curve within the target time period as the expected resource consumption curve for the multimedia content within the target time period. When the expected delivery plan is determined based on conversion results, the server can directly determine the conversion result curve within the target time period as the expected resource consumption curve for the multimedia content within the target time period.

[0061] Step 301c: Based on the expected delivery plan, plot the expected resource consumption curve of the multimedia content within the target time period, where the expected resource consumption curve is the expected resource consumption information.

[0062] In this embodiment of the invention, the expected resource consumption information of multimedia content within a target time period can be represented by an expected resource consumption curve. This expected resource consumption curve is used to represent the relationship between the planned investment and time for multimedia content delivery within the target time period. (Refer to the reference...) Figure 5 This diagram illustrates a projected resource consumption curve provided by an embodiment of the present invention. The projected resource consumption curve represents the correspondence between planned investment and time for multimedia content delivery within a day.

[0063] Step 302: Based on the expected resource consumption information and actual resource consumption information of the multimedia content in the time window before the i-th time window out of n time windows, determine the investment adjustment parameters of the multimedia content in the i-th time window, where i is an integer greater than 1 and less than or equal to n.

[0064] The expected resource consumption information includes the expected expenditure amount. Optionally, the expected expenditure amount can be calculated based on the expected resource consumption curve and time. The actual resource consumption information is used to indicate the resource consumption statistics based on the actual delivery of multimedia content. Optionally, the actual resource consumption information includes the actual expenditure amount. The investment adjustment parameter for multimedia content in the i-th time window is used to adjust the planned delivery investment in the i-th time window to determine the actual delivery investment of multimedia content in the i-th time window.

[0065] The investment adjustment parameters for multimedia content within the i-th time window can be determined based on the adjustment control parameters for multimedia content within the i-th time window. These adjustment control parameters are then controlled using a proportional-integral-derivative (PID) control algorithm.

[0066] PID control is a control method that corrects based on the output feedback of the controlled object. In this embodiment of the invention, the PID control algorithm is used to fit the actual investment in multimedia content delivery within each time window with the expected resource consumption curve of the multimedia content within the target time period. This allows the expected resource consumption information and actual resource consumption information of the multimedia content within the aforementioned delivery period to be as close as possible. This reduces the probability of the total budget not being fully spent within the delivery period, and also reduces the probability of the actual expenditure exceeding the total budget within the delivery period, thus effectively controlling the budget.

[0067] Adjusting the control coefficients includes proportional control parameters, integral control parameters, and derivative control parameters. The proportional control parameter is used to regulate the actual investment to better approximate the expected resource consumption curve, that is, to make the value indicated by the expected resource consumption information within a certain time window closer to the value indicated by the actual resource consumption information within that time window. The integral control parameter is used to control the value indicated by the expected resource consumption information from the start of multimedia content deployment to the present, making it closer to the value indicated by the actual resource consumption information within that time window. The derivative control parameter is the rate of change of the proportional control parameter, preventing excessive fluctuations in actual investment.

[0068] Optionally, step 302 can be specifically implemented as follows: calculating the funding adjustment parameter pacing_rate for the multimedia content in the i-th time window according to the following formula:

[0069] pacing_rate=α×p_error+β×i_error+γ×d_error+1;

[0070] Where α, β, and γ are preset weighting coefficients, p_error represents the proportional control parameter of the multimedia content in the i-th time window, i_error represents the integral control parameter of the multimedia content in the i-th time window, and d_error represents the derivative control parameter of the multimedia content in the i-th time window.

[0071] In addition, the investment adjustment parameters for multimedia content in the first time window can be calculated as follows: Based on the expected resource consumption information of the multimedia content in the target period and the historical resource consumption information of the multimedia content, the investment adjustment parameters for the multimedia content in the first time window are determined.

[0072] The expected resource consumption information for multimedia content within the target time period also includes the total budget for the multimedia content within the target time period, which is usually set by the multimedia content provider. For example, the expected resource consumption information for multimedia content within the target period might be a budget of 100 yuan for one day of multimedia content delivery. The budget adjustment parameters for multimedia content in the first time window are positively correlated with the total budget for multimedia content within the target time period. Optionally, the larger the total budget for multimedia content within the target time period, the larger the budget adjustment parameters for multimedia content within the first time window; conversely, the smaller the total budget for multimedia content within the target time period, the smaller the budget adjustment parameters for multimedia content within the first time window.

[0073] Historical resource consumption information is used to indicate resource consumption statistics based on the historical delivery of multimedia content. Optionally, when historical resource consumption information indicates that the multimedia content consumes resources quickly, the investment adjustment parameters for the multimedia content in the first time window are set to be smaller; when historical resource consumption information indicates that the multimedia content consumes resources slowly, the investment adjustment parameters for the multimedia content in the first time window are set to be larger.

[0074] Step 303: Determine the actual investment of the multimedia content in the i-th time window based on the initial investment and the investment adjustment parameters of the multimedia content in the i-th time window.

[0075] The initial deployment cost of multimedia content refers to the resources that an entity plans to consume when deploying multimedia content, which is usually set by the multimedia content provider. The initial deployment cost of multimedia content can be the resources planned to be consumed when the multimedia content is clicked once; it can also be the resources planned to be consumed when the multimedia content is displayed once. This embodiment of the invention does not limit this.

[0076] The actual deployment cost of multimedia content within the i-th time window refers to the resources actually consumed by a unit when deploying multimedia content within the i-th time window. Optionally, the above-mentioned actual deployment cost is the actual deployment unit price. The actual deployment unit price of multimedia content within the i-th time window can be the resources actually consumed when the multimedia content is clicked once within the i-th time window; it can also be the resources actually consumed when the multimedia content is displayed once within the i-th time window. This embodiment of the invention does not limit this.

[0077] In this embodiment of the invention, the server dynamically adjusts the actual investment of multimedia content in different time windows based on the initial investment and the investment adjustment parameters of multimedia content in different time windows.

[0078] Optionally, when the investment adjustment parameter is an investment discount coefficient, step 203 is specifically implemented as follows: multiply the initial investment of the multimedia content by the investment discount coefficient of the multimedia content in the i-th time window to obtain the actual investment of the multimedia content in the i-th time window. The actual investment real_bid can be expressed by the following formula:

[0079] real_bid = pacing_rate * bid;

[0080] Here, pacing_rate refers to the discount factor for investment in multimedia content within the i-th time window; bid is the initial investment for multimedia content.

[0081] For example, if the initial investment in multimedia content is 5 yuan, and the investment discount factor for multimedia content in the i-th time window is 0.8, then the actual investment in multimedia content in the i-th time window is 4 yuan.

[0082] The technical solution provided by this invention determines the actual investment for multimedia content in the next time window by considering the expected resource consumption information during the delivery period and the actual resource consumption information from the start of delivery to the present. Because the determination of actual investment considers factors such as actual and expected resource consumption information, the set actual investment is more accurate. Furthermore, the above method for determining actual investment can make the total budget and actual expenditure of multimedia content during the delivery period as close as possible, reducing the probability of incomplete consumption and exceeding budget limits, thereby improving the accuracy of budget control.

[0083] In addition, the expected delivery plan for multimedia content during the delivery period is determined based on traffic, thereby increasing the exposure probability of multimedia content when traffic is high, and increasing the probability of multimedia content being viewed or clicked; furthermore, the expected delivery plan for multimedia content during the delivery period is determined based on conversion results, thereby increasing the exposure probability of multimedia content when conversion results are good, and improving the conversion effect of multimedia content.

[0084] As described in the examples above, the control parameters to be adjusted include proportional control parameters, integral control parameters, and derivative control coefficients. The calculation process for each of these three types of control parameters will be explained below.

[0085] 1. Proportional control parameters.

[0086] The calculation process for proportional control parameters may include the following steps:

[0087] Step 401: Determine the first consumption deviation information based on the expected resource consumption information of the multimedia content in the (i-1)th time window out of n time windows, and the actual resource consumption information of the multimedia content in the (i-1)th time window out of n time windows.

[0088] The expected resource consumption information of multimedia content within the (i-1)th time window out of n time windows can be calculated based on the expected resource consumption curve of the multimedia content within the target time period. Specifically, the server calculates the first area enclosed by the first straight line, the second straight line, and the expected resource consumption curve, and then multiplies the first area by the total budget of the multimedia content within the target time period to determine the expected resource consumption information of the multimedia content within the (i-1)th time window out of n time windows. The first straight line is perpendicular to the horizontal axis, and the x-coordinate of its intersection with the horizontal axis is the start timestamp of the (i-1)th time window. The second straight line is perpendicular to the horizontal axis, and the x-coordinate of its intersection with the horizontal axis is the end timestamp of the (i-1)th time window.

[0089] In a specific example, the value min_goal_cost, indicated by the expected resource consumption information of multimedia content within the (i-1)th time window out of n time windows, can be calculated using the following formula:

[0090]

[0091] Where total_budget refers to the total budget of multimedia content within the target time period, t is the current time, window is the length of the time window, T is the length of the target time period, and b(t) represents the expected resource consumption curve of multimedia content within the target time period.

[0092] The actual resource consumption information of multimedia content within the (i-1)th time window can be obtained by the server based on the actual investment in the multimedia content during that time window. For example, if the actual investment in the multimedia content during the (i-1)th time window is 5 yuan per click, and the multimedia content is clicked 12 times during that time window, then the actual resource consumption information of the multimedia content during the (i-1)th time window indicates a value of 5 * 12 = 60 yuan.

[0093] The first consumption deviation information is used to indicate the difference between the actual resource consumption of the multimedia content and the expected resource consumption in the (i-1)th time window. This difference is also the difference between the value indicated by the expected resource consumption information of the multimedia content in the (i-1)th time window and the value indicated by the actual resource consumption information of the multimedia content in the (i-1)th time window.

[0094] Step 402: Based on the first consumption deviation information, determine the proportional control parameters of the multimedia content within the i-th time window.

[0095] Optionally, the server determines the ratio between the value indicated by the first consumption deviation information and the total budget of the multimedia content within the target time period as the proportional control parameter of the multimedia content in the i-th time window. In this embodiment of the invention, after calculating the value indicated by the resource consumption deviation information of the multimedia content in the (i-1)-th time window, it is normalized by the total budget of the multimedia content within the target time period, thereby reducing the amount of computation.

[0096] In a specific example, the integral control parameter P_error of the multimedia content within the i-th time window can be expressed by the following formula:

[0097]

[0098] Where, real_cost window This refers to the actual resource consumption of multimedia content within the (i-1)th time window; real_cost window -min_goal_cost refers to the value indicated by the first consumption deviation information.

[0099] 2. Integral control parameters

[0100] The calculation process for integral control parameters may include the following two steps:

[0101] Step 403: Determine the second consumption deviation information based on the expected resource consumption information of the multimedia content within the first time window to the (i-1)th time window, and the actual resource consumption information of the multimedia content within the first time window to the (i-1)th time window.

[0102] The expected resource consumption information of the multimedia content within the first to (i-1)th time windows can be calculated based on the expected resource consumption curve of the multimedia content within the target time period. Specifically, the server calculates the second area enclosed by the second and third straight lines and the aforementioned expected resource consumption curve. Then, the product of this second area and the total budget of the multimedia content within the target time period is determined as the expected resource consumption information of the multimedia content within the first to (i-1)th time windows. The second straight line is a straight line composed of points whose horizontal coordinates are the end timestamps of the (i-1)th time window, and the third straight line is a straight line composed of points whose horizontal coordinates are the start timestamps of the first time window.

[0103] In a specific example, the value Pre_expect_cost, indicated by the expected resource consumption information of multimedia content within the first to (i-1)th time windows, can be calculated using the following formula:

[0104]

[0105] Where total_budget refers to the total budget for multimedia content within the target time period; b(t) refers to the expected resource consumption curve for multimedia content within the target time period.

[0106] The values ​​indicated by the actual resource consumption information of multimedia content within the first to the (i-1)th time windows can be obtained by the server based on the actual deployment investment of multimedia content within the first to the (i-1)th time windows.

[0107] The second consumption deviation information is used to indicate the difference between the actual resource consumption and the expected resource consumption of the multimedia content within the first to (i-1)th time windows. This difference is also the difference between the value indicated by the expected resource consumption information of the multimedia content within the first to (i-1)th time windows and the value indicated by the actual resource consumption information of the multimedia content within the first to (i-1)th time windows.

[0108] Step 404: Determine the integral control parameters of the multimedia content within the i-th time window based on the second consumption deviation information.

[0109] Optionally, the server determines the ratio between the value indicated by the second consumption deviation information and the total budget of the multimedia content within the target time period as the proportional control parameter of the multimedia content in the i-th time window. In this embodiment of the invention, after calculating the value indicated by the resource consumption deviation information of the multimedia content from the first time window to the (i-1)-th time window, it is normalized by the total budget of the multimedia content within the target time period, thereby reducing the amount of computation.

[0110] In a specific example, the integral control parameter I_error of the multimedia content within the i-th time window can be expressed by the following formula:

[0111]

[0112] Where, real_cost t Real_cost refers to the actual resource consumption of multimedia content within the first to (i-1)th time windows. t -pre_expect_cost refers to the value indicated by the second consumption deviation information.

[0113] 3. Differential control parameters.

[0114] The calculation process for differential control parameters may include the following steps:

[0115] Step 405: The difference between the proportional control parameter of the multimedia content in the i-th time window and the proportional control parameter of the multimedia content in the (i-1)-th time window is determined as the differential control parameter of the multimedia content in the i-th time window.

[0116] In a specific example, the differential control parameter D_error of the multimedia content in the i-th time window can be represented by the following formula:

[0117] D_error=p_error i -p_error i-1 ;

[0118] Among them, p_error i This refers to the proportional control parameter of multimedia content within the i-th time window.

[0119] p_error i-1 This refers to the proportional control parameter of multimedia content within the (i-1)th time window.

[0120] Among them, the proportional control parameter p_error of multimedia content within the (i-1)th time window. i-1 The calculation process is as follows: Based on the expected resource consumption information of the multimedia content in the (i-2)th time window out of n time windows, and the actual resource consumption information of the multimedia content in the (i-2)th time window, the resource consumption deviation information of the multimedia content in the (i-2)th time window is determined. The resource consumption deviation information is used to indicate the difference between the actual resource consumption and the expected resource consumption. Based on the resource consumption deviation information of the multimedia content in the (i-2)th time window, the proportional control parameter of the multimedia content in the (i-1)th time window is determined.

[0121] Optionally, after determining the adjustment control parameters of the multimedia content within the i-th time window, it is also necessary to adjust the above adjustment control parameters. The adjustment process is as follows: compare the magnitude relationship between the adjustment control parameters and the first threshold and the second threshold. Both the first threshold and the second threshold can be set according to actual adjustment needs, and this embodiment of the invention does not limit this. The first threshold is less than the second threshold;

[0122] If the adjusted control parameter is less than the first threshold, then the first threshold is determined as the adjusted control parameter. If the adjusted control parameter is greater than the second threshold, then the second threshold is determined as the adjusted control parameter. If the adjusted control parameter is greater than or equal to the first threshold and less than or equal to the second threshold, then no adjustment is needed. For example, the first threshold is 0.8 and the second threshold is 1.5. When the adjusted control parameter is 0.7, it is adjusted to 0.8; when the adjusted control parameter is 1.6, it is adjusted to 1.5; when the adjusted control parameter is 1.1, no adjustment is needed.

[0123] Furthermore, as mentioned in the above embodiments, the adjustment control coefficients include proportional control parameters, integral control parameters, and derivative control coefficients. The first threshold and second threshold corresponding to different adjustment control coefficients may be the same or different, and can be set according to actual needs; this embodiment of the invention does not impose such limitations.

[0124] In related technologies, the server first calculates the exposure probability of each multimedia content, then filters it based on the exposure probability, removing multimedia content with low exposure probabilities. The remaining multimedia content is then sorted, and the content with higher ranking positions is delivered. Because some multimedia content is filtered before sorting, the number of multimedia content items during sorting is reduced, thus shortening the competition queue length and reducing competition.

[0125] In this embodiment of the invention, the process of the server delivering multimedia content is as follows:

[0126] Step 501: Generate a delivery queue based on the actual delivery investment of multimedia content in the i-th time window and the actual delivery investment of at least one other multimedia content in the i-th time window.

[0127] The delivery queue includes multimedia content and at least one other multimedia content.

[0128] Optionally, step 501 may include the following sub-steps:

[0129] Step 501a: Determine the expected revenue of the multimedia content in the i-th time window based on the actual investment in the multimedia content within the i-th time window and the first expected click-through rate.

[0130] The first expected click-through rate (Pctr) indicates the probability that multimedia content will be clicked within the i-th time window. The expected revenue is determined based on the actual investment in the multimedia content and the actual Pctr. Specifically, the server determines the revenue of the multimedia content within the i-th time window by multiplying the actual investment in the multimedia content within the i-th time window by Pctr. Pctr indicates the probability that the multimedia content will be clicked. For example, if the actual investment in the multimedia content within the i-th time window is 5 yuan per click, and the Pctr for the multimedia content within the i-th time window is 0.8, then the revenue of the multimedia content within the i-th time window is 4 yuan per click.

[0131] Step 501b: Determine the expected revenue of at least one other multimedia content in the i-th time window based on the actual investment in the i-th time window and the second expected click-through rate.

[0132] The second expected click-through rate is used to indicate the probability that at least one other multimedia content will be clicked within the i-th time window.

[0133] Step 501c: Generate a delivery queue based on the expected revenue of the multimedia content in the i-th time window and the expected revenue of at least one other multimedia content in the i-th time window.

[0134] Optionally, the server ranks the multimedia content into a delivery queue based on the revenue generated by the multimedia content within the i-th time window and the revenue generated by at least one other multimedia content within the i-th time window. Specifically, the higher the revenue generated by a multimedia content within the i-th time window, the higher its position in the delivery queue; conversely, the lower the revenue generated, the lower its position. By combining the actual investment in multimedia content delivery with the PCTR for sorting, the revenue of the platform delivering the multimedia content can be optimized.

[0135] In other possible examples, the generation of the delivery queue also needs to consider other factors, such as the personal information and interests of the user sending the multimedia content display request, etc., which are not limited in this embodiment of the invention. In addition, the server can generate the delivery queue after calculating the actual delivery investment of each multimedia content in the i-th time window, or it can generate the delivery queue when it receives the multimedia content display request sent by the user terminal. The timing of the generation of the delivery queue is not limited in this embodiment of the invention.

[0136] Step 502: Select the multimedia content to be delivered according to the delivery queue.

[0137] Multimedia content located at different positions in the delivery queue has varying probabilities of being selected for delivery. Optionally, multimedia content located earlier in the queue has a higher probability of being selected for delivery, while multimedia content located later in the queue has a lower probability of being selected for delivery.

[0138] Optionally, the server determines the first item in the delivery queue as the multimedia content to be delivered. Optionally, the server determines the first m items in the delivery queue as the multimedia content to be delivered, where m is a positive integer; where m can be determined according to the required number of multimedia content to be displayed, and this embodiment of the invention does not limit this.

[0139] After selecting the multimedia content to be displayed, the server sends the selected multimedia content to other devices (such as the terminal that sent the multimedia content display request), so that the other devices can display the multimedia content.

[0140] It should be noted that the technical solution provided by the embodiments of the present invention has a positive impact on both platforms and providers of multimedia content. Experimental data shows that, by adopting the technical solution provided by the embodiments of the present invention, for platforms delivering multimedia content, the filtering of multimedia content is avoided, thus increasing the length of the competition queue. This results in an increase in the length of the competition queue under different traffic levels, ranging from 5% to 12%, leading to an overall revenue increase of 0.5%. For providers of multimedia content, the actual investment in multimedia content delivery is significantly reduced, with an overall decrease of 1.9%. Furthermore, for cost-per-click (CPC) ads, the CPC decreases by 4.3%, and the click-through rate (CTR) increases by 4.1%. This improves delivery effectiveness while reducing delivery costs.

[0141] In a specific example, referring to the reference Figure 6 This diagram illustrates a multimedia content delivery method according to an embodiment of the present invention. The advertising delivery system performs offline calculations based on real-time feedback data and other input data to obtain the pacing rate for each advertisement. Then, based on the pacing rate of each advertisement, it calculates the actual investment for each advertisement and delivers the advertisements according to the actual investment. The real-time feedback data refers to the actual resource consumption information of an advertisement from the start of its delivery to the present. The other input data refers to the expected resource consumption information of the advertisement within the target time period. The pacing rate of the advertisement is also the investment adjustment parameter for that advertisement.

[0142] In summary, the technical solution provided by the embodiments of the present invention delivers subsequent multimedia content by dynamically adjusting the investment for each multimedia content. Since the dynamically adjusted investment is usually less than the investment set by the multimedia content provider, it can help the multimedia content provider obtain more exposure opportunities at a lower cost, thereby improving ROI and playback effect.

[0143] Furthermore, since multimedia content is not filtered during the sorting process, the competition queue in the embodiments of the present invention is not shortened or the competition is weakened compared to related technologies.

[0144] The following are embodiments of the apparatus of the present invention, which can be used to execute embodiments of the method of the present invention. For details not disclosed in the embodiments of the apparatus of the present invention, please refer to the embodiments of the method of the present invention.

[0145] Please refer to Figure 7 This diagram illustrates a block diagram of a multimedia content delivery funding determination apparatus according to an embodiment of the present invention. This apparatus can be applied to a computer device. The apparatus has the functions described in the method example above; these functions can be implemented in hardware or by hardware executing corresponding software. The apparatus may include:

[0146] The information acquisition module 701 is used to acquire the expected resource consumption information of multimedia content within a target time period. The expected resource consumption information is used to indicate the resource consumption situation obtained according to the expected delivery plan of the multimedia content. The target time period includes n time windows, where n is an integer greater than 1.

[0147] The parameter determination module 702 is used to determine the investment adjustment parameters of the multimedia content in the i-th time window based on the expected resource consumption information and the actual resource consumption information of the multimedia content in the time window before the i-th time window in the n time windows; wherein, the actual resource consumption information is used to indicate the resource consumption situation statistically calculated based on the actual deployment of the multimedia content, and i is an integer greater than 1 and less than or equal to n.

[0148] The investment determination module 703 is used to determine the actual investment of the multimedia content in the i-th time window based on the initial investment of the multimedia content and the investment adjustment parameters of the multimedia content in the i-th time window.

[0149] The technical solution provided by this invention determines the actual investment for multimedia content in the next time window by considering the expected resource consumption information during the delivery period and the actual resource consumption information from the start of delivery to the present. Because the determination of actual investment considers factors such as actual and expected resource consumption information, the set actual investment is more accurate. Furthermore, the above method for determining actual investment can make the total budget and actual expenditure of multimedia content during the delivery period as close as possible, reducing the probability of incomplete consumption and exceeding budget limits, thereby improving the accuracy of budget control.

[0150] Based on Figure 7 In one optional embodiment of the illustrated example, the investment adjustment parameter is an investment discount coefficient; the investment determination module 703 is used to multiply the initial investment of the multimedia content and the investment discount coefficient of the multimedia content in the i-th time window to obtain the actual investment of the multimedia content in the i-th time window.

[0151] Based on Figure 7 In another optional embodiment provided by the illustrated embodiment, the investment adjustment parameter of the multimedia content in the i-th time window is determined according to the adjustment control parameter of the multimedia content in the i-th time window, and the adjustment control parameter is used to control the investment adjustment parameter using a proportional-integral-derivative PID control algorithm.

[0152] Optionally, the parameter determination module 702 is used for:

[0153] Based on the expected and actual resource consumption information of the multimedia content within the time window before the i-th time window in the n time windows, the adjustment control parameters of the multimedia content within the i-th time window are determined. The adjustment control parameters are used to control the investment adjustment parameters using a proportional-integral-derivative PID control algorithm.

[0154] Based on the adjustment control parameters of the multimedia content within the i-th time window, determine the investment adjustment parameters of the multimedia content within the i-th time window.

[0155] Optionally, the adjustment control parameters include proportional control parameters; the parameter determination module 702 is used for:

[0156] Based on the expected resource consumption information of the multimedia content in the (i-1)th time window of the n time windows, and the actual resource consumption information of the multimedia content in the (i-1)th time window, a first consumption deviation information is determined. The first consumption deviation information is used to indicate the difference between the actual resource consumption and the expected resource consumption of the multimedia content in the i-th time window.

[0157] Based on the first consumption deviation information, the proportional control parameters of the multimedia content within the i-th time window are determined.

[0158] Optionally, the adjustment control parameters include integral control parameters; the parameter determination module 702 is used for:

[0159] Based on the expected resource consumption information of the multimedia content within the first time window to the (i-1)th time window, and the actual resource consumption information of the multimedia content within the first time window to the (i-1)th time window, a second consumption deviation information is determined. The second consumption deviation information is used to indicate the difference between the actual resource consumption and the expected resource consumption of the multimedia content within the first time window to the (i-1)th time window.

[0160] Based on the resource consumption deviation information of the multimedia content within the first to (i-1)th time windows, the integral control parameters of the multimedia content within the i-th time window are determined.

[0161] Optionally, the adjustment control parameters include differential control parameters; the parameter determination module 702 is used to determine the difference between the proportional control parameter of the multimedia content in the i-th time window and the proportional control parameter of the multimedia content in the (i-1)-th time window as the differential control parameter of the multimedia content in the i-th time window.

[0162] Optionally, the parameter determination module 702 is used to calculate the funding adjustment parameter pacing_rate of the multimedia content within the i-th time window according to the following formula:

[0163] pacing_rate=α×p_error+β×i_error+γ×d_error+1;

[0164] Wherein, α, β, and γ are preset weighting coefficients, p_error represents the proportional control parameter of the multimedia content in the i-th time window, i_error represents the integral control parameter of the multimedia content in the i-th time window, and d_error represents the derivative control parameter of the multimedia content in the i-th time window.

[0165] Alternatively, please refer to Figure 8 The device further includes a parameter adjustment module 704.

[0166] Parameter adjustment module 704 is used for:

[0167] Compare the magnitude relationship between the adjustment control parameter and the first threshold and the second threshold, wherein the first threshold is smaller than the second threshold;

[0168] If the adjustment control parameter is less than the first threshold, then the first threshold is determined as the adjustment control parameter;

[0169] If the adjustment control parameter is greater than the second threshold, then the second threshold is determined as the adjustment control parameter.

[0170] Based on Figure 7 In another optional embodiment provided by the illustrated embodiment, the information acquisition module 701 is used for:

[0171] Obtain the delivery pattern of the multimedia content during the target time period;

[0172] Based on the delivery mode, the expected delivery plan for the multimedia content during the target time period is determined, and the expected delivery plan is determined based on at least one of the following: traffic, conversion effect, and time;

[0173] Based on the expected delivery plan, a resource consumption curve for the multimedia content is plotted within the target time period, wherein the expected resource consumption curve represents the expected resource consumption information.

[0174] Based on Figure 7 In another alternative embodiment provided by the illustrated example, please refer to Figure 8 The device further includes a queue generation module 705 and a content selection module 706.

[0175] The queue generation module 705 is used to generate a delivery queue based on the actual delivery investment of the multimedia content in the i-th time window and the actual delivery investment of at least one other multimedia content in the i-th time window, wherein the delivery queue includes the multimedia content and the at least one other multimedia content.

[0176] The content selection module 706 is used to select multimedia content to be delivered according to the delivery queue, wherein multimedia content located at different positions in the delivery queue has a different probability of being selected for delivery. Optionally, the queue generation module 708 is used to:

[0177] Based on the actual investment in the multimedia content within the i-th time window and the first expected click-through rate, the expected revenue of the multimedia content within the i-th time window is determined, whereby the first expected click-through rate is used to indicate the probability that the multimedia content will be clicked within the i-th time window.

[0178] Based on the actual investment of the at least one other multimedia content in the i-th time window and the second expected click-through rate, the expected revenue of the at least one other multimedia content in the i-th time window is determined, and the second expected click-through rate is used to indicate the probability that the at least one other multimedia content is clicked in the i-th time window.

[0179] The delivery queue is generated based on the expected revenue of the multimedia content within the i-th time window and the expected revenue of at least one other multimedia content within the i-th time window.

[0180] Based on Figure 7 In another optional embodiment provided by the illustrated embodiment, the parameter determination module 702 is used to determine the investment adjustment parameters of the multimedia content in the first time window based on the expected resource consumption information of the multimedia content in the target time period and the historical resource consumption information of the multimedia content; wherein, the historical resource consumption information is used to indicate the resource consumption situation statistically calculated based on the historical deployment of the multimedia content.

[0181] Please refer to Figure 9 This diagram illustrates the structure of a computer device according to an embodiment of the present invention. The computer device may be a server. This computer device is used to implement the method for determining the investment in multimedia content delivery provided in the above embodiments. Specifically:

[0182] Computer device 900 includes a central processing unit (CPU) 901, a system memory 904 including random access memory (RAM) 902 and read-only memory (ROM) 903, and a system bus 905 connecting the system memory 904 and the CPU 901. Computer device 900 also includes a basic input / output system (I / O system) 906 that facilitates information transfer between various devices within the computer, and a mass storage device 907 for storing the operating system 913, application programs 914, and other program modules 915.

[0183] The basic input / output system 906 includes a display 908 for displaying information and an input device 909 for user input, such as a mouse or keyboard. Both the display 908 and the input device 909 are connected to the central processing unit 901 via an input / output controller 910 connected to the system bus 905. The basic input / output system 906 may also include the input / output controller 910 for receiving and processing input from multiple other devices such as a keyboard, mouse, or electronic stylus. Similarly, the input / output controller 910 also provides output to a display screen, printer, or other types of output devices.

[0184] Mass storage device 907 is connected to central processing unit 901 via a mass storage controller (not shown) connected to system bus 905. Mass storage device 907 and its associated computer-readable media provide non-volatile storage for computer device 900. That is, mass storage device 907 may include computer-readable media (not shown) such as hard disk or CD-ROM drive.

[0185] Without loss of generality, computer-readable media can include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented using any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer storage media include RAM, ROM, EPROM, EEPROM, flash memory or other solid-state storage technologies, CD-ROM, DVD or other optical storage, magnetic tape cassettes, magnetic tape, disk storage, or other magnetic storage devices. Of course, those skilled in the art will recognize that computer storage media are not limited to the above-mentioned types. The system memory 904 and mass storage device 907 described above can be collectively referred to as memory.

[0186] According to various embodiments of the present invention, the computer device 900 can also be connected to a remote computer on a network, such as the Internet. That is, the computer device 900 can be connected to a network 912 via a network interface unit 911 connected to a system bus 905, or the network interface unit 911 can be used to connect to other types of networks or remote computer systems (not shown).

[0187] The memory also includes one or more programs stored in the memory and configured to be executed by one or more processors. The one or more programs contain instructions for performing the method for determining the delivery and distribution of the multimedia content.

[0188] In an exemplary embodiment, a computer-readable storage medium is also provided, the storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor of a computer device to implement the method for determining the delivery funding of multimedia content in the above method embodiments.

[0189] Optionally, the aforementioned computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0190] In an exemplary embodiment, a computer program product is also provided, which, when executed, performs the method for determining the delivery funding of multimedia content as described above.

[0191] It should be understood that "multiple" as used in this document refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship. The terms "first," "second," and similar words used in this document do not indicate any order, quantity, or importance, but are merely used to distinguish different components.

[0192] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0193] The above are merely exemplary embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for delivering multimedia content, characterized in that, When applied in a computer device, the method includes: The multimedia content delivery pattern within a target time period is obtained. The delivery pattern is determined based on the selection operation received on the displayed delivery interface. The delivery pattern is used to indicate the overall trend of the multimedia content delivery within the target time period. The delivery pattern includes a uniform delivery pattern and a fast delivery pattern. The delivery pattern is determined by the multimedia content provider by triggering the corresponding option on the delivery interface. The target time period includes n time windows, where n is an integer greater than 1, and the length of each time window is different. Wherein, when the delivery mode is the uniform delivery mode, the expected delivery plan of the multimedia in the target time period is that the resources consumed by the multimedia content in the target time period can be smoothly distributed throughout the target time period; when the delivery mode is the fast delivery mode, the expected delivery plan is that the total budget of the multimedia content in the target time period can be consumed as soon as possible, and the value indicated by the actual resource consumption information of the multimedia content in the target time period does not exceed the total budget. When the statistically obtained demand requires the multimedia content to be viewed by more users, the expected delivery plan is determined based on traffic according to the delivery mode, and the traffic distribution curve within the target time period is determined as the expected resource consumption curve of the multimedia content within the target time period according to the expected delivery plan; when the statistically obtained demand requires the multimedia content to have a better conversion effect, the expected delivery plan is determined based on conversion effect according to the delivery mode, and the resource conversion effect curve within the target time period is determined as the expected resource consumption curve of the multimedia content within the target time period according to the expected delivery plan; the expected resource consumption curve is used to indicate the expected resource consumption information of the multimedia content within the target time period, and the expected resource consumption curve is used to represent the relationship between the initial delivery investment and time of the multimedia content within the target time period; the initial delivery investment of the multimedia content refers to the planned resources consumed per unit when delivering multimedia content, which is customized by the provider of the multimedia content; Based on the expected resource consumption information of the multimedia content during the target time period and the historical resource consumption information of the multimedia content, the investment adjustment parameters of the multimedia content in the first time window are determined; wherein, the historical resource consumption information is used to indicate the resource consumption situation statistically derived from the historical deployment of the multimedia content, and the resource consumption rate of the multimedia content indicated by the historical resource consumption information is negatively correlated with the investment adjustment parameters of the multimedia content in the first time window; the investment adjustment parameters of the multimedia content in the first time window are positively correlated with the total budget of the multimedia content during the target time period; Based on the expected and actual resource consumption information of the multimedia content within the time window preceding the i-th time window out of the n time windows, the investment adjustment parameters for the multimedia content within the i-th time window are determined, where i is an integer greater than 1 and less than or equal to n. The actual resource consumption information indicates the resource consumption statistics based on the actual deployment of the multimedia content. The investment adjustment parameters for the multimedia content within the i-th time window are used to adjust the initial deployment investment within the i-th time window to determine the actual deployment investment of the multimedia content within the i-th time window. The actual deployment investment of the multimedia content within the i-th time window refers to the actual resources consumed per unit of multimedia content deployment within the i-th time window. The investment adjustment parameter is the investment discount coefficient; the initial investment of the multimedia content and the investment discount coefficient of the multimedia content in the i-th time window are multiplied to obtain the actual investment of the multimedia content in the i-th time window, and the actual investment is less than the initial investment. Based on the relationship between the revenue generated by the multimedia content during the i-th time window and the revenue generated by at least one other multimedia content during the i-th time window, the multimedia content and the at least one other multimedia content are arranged to form a delivery queue. The multimedia content to be delivered is determined by placing the first or first m items in the delivery queue. Here, m is a positive integer. The revenue generated is determined based on the actual investment and the probability of the multimedia content being clicked. The order of the multimedia content and the at least one other multimedia content in the delivery queue is determined based on the revenue generated by each multimedia content and the personal information of the user terminal that sent the multimedia content display request. The multimedia content with the higher the revenue generated is placed earlier in the delivery queue. Selected multimedia content is sent to the user terminal so that the user terminal displays the selected multimedia content and returns the delivery result to the computer device. The delivery result includes at least one of the following: whether the user viewed the delivered multimedia content, the viewing duration, and whether the user clicked on the delivered multimedia content. The actual delivery cost for each multimedia content is adjusted according to the delivery result. The investment adjustment parameters are determined based on the adjustment control parameters, which are used to control the investment adjustment parameters using a proportional-integral-derivative (PID) control algorithm. The PID control algorithm is used to fit the actual investment of the multimedia content in each time window to the expected resource consumption curve of the multimedia content in the target time period. After determining the adjustment control parameters of the multimedia content in the i-th time window, the method further includes: Compare the magnitude relationship between the adjustment control parameter and the first threshold and the second threshold, wherein the first threshold is smaller than the second threshold; If the adjustment control parameter is less than the first threshold, then the first threshold is determined as the adjustment control parameter; if the adjustment control parameter is greater than the second threshold, then the second threshold is determined as the adjustment control parameter; if the adjustment control parameter is greater than or equal to the first threshold and less than or equal to the second threshold, then the adjustment control parameter is not adjusted. The first threshold and the second threshold are different for different adjustment control parameters.

2. The method according to claim 1, characterized in that, The adjustment control parameters include proportional control parameters; the method further includes: Based on the expected resource consumption information of the multimedia content in the (i-1)th time window of the n time windows, and the actual resource consumption information of the multimedia content in the (i-1)th time window, a first consumption deviation information is determined, wherein the first consumption deviation information is used to indicate the difference between the actual resource consumption and the expected resource consumption of the multimedia content in the (i-1)th time window. Based on the first consumption deviation information, the proportional control parameters of the multimedia content within the i-th time window are determined.

3. The method according to claim 1, characterized in that, The adjusted control parameters include integral control parameters; the method further includes: Based on the expected resource consumption information of the multimedia content within the first time window to the (i-1)th time window, and the actual resource consumption information of the multimedia content within the first time window to the (i-1)th time window, a second consumption deviation information is determined, wherein the second consumption deviation information is used to indicate the difference between the actual resource consumption and the expected resource consumption of the multimedia content within the first time window to the (i-1)th time window. Based on the second consumption deviation information, the integral control parameters of the multimedia content within the i-th time window are determined.

4. The method according to claim 1, characterized in that, The adjusted control parameters include derivative control parameters; the method further includes: The difference between the proportional control parameter of the multimedia content in the i-th time window and the proportional control parameter of the multimedia content in the (i-1)-th time window is determined as the differential control parameter of the multimedia content in the i-th time window.

5. The method according to any one of claims 2 to 4, characterized in that, The pacing_rate parameter for adjusting the investment of the multimedia content within the i-th time window is determined according to the following formula: pacing_rate=α×p_error+β×i_error+γ×d_error+1; Wherein, α, β, and γ are preset weighting coefficients, p_error represents the proportional control parameter of the multimedia content in the i-th time window, i_error represents the integral control parameter of the multimedia content in the i-th time window, and d_error represents the derivative control parameter of the multimedia content in the i-th time window.

6. The method according to any one of claims 1 to 4, characterized in that, The method further includes: Based on the actual investment in the multimedia content within the i-th time window and the first expected click-through rate, the expected revenue of the multimedia content within the i-th time window is determined; wherein, the first expected click-through rate is used to indicate the probability that the multimedia content is clicked within the i-th time window; Based on the actual investment in the at least one other multimedia content within the i-th time window and the second expected click-through rate, the expected revenue of the at least one other multimedia content within the i-th time window is determined; wherein, the second expected click-through rate is used to indicate the probability that the at least one other multimedia content is clicked within the i-th time window; The delivery queue is generated based on the expected revenue of the multimedia content within the i-th time window and the expected revenue of at least one other multimedia content within the i-th time window.

7. A multimedia content delivery device, characterized in that, The device, used in computer equipment, includes: An information acquisition module is used to acquire the delivery mode of multimedia content within a target time period. The delivery mode is determined based on a selection operation received on the displayed delivery interface. The delivery mode indicates the overall trend of delivering the multimedia content within the target time period. The delivery mode includes a uniform delivery mode and a fast delivery mode. The delivery mode is determined by the multimedia content provider by triggering the corresponding option on the delivery interface. The target time period includes n time windows, where n is an integer greater than 1, and each time window has a different length. When the delivery mode is the uniform delivery mode, the expected delivery plan for the multimedia content within the target time period is that the resource consumption of the multimedia content within the target time period can be smoothly distributed throughout the entire target time period. When the delivery mode is the fast delivery mode, the expected delivery plan is that the total budget of the multimedia content within the target time period can be consumed as quickly as possible, and the value indicated by the actual resource consumption information of the multimedia content within the target time period does not exceed the total budget. When the statistically obtained demand requires the multimedia content to be viewed by more users, the expected delivery plan is determined based on traffic according to the delivery mode, and the traffic distribution curve within the target time period is determined as the expected resource consumption curve of the multimedia content within the target time period according to the expected delivery plan; when the statistically obtained demand requires the multimedia content to have a better conversion effect, the expected delivery plan is determined based on conversion effect according to the delivery mode, and the resource conversion effect curve within the target time period is determined as the expected resource consumption curve of the multimedia content within the target time period according to the expected delivery plan; the expected resource consumption curve is used to indicate the expected resource consumption information of the multimedia content within the target time period, and the expected resource consumption curve is used to represent the relationship between the initial delivery investment and time of the multimedia content within the target time period; the initial delivery investment of the multimedia content refers to the planned resources consumed per unit when delivering multimedia content, which is customized by the provider of the multimedia content; The parameter determination module is used to determine the investment adjustment parameters of the multimedia content in the first time window based on the expected resource consumption information of the multimedia content in the target time period and the historical resource consumption information of the multimedia content; wherein, the historical resource consumption information is used to indicate the resource consumption situation statistically derived from the historical deployment of the multimedia content, and the resource consumption rate of the multimedia content indicated by the historical resource consumption information is negatively correlated with the investment adjustment parameters of the multimedia content in the first time window; the investment adjustment parameters of the multimedia content in the first time window are positively correlated with the total budget of the multimedia content in the target time period; The parameter determination module is further configured to determine the investment adjustment parameters of the multimedia content in the i-th time window based on the expected resource consumption information and actual resource consumption information of the multimedia content in the time window preceding the i-th time window in the n time windows, where i is an integer greater than 1 and less than or equal to n; wherein, the actual resource consumption information is used to indicate the resource consumption situation statistically calculated based on the actual deployment of the multimedia content; the investment adjustment parameters of the multimedia content in the i-th time window are used to adjust the initial deployment investment in the i-th time window to determine the actual deployment investment of the multimedia content in the i-th time window; the actual deployment investment of the multimedia content in the i-th time window refers to the actual resources consumed per unit of multimedia content deployment in the i-th time window; The investment adjustment parameter is the investment discount coefficient; the investment determination module is used to multiply the initial investment of the multimedia content and the investment discount coefficient of the multimedia content in the i-th time window to obtain the actual investment of the multimedia content in the i-th time window, and the actual investment is less than the initial investment. A queue generation module is used to arrange the multimedia content and the at least one other multimedia content in the i-th time window according to the relationship between the revenue generated by the multimedia content and the revenue generated by at least one other multimedia content in the i-th time window, thereby obtaining a delivery queue. The revenue generated is determined based on the actual investment and the probability of the multimedia content being clicked. The order of the multimedia content and the at least one other multimedia content in the delivery queue is determined based on the revenue generated by each multimedia content and the personal information of the user terminal that sent the multimedia content display request; multimedia content with higher revenue is placed earlier in the delivery queue. The content selection module is used to determine the first or first m items in the delivery queue as the multimedia content to be delivered, where m is a positive integer; A module for performing the following steps: sending selected multimedia content to the user terminal, so that the user terminal displays the selected multimedia content and returns the delivery result to the computer device, the delivery result including at least one of whether the user viewed the delivered multimedia content, the viewing duration, and whether the user clicked on the delivered multimedia content; adjusting the actual delivery cost of each multimedia content according to the delivery result; The investment adjustment parameters are determined based on the adjustment control parameters. The adjustment control parameters are used to control the investment adjustment parameters using a proportional-integral-derivative (PID) control algorithm. The PID control algorithm is used to fit the actual investment of the multimedia content in each time window with the expected resource consumption curve of the multimedia content in the target time period. The device also includes a parameter adjustment module, which is used to: after determining the adjustment control parameters of the multimedia content in the i-th time window, compare the magnitude relationship between the adjustment control parameters and a first threshold and a second threshold, wherein the first threshold is less than the second threshold. If the adjustment control parameter is less than the first threshold, then the first threshold is determined as the adjustment control parameter; if the adjustment control parameter is greater than the second threshold, then the second threshold is determined as the adjustment control parameter; if the adjustment control parameter is greater than or equal to the first threshold and less than or equal to the second threshold, then the adjustment control parameter is not adjusted. The first threshold and the second threshold are different for different adjustment control parameters.

8. The apparatus according to claim 7, characterized in that, The adjustment control parameters include proportional control parameters; the parameter determination module is used for: Based on the expected resource consumption information of the multimedia content in the (i-1)th time window of the n time windows, and the actual resource consumption information of the multimedia content in the (i-1)th time window, a first consumption deviation information is determined, wherein the first consumption deviation information is used to indicate the difference between the actual resource consumption and the expected resource consumption of the multimedia content in the (i-1)th time window. Based on the first consumption deviation information, the proportional control parameters of the multimedia content within the i-th time window are determined.

9. The apparatus according to claim 7, characterized in that, The adjusted control parameters include integral control parameters; the parameter determination module is used for: Based on the expected resource consumption information of the multimedia content within the first time window to the (i-1)th time window, and the actual resource consumption information of the multimedia content within the first time window to the (i-1)th time window, a second consumption deviation information is determined, wherein the second consumption deviation information is used to indicate the difference between the actual resource consumption and the expected resource consumption of the multimedia content within the first time window to the (i-1)th time window. Based on the second consumption deviation information, the integral control parameters of the multimedia content within the i-th time window are determined.

10. The apparatus according to claim 7, characterized in that, The adjusted control parameters include derivative control parameters; the parameter determination module is used for: The difference between the proportional control parameter of the multimedia content in the i-th time window and the proportional control parameter of the multimedia content in the (i-1)-th time window is determined as the differential control parameter of the multimedia content in the i-th time window.

11. The apparatus according to any one of claims 8 to 10, characterized in that, The parameter determination module is used to calculate the funding adjustment parameter pacing_rate for multimedia content within the i-th time window according to the following formula: pacing_rate=α×p_error+β×i_error+γ×d_error+1; Wherein, α, β, and γ are preset weighting coefficients, p_error represents the proportional control parameter of the multimedia content in the i-th time window, i_error represents the integral control parameter of the multimedia content in the i-th time window, and d_error represents the derivative control parameter of the multimedia content in the i-th time window.

12. The apparatus according to any one of claims 7 to 10, characterized in that, The queue generation module is used for: Based on the actual investment in the multimedia content within the i-th time window and the first expected click-through rate, the expected revenue of the multimedia content within the i-th time window is determined; wherein, the first expected click-through rate is used to indicate the probability that the multimedia content is clicked within the i-th time window; Based on the actual investment in the at least one other multimedia content within the i-th time window and the second expected click-through rate, the expected revenue of the at least one other multimedia content within the i-th time window is determined; wherein, the second expected click-through rate is used to indicate the probability that the at least one other multimedia content is clicked within the i-th time window; The delivery queue is generated based on the expected revenue of the multimedia content within the i-th time window and the expected revenue of at least one other multimedia content within the i-th time window.

13. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing at least one program, which is loaded and executed by the processor to implement the method for delivering multimedia content as described in any one of claims 1 to 6.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one program, which is loaded and executed by a processor to implement the method for delivering multimedia content as described in any one of claims 1 to 6.

15. A computer program product, when executed, for performing the method of delivering multimedia content as described in any one of claims 1 to 6.

Images