Advertisement delivery method, electronic device, storage medium, and program product

Abstract

This application provides an advertising delivery method, electronic device, storage medium, and program product, belonging to the field of electronic devices. The method includes obtaining the total exposure and exposure period agreed upon in the target contract advertisement; dividing the exposure period into N time slots according to a preset duration; determining the expected exposure for the first time slot based on the total exposure and the N time slots; delivering the target contract advertisement in the first time slot according to a first service rate; for the nth time slot after the first time slot, determining the expected exposure for the nth time slot based on the expected exposure for the (n-1)th time slot before the nth time slot and the actual exposure for the (n-1)th time slot; determining the nth service rate for the nth time slot based on the expected exposure for the nth time slot; and delivering the target contract advertisement in the nth time slot according to the nth service rate. This method can complete the exposure and achieves uniform exposure as much as possible, better meeting the needs of advertisers.

Description

Technical Field

[0001] This application relates to the field of electronic devices, and more particularly to an advertising delivery method, electronic device, storage medium, and program product. Background Technology

[0002] Contract advertising, as a form of contractual advertising, typically involves an agreement between the advertiser and the advertising platform to ensure that the advertiser can purchase a predetermined amount of exposure from the platform. If the advertising platform fails to fulfill the contract, i.e., fails to meet the advertiser's purchase of the required amount of exposure, the platform is liable for corresponding compensation, such as paying the advertiser twice the price for the difference in exposure.

[0003] Typically, contract advertising only has specific requirements for exposure. Therefore, the optimization of contract advertising mainly focuses on improving the fulfillment rate, without much consideration for other aspects. Summary of the Invention

[0004] In view of this, this application provides an advertising delivery method, electronic device, storage medium, or program product that can better expose the advertisements delivered by advertisers.

[0005] Some embodiments of this application provide an advertising delivery method. The application is described below from multiple aspects, and the embodiments and beneficial effects of these aspects can be referenced each other.

[0006] In a first aspect, embodiments of this application provide a method for obtaining the total exposure and exposure period agreed upon in a target contract advertisement, dividing the exposure period into N time slots according to a preset duration, where N is an integer greater than 1; determining the expected exposure for the first time slot based on the total exposure and the N time slots; placing the target contract advertisement in the first time slot according to a first service rate; for the nth time slot after the first time slot, determining the expected exposure for the nth time slot based on the expected exposure for the (n-1)th time slot before the nth time slot and the actual exposure for the (n-1)th time slot, where n is less than or equal to N; determining the nth service rate for the nth time slot based on the expected exposure for the nth time slot; and placing the target contract advertisement in the nth time slot according to the nth service rate.

[0007] According to the method in this application embodiment, while ensuring the completion of the total exposure of the contracted advertisement, time slices are used and the service rate corresponding to the subsequent time slices is dynamically adjusted based on the actual exposure situation. This aims to make the advertisement exposure evenly distributed within the campaign period, avoid the exposure being concentrated in certain time periods, and meet the advertiser's need for uniform exposure of the contracted advertisement.

[0008] As an embodiment of the first aspect of this application, determining the required exposure for the nth time slot based on the required exposure for the (n-1)th time slot preceding the nth time slot and the actual exposure for the (n-1)th time slot includes: determining the difference R between the required exposure for the (n-1)th time slot and the actual exposure for the (n-1)th time slot. n-1 ; the difference R n-1 The corresponding exposure is allocated to at least one time slice after n-1 time slices; based on the difference R n-1 The corresponding exposure allocation, along with the total exposure and N time slices, determines the exposure required for the nth time slice.

[0009] As an embodiment of the first aspect of this application, the difference R n-1 The corresponding exposure is allocated to at least one time slice after n-1 time slices, including: when there are multiple time slices after n-1 time slices, the difference R is... n-1 The corresponding exposure is evenly distributed across multiple time slices. This method can further improve the uniformity of exposure.

[0010] As an embodiment of the first aspect of this application, determining the nth service rate corresponding to the nth time slice based on the required exposure for the nth time slice includes:

[0011] Traffic quality is stratified according to traffic quality stratification rules. The traffic quality is used to represent the historical click pass rate of a request, and each stratification is distributed across N time slices.

[0012] Determine the service rate for each time slice corresponding to the tier;

[0013] Based on the (n-1)th service rate of the (n-1)th time slice, and the difference Rn-1, the service rate of the corresponding layer in the nth time slice is adjusted to obtain the nth service rate, where the nth service rate includes the service rates of each layer. This application embodiment incorporates a traffic quality layer design into the service rate adjustment, which can effectively improve the effectiveness of advertising.

[0014] As an embodiment of the first aspect of this application, the traffic quality stratification rule is to stratify the traffic according to the historical click rate corresponding to the request, from high to low.

[0015] As an embodiment of the first aspect of this application, the traffic quality stratification rule is to divide the traffic into high-quality stratification, medium-quality stratification and low-quality stratification according to the historical click rate from high to low, and the service rate of high-quality stratification is greater than that of medium-quality stratification, which is greater than that of low-quality stratification.

[0016] As an embodiment of the first aspect of this application, determining the service rate of each time slice corresponding to a tier includes: the service rate of the low-quality tier corresponding to the nth service rate is 0.9 times the nth service rate; the service rate of the medium-quality tier corresponding to the nth service rate is the nth service rate; and the service rate of the high-quality tier corresponding to the nth service rate is greater than the nth service rate and less than 1. This calculation method can maximize the service rate corresponding to the high-quality tier, which is beneficial to improving click-through rate.

[0017] As an embodiment of the first aspect of this application, the actual exposure of the nth time slice is the sum of the actual exposures corresponding to different flow quality layers of the nth time slice.

[0018] As an embodiment of the first aspect of this application, the first service rate is obtained based on a greedy algorithm.

[0019] As an embodiment of the first aspect of this application, determining the required exposure for the first time slice based on the total exposure and N time slices includes: determining the required exposure for the first time slice based on the historical traffic distribution and the total exposure within the N time slices.

[0020] As an embodiment of the first aspect of this application, the exposure of the first time slice is the product of the total exposure and the estimated traffic percentage of the corresponding first time slice.

[0021] As an embodiment of the first aspect of this application, the advertising delivery method further includes: receiving an advertising delivery request, the request including targeting conditions for the advertisement to be delivered; responding to the advertising delivery request, matching contract advertisements based on the targeting conditions; obtaining the service rate of the quality tier corresponding to each contract advertisement, and determining the target contract advertisement when the service rate of the quality tier reaches a preset service rate.

[0022] As an embodiment of the first aspect of this application, determining the target contract advertisement includes: determining a plurality of candidate contract advertisements, and determining the final target contract advertisement according to the product of the service rate corresponding to each candidate contract advertisement and the historical click pass rate at the corresponding time.

[0023] Secondly, this application also discloses an electronic device, comprising: a memory for storing instructions executed by one or more processors of the electronic device, and a processor for executing the advertising delivery method explained in the first aspect.

[0024] Thirdly, this application also discloses a computing device cluster, including at least one computing device, each computing device including a processor and memory;

[0025] A processor of at least one computing device is used to execute instructions stored in the memory of at least one computing device to cause the cluster of computing devices to execute the advertising delivery method explained in the first aspect.

[0026] Fourthly, this application also discloses a computer-readable storage medium storing instructions that, when executed on an electronic device, cause the electronic device to perform the advertising delivery method explained in the first aspect.

[0027] Fifthly, this application also discloses a computer program product containing instructions that, when run on an electronic device, cause the electronic device to perform the advertising delivery method explained in the first aspect.

[0028] Sixthly, this application also discloses a chip that, when operated on an electronic device, causes the electronic device to perform the advertising delivery method explained in the first aspect. Attached Figure Description

[0029] Figure 1 This is a scene diagram illustrating the advertising delivery method according to an embodiment of this application;

[0030] Figure 2 This is a schematic diagram of the structure of the electronic device of this application;

[0031] Figure 3a This is a system architecture diagram of an advertising delivery method according to another embodiment of this application;

[0032] Figure 3b This is a flowchart of an advertising delivery method according to an embodiment of this application;

[0033] Figure 4 This is a daily traffic distribution map of the advertising platform according to an embodiment of this application;

[0034] Figure 5 This is a flowchart illustrating a method for determining the service rate of a time slice according to an embodiment of this application.

[0035] Figure 6 This is a flowchart illustrating the determination of the initial service rate based on a greedy algorithm, as described in an embodiment of this application.

[0036] Figure 7 This is a diagram showing the relationship between traffic and contract allocation in an embodiment of this application;

[0037] Figure 8 This is a schematic diagram of a computing device cluster according to an embodiment of this application;

[0038] Figure 9 This is a schematic diagram of an on-chip system according to an embodiment of this application. Detailed Implementation

[0039] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0040] To facilitate understanding of the technical solutions of the embodiments of this application, the technical problems to be solved by the embodiments of this application will be explained first.

[0041] refer to Figure 1 , Figure 1 A scenario diagram illustrating the advertising delivery method according to an embodiment of this application is shown.

[0042] like Figure 1 As shown, this scenario may include an advertiser-side device 10, a user-side device 20, and an advertising service center 30. The advertiser-side device 10 can be a smartphone, tablet, or computer. Advertisers sign advertising contracts with advertising platforms and send them to the advertising service center 30 via the advertiser-side device 10. Typically, the contract advertisement records information about the advertiser's needs, such as the specific amount of exposure purchased from the advertising platform and the advertiser's targeting requirements for users. The advertising service center 30 is the core of the entire advertising delivery system, responsible for coordinating and managing the distribution of advertisements. The advertiser-side device 10 sends relevant information about the contract advertisement to the advertising service center 30. The user-side device 20 triggers an advertising request based on the user's browsing behavior, such as opening a webpage or application, and sends the advertising request to the advertising service center 30. The advertising service center 30 filters targeting conditions based on user information corresponding to the advertising request, such as age, gender, and viewed content, and selects suitable contract advertisements for users based on internally set strategies, while simultaneously satisfying the advertiser's requirements for the exposure of the contract advertisements.

[0043] However, in some implementations, contract advertising is primarily delivered to meet exposure requirements and fulfillment rates. Typically, advertisers prefer contract advertising exposure to be smoothly distributed throughout the entire time period, and current delivery methods do not meet these needs.

[0044] To address the aforementioned technical problems, embodiments of this application provide an advertising delivery method that, while ensuring the desired exposure volume for contract advertisements, distributes the exposure of contract advertisements as evenly as possible within the delivery period, achieving uniform exposure of contract advertisements and thereby improving the advertiser's experience.

[0045] The advertising delivery method of this application embodiment will be described below.

[0046] The advertising delivery method of this application embodiment can be implemented by, for example, Figure 1The advertising service center, as shown, executes the process. Once the advertising service center obtains the total exposure and exposure period agreed upon in the target contract advertisement, it divides the exposure period into multiple smaller time slots. For example, it can divide the period into N time slices according to a preset duration, where N is an integer greater than 1. The preset duration can be 10 minutes, 20 minutes, or 1 hour, etc. Generally, setting the preset duration to less than 1 day is more conducive to even out the exposure.

[0047] Before ad delivery, the expected exposure for each time slot is calculated. Based on the total exposure and N time slots, the expected exposure for the first time slot is determined. For example, the original expected exposure for each time slot can be calculated based on the traffic distribution percentage, multiplied by the total exposure by the traffic percentage for each time slot; or the total exposure can be evenly distributed across each time slot to obtain the theoretical number of ad displays for each time slot. When delivering the ad, the target contract ad is first delivered according to the first service rate, and the actual exposure for the first time slot is obtained. The first service rate can be the initial service rate configured by the system for the target contract ad.

[0048] Subsequently, for the nth time slot after the first time slot, the expected exposure for the nth time slot is determined based on the expected exposure for the (n-1)th time slot before the nth time slot and the actual exposure for the (n-1)th time slot, where n is less than or equal to N. The nth service rate for the nth time slot is then determined based on the expected exposure for the nth time slot. The target contract ad is then delivered in the nth time slot according to the nth service rate. For example, when delivering the ad in the second time slot, the expected exposure for the second time slot can be determined based on the expected exposure for the first time slot and the actual exposure for the first time slot. It's important to note that the expected exposure for the second time slot is adjusted from the actual and expected exposure for the first time slot, not the original expected exposure described above, but rather an adjusted exposure based on the original expected exposure. For example, as mentioned earlier, the original expected exposures for the first and second time slots, calculated based on traffic distribution, are 100 and 105 exposures respectively. In actual contract advertising, the first time slot corresponds to 95 actual impressions, which is 5 impressions short of the expected impressions. Therefore, when calculating the second time slot, the 5 missing impressions need to be made up. This can be achieved by distributing the shortfall across several consecutive time slots, or across several non-consecutive time slots, or by using a different allocation method; there are no specific limitations here. Assuming 1 impression is allocated to the second time slot, the expected impressions for the second time slot are the original expected impressions plus the allocated impressions, which is 105 + 1 = 106 impressions. It should be noted that this explanation only considers the distance between the first and second time slots; in actual calculations, it can be understood as the distance between the (n-1)th and nth time slots.

[0049] Next, based on the expected exposure for the second time slot, determine the second service rate. When delivering the ad for the third time slot, the expected exposure for the third time slot can be determined based on the expected exposure and the actual exposure for the second time slot. The third service rate is then determined based on the expected exposure for the third time slot. This process is repeated to determine the expected exposure and service rate for each time slot until the target contract ad for the Nth time slot pair is successfully delivered.

[0050] According to the advertising delivery method of this application embodiment, the complete exposure period is divided into several consecutive time slices, and the total exposure volume agreed upon in the contract is initially allocated relatively evenly according to the number of time slices. During the actual delivery of contracted advertisements, the deviation between the actual exposure volume and the expected exposure volume of each time slice is continuously monitored, and the service rate of subsequent time slices is dynamically adjusted based on the deviation value, thereby achieving dynamic adjustment of exposure volume. Through this dynamic adjustment method, it is possible to ensure that the total exposure volume requirement stipulated in the contract is ultimately achieved, while effectively controlling the fluctuation range of exposure volume in each time period, and achieving uniform delivery of advertisement exposure volume. Through the refinement of the time dimension, the advertiser's marketing information can stably reach the target audience at different times throughout the day, significantly improving the reliability of advertisement delivery and the consistency of user experience.

[0051] The advertising delivery method of this application embodiment will be described below in conjunction with the specific structure of the electronic device.

[0052] refer to Figure 2 , Figure 2 A schematic diagram of the structure of an electronic device 100 according to an embodiment of this application is shown.

[0053] like Figure 2 As shown, the electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) connector 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone jack 170D, a sensor module 180, buttons 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, a barometric pressure sensor 180C, a magnetic sensor 180D, an accelerometer sensor 180E, a distance sensor 180F, a proximity sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0054] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device 100. In other embodiments of this application, the electronic device 100 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0055] Processor 110 may include one or more processing units, such as application processors (APs), modem processors, graphics processing units (GPUs), image signal processors (ISPs), controllers, video codecs, digital signal processors (DSPs), baseband processors, and / or neural network processing units (NPUs). These different processing units may be independent devices or integrated into one or more processors.

[0056] The processor 110 can generate operation control signals based on the instruction opcode and timing signals to control the instruction fetching and execution.

[0057] The processor 110 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. This memory can store instructions or data that the processor 110 has just used or that are used repeatedly. If the processor 110 needs to use the instruction or data again, it can retrieve it directly from the memory. This avoids repeated accesses, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0058] In some embodiments, the processor 110 can obtain the total exposure and exposure period agreed upon in the target contract advertisement, and divide the exposure period into N time slots according to a preset duration, where N is an integer greater than 1. Then, based on the total exposure and the N time slots, the expected exposure for the first time slot is determined. Upon receiving an advertisement request, the target contract advertisement is delivered in the first time slot according to a first service rate. Furthermore, during the actual delivery execution phase, for the nth time slot after the first time slot, the processor 110 determines the expected exposure for the nth time slot based on the expected exposure for the (n-1)th time slot before the nth time slot and the actual exposure for the (n-1)th time slot, where n is less than or equal to N. Based on the expected exposure for the nth time slot, the processor 110 determines the nth service rate for the nth time slot and delivers the target contract advertisement in the nth time slot according to the nth service rate. In other words, the processor 110 continuously monitors the deviation between the actual exposure and the expected exposure for each time slot and adjusts the service rate for subsequent time slots based on this deviation, thereby achieving dynamic adjustment of the exposure. This closed-loop control mechanism ensures that the total exposure requirement stipulated in the contract is met, while effectively controlling the fluctuation range of exposure at different times, thus achieving a steady and progressive delivery of advertising exposure.

[0059] In some embodiments, the processor 110 can also stratify traffic quality according to traffic quality stratification rules. Traffic quality represents the historical click-through rate (CTR) of a request, and each stratification corresponds to N time slices. The processor determines the service rate of each stratification for each time slice. Based on the (n-1)th service rate of the (n-1)th time slice and the difference Rn-1, the processor determines the nth service rate for the nth time slice, where the nth service rate includes the service rates of each stratification. This stratified service rate calculation method ensures that users with high CTRs always receive a higher service rate than those with low CTRs, achieving the purpose of traffic filtering and improving advertising effectiveness within the contract advertising period.

[0060] The wireless communication function of electronic device 100 can be realized through antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, modem processor and baseband processor, etc.

[0061] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 can be used to cover one or more communication frequency bands. Different antennas can also be multiplexed to improve antenna utilization. For example, antenna 1 can be multiplexed as a diversity antenna for a wireless local area network. In some other embodiments, the antennas can be used in conjunction with tuning switches.

[0062] The mobile communication module 150 can provide solutions for wireless communication, including 2G / 3G / 4G / 5G, applied to the electronic device 100. The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves via antenna 1, and perform filtering, amplification, and other processing on the received electromagnetic waves before transmitting them to a modem processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modem processor and convert it into electromagnetic waves for radiation via antenna 1. In some embodiments, at least some functional modules of the mobile communication module 150 may be housed in the processor 110. In some embodiments, at least some functional modules of the mobile communication module 150 and at least some modules of the processor 110 may be housed in the same device.

[0063] The wireless communication module 160 can provide solutions for wireless communication applications on the electronic device 100, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via antenna 2, performs frequency modulation and filtering of the electromagnetic wave signals, and sends the processed signal to processor 110. The wireless communication module 160 can also receive signals to be transmitted from processor 110, perform frequency modulation and amplification, and convert them into electromagnetic waves for radiation via antenna 2.

[0064] In some embodiments, both the mobile communication module 150 and the wireless communication module 160 can enable the electronic device 100 to communicate with other devices. The processor 110 can control the mobile communication module to obtain relevant information about the contract advertisement, such as the contract advertisement planID, targeting conditions, total exposure of the contract, etc., and to determine which user terminal device receives the relevant advertisement request and to determine the matching advertisement contract based on the request matching.

[0065] The advertising delivery method provided in this application embodiment will be described in detail below with reference to the accompanying drawings. This method can be applied to applications such as... Figure 2In electronic devices with the hardware structure shown, or in electronic devices with more or fewer components than shown, or in electronic devices with similar hardware and software structures, or in electronic devices with different component arrangements, or in electronic devices with different component arrangements.

[0066] The advertising delivery method provided in this application can be applied to an electronic device or a cluster of computing devices. For example, the electronic device can be a server or a cluster of computing devices composed of multiple servers. Furthermore, the electronic device can also be a mobile phone, computer, ultra-mobile personal computer (UMPC), artificial intelligence device, or other device with a certain data processing capability. This application does not limit the specific type of electronic device. In the following embodiments, the electronic device is described as a server.

[0067] refer to Figure 3a , Figure 3a A system architecture diagram of an advertising delivery method according to another embodiment of this application is shown. Figure 3a As shown, the system includes a contract signing module 01, an advertising management platform 02, a contract service rate calculation module 03, a CTR prediction server 04, a contract advertising real-time decision control module 05, and an advertising server 06. In some embodiments of this application, the contract service rate calculation module 03, the CTR prediction server 04, the contract advertising real-time decision control module 05, and the advertising server 06 can be independent devices capable of establishing communication connections, or they can be integrated into a computing device. The embodiments of this application are not limited in this respect.

[0068] like Figure 3a As shown, the contract signing module 01 is used by advertisers and the platform to sign advertising contracts that guarantee exposure. The contract information is generated electronically in the contract signing module 01 and then stored in the advertising management platform 02.

[0069] The advertising management platform 02 is used to store and manage contract advertisements and send contract advertisement information to the real-time decision control module 05 for contract advertisements.

[0070] Service rate calculation module 03 is used to calculate the initial service rate corresponding to the contract advertisement and the service rate updated based on quality traffic tiers. This will be described in detail in later embodiments.

[0071] CTR prediction server 04 is used to predict the click-through rate of the user corresponding to the request based on user behavior, such as browsing pages and click-through rate, and send the predicted click-through rate to the contract advertising real-time decision control module 05.

[0072] The real-time decision control module 05 for contract advertising is used by the real-time decision-making module to determine the quality tier based on the estimated click-through rate, and obtain the service rate of the corresponding quality tier for the contract advertising from the contract service rate calculation module 03. The pass rate of contract advertisements is determined by the random function. Then determine whether this request is a normal service under the contract; otherwise, filter the contract. Simultaneously, filter advertisements for contracts whose terms have expired.

[0073] Upon receiving an ad request from a user's device, ad server 06 filters contract ads based on user characteristics, obtaining a subset of ads that match those characteristics. Simultaneously, it sends a request ad decision list to the real-time contract ad decision control module 05. Upon receiving the decision list, if there is only one contract ad, it directly returns the ad and its corresponding exposure based on the impressions in the decision list and the set service rate. If the real-time contract ad decision control module 05 returns multiple contract ads, ad server 06 further filters them, sorting them from highest to lowest based on the service rate multiplied by the click-through rate, determining the final target contract ad for playback, and returning the target contract ad to the terminal for display to the user.

[0074] The advertising delivery method of this application embodiment will now be described in detail with reference to the accompanying drawings. This method can be derived from the above... Figure 3a Each module in the process is executed.

[0075] refer to Figure 3b , Figure 3b A flowchart illustrating an embodiment of the advertising delivery method of this application is shown. This method can be executed by a server, for example, Figure 3a The server execution is integrated with the contract service rate calculation module 03, the CTR prediction server 04, the contract advertising real-time decision control module 05, and the advertising server 06. It can also be executed by multiple servers. The method includes S310-S390.

[0076] S310 receives instructions for advertising delivery tasks.

[0077] Among them, the ad delivery task instruction can be a task instruction sent by the advertiser or the ad platform to the ad server through the management backend or API interface.

[0078] In embodiments of this application, the advertising delivery task instruction may include information related to the content of the contracted advertisement. For example, it may include a plan identifier (planID), targeting conditions, total impressions of the advertising campaign, total budget, and delivery period. The planID is a unique identifier assigned by the platform to each advertising plan to distinguish different plans; targeting conditions refer to the target audience or display conditions for the advertisement, such as region, age, gender, and interests, which determine which users the advertisement will be shown to; total impressions are the total number of times the advertisement is displayed to the advertiser, which is usually a key metric in the contract used to measure the effectiveness of the advertising campaign and the platform's fulfillment of its obligations.

[0079] S320 responds to advertising delivery task instructions and obtains the total exposure volume and exposure period agreed in the contract advertisement.

[0080] This process can be referenced. Figure 3a The system architecture diagram shown indicates that the contract service rate calculation module 03 obtains contract advertising information from the advertising management platform 02, including the total exposure and exposure period agreed in the contract advertising.

[0081] The S330 divides the exposure cycle into N time slices according to the preset duration.

[0082] In the embodiments of this application, the preset duration can be several minutes, tens of minutes, or several hours. For example, it can be set to 10 minutes, dividing each day into 144 time slices. Furthermore, in some embodiments, more or fewer time slices can be divided according to the advertiser's requirements. More time slices result in a more consistent delivery of contracted advertisements.

[0083] S340, determine the service rate corresponding to the contract advertisement.

[0084] The service rate corresponding to contract advertising refers to the initial service rate of contract advertising.

[0085] In the embodiments of this application, the service rate corresponding to the contract advertisement can be calculated using a greedy algorithm (High Water Mark, HWM) to maximize the exposure within each time slice and ensure that the total exposure is achieved on time. The process of solving the initial service rate will be further explained in later embodiments.

[0086] S350 receives an advertising placement request, identifies the target contract advertisement, and places the target contract advertisement.

[0087] An ad delivery request refers to an ad request sent by a client device to an ad server when a user visits a website or application, such as a browser or application. Ad delivery requests may include, but are not limited to, user information such as user identifier, device identifier, and geographic location; page or application context information such as page Uniform Resource Locator (URL) and content category; ad placement information such as ad placement size and ad placement identifier; and a timestamp, indicating the time of the request.

[0088] S360 will place target contract ads in the first time slot based on the service rate corresponding to the contract ads.

[0089] The service rate corresponding to the first time slice (the first service rate) is the initial service rate.

[0090] S370, for the nth time slice after the first time slice, determine the required exposure for the nth time slice based on the required exposure for the (n-1)th time slice before the nth time slice and the actual exposure for the (n-1)th time slice.

[0091] In one embodiment of this application, the difference R between the required exposure for the (n-1)th time slice and the actual exposure for the (n-1)th time slice is first determined. n-1 Then the difference R n-1 The corresponding exposure is allocated to at least one time slice after n-1 time slices. Finally, based on the difference R... n-1 The corresponding exposure allocation, along with the total exposure and N time slices, determines the exposure required for the nth time slice.

[0092] For example, the expected exposure for the first time slice is 500 shots, but the actual exposure is 510 shots, with a difference R. n-1 The exposures are 10. These 10 exposures can be distributed across time slots following the first time slot, for example, across the second time slot and the next 9 time slots. With an even distribution, each time slot would receive 1 exposure. The expected exposure for the second time slot would then be the initial expected exposure for that second time slot plus 1 exposure.

[0093] The above embodiment illustrates the example of evenly distributing 10 exposures across subsequent time slices. In some embodiments, the exposures can also be evenly distributed across 2, 3, 4, or other subsequent time slices. These time slices can be continuous or discontinuous, and this application does not limit this to a single time slice.

[0094] It's important to note that before ad delivery, the expected exposure for each time slot is considered the initial expected exposure. After subsequent actual exposures, the initial expected exposure needs to be adjusted promptly to obtain the expected exposure for the nth time slot. Furthermore, the expected exposure for the first time slot is the initial expected exposure.

[0095] The initial exposure corresponding to the time slice described above can be calculated based on the flow distribution, as illustrated below.

[0096] For example, taking an exposure period of 1 day and a preset time slice duration of 10 minutes as an example, first determine the historical traffic distribution for the day, divide the day into 144 time slices according to the 10-minute interval, and then denote the time slices as Imp1, Imp2, Imp3, ..., Imp144. The total exposure = (Imp1, Imp2, ..., Imp144), and the target exposure for each time slice is denoted as I. 1 I 2 I 3 I 4 I 5 , ..., I 144 .

[0097] Next, the total exposure agreed upon in the contract advertisement is allocated to these K time slots. The target exposure to be achieved in each time slot is then denoted as: I 1 I 2 I 3 I 4 I 5 , ..., I K Among them, I K = I * the traffic share of this time slot, where I represents the total exposure agreed upon in the contract advertisement. The traffic share of each time slot can be calculated based on the statistical historical traffic data.

[0098] The calculation process for the required exposure for a time slice is explained below with reference to the accompanying diagram.

[0099] refer to Figure 4 , Figure 4 A daily traffic distribution chart of the advertising platform according to an embodiment of this application is shown. Figure 4 As shown, this traffic distribution map is a curve and graph drawn based on historical traffic data within a day. The map is plotted with the time axis on the horizontal axis and the traffic distribution data on the vertical axis. Specifically, it uses a point-plotting method, with each minute's exposure as a point, and connects 24*60 exposure data points throughout the day to obtain the traffic distribution map. This traffic distribution map shows the changes in user activity throughout the day. Based on this, the traffic share for each time slot can be calculated.

[0100] like Figure 4 As shown, by calculating the exposure of each time slot divided by the total exposure of the day, denoted as lambda, the traffic share of each time slot can be obtained. Figure 4 The area of ​​the rectangle corresponding to T represents the exposure from 12:50 to 13:00. That is, the required exposure for each time slot = lambda multiplied by the exposure purchased under the contract.

[0101] S380, determine the nth service rate corresponding to the nth time slice based on the exposure amount corresponding to the nth time slice.

[0102] For example, if the current time slice is the second time slice, the expected exposure and actual exposure of the first time slice are determined first, then the expected exposure of the second time slice is determined, and then the service rate corresponding to the second time slice (second service rate) is adjusted.

[0103] In the embodiments of this application, the required exposure for the nth time slot is determined relative to the exposure of the previous time slot. When the actual exposure for the (n-1)th time slot is less than the required exposure, it indicates insufficient exposure. In this case, the required exposure for the nth time slot calculated in step S370 will no longer be the required exposure for the nth time slot, but rather the exposure after distributing the insufficient exposure from the (n-1)th time slot across at least the nth time slot. The corresponding service rate will also no longer be the initial service rate, but rather a service rate adjusted based on historical experience. Conversely, if the exposure for the (n-1)th time slot is greater than the required exposure, the required exposure for the second time slot can be reduced, and correspondingly, the service rate for the nth time slot can also be reduced, thereby achieving dynamic adjustment of the service rate. By dividing the time slots, the service rate for each time slot is adjusted in a timely manner, ensuring that the exposure for each time slot is adjusted promptly and that the advertiser's ads are exposed at a uniform rate.

[0104] S390, deliver the target contract advertisement in the nth time slot according to the nth service rate.

[0105] According to the advertising delivery method of this application embodiment, while ensuring the completion of the total exposure of the contracted advertisement, time slices are divided and the service rate corresponding to the subsequent time slices is dynamically adjusted based on the actual exposure situation, so as to make the advertisement exposure evenly distributed within the delivery period and avoid the exposure being concentrated in certain time periods, thereby meeting the advertiser's need for uniform exposure of the contracted advertisement.

[0106] In some embodiments, advertisers not only have requirements for the fulfillment of exposure volume and uniform exposure rate, but also hope to improve the effect, that is, to increase the user's click-through rate, so as to achieve the advertiser's marketing effect.

[0107] To further address advertisers' requirements, embodiments of this application, based on the aforementioned uniform exposure scheme, further incorporate traffic quality features in S380, thereby meeting users' needs for improved performance.

[0108] refer to Figure 5 , Figure 5 A flowchart of a method for determining the service rate of a time slice according to an embodiment of this application is shown. The method is executed by a server and includes steps S381-S383.

[0109] S381, stratifies traffic quality based on historical traffic quality.

[0110] Historical traffic quality refers to the historical click-through rate (CTR) of requests. CTR is a metric that measures how frequently an ad or content is clicked; CTR = Clicks / Impressions. Traffic here refers to user traffic visiting a website, application, or ad. Traffic quality refers to the value, activity level, conversion rate, and other metrics of these users. For example, traffic can be categorized into high-quality, medium-quality, and low-quality traffic. Generally, higher-quality traffic means users are more likely to perform the desired action (such as purchase, registration, or download). Higher traffic quality generally indicates a higher CTR. Historical traffic quality data can be used to predict the approximate traffic quality distribution for the current time slot and make corresponding adjustments, effectively improving the efficiency of ad placement.

[0111] This application embodiment utilizes previously collected CTR data corresponding to requests to classify user traffic into different quality levels based on the performance of their click behavior.

[0112] In some embodiments, requests can be categorized into multiple layers based on their click-through rates (CTRs) in descending order. For example, considering three requests: request 1 has a CTR of 0.1, request 2 has a CTR of 0.2, and request 3 has a CTR of 0.3. The CTRs can then be categorized as follows: CTRs less than 0.15 are layer 1; CTRs between 0.15 and 0.25 are layer 2; and CTRs greater than 0.25 are layer 3.

[0113] In the embodiments of this application, traffic quality stratification can be divided into three layers—high-quality, medium-quality, and low-quality—arranged from high to low based on historical click-through rates. In other embodiments, it may be divided into more or fewer layers, and this application is not limited to this.

[0114] S382, determine the service rate of each time slice corresponding to the tier.

[0115] For example, in the above embodiment, the quality flow rate is divided into 3 layers, and the service rate of each layer is solved based on the initial service rate r (corresponding to the service rate in S340).

[0116] Based on the initial service rate, when calculating the initial service rate for each tier, those skilled in the art can set the relationship between the tiered service rate and the base service rate for each tier. An example is given below for reference:

[0117] If traffic has already been stratified into high-quality, medium-quality, and low-quality strata, then for each stratum, the service rate for the low-quality strata can be set to r. low =a1*r, where the service rate for the quality stratification is r. mid = a² * r, where the service rate for high-quality tiered services is r. high =min(1.0, a3*r); where r is the initial service rate, and a1, a2, and a3 are coefficients, for example, a1 = 0.9, a2 = 1.0, and a3 = 1.1. The coefficients 0.9 and 1.1 are empirical values, obtained through extensive experimental verification, and can effectively improve the performance of contract advertising. It is understood that those skilled in the art can set these values ​​according to their experience as needed, and this application does not impose specific limitations on them. For example, when corresponding to the first time slice, the first service rate is 0.8, then the service rate corresponding to the high-quality tier is min(1.0, 1.1*0.8), the service rate for the medium-quality tier is 1.0*0.8, and the service rate for the low-quality tier is 0.9*0.8, thus calculating the service rate for each tier.

[0118] S383, based on the (n-1)th service rate, the difference R n-1 Adjust the service rate of the layer corresponding to the nth time slice.

[0119] In S382, after the layers of the first time slice are determined, when determining the time slices after the second time slice, the difference R between the actual exposure and the expected exposure corresponding to the previous time slice is used. n-1 Adjustments are made. During adjustments, the service rate is adjusted in descending order of traffic quality, prioritizing the high-quality tier. The adjustment of the high-quality tier's service rate can be based on the service rate of the high-quality tier corresponding to the previous time slice. If the actual exposure volume is already met after adjusting the high-quality tier's service rate, the service rates of the medium-quality and low-quality tiers are no longer adjusted. Otherwise, adjustments to the medium-quality and low-quality tiers continue until the exposure volume meets the requirements. This will be further explained in later embodiments.

[0120] The process of solving the initial service rate in S340 in Figure 3 is explained below with reference to the accompanying drawings.

[0121] refer to Figure 6 and Figure 7 , Figure 6 This document illustrates a flowchart of an embodiment of the greedy algorithm used to determine the initial service rate according to this application. Figure 7 A diagram illustrating the relationship between traffic and contract allocation in an embodiment of this application is shown. Figure 6 As shown, the process of determining the initial service rate may include the following steps S341-S343.

[0122] S341, obtain traffic characteristic information and contract advertising demand information.

[0123] The feature information includes at least labels and quantities; labels can be, for example, gender and age. Similarly, the demand information includes at least labels and quantities; here, labels can be, for example, gender and age.

[0124] It should be noted that there can be one or more traffic and contract ads here.

[0125] For ease of explanation, Figure 7 In the case where both traffic and contract ads are present in two quantities, traffic includes traffic S1 and traffic S2, and contract ads include contract ads D1 and contract ads D2. Specifically, traffic S1 is tagged as male, age 5, and has a quantity of 100k; traffic S2 is tagged as age 5, and has a quantity of 300k; contract ads D1 is tagged as age 5, and has a quantity of 200k; and contract ads D2 is tagged as male, and has a quantity of 100k.

[0126] S342 matches traffic and contract advertising based on traffic feature information and contract advertising demand information.

[0127] Combination Figure 7 For example, based on the tags, we know that traffic S1 and traffic S2 both meet the requirements of contract ad D1, and traffic S2 meets the requirements of contract ad D2. Therefore, the traffic that matches contract ad D1 is traffic S1 and traffic S2, and the traffic that matches contract ad D2 is traffic S2.

[0128] S343, calculate the total number of traffic, and obtain the initial service rate based on the ratio between the number of each contract advertisement and the total number of traffic.

[0129] Continue to combine Figure 7 For example, the total number of traffic is 100k + 300k = 400k.

[0130] The ratio between the number of contract ads D1 and the total number of traffic is 1 / 2, and the ratio between the number of contract ads D2 and the total number of traffic is 1 / 4. If sorted in ascending order, the sorting result is: contract ads D2, contract ads D1.

[0131] Initial service rate = Number of contracted ads / Total amount of allocatable traffic. Here, total amount of allocatable traffic = Total amount of traffic matching all contracted ads - Number of allocatable ads already allocated.

[0132] Understandably, since the priority of allocation is determined by the sorted contract ads, traffic that has been allocated once cannot be allocated to other contract ads. Therefore, when calculating the initial service rate, the amount of traffic that has already been allocated needs to be removed from the total amount of traffic that matches all contract ads.

[0133] The initial service rate of contract ad D2 is calculated below. The traffic that matches contract ad D2 is traffic S1. Then the initial service rate of contract ad D2 = number of contract ads D2 / total number of allocable traffic = number of contract ads D2 / number of traffic S1 = 100k / 100k = 1. That is, all traffic S1 needs to be allocated to contract ad D2.

[0134] Next, calculate the initial service rate of contract ad D1. Although the traffic matching contract ad D1 is traffic S1 and traffic S2, traffic S1 has been fully allocated to contract ad D2, and the amount of allocated traffic is 100K. Therefore, the initial service rate of contract ad D1 = the number of contract ads D1 / the total amount of allocable traffic = the number of contract ads D1 / the amount of traffic S1 + the amount of traffic S2 - the amount of traffic S1 = 200k / 300k = 2 / 3.

[0135] According to the embodiments of this application, traffic quality is stratified. During the contract advertising campaign, the service rate can be adjusted based on the traffic quality. While ensuring exposure, the value of traffic can be better utilized, advertising strategies can be optimized, and the campaign effect can be improved.

[0136] In the embodiments of this application, during the contract advertising delivery process, the service rate corresponding to each layer of the current time slice is dynamically adjusted based on the exposure of the previous time slice.

[0137] As shown in Figure 3 above, after S370 is completed, the service rate corresponding to each layer is adjusted based on the difference in exposure for the (n-1)th time slice. The specific adjustment process can include the following three scenarios:

[0138] Wherein, the target exposure difference W: the difference between the actual exposure and the required exposure in the previous time slice Rn-1 and the difference R n-1 After amortization, the average exposure for the current time slice is obtained;

[0139] First target exposure: The amount of exposure that should be provided before amortization for the current time slice;

[0140] Second target exposure: The average exposure amount corresponding to the current time slice;

[0141] In the following three cases, the previous time slice corresponds to the (n-1)th time slice mentioned above, and the current time slice corresponds to the nth time slice mentioned above.

[0142] Scenario 1:

[0143] If the target exposure difference W for the current time slice is determined to be 0, meaning the second target exposure for the current time slice equals the first target exposure for the current time slice, then no service rate adjustment is needed. Instead, the service rate for each layer of the current time slice is directly determined to be consistent with the corresponding service rate of the previous time slice.

[0144] The formula is expressed as:

[0145]

[0146] In the formula, This represents the service rate of each layer in the current time slice;

[0147] This indicates the service rate of each layer in the previous time slice.

[0148] It is understandable that the service rate of each layer in the current time slice remains consistent with the corresponding service rate in the previous time slice, meaning that the service rate of a certain layer in the current time slice is consistent with the service rate of that layer in the previous time slice. For example, combining the above, if low-quality, medium-quality, and high-quality layers are obtained through quality stratification, then the service rates of each layer here are as follows: in, This indicates the service rate of the current time slice high-quality tier. This indicates the service rate of high-quality tiers in the previous time segment; This indicates the service rate of the quality stratification within the current time slice. This indicates the service rate of the quality stratification within the film at the previous time. This indicates the service rate of the low-quality tier in the current time slice. This indicates the service rate of low-quality tiers in the previous period.

[0149] Scenario 2:

[0150] If the difference W between the target exposures of the current time slot is greater than 0, it means that the second target exposure of the current time slot is greater than the first target exposure of the current time slot. This indicates that before the current time slot, the actual exposure of the contracted advertisement was less than the target exposure.

[0151] Therefore, in this situation, following the principle of prioritizing the adjustment of service rates for higher-level traffic quality, the service rate for each layer of the current time slice needs to be determined sequentially, and the target exposure difference W for the current time slice needs to be updated accordingly, until the target exposure difference W for the current time slice is no greater than 0, at which point the service rate adjustment stops. Furthermore, this process is a service rate improvement process.

[0152] Specifically, following the principle of prioritizing the adjustment of service rates for high-level traffic quality, the service rate for each layer in the current time slice is determined sequentially using the following formula:

[0153]

[0154] In the formula, This represents the service rate of each layer in the current time slice;

[0155] This indicates the service rate of each tier in the previous time slice;

[0156] This indicates the actual exposure of each layer in the previous time frame;

[0157] W represents the target exposure difference for the current time slice; W = I′ n -I n , I′ n I represents the second target exposure in the current time slice. n This indicates the first target exposure for the current time slice.

[0158] Understandably, after adjusting the service rate of one layer, it is necessary to update the target exposure difference W for the current time slice in a timely manner to determine whether the second target exposure for the current time slice is still greater than the first target exposure for the current time slice, and whether further service rate adjustments are needed. The following formula is used to update the target exposure difference W for the current time slice:

[0159]

[0160] In the formula, W ′ This represents the updated value of the target exposure difference for the current time slice;

[0161] W represents the difference in target exposure for the current time slice, which is the value before the update;

[0162] This indicates the actual exposure of each layer in the previous time frame;

[0163] This indicates the service rate of each tier in the previous time slice;

[0164] This represents the service rate of each layer in the current time slice.

[0165] Understandably, in the formula This indicates the relevant data within the same layer. For example, combining the above, after layering traffic according to quality to obtain low-quality, medium-quality, and high-quality layers, when determining the service rate of each layer in the current time slice according to the principle of prioritizing the adjustment of service rates for higher-level traffic quality, the first step is to determine the value in the formula... They are respectively This calculates the service rate for the high-quality stratum in the current time slice. Once determined, the target exposure difference W for the current time slice is updated. Then, if the updated target exposure difference indicates that the second target exposure for the current time slice is not greater than the first target exposure, the adjustment stops. For the service rates of other strata in the current time slice, they should remain consistent with those of the previous time slice. Conversely, if the second target exposure for the current time slice is still greater than the first target exposure, the service rate for the medium-quality stratum is further adjusted, i.e., the value in the formula is determined. They are respectively I will not go into details here.

[0166] To further understand, the following examples use specific numerical values:

[0167] if Substituting into the corresponding formula, we can obtain...

[0168] Calculate Then, by updating the target exposure difference W for the current time slice in a timely manner, we can obtain... If the underexposed portion can be recovered by adjusting the service rate of the high-quality tier, then there is no need to continue increasing the service rates of the medium-quality and low-quality tiers. In this case, the service rates of the medium-quality and low-quality tiers can remain consistent with those of the previous time slice.

[0169] Scenario 3:

[0170] If the difference W between the target exposures of the current time slot is less than 0, it means that the second target exposure of the current time slot is less than the first target exposure of the current time slot. This indicates that before the current time slot, the actual exposure of the contracted advertisement was more than the target exposure.

[0171] Therefore, in this situation, following the principle of prioritizing the adjustment of service rates for lower-layer traffic quality, the service rate for each layer in the current time slice needs to be determined sequentially, and the target exposure difference W for the current time slice needs to be updated accordingly, until the target exposure difference W for the current time slice is not less than 0, at which point the service rate adjustment stops. Furthermore, this process is a service rate reduction process.

[0172] Specifically, following the principle of prioritizing the adjustment of service rates for lower-layer traffic quality, the service rate of each layer in the current time slice is determined sequentially using the following formula:

[0173]

[0174] In the formula, This represents the service rate of each layer in the current time slice;

[0175] This indicates the service rate of each tier in the previous time slice;

[0176] This indicates the actual exposure of each layer in the previous time frame;

[0177] W represents the target exposure difference for the current time slice; W = I′ n -I n , I′ n I represents the second target exposure in the current time slice. n This indicates the first target exposure for the current time slice.

[0178] Similarly, after adjusting the service rate of one layer, the target exposure difference W for the current time slice needs to be updated promptly to determine whether the second target exposure for the current time slice is still less than the first target exposure, and whether further service rate adjustments are necessary. The following formula is used to update the target exposure difference W for the current time slice:

[0179]

[0180] In the formula, W ′ This represents the updated value of the target exposure difference for the current time slice;

[0181] W represents the difference in target exposure for the current time slice, which is the value before the update;

[0182] This indicates the actual exposure of each layer in the previous time frame;

[0183] This indicates the service rate of each tier in the previous time slice;

[0184] This represents the service rate of each layer in the current time slice. It's understandable that the formula... This indicates related data within the same layer. For a detailed explanation, please refer to the description in Case 2 above; it will not be repeated here.

[0185] According to the method of this application embodiment, on the one hand, time slices are introduced, and the exposure volume of each time slice is set to ensure that the exposure of contract advertisements is evenly distributed in various time periods, achieving the purpose of uniform playback. This allows the advertisements to reach the target audience in each time period, achieving the effect of uniform exposure of contract advertisements. On the other hand, the concepts of traffic quality and quality stratification are introduced. By calculating the initial service rate of each layer of quality traffic, the advertisements are placed according to the contract to complete the exposure, maximizing the platform's current advertising revenue and minimizing compensation due to insufficient order volume. Secondly, based on the data fed back in real time during the placement process, when the exposure volume does not meet the requirements, the service rate is adjusted in a timely manner to further ensure the exposure volume. When there is more exposure, the exposure is reduced from the lower-level quality traffic first, and when there is less exposure, the exposure is increased from the higher-level quality traffic first. This ensures that the high CTR audience receives a higher service rate than the low CTR audience, achieving the purpose of traffic filtering, improving the advertising effect within the contract advertisement placement period, enhancing the advertising placement value, and improving the advertiser's marketing effect.

[0186] In the above embodiments, dynamically adjusting the tiered service rate not only improves the click-through rate of campaigns, but also enhances other metrics such as return on investment (ROI) and conversion rate (CVR).

[0187] This application also provides a computing device cluster. The computing device cluster includes at least one computing device. The computing device can be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device can also be a terminal device such as a desktop computer, a laptop computer, or a smartphone.

[0188] like Figure 8 As shown, the computing device cluster includes at least one computing device 800. The memory 806 in one or more computing devices 800 within the computing device cluster may store the same memory for executing the above embodiments. Figures 2-7 Instructions for the advertising placement method explained.

[0189] In some possible implementations, the memory 806 of one or more computing devices 800 in the computing device cluster may also store memory for executing the above embodiments. Figures 2-7The explained voice interaction method includes some instructions. In other words, a combination of one or more computing devices 800 can jointly execute instructions for performing the above embodiments. Figures 2-7 Instructions for the advertising placement method explained.

[0190] It should be noted that the memories 806 in different computing devices 800 within the computing device cluster can store different instructions, each used to execute a portion of the functions of the voice interaction device. That is, the instructions stored in the memories 806 of different computing devices 800 can implement the functions described in the above embodiments.

[0191] This application also provides another computing device cluster. The connection relationships between the computing devices in this computing device cluster can be similarly referred to... Figure 8 The connection method of the computing device cluster. The difference is that the memory 806 of one or more computing devices 800 in this computing device cluster can store the same memory used to execute the above embodiments. Figures 2-7 Instructions for the advertising placement method explained.

[0192] In some possible implementations, the memory 806 of one or more computing devices 800 in the computing device cluster may also store memory for executing the above embodiments. Figures 2-7 The instructions for the explained advertising delivery method are partial. In other words, a combination of one or more computing devices 800 can jointly execute instructions for performing the above embodiments. Figures 2-7 Instructions for the advertising delivery method explained herein. This application also provides an electronic device, comprising:

[0193] Memory, used to store instructions executed by one or more processors of the device, and

[0194] Processor, used to execute the above embodiments combined with Figures 2 to 7 The advertising placement methods explained.

[0195] This application also provides a computer-readable storage medium, which can be any available medium that a computing device can store, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to perform a method XXX, or instruct the computing device to perform the above-described embodiments. Figures 2 to 7 The advertising placement methods explained.

[0196] This application also provides a computer program product containing instructions. The computer program product may be software or a program product containing instructions, capable of running on a computing device or stored on any usable medium. When the computer program product is run on at least one computing device, it causes the at least one computing device to perform the above-described embodiments. Figures 2 to 7 The advertising placement methods explained.

[0197] Now for reference Figure 9 The diagram shown is a block diagram of a SoC (System on Chip) 900 according to an embodiment of this application. Figure 9 In the diagram, similar components share the same reference numerals. Additionally, dashed boxes are an optional feature for more advanced SoCs. Figure 9 In this SoC 900, the following components are included: an interconnect unit 950 coupled to an application processor 910; a system proxy unit 980; a bus controller unit 990; an integrated memory controller unit 940; a group or one or more coprocessors 920, which may include integrated graphics logic, an image processor, an audio processor, and a video processor; a static random access memory (SRAM) unit 930; and a direct memory access (DMA) unit 960. In one embodiment, the coprocessor 920 includes a dedicated processor, such as, for example, a network or communication processor, a compression engine, a general-purpose computing on GPU (GPGPU), a high-throughput many-integrated core (MIC) processor, or an embedded processor.

[0198] The static random access memory (SRAM) cell 930 may include one or more computer-readable media for storing data and / or instructions. The computer-readable storage medium may store instructions, specifically, temporary and permanent copies of those instructions. These instructions may include, when executed by at least one unit in the processor, causing the SoC 900 to perform a processing method according to the above embodiments, as detailed in the above embodiments. Figure 2 and Figure 7 The advertising placement methods explained will not be repeated here.

[0199] The various embodiments of the mechanisms disclosed in this application can be implemented in hardware, software, firmware, or a combination of these implementation methods. Embodiments of this application can be implemented as computer programs or program code executable on a programmable system, the programmable system including at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device.

[0200] Program code can be applied to input instructions to execute the functions described in this application and generate output information. The output information can be applied to one or more output devices in a known manner. For the purposes of this application, the processing system includes any system having a processor such as, for example, a digital signal processor (DSP), a microcontroller, an application-specific integrated circuit (ASIC), or a microprocessor.

[0201] The program code can be implemented using a high-level procedural language or an object-oriented programming language to communicate with the processing system. Assembly language or machine language can also be used when needed. In fact, the mechanisms described in this application are not limited to any particular programming language. In either case, the language can be a compiled language or an interpreted language.

[0202] In some cases, the disclosed embodiments may be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments may also be implemented as instructions carried or stored thereon on one or more temporary or non-temporary machine-readable (e.g., computer-readable) storage media, which may be read and executed by one or more processors. For example, the instructions may be distributed via a network or through other computer-readable media. Therefore, machine-readable media may include any mechanism for storing or transmitting information in a machine-readable (e.g., computer-readable) form, including but not limited to floppy disks, optical disks, CD-ROMs, magneto-optical disks, read-only memory (ROM), random access memory (RAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic cards or optical cards, flash memory, or tangible machine-readable storage for transmitting information (e.g., carrier waves, infrared signals, digital signals, etc.) using the Internet in the form of electrical, optical, acoustic, or other propagation signals. Therefore, machine-readable media include any type of machine-readable medium suitable for storing or transmitting electronic instructions or information in a machine-readable (e.g., computer-readable) form.

[0203] In the accompanying drawings, some structural or methodological features may be shown in a specific arrangement and / or order. However, it should be understood that such a specific arrangement and / or order may not be necessary. Rather, in some embodiments, these features may be arranged in a manner and / or order different from that shown in the illustrative drawings. Furthermore, the inclusion of structural or methodological features in a particular figure does not imply that such features are required in all embodiments, and in some embodiments, these features may be omitted or may be combined with other features.

[0204] Although this application has been illustrated and described with reference to certain preferred embodiments thereof, those skilled in the art should understand that various changes in form and detail may be made thereto without departing from the spirit and scope of this application.

Claims

1. An advertising placement method, characterized in that, Applied to electronic devices, the method includes: Obtain the total exposure and exposure period agreed in the target contract advertisement, and divide the exposure period into N time slices according to a preset duration, where N is an integer greater than 1; The required exposure for the first time slot is determined based on the total exposure and the N time slots. The target contract advertisement is delivered in the first time slot according to the first service rate; For the nth time slot after the first time slot, the required exposure for the nth time slot is determined based on the required exposure for the (n-1)th time slot before the nth time slot and the actual exposure for the (n-1)th time slot, where n is less than or equal to N; Based on the exposure amount corresponding to the nth time slot, determine the nth service rate corresponding to the nth time slot; The target contract advertisement is delivered in the nth time slot according to the nth service rate.

2. The advertising placement method according to claim 1, characterized in that, Based on the required exposure for the (n-1)th time slot preceding the nth time slot and the actual exposure for the (n-1)th time slot, the required exposure for the nth time slot is determined, including: Determine the difference R between the required exposure for the (n-1)th time slot and the actual exposure for the (n-1)th time slot. n-1 ; The difference R n-1 The corresponding exposure is allocated to at least one time slice after the n-1 time slices; Based on the difference R n-1 The corresponding exposure allocation, along with the total exposure and the N time slices, determines the appropriate exposure for the nth time slice.

3. The advertising placement method according to claim 2, characterized in that, The difference R n-1 The corresponding exposure is allocated to at least one time slice after the n-1 time slices, including: When the time slice after n-1 consists of multiple time slices, the difference R is... n-1 The corresponding exposure is evenly distributed across the multiple time slices.

4. The advertising placement method according to claim 2 or 3, characterized in that, Based on the required exposure for the nth time slot, determine the nth service rate corresponding to the nth time slot, including: Traffic quality is stratified according to traffic quality stratification rules, whereby traffic quality is used to represent the historical click pass rate of a request, and each stratification is distributed across the N time slices. Determine the service rate for each time slice corresponding to the tier; Based on the (n-1)th service rate of the (n-1)th time slice, the difference R n-1 The service rate of the layer corresponding to the nth time slice is adjusted to obtain the nth service rate, and the nth service rate includes the service rates of each layer.

5. The advertising placement method according to claim 4, characterized in that, The traffic quality stratification rule is to stratify the requests according to their historical click rates, from highest to lowest.

6. The advertising placement method according to claim 5, characterized in that, The traffic quality stratification rule is to divide the traffic into high-quality stratification, medium-quality stratification and low-quality stratification according to the historical click rate from high to low, and the service rate of high-quality stratification is greater than that of medium-quality stratification, which is greater than that of low-quality stratification.

7. The advertising placement method according to claim 6, characterized in that, The determination of the service rate for each time slice includes: the service rate of the low-quality stratum corresponding to the nth service rate is 0.9 times the nth service rate; the service rate of the medium-quality stratum corresponding to the nth service rate is the nth service rate; and the service rate of the high-quality stratum corresponding to the nth service rate is greater than the nth service rate and less than 1.

8. The advertising placement method according to claim 4 or 5, characterized in that, The actual exposure of the nth time slice is the sum of the actual exposures corresponding to different flow quality layers of the nth time slice.

9. The advertising placement method according to any one of claims 1 to 8, characterized in that, The first service rate was obtained based on a greedy algorithm.

10. The advertising placement method according to any one of claims 1-9, characterized in that, The step of determining the required exposure for the first time slot based on the total exposure and the N time slots includes: Based on the historical traffic distribution within the N time slices and the total exposure, the required exposure for the first time slice is determined.

11. The advertising placement method according to claim 10, characterized in that, The exposure amount for the first time slot is the product of the total exposure amount and the estimated traffic percentage corresponding to the first time slot.

12. The advertising placement method according to claim 4, characterized in that, Also includes: Receive an ad delivery request, the request including the targeting conditions of the ad to be delivered; In response to the ad delivery request, an ad is delivered based on the targeting conditional contract. Obtain the service rate of the quality tier corresponding to each contract advertisement. When the service rate of the quality tier reaches the preset service rate, determine the target contract advertisement.

13. The advertising placement method according to claim 11, characterized in that, Identifying the target contract advertisement includes: Multiple candidate contract advertisements are identified, and the final target contract advertisement is determined based on the product of the service rate corresponding to each candidate contract advertisement and the historical click pass rate at the corresponding time.

14. An electronic device, characterized in that, include: A memory for storing instructions executed by one or more processors of an electronic device, and a processor for performing the advertising delivery method according to any one of claims 1 to 13.

15. A computing device cluster, characterized in that, It includes at least one computing device, each computing device including a processor and memory; The processor of the at least one computing device is used to execute instructions stored in the memory of the at least one computing device to cause the cluster of computing devices to perform the advertising delivery method as described in any one of claims 1 to 13.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on an electronic device, cause the electronic device to perform the advertising delivery method according to any one of claims 1 to 13.

17. A computer program product containing instructions, characterized in that, When the computer program product is run on an electronic device, the electronic device performs the advertising delivery method according to any one of claims 1 to 13.

Images