Intelligent frequency tracking method and device in advertisement putting, computer equipment and readable storage medium

Abstract

The invention discloses an intelligent frequency tracking method and device in advertisement putting, computer equipment and a readable storage medium, and the method comprises the steps: firstly obtaining an advertisement putting request containing a current frequency and a corresponding equipment number, and then obtaining a pre-configured frequency tracking calculation model to determine a target equipment demand number of the current frequency, judging whether the current equipment quantity reaches the target required quantity or not; if yes, responding to the request to carry out advertisement putting and recording frequency distribution; and if not, not responding. By means of the design, accurate tracking and intelligent control over the advertisement putting frequency are achieved, resource configuration is optimized, and the advertisement putting effect and the user experience are improved.

Description

Technical Field

[0001] The present invention relates to the field of advertising management, and in particular to a method, device, computer equipment and readable storage medium for intelligent frequency tracking in advertising delivery. Background Art

[0002] In the current advertising field, accurately controlling the frequency of advertising to achieve the best results is an important challenge. Traditional advertising methods often lack effective tracking and intelligent control of frequency, resulting in poor advertising results, and may cause overexposure or underexposure, affecting user experience and advertising effectiveness. At the same time, it is impossible to accurately decide whether to place an advertisement based on the relationship between the current number of devices and the target demand, making it difficult to achieve optimal resource allocation. Summary of the invention

[0003] The object of the present invention is to provide a method, device, computer equipment and readable storage medium for intelligent frequency tracking in advertising delivery.

[0004] In a first aspect, an embodiment of the present invention provides a method for intelligent frequency tracking in advertisement delivery, comprising:

[0005] Obtaining an advertisement delivery request, the advertisement delivery request including a current frequency and a current number of devices corresponding to the current frequency;

[0006] Obtain a pre-configured frequency tracking calculation model to determine the required number of target devices corresponding to the current frequency;

[0007] Determine whether the current number of devices reaches the target number of devices required;

[0008] If yes, respond to the advertisement delivery request to deliver the advertisement and record the frequency distribution;

[0009] If not, the advertisement delivery request is not responded to.

[0010] In a possible implementation manner, the obtaining of a preconfigured frequency tracking calculation model to determine the required number of target devices corresponding to the current frequency includes:

[0011] Obtaining order information, wherein the order information includes the number of times to be followed, the following requirements, and the exposure amount;

[0012] Obtaining a frequency distribution, wherein the frequency distribution includes a plurality of frequencies;

[0013] Calculate the frequency distance of each frequency according to the difference between the frequency distribution and the frequency to be chased;

[0014] Determining the remaining frequency proportion of each frequency according to the ratio of the reciprocal of the frequency distance to the sum of the reciprocals of the frequency distances;

[0015] taking the final frequency device ratio of each frequency as the product of the complementary number of the frequency pursuit requirement and the remaining frequency ratio of each frequency, and the sum of the frequency pursuit requirement and the complementary number of the frequency pursuit requirement is 1;

[0016] According to the final frequency device proportion and the exposure amount, the required number of devices corresponding to each frequency is calculated.

[0017] In a possible implementation, calculating the number of devices required for each frequency according to the final frequency device proportion and the exposure amount includes:

[0018] Obtaining the product of each of the frequencies and the final frequency device ratio of each of the frequencies and summing them up to obtain a sum of multiple frequencies and the corresponding final frequency device ratios;

[0019] Obtaining the total required number of devices according to the ratio of the exposure amount to the sum result;

[0020] The device requirement quantity corresponding to each frequency is obtained according to the product of the final frequency device proportion of each frequency and the total required device quantity.

[0021] In a possible implementation, the recording frequency distribution includes:

[0022] A cumulative frequency recording strategy is used to record each of the frequencies mentioned and the cumulative number of devices.

[0023] In a possible implementation, the method further includes:

[0024] When the current number of devices does not reach the target required number of devices, the current number of devices is obtained again for determination according to a preset waiting time interval until the target required number of devices is reached or a preset maximum number of waiting times is reached.

[0025] In a possible implementation, the method further includes:

[0026] The waiting time interval is dynamically adjusted according to historical delivery data and the activity level of the current time period.

[0027] In a possible implementation manner, after delivering advertisements in response to the advertisement delivery request and recording frequency distribution, the method further includes:

[0028] The advertising delivery effect is monitored in real time, and the frequency tracking calculation model is dynamically adjusted according to the advertising delivery effect.

[0029] In a second aspect, an embodiment of the present invention provides an intelligent frequency tracking device in advertising delivery, comprising:

[0030] An acquisition module is used to acquire an advertisement delivery request, wherein the advertisement delivery request includes a current frequency and a current number of devices corresponding to the current frequency; acquire a pre-configured frequency tracking calculation model to determine a required number of target devices corresponding to the current frequency;

[0031] The determination module is used to determine whether the current number of devices reaches the target number of devices required; if so, respond to the advertisement delivery request to deliver the advertisement and record the frequency distribution; if not, do not respond to the advertisement delivery request.

[0032] In a third aspect, an embodiment of the present invention provides a computer device, comprising a processor and a non-volatile memory storing computer instructions, wherein when the computer instructions are executed by the processor, the computer device executes the method described in at least one possible implementation of the first aspect.

[0033] In a fourth aspect, an embodiment of the present invention provides a readable storage medium, wherein the readable storage medium includes a computer program, and when the computer program is run, the computer device where the readable storage medium is located is controlled to execute the method described in at least one possible implementation manner of the first aspect.

[0034] Compared with the prior art, the beneficial effects provided by the present invention include: using the intelligent frequency tracking method, device, computer equipment and readable storage medium disclosed in the present invention in advertising delivery, obtaining an advertising delivery request including the current frequency and the corresponding number of devices, and then obtaining a pre-configured frequency tracking calculation model to determine the target device demand number of the current frequency, and then judging whether the current number of devices reaches the target demand number. If reached, respond to the request for advertising delivery and record the frequency distribution; if not reached, do not respond. This method realizes accurate tracking and intelligent control of advertising delivery frequency, optimizes resource allocation, and improves advertising delivery effect and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can also be obtained based on these drawings without creative work.

[0036] Figure 1 A schematic diagram of the steps of the intelligent frequency tracking method in advertising delivery provided by an embodiment of the present invention;

[0037] Figure 2 A schematic block diagram of the structure of an intelligent frequency tracking device for advertisement delivery provided by an embodiment of the present invention;

[0038] Figure 3 A schematic block diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0040] The specific implementation modes of the present invention are described in detail below in conjunction with the accompanying drawings.

[0041] In order to solve the technical problems in the aforementioned background technology, Figure 1 This is a flow chart of the intelligent frequency tracking method in advertising delivery provided by an embodiment of the present disclosure. The intelligent frequency tracking method in advertising delivery is introduced in detail below.

[0042] Step S201, obtaining an advertisement delivery request, wherein the advertisement delivery request includes a current frequency and a current number of devices corresponding to the current frequency;

[0043] Step S202, obtaining a pre-configured frequency tracking calculation model to determine the required number of target devices corresponding to the current frequency;

[0044] Step S203, determining whether the current number of devices reaches the target number of devices required;

[0045] Step S204: if yes, respond to the advertisement delivery request to deliver advertisements, and record the frequency distribution;

[0046] Step S205: If not, then do not respond to the advertisement delivery request.

[0047] In the embodiment of the present invention, for example, in a busy network environment, the server continuously receives requests from various terminals. At a certain moment, the server receives an advertisement delivery request. This request contains key information such as the current frequency and the current number of devices corresponding to the frequency.

[0048] Assume that the current ad delivery request is about the promotion of a newly launched smartphone, and its current frequency is marked as 2 times, and the corresponding current number of devices is 50. This means that so far, 50 devices have received this smartphone advertisement 2 times.

[0049] After receiving the ad delivery request, the server immediately obtains the pre-configured frequency tracking calculation model. To better understand this process, we assume the following order information and related configurations:

[0050] The order information shows that this advertising campaign needs to achieve 500 exposures, and the tracking requirement is that the proportion of devices with an exposure frequency greater than or equal to 3 times is greater than or equal to 70%, and the cycle frequency of each device is set to 5 times.

[0051] First, the server obtains the order information and frequency distribution. The frequency distribution shows that there is a certain distribution from 1 to 5 times.

[0052] Then, the server calculates the frequency distance of each frequency based on the difference between the frequency distribution and the frequency to be tracked (i.e., 3 times). For example, for a frequency of 1, its frequency distance from 3 is 2; for a frequency of 2, its frequency distance from 3 is 1.

[0053] Next, the server calculates the reciprocal of each frequency distance. For the above example, the reciprocal of the frequency distance of 1 is 1 / 2, and the reciprocal of the frequency distance of 2 is 1 / 1.

[0054] After that, the server adds up the reciprocals of all frequency distances to get the total. Assume that the total is 3 (1 / 2+1 / 1+1 / 0+1 / (-1)+1 / (-2)).

[0055] Then, the remaining frequency ratio of each frequency is determined based on the ratio of the reciprocal of the frequency distance to the sum of the reciprocals. For example, the remaining frequency ratio of 1 is 1 / 2÷3=1 / 6; the remaining frequency ratio of 2 is 1 / 1÷3=1 / 3.

[0056] Since the frequency chasing requirement is that the proportion of devices with an exposure frequency of 3 or more times is greater than or equal to 70%, the complementary number is 30%. The server multiplies the complementary number of the frequency chasing requirement by the remaining frequency proportion of each frequency to obtain the final frequency device proportion of each frequency. For example, the final frequency device proportion of 1 time is 30%×1 / 6=5%; the final frequency device proportion of 2 times is 30%×1 / 3=10%.

[0057] Finally, the server calculates the number of devices required for each frequency based on the final frequency device ratio and exposure (500 times).

[0058] The specific calculation process is as follows:

[0059] First, the server calculates the product of each frequency and the final frequency device ratio. For example, the product of 1 time is 1×5%=5%; the product of 2 times is 2×10%=20%.

[0060] Then, these product results are added together to obtain a sum result. Assume that the sum result is 80%.

[0061] Next, the server divides the exposure amount of 500 by the summed result of 80%, and the total number of devices required is 625.

[0062] Finally, the server calculates the product of the final frequency device ratio of each frequency and the total number of required devices to obtain the number of devices required for each frequency. For example, the number of devices required for 1 time is 625×5%=31.25 units (approximately 31 units); the number of devices required for 2 times is 625×10%=62.5 units (approximately 63 units).

[0063] Through the above complex but precise calculations, the server determines that the target device demand quantity corresponding to the current frequency of 2 is 100.

[0064] The server compares the current number of devices (50) corresponding to the current frequency 2 with the calculated target number of devices required (100).

[0065] Obviously, 50 devices are less than 100 devices, and the current number of devices does not meet the target device demand.

[0066] Since the current number of devices does not meet the target number of devices, the server decides not to respond to this ad delivery request. The server will temporarily put this request on hold and wait for more devices to meet the corresponding frequency conditions.

[0067] Assume that after a period of time, new devices are added, making the number of devices corresponding to the current frequency 2 reach 100.

[0068] After the server confirms that the current number of devices has reached the target number of devices required, it responds to the advertisement delivery request and delivers advertisements to these devices.

[0069] At the same time, the server uses a cumulative frequency recording strategy to record the frequency distribution.

[0070] Through such detailed and accurate records, the server can grasp the frequency distribution of advertising in real time, providing strong data support for subsequent optimization and adjustment.

[0071] In summary, through the above series of rigorous steps and calculations, the server has achieved the tracking and control of the intelligent frequency in advertising delivery, ensuring the optimal effect and efficiency of advertising delivery.

[0072] In the embodiment of the present invention, the obtaining of a preconfigured frequency tracking calculation model and the determination of the required number of target devices corresponding to the current frequency may be implemented through the following examples.

[0073] Obtaining order information, wherein the order information includes the number of times to be followed, the following requirements, and the exposure amount;

[0074] Obtaining a frequency distribution, wherein the frequency distribution includes a plurality of frequencies;

[0075] Calculate the frequency distance of each frequency according to the difference between the frequency distribution and the frequency to be chased;

[0076] Determining the remaining frequency proportion of each frequency according to the ratio of the reciprocal of the frequency distance to the sum of the reciprocals of the frequency distances;

[0077] taking the final frequency device ratio of each frequency as the product of the complementary number of the frequency pursuit requirement and the remaining frequency ratio of each frequency, and the sum of the frequency pursuit requirement and the complementary number of the frequency pursuit requirement is 1;

[0078] According to the final frequency device proportion and the exposure amount, the required number of devices corresponding to each frequency is calculated.

[0079] In the embodiment of the present invention, illustratively, when processing the task of advertising delivery, the server first obtains a pre-configured frequency tracking calculation model to determine the number of target device requirements corresponding to the current frequency.

[0080] The server obtains the order information. Assuming that this order is for promoting a new smart watch, the order information includes that the tracking frequency must be 4 times. The tracking requirement is that the proportion of devices with an exposure frequency greater than or equal to 4 times is not less than 60%, and the exposure volume is 800 times.

[0081] At the same time, the server obtains the current frequency distribution. Assume that the frequency distribution is: there are 150 devices for 1 time, 100 devices for 2 times, 80 devices for 3 times, 50 devices for 4 times, and 30 devices for 5 times.

[0082] Next, the server calculates the frequency distance of each frequency based on the difference between the frequency distribution and the frequency to be tracked (4 times). The frequency distance of 1 is 3, the frequency distance of 2 is 2, the frequency distance of 3 is 1, the frequency distance of 4 is 0, and the frequency distance of 5 is -1.

[0083] Then, calculate the reciprocal of each frequency distance. The reciprocal of the frequency distance of 1 is 1 / 3, 2 is 1 / 2, 3 is 1, 4 is 0, and the reciprocal is considered infinite, and 5 is -1 (because the distance is negative, the reciprocal is treated as -1).

[0084] Then add up the reciprocals of all frequency distances. Assume the sum is 5 (1 / 3+1 / 2+1+infinity-1).

[0085] After that, the remaining frequency ratio of each frequency is determined based on the ratio of the reciprocal of the frequency distance to the sum of the reciprocals. The remaining frequency ratio of 1 time is 1 / 3÷5=1 / 15, 2 times is 1 / 2÷5=1 / 10, 3 times is 1÷5=1 / 5, 4 times is considered as 0 because the distance is 0, and 5 times is -1÷5=-1 / 5 (here, the ratio cannot be negative, so it is treated as 0).

[0086] Since the frequency tracking requirement is that the proportion of devices with an exposure frequency of 4 times or more must be no less than 60%, the complementary number is 40%. The server multiplies the complementary number of the frequency tracking requirement by the remaining frequency proportion of each frequency to obtain the final frequency device proportion of each frequency. The final frequency device proportion of 1 time is 40%×1 / 15≈2.67%, 2 times is 40%×1 / 10=4%, 3 times is 40%×1 / 5=8%, 4 times is 40%×0=0, and 5 times is 40%×0=0.

[0087] Finally, the server calculates the number of devices required for each frequency based on the final frequency device share and exposure.

[0088] First, calculate the product of each frequency and the final frequency device ratio. The product of 1 time is 1×2.67%≈2.67%, 2 times is 2×4%=8%, and 3 times is 3×8%=24%.

[0089] These multiplication results are then added together, assuming the sum is 34.67%.

[0090] Next, divide the exposure amount 800 by the summed result 34.67%, and the total number of devices required is approximately 2,307.

[0091] Finally, the product of the final frequency equipment ratio of each frequency and the total number of equipment required is calculated to obtain the number of equipment required for each frequency. The number of equipment required for 1 time is about 2307×2.67%≈62 units, the number of equipment required for 2 times is about 2307×4%=92 units, and the number of equipment required for 3 times is about 2307×8%=185 units.

[0092] Through such precise and detailed calculations, the server successfully determined the number of target devices required for each frequency, providing accurate data support for subsequent advertising decisions.

[0093] In the embodiment of the present invention, the required number of devices corresponding to each frequency is calculated according to the final frequency device proportion and the exposure amount, which can be implemented through the following example.

[0094] Obtaining the product of each of the frequencies and the final frequency device ratio of each of the frequencies and summing them up to obtain a sum of multiple frequencies and the corresponding final frequency device ratios;

[0095] Obtaining the total required number of devices according to the ratio of the exposure amount to the sum result;

[0096] The device requirement quantity corresponding to each frequency is obtained according to the product of the final frequency device proportion of each frequency and the total required device quantity.

[0097] In the embodiment of the present invention, exemplarily, during the process of processing advertisement delivery, the server needs to accurately calculate the number of devices required for each frequency based on the final frequency device ratio and exposure.

[0098] Assume that the final frequency device proportions obtained by the server are as follows: the final frequency device proportions of 1 time are 5%, 2 times are 10%, 3 times are 15%, 4 times are 20%, and 5 times are 25%.

[0099] First, the server calculates the product of each frequency and the final frequency device ratio of each frequency. The product of 1 time is 1×5%=0.05, the product of 2 times is 2×10%=0.2, the product of 3 times is 3×15%=0.45, the product of 4 times is 4×20%=0.8, and the product of 5 times is 5×25%=1.25.

[0100] Then, the server sums these product results. 0.05+0.2+0.45+0.8+1.25=2.75, which is the sum of multiple frequencies and the corresponding final frequency device proportions.

[0101] Next, assume that the exposure of this ad is set to 1000 times. The server obtains the total number of devices required based on the ratio of the exposure to the above summation result. That is, 1000÷2.75≈363.64 (rounded up to 364), which is the total number of devices required.

[0102] Finally, the server obtains the number of devices required for each frequency based on the product of the final frequency device ratio of each frequency and the total number of required devices.

[0103] The number of equipment required for 1 time is 364×5%=18.2 (rounded up to 19) units.

[0104] The number of equipment required for the second time is 364×10%=36.4 (rounded up to 37).

[0105] The number of equipment required for the third time is 364×15%=54.6 (rounded up to 55).

[0106] The number of equipment required for the 4th time is 364×20%=72.8 (rounded up to 73) units.

[0107] The number of equipment required for 5 times is 364×25%=91 (units).

[0108] Through such rigorous and detailed calculations, the server accurately obtains the number of devices required for each frequency. This provides a solid data foundation for the server to accurately control and optimize the delivery strategy in subsequent advertising. For example, when there is a new ad delivery request, the server can quickly determine whether the number of devices corresponding to the current frequency meets the demand, and thus decide whether to deliver the ad. It can also dynamically adjust the subsequent delivery strategy according to the actual delivery situation to achieve the best advertising delivery effect and resource utilization efficiency.

[0109] In the embodiment of the present invention, the recording frequency distribution may be implemented through the following examples.

[0110] A cumulative frequency recording strategy is used to record each of the frequencies mentioned and the cumulative number of devices.

[0111] In the embodiment of the present invention, for example, during the process of advertisement delivery, the server needs to accurately record the frequency distribution. Assume that advertisement delivery is currently being performed for a popular online game.

[0112] When the server starts, it initializes a table that records the frequency distribution, as shown in Table 1:

[0113] Table 1

[0114] Frequency Cumulative number of devices 1 time 0 2 times 0 3 times 0 4 times 0 5 times 0

[0115] When the first batch of ad delivery requests arrives, 10 devices receive the first ad delivery. The server updates the record to Table 2 according to the cumulative frequency recording strategy:

[0116] Table 2

[0117] Frequency Cumulative number of devices 1 time 10 2 times 0 3 times 0 4 times 0 5 times 0

[0118] Then, another 5 devices received the second advertisement. At this time, the server updates the record again, which can be seen in Table 3:

[0119] Table 3

[0120] Frequency Cumulative number of devices 1 time 10 2 times 5 3 times 0 4 times 0 5 times 0

[0121] As the ad delivery continued, another 8 devices received the third ad delivery.

[0122] The record becomes Table 4:

[0123] Table 4

[0124] Frequency Cumulative number of devices 1 time 10 2 times 5 3 times 8 4 times 0 5 times 0

[0125] After that, devices received advertisements of different frequencies. For example, three devices received the fourth advertisement, and the records were updated to Table 5:

[0126] Table 5

[0127] Frequency Cumulative number of devices 1 time 10 2 times 5 3 times 8 4 times 3 5 times 0

[0128] Finally, when two devices received the fifth advertisement, the final record was as shown in Table 6:

[0129] Table 6

[0130] Frequency Cumulative number of devices 1 time 10 2 times 5 3 times 8 4 times 3 5 times 2

[0131] Through such a cumulative frequency recording strategy, the server can clearly understand the number of devices covered by each frequency of advertising. This is of great significance for the subsequent analysis of advertising effects, optimization of delivery strategies, and meeting advertisers' delivery requirements. For example, the server can judge whether the predetermined delivery target has been achieved based on these records, and whether the intensity and scope of delivery need to be adjusted. If the advertiser wants more devices to achieve a higher delivery frequency, the server can increase the advertising delivery to specific devices in a targeted manner based on the current records, so as to improve the overall delivery effect and meet the expectations of the advertiser.

[0132] In short, by adopting the cumulative frequency recording strategy, the server can fully and accurately grasp the frequency distribution of advertising delivery, providing strong data support for the optimization and management of the entire advertising delivery process.

[0133] In an embodiment of the present invention, the method further includes:

[0134] When the current number of devices does not reach the target required number of devices, the current number of devices is obtained again for determination according to a preset waiting time interval until the target required number of devices is reached or a preset maximum number of waiting times is reached.

[0135] In the embodiment of the present invention, for example, it is assumed that the server is processing an advertisement delivery task for a car brand. The target device demand quantity corresponding to the current frequency is 500, but the current number of devices obtained is only 300, which does not reach the target device demand quantity.

[0136] The server obtains the current number of devices again for judgment according to the preset waiting time interval. The preset waiting time interval is 10 minutes.

[0137] Ten minutes later, the server obtains the current number of devices again and finds that it has increased to 350, which is still below the target of 500, so it continues to wait.

[0138] After another 10 minutes, the server checked again. At this time, the current number of devices reached 420, which still did not meet the target device requirement, so it continued to wait.

[0139] In this way, every 10 minutes, the server will re-acquire and determine the current number of devices.

[0140] After waiting for many times, for example, 50 minutes, the server obtains that the current number of devices is 480, which still does not reach the target of 500.

[0141] However, at this time, the preset maximum waiting number has been reached, assuming that the maximum waiting number is 6. Since the maximum waiting number has been reached, even if the current number of devices does not reach the target device requirement number, the server will no longer continue to wait, but will perform corresponding processing according to the current situation.

[0142] Or, in a check after waiting, the server finds that the current number of devices has finally reached the target of 500. At this time, the server will respond to the ad delivery request, deliver the ad, and record the frequency distribution and other related operations according to the process described above.

[0143] In another case, if this is an advertisement for a newly launched smartphone accessory, the target device demand quantity is 800 units and the initial current device quantity is 400 units.

[0144] The server also repeats the acquisition and judgment operations with a waiting time interval of 15 minutes.

[0145] After the first 15-minute wait, the current number of devices becomes 480; after the second 15-minute wait, the number becomes 550; after the third 15-minute wait, the number becomes 620; after the fourth 15-minute wait, the number becomes 700; and after the fifth 15-minute wait, the number becomes 760.

[0146] After the sixth wait of 15 minutes, the server obtained that the current number of devices was 780, which did not reach the target number of 800. However, since the preset maximum number of waiting times of 6 was reached, the server stopped waiting.

[0147] Through such a mechanism, the server can flexibly handle the situation where the current number of devices does not meet the target number of devices within a certain time and number of times, so as to balance the effectiveness and efficiency of advertising delivery.

[0148] In an embodiment of the present invention, the method further includes:

[0149] The waiting time interval is dynamically adjusted according to historical delivery data and the activity level of the current time period.

[0150] In the embodiment of the present invention, for example, assume that the server is processing an advertisement delivery task for a popular game. In the past historical delivery data, the server finds that the user activity in the morning is relatively low and the number of devices grows slowly; while in the afternoon and evening, the user activity is high and the number of devices grows rapidly.

[0151] In the current delivery process, the server receives an ad delivery request at 9 a.m., and the initial waiting time interval is set to 15 minutes. After the first 15-minute wait, the server obtains the current number of devices and finds that only 50 devices have been added, which is far lower than expected. The server analyzes historical delivery data and confirms that the activity level is usually low during the morning hours, so it extends the waiting time interval to 30 minutes.

[0152] At 12 noon, user activity began to increase. The server obtained the current number of devices again at 30-minute intervals. This time, it found that the number of devices increased by 150, and the growth rate increased, but it still did not reach the target number of devices. Based on the rising trend of activity in the current period and the performance of similar periods in historical data, the server adjusted the waiting time interval to 20 minutes.

[0153] At 2 p.m., the server obtains the data again, and the number of devices has increased by 250, with a significantly faster growth rate. At this time, the server refers to the high activity in the afternoon in the historical data and further shortens the waiting time interval to 10 minutes.

[0154] At 5 p.m., when user activity was at its peak, the server retrieved the current number of devices after a 10-minute interval and found that it had increased by 400. As activity continued to rise, the server continued to wait for 10 minutes.

[0155] At 8 p.m., the activity level gradually stabilized and the growth rate of the number of devices slowed down. The server adjusted the waiting time interval to 15 minutes based on the trend of this period in historical data and the current growth situation.

[0156] By constantly referring to historical delivery data and monitoring the activity of the current period in real time, the server can dynamically and accurately adjust the waiting time interval to more efficiently meet the target number of device requirements and optimize advertising delivery effects and resource utilization efficiency.

[0157] For example, the server is placing ads for a new e-commerce app. In the historical weekend data, the server found that the user activity on Saturday morning was average, and the initial waiting time interval was set to 20 minutes. After the first acquisition, the number of current devices did not increase much, so the server extended the interval to 25 minutes after analysis.

[0158] At noon, the activity level increased, and the server adjusted the waiting time interval to 18 minutes based on historical data of similar weekend noon situations.

[0159] During the afternoon, activity continued to increase, and the server gradually shortened the waiting time interval to 12 minutes.

[0160] During the evening, activity reaches a peak and then begins to decline, and the server appropriately extends the waiting time interval to 15 minutes.

[0161] In this way, the server can flexibly and accurately adjust the waiting time interval according to different applications, different dates and time periods, ensuring that advertising can achieve the best effect at the most appropriate time.

[0162] In the embodiment of the present invention, after delivering advertisements in response to the advertisement delivery request and recording the frequency distribution, the following implementation methods are also provided.

[0163] The advertising delivery effect is monitored in real time, and the frequency tracking calculation model is dynamically adjusted according to the advertising delivery effect.

[0164] In the embodiment of the present invention, for example, it is assumed that the server has responded to an advertisement delivery request for a promotion activity on an e-commerce platform and recorded the frequency distribution. After the advertisement delivery begins, the server monitors various indicators in real time to evaluate the effect of the advertisement delivery.

[0165] The first thing the server looks at is the click-through rate (CTR). By analyzing the data, the server found that the CTR was 2% in the initial delivery phase. As time went on, the CTR gradually dropped to 1.5%. The server further analyzed and found that the CTR of certain ads with certain frequencies was significantly lower than the average.

[0166] For example, for an ad that has been run 5 times, the click-through rate is only 1%. The server also pays attention to the conversion rate, that is, the proportion of purchases that are completed through ad clicks. Assume that the initial conversion rate is 5%, but in subsequent monitoring, it is found that the conversion rate is stagnant and has not reached the expected growth trend.

[0167] The server compares and analyzes these data with the previously set frequency tracking calculation model. In the original frequency tracking calculation model, the proportion of high-frequency (such as 5 times) devices is relatively high, but the actual results show that high-frequency ads do not bring corresponding effect improvement.

[0168] Based on this, the server dynamically adjusts the frequency tracking calculation model. First, it reduces the proportion of high-frequency (such as 5 times) devices, and allocates more delivery opportunities to low-frequency but better-performing intervals. For example, some devices that were originally planned to be delivered 5 times are adjusted to be delivered 3 times.

[0169] At the same time, the server will also make more detailed adjustments based on user behavior data. For example, it is found that young user groups respond better to advertisements, while the response of elderly user groups is relatively weak. Then when adjusting the frequency tracking calculation model, for devices with young user groups, the delivery frequency is appropriately increased or the delivery time is optimized; for devices with elderly user groups, the delivery frequency is reduced or the delivery content is adjusted.

[0170] In addition, if the server monitors that the advertising effect is particularly good in a certain time period (such as 8pm to 10pm), and the click-through rate and conversion rate are significantly higher than other time periods, then in subsequent delivery, the delivery volume will be increased in this time period, and the delivery frequency in other time periods will be adjusted accordingly.

[0171] For example, when launching a new mobile app ad, the server found that the initial frequency tracking calculation model caused the ad to be overexposed in some areas and underexposed in other areas. Therefore, the server readjusted the device frequency distribution based on user feedback and engagement in different regions to achieve more balanced and effective ad coverage.

[0172] By monitoring the effectiveness of advertising in real time and dynamically adjusting the frequency tracking calculation model, the server can continuously optimize the advertising delivery strategy and improve the effectiveness of advertising and the return on investment.

[0173] In order to more clearly describe the solution of the present application, a more complete implementation scheme is provided below.

[0174] The first part is to calculate the number of frequency devices

[0175] The operator enters the order information;

[0176] The operator enters the frequency tracking requirements, for example, the proportion of devices with exposure frequency greater than or equal to 3 times is greater than or equal to 70%;

[0177] Calculate the number of devices required for each frequency based on the intelligent frequency tracking calculation model:

[0178] Intelligent frequency tracking calculation model formula: Assuming that the delivery requires the ad to be played 100 times, the cycle frequency of each device is 5, and the proportion of devices with frequency tracking of 3 times or more must be at least 0.7, then the proportion of devices with N times can be defined as 0.7, and the proportion of devices with the remaining frequencies is 0.3. The overall number of devices for each frequency is calculated as follows:

[0179] The frequency distribution is obtained as 1-5, the frequency to be chased is 3, and the frequency chasing requirement is 0.7. The distance between other frequencies and the frequency 3 of the chasing frequency is determined, and then the reciprocal of the distance from other frequencies to the frequency 3 of the chasing frequency is determined; according to the reciprocal sum of other frequencies, how to distribute the remaining 30% of devices for the remaining frequencies is determined, and according to the device proportion of all frequencies, except for the frequency chasing frequency 3, the device proportion of other frequencies is calculated to obtain the single required exposure number 100, and the equation for calculating the exposure number through the frequency proportion, frequency, and variable x is obtained, and the variable x is 33.33, and then the final number of devices for each frequency is calculated from 1 to 5 as 2, 3, 23, 3, and 2. Through the above calculation, the final proportion of devices greater than or equal to frequency 3 is 85%, and the number of device requirements calculated previously is written into the database.

[0180] The ad delivery service controls the number of times each device is delivered based on the results of the previous calculation:

[0181] The terminal requests the advertising system;

[0182] Read the frequency tracking requirements, that is, the calculated number of devices for each frequency;

[0183] Determine whether the frequency corresponding to the current order has reached the device number requirement;

[0184] If it is reached, it cannot be delivered; if it is not reached, it can be delivered;

[0185] If delivered, record the frequency distribution;

[0186] Frequency distribution records are recorded in the form of cumulative frequency records.

[0187] Please refer to Figure 2 , Figure 2 An intelligent frequency tracking device 110 for advertising delivery provided by an embodiment of the present invention includes:

[0188] The acquisition module 1101 is used to acquire an advertisement delivery request, wherein the advertisement delivery request includes a current frequency and a current number of devices corresponding to the current frequency; acquire a pre-configured frequency tracking calculation model to determine a required number of target devices corresponding to the current frequency;

[0189] The determination module 1102 is used to determine whether the current number of devices reaches the target number of devices required; if so, respond to the advertisement delivery request to deliver the advertisement and record the frequency distribution; if not, do not respond to the advertisement delivery request.

[0190] It should be noted that the implementation principle of the intelligent frequency tracking device 110 in the aforementioned advertising delivery can refer to the implementation principle of the intelligent frequency tracking method in the aforementioned advertising delivery, and will not be repeated here. It should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the intelligent frequency tracking device 110 in advertising delivery can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The function of the intelligent frequency tracking device 110 in the above advertising delivery. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in a processor element or an instruction in software form.

[0191] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASICs), or one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (FPGAs), etc. For another example, when a module above is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0192] The embodiment of the present invention provides a computer device 100, which includes a processor and a non-volatile memory storing computer instructions. When the computer instructions are executed by the processor, the computer device 100 executes the aforementioned intelligent frequency tracking device 110 in advertising delivery. Figure 3 As shown, Figure 3 The computer device 100 is a block diagram of a structure of a computer device 100 provided in an embodiment of the present invention. The computer device 100 includes an intelligent frequency tracking device 110 for advertisement delivery, a memory 111, a processor 112 and a communication unit 113.

[0193] In order to realize data transmission or interaction, the memory 111, the processor 112 and the communication unit 113 are electrically connected to each other directly or indirectly. For example, the electrical connection between these components can be realized through one or more communication buses or signal lines. The intelligent frequency tracking device 110 for advertising delivery includes at least one software function module that can be stored in the memory 111 in the form of software or firmware or solidified in the operating system (OS) of the computer device 100. The processor 112 is used to execute the intelligent frequency tracking device 110 for advertising delivery stored in the memory 111, such as the software function modules and computer programs included in the intelligent frequency tracking device 110 for advertising delivery.

[0194] An embodiment of the present invention provides a readable storage medium, which includes a computer program. When the computer program is executed, the computer device where the readable storage medium is located is controlled to execute the aforementioned intelligent frequency tracking method in advertising delivery.

[0195] For illustrative purposes, the foregoing description is made with reference to specific embodiments. However, the above illustrative discussion is not intended to be exhaustive or to limit the present disclosure to the precise form disclosed. Numerous modifications and variations are possible in accordance with the above teachings. These embodiments are selected and described in order to best illustrate the principles of the present disclosure and its practical application, so that those skilled in the art can best utilize the present disclosure and utilize various embodiments with different modifications to suit the intended specific application.

Claims

1. An intelligent frequency tracking method in advertising delivery, characterized in that: include: Obtaining an advertisement delivery request, the advertisement delivery request including a current frequency and a current number of devices corresponding to the current frequency; Obtain a pre-configured frequency tracking calculation model to determine the required number of target devices corresponding to the current frequency; Determine whether the current number of devices reaches the target number of devices required; If yes, respond to the advertisement delivery request to deliver the advertisement and record the frequency distribution; If not, the advertisement delivery request is not responded to.

2. The method according to claim 1, characterized in that The obtaining of a pre-configured frequency tracking calculation model to determine the required number of target devices corresponding to the current frequency includes: Obtaining order information, wherein the order information includes the number of times to be followed, the following requirements, and the exposure amount; Obtaining a frequency distribution, wherein the frequency distribution includes a plurality of frequencies; Calculate the frequency distance of each frequency according to the difference between the frequency distribution and the frequency to be chased; Determining the remaining frequency proportion of each frequency according to the ratio of the reciprocal of the frequency distance to the sum of the reciprocals of the frequency distances; taking the final frequency device proportion of each frequency as the product of the complementary number of the frequency pursuit requirement and the remaining frequency proportion of each frequency, and the sum of the frequency pursuit requirement and the complementary number of the frequency pursuit requirement is 1; According to the final frequency device proportion and the exposure amount, the required number of devices corresponding to each frequency is calculated.

3. The method according to claim 2, characterized in that According to the final frequency device proportion and the exposure, the number of devices required for each frequency is calculated, including: Obtaining the product of each of the frequencies and the final frequency device ratio of each of the frequencies and summing them up to obtain a sum of multiple frequencies and the corresponding final frequency device ratios; Obtaining the total required number of devices according to the ratio of the exposure amount to the sum result; The device requirement quantity corresponding to each frequency is obtained according to the product of the final frequency device proportion of each frequency and the total required device quantity.

4. The method according to claim 1, characterized in that: The record frequency distribution includes: A cumulative frequency recording strategy is used to record each of the frequencies mentioned and the cumulative number of devices.

5. The method according to claim 1, characterized in that The method further comprises: When the current number of devices does not reach the target required number of devices, the current number of devices is obtained again for determination according to a preset waiting time interval until the target required number of devices is reached or a preset maximum number of waiting times is reached.

6. The method according to claim 5, characterized in that The method further comprises: The waiting time interval is dynamically adjusted according to historical delivery data and the activity level of the current time period.

7. The method according to claim 1, characterized in that After delivering advertisements in response to the advertisement delivery request and recording the frequency distribution, the method further includes: The advertising delivery effect is monitored in real time, and the frequency tracking calculation model is dynamically adjusted according to the advertising delivery effect.

8. An intelligent frequency tracking device for advertising delivery, characterized in that: include: An acquisition module, configured to acquire an advertisement delivery request, wherein the advertisement delivery request includes a current frequency and a current number of devices corresponding to the current frequency; Obtain a pre-configured frequency tracking calculation model to determine the required number of target devices corresponding to the current frequency; The determination module is used to determine whether the current number of devices reaches the target number of devices required; if so, respond to the advertisement delivery request to deliver the advertisement and record the frequency distribution; if not, do not respond to the advertisement delivery request.

9. A computer device, characterized in that: The computer device comprises a processor and a non-volatile memory storing computer instructions. When the computer instructions are executed by the processor, the computer device executes the method according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium includes a computer program, and when the computer program is executed, the computer device where the readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

Images