Information processing method, device and storage medium

By obtaining the adjustment information and historical data of advertising delivery, dynamically adjusting the initial allocation data and competition probability of advertising delivery, the problem of insufficient data accumulation and out-of-synchronization of traffic quality and quantity in the cold start stage of advertising delivery is solved, and the advertising delivery is improved Accuracy and effectiveness optimize cost-effectiveness.

CN113743703BActive Publication Date: 2024-11-15BEIJING WODONG TIANJUN INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110152370.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-02-03
Publication Date
2024-11-15
Estimated Expiration
2041-02-03

AI Technical Summary

Technical Problem

The existing technology has failed to effectively solve the problems of insufficient data accumulation and out-of-synchronization of traffic quality and quantity in the cold start stage, resulting in unreliable advertising effect, and the budget allocation method cannot be dynamically adjusted according to traffic quality, affecting the advertising effect. .

Method used

By obtaining the adjustment information, historical data allocation information and expected data for the current time period, determine the initial allocation data and target competition probability of the next time period, and dynamically adjust it based on the adjustment information, initial allocation data and time period information to the next time period The competition process is carried out during the time period to improve the accuracy and effectiveness of advertising delivery.

Benefits of technology

Improve the accuracy and effectiveness of advertising delivery, increase the amount of user feedback data, optimize the output/input ratio, and ensure that advertising delivery is more allocated for periods of good traffic quality, and less allocated for poor traffic quality, achieving the best cost-effectiveness change.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113743703B_ABST
    Figure CN113743703B_ABST
Patent Text Reader

Abstract

The embodiment of the present invention discloses an information processing method and device, and a storage medium, including obtaining adjustment information of a target object in a current time period, historical data allocation information of the target object, and expected data of the target object; determining initial allocation data corresponding to the next time period from expected data according to the historical data allocation information and the adjustment information; determining a target competition probability of the target object in the next time period according to the adjustment information, the initial allocation data, the initial competition probability, and the time period information; the initial competition probability is the competition probability of the target object in the current time period, and the time period information includes the current time period and the next time period; and executing the competition process of the target object according to the target competition probability when the next time period arrives.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to an information processing method and device, and a storage medium. Background Art

[0002] In recent years, with the continuous development of Internet technology, Internet technology can be used to promote and publicize information of target objects, which has also caused a series of problems.

[0003] In the prior art, when the expected data of the target object is obtained, the expected data is evenly distributed according to the number of preset time periods to obtain average expected data, so that the target object is publicized and promoted according to the average expected data within each preset time period, so that the amount of user feedback data obtained when the target object is processed using the average expected data is small, thereby reducing the accuracy of processing the target object. Summary of the invention

[0004] In order to solve the above technical problems, embodiments of the present invention are intended to provide an information processing method and device, and a storage medium, which can improve the accuracy of an information processing device when processing a target object.

[0005] The technical solution of the present invention is achieved in this way:

[0006] The present application provides an information processing method, including:

[0007] Acquire adjustment information of a target object in a current time period, historical data allocation information of the target object, and expected data of the target object;

[0008] Determining initial allocation data corresponding to a next time period from the expected data according to the historical data allocation information and the adjustment information;

[0009] The target competition probability of the target object in the next time period is determined according to the adjustment information, the initial allocation data, the initial competition probability and the time period information; the initial competition probability is the competition probability of the target object in the current time period, and the time period information includes the current time period and the next time period; when the next time period arrives, the competition process of the target object is executed according to the target competition probability.

[0010] The present application provides an information processing device, the device comprising:

[0011] an acquisition unit, configured to acquire adjustment information of a target object in a current time period, historical data allocation information of the target object, and expected data of the target object;

[0012] A determination unit is used to determine the initial allocation data corresponding to the next time period from the expected data according to the historical data allocation information and the adjustment information; determine the target competition probability of the target object in the next time period according to the adjustment information, the initial allocation data, the initial competition probability and the time period information of the target object; the initial competition probability is the competition probability of the target object in the current time period, and the time period information includes the current time period and the next time period; so that when the next time period arrives, the competition process of the target object is executed according to the target competition probability.

[0013] The present application provides an information processing device, the device comprising:

[0014] A memory, a processor and a communication bus, wherein the memory communicates with the processor via the communication bus, and the memory stores an information processing program executable by the processor. When the information processing program is executed, the information processing method described above is executed by the processor.

[0015] An embodiment of the present application provides a storage medium having a computer program stored thereon, which is applied to an information processing device, and is characterized in that the computer program implements the above-mentioned information processing method when executed by a processor.

[0016] The embodiment of the present invention provides an information processing method, device and storage medium. The information processing method includes: obtaining adjustment information of a target object in a current time period, historical data allocation information of the target object and expected data of the target object; determining the initial allocation data corresponding to the next time period from the expected data according to the historical data allocation information and the adjustment information; determining the target competition probability of the target object in the next time period according to the adjustment information, the initial allocation data, the initial competition probability and the time period information; the initial competition probability is the competition probability of the target object in the current time period, and the time period information includes the current time period and the next time period; when the next time period arrives, the competition process of the target object is executed according to the target competition probability. The above method is adopted to implement the scheme, and the information processing device obtains the adjustment information of the target object, determines the initial allocation data of the target object from the expected data of the target object according to the adjustment information and the historical data allocation information of the target object, and determines the target competition probability of the next time period of the target object according to the adjustment information, the initial allocation data, the initial competition probability and the time period information, so as to execute the competition process of the target object in the next time period according to the target competition probability, thereby increasing the amount of user feedback data and improving the accuracy of the information processing device in processing the target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flow chart of an information processing method provided in an embodiment of the present application;

[0018] Figure 2 A flowchart of an exemplary information processing method provided in an embodiment of the present application;

[0019] Figure 3 A schematic diagram of the structure of an information processing device provided in an embodiment of the present application Figure 1 ;

[0020] Figure 4 A schematic diagram of the structure of an information processing device provided in an embodiment of the present application Figure 2 . DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0022] In the online advertising industry, the smart bidding product OCPX (such as OCPC, OCPM, OCPA, and TCPA) is a product with a relatively large usage rate and revenue scale among advertisers in the market. In smart bidding products, the system automatically adjusts the bid based on the conversion effect, and the indicator that advertisers are concerned about is the output / input ratio. When the advertiser's input cost is fixed, how to improve the output is a very worthy issue to study, which can optimize the common interests of both the platform and the advertiser. Taking e-commerce advertisers as an example, the indicator that advertisers usually pay attention to is orders, and they hope that the ads they put out can bring as many orders as possible. However, the budget of a single advertiser is usually limited, so optimizing the output / input ratio is to optimize the effect of advertising (such as orders) under the condition of budget constraints.

[0023] The advertiser's budget is usually set based on their own funds and delivery experience to expect stable advertising delivery daily consumption. However, for the ocpx product, the initial advertising delivery must go through a cold start phase. In this phase, the accumulated data of the advertisement is small and the effect is not yet stable. It is necessary to accumulate data with a relatively low budget first, and then enter the normal delivery phase after reaching the data confidence threshold. In order to handle the special situation of cold start, this method adjusts the daily budget set by the advertiser based on the budget set by the advertiser and the delivery time and effect.

[0024] In the normal delivery stage, the effect of advertising is closely related to the quality of traffic. During the day, the distribution of traffic quality is uneven. Therefore, the budget during the day should be allocated in direct proportion to the quality of traffic. The usual practice is to allocate more budget in time periods with good traffic quality and less budget in time periods with poor traffic quality. The budget of the current time period is determined in advance. The probability of participating in the competition in the current time period is calculated based on the budget of the current time period to control the traffic. There are many budget allocation methods at present. The simplest one is to divide a day into 24 time periods by hour, and evenly allocate the advertiser's budget to each hour. After the budget of this hour is spent, there will be no more traffic in this hour. In the next hour, the traffic will be taken again under the new budget conditions with a certain probability of participating in the competition to ensure that the budget is spent more smoothly in a day. Another budget allocation method is to allocate the advertiser's budget according to the traffic distribution of yesterday or the previous few days, so as to ensure that the budget is more during the peak traffic period, and the advertiser can get more traffic during the peak traffic period. The third method is to have dynamically adjusted traffic control, that is, to determine the budget and competition probability of the next time period based on the ratio of the actual expenditure and budget of the previous time period.

[0025] Current traffic control technologies have some inherent defects. For example, they do not take into account the particularity of the cold start phase of advertising delivery, and directly adjust the budget for advertisements with insufficient data accumulation. Another example is the technology of evenly allocating the budget by hour to control hourly traffic. Although it ensures the stable expenditure of the budget and avoids the situation where the budget is exhausted in a few hours and no traffic is obtained in the later period, the even allocation method cannot allocate the budget according to the quality of traffic to control the traffic, which is not suitable for advertisers who focus on results. The technology of allocating budgets according to historical traffic distribution improves this problem, allowing advertisers to get more traffic during peak traffic. However, peak traffic is the peak of traffic quantity, and the quality of traffic may still be uneven, which is still not very reliable for ensuring the effect of advertising delivery. At present, the most widely used traffic control technology in major companies is the dynamic adjustment of traffic control technology, that is, according to the ratio of actual expenditure to budget in the previous time period, the budget and competition probability of the next time period are determined. The basic idea is that the traffic distribution is continuously changing. The more money spent in the previous time period, the more budget allocated in the next time period. Although this method can quickly adjust the budget and competition probability according to the traffic distribution, it still does not take into account the problem of the lack of synchronization between traffic quantity and quality.

[0026] Embodiment 1

[0027] The present application embodiment provides an information processing method, Figure 1 An information processing method provided in the embodiment of the present application Figure 1 ,like Figure 1 As shown, the information processing method may include:

[0028] S101: Acquire adjustment information of a target object in a current time period, historical data allocation information of the target object, and expected data of the target object.

[0029] An information processing method provided in an embodiment of the present application is applicable to a scenario in which an information processing device determines a target competition probability of a target object.

[0030] In the embodiments of the present application, the information processing device can be implemented in various forms. For example, the information processing device described in the present application may include devices such as mobile phones, cameras, tablet computers, laptop computers, PDAs, portable media players (PMPs), navigation devices, wearable devices, smart bracelets, pedometers, and devices such as digital TVs and desktop computers.

[0031] In the embodiment of the present application, the target object may be an advertisement. Specifically, the target object may be a clothing advertisement or a food advertisement. The target object may also be an advertisement for other commodities. The specific one may be determined according to actual conditions, and the embodiment of the present application does not limit this.

[0032] In the embodiment of the present application, if the target object is an advertisement, the target object may be an advertisement played on the Douyin platform, an advertisement played on the JD platform, or an advertisement played on other platforms. The specific amount may be determined based on actual conditions, and the embodiment of the present application does not limit this.

[0033] In the embodiment of the present application, in a real-time bidding (RTB) advertisement, whether an advertisement unit participates in the bidding is determined based on the bidding probability.

[0034] In the embodiment of the present application, the adjustment information of the target object may be information obtained according to the current historical expected data and the current historical consumption information of the target object.

[0035] In the embodiment of the present application, the historical data allocation information may be a ratio between the total value of the allocation information of the target object at the same time point in the past period of time and the total value of the expected data of the target object in the past period of time.

[0036] Exemplarily, if the same time point is 8-9 o'clock, the historical data allocation information may be the data allocation information of the target object at 8-9 o'clock every day in the past 5 days; if the data allocation information of the target object at 8-9 o'clock every day in the past 5 days totals 500 yuan, and if the expected data in the past 5 days totals 2000 yuan, then the historical data allocation information is the ratio between the data allocation information of the target object at 8-9 o'clock every day in the past 5 days and the expected data in the past 5 days, that is, the historical data allocation information is 500:2000=1:4.

[0037] In the embodiment of the present application, the expected data of the target object may be the estimated expenditure information of the target object on the day. For example, if the information processing device obtains that the estimated expenditure of the target object in one day is 2,000 yuan, the expected data of the target object is 2,000 yuan.

[0038] In the embodiment of the present application, the information processing device needs to allocate the expected data of the target object every day to determine the multiple time period spending information corresponding to the multiple time periods of the target object within a day.

[0039] It should be noted that a plurality of time periods correspond to a plurality of time period spending information one by one, wherein one time period corresponds to one time period spending information.

[0040] Exemplarily, the information processing device may divide a day into hours to obtain 24 time periods, each of which lasts for one hour.

[0041] In the embodiment of the present application, the information processing device may calculate the initial allocation data and the target competition probability at a preset time point in each time period.

[0042] Exemplarily, the information processing device may start calculating the initial allocation data and the target competition probability at the hour of each time period; the information processing device may also start calculating the initial allocation data and the target competition probability at 59 minutes into each time period; the information processing device may also start calculating the initial allocation data and the target competition probability at other time points in each time period. The specific time points may be determined based on actual conditions, and the embodiments of the present application are not limited to this.

[0043] In an embodiment of the present application, the information processing device may generate an instruction for obtaining the competition probability at a preset time point in each time period, and then the information processing device may calculate the initial allocation data and the target competition probability according to the instruction for obtaining the competition probability.

[0044] In an embodiment of the present application, before the information processing device obtains the adjustment information of the target object in the current time period, the information processing device also obtains the historical consumption information, historical feedback quantity and historical expected consumption information of the target object; the information processing device determines the initial adjustment information based on the historical consumption information, historical feedback quantity and historical expected consumption information; the information processing device performs proportional and differential processing on the initial adjustment information to obtain the adjustment information.

[0045] In an embodiment of the present application, in an embodiment of the present application, the information processing device determines the process of initial adjustment information based on historical consumption information, historical feedback quantity and historical expected consumption information. The information processing device can obtain the quotient of historical consumption information and historical feedback quantity to obtain actual spending information of the target object. The information processing device then determines the difference between the actual spending information of the target object and the historical expected consumption information; and divides the difference by the historical expected consumption information to obtain adjustment information.

[0046] In the embodiment of the present application, the information processing device determines the process of initial adjustment information according to the historical consumption information, the historical feedback quantity and the historical expected consumption information, as shown in formulas (1)-(2):

[0047] cpa_diff=(cpa-tcpa) / tcpa (1)

[0048] cpa = cost / order_num (2)

[0049] Among them, cpa_diff is the initial adjustment information; cost is the historical consumption information, that is, the current consumption information of the target object on that day; order_num is the historical feedback quantity, that is, the current order quantity of the target object on that day; tcpa is the historical expected consumption information, that is, the historical expected expenditure (target cost per action) of the target object; cpa is the actual expenditure (cost per action) information of the target object.

[0050] It should be noted that the meaning of cpa_diff is in the conversion dimension, that is, the difference between the cpa (actual cost) and tcpa (expected cost) of a single conversion. When cpa_diff is greater than 0, it means that the actual cost is greater than the expected cost, which is an over-cost state. When cpa_diff is less than or equal to 0, it means that the actual cost is less than the expected cost, which is generally called the achievement state.

[0051] It should also be noted that if the current target object's ad unit is in an over-cost state, it means that the current traffic can bring less conversions than advertisers expect, the traffic quality cannot meet advertisers' needs, and the traffic quality is poor. If the current ad unit is in an achieved state, it means that the current traffic can bring more conversions than advertisers expect, and the traffic quality is good. A basic idea to ensure the effectiveness of the unit is to get more traffic when the traffic quality is good and less traffic when the traffic quality is poor. On the premise of ensuring that the daily expenditure does not exceed the advertiser's budget, try to allocate the budget to the time period with good traffic quality, so that the single conversion cost is as small as possible and the ad unit is achieved as much as possible.

[0052] In the embodiment of the present application, the process of the information processing device performing proportional and differential processing on the initial adjustment information is as shown in formula (3):

[0053] delta=c1*cpa_diff1+c2*(cpa_diff1-cpa_diff2) (3)

[0054] Among them, cpa_diff1 is the initial information, c1*cpa_diff1 is the process of the information processing device performing proportional processing on the initial adjustment information, c2*(cpa_diff1-cpa_diff2) is the process of the information processing device performing differential processing on the initial adjustment information. The information processing device sums the process of performing proportional processing on the initial adjustment information and the process of performing differential processing on the initial adjustment information to obtain the adjustment information.

[0055] It should be noted that cpa_diff2 is the initial adjustment information determined by the information processing device in the previous time period, cpa_diff1-cpa_diff2 is the difference between two adjacent initial adjustment information determined by the information processing device, which is used to indicate the changing trend of the initial adjustment information; c1 is the first preset hyperparameter when the information processing device performs proportional processing on the initial adjustment information, and c2 is the second preset hyperparameter when the information processing device performs differential processing on the initial adjustment information.

[0056] It should also be noted that the first preset hyperparameter and the second preset hyperparameter are both preset values, which are values ​​configured in the information processing device. The first preset hyperparameter and the second preset hyperparameter can also be the values ​​received by the information processing device before performing proportional and differential processing on the initial adjustment information. The specific values ​​can be determined according to actual conditions, and the embodiments of the present application are not limited to this.

[0057] In the embodiment of the present application, the information processing device can determine the adjustment information once every period of time according to the historical consumption information, the historical feedback quantity and the historical expected consumption information. The length of a period of time can be 1 minute, 1 second, 0.5 ms, or other time lengths, which can be determined according to actual conditions and are not limited in the embodiment of the present application.

[0058] S102: Determine initial allocation data corresponding to the next time period from expected data according to historical data allocation information and adjustment information.

[0059] In an embodiment of the present application, after the information processing device obtains the adjustment information of the target object in the current time period, the historical data allocation information of the target object and the expected data of the target object, the information processing device determines the initial allocation data corresponding to the next time period from the expected data based on the historical data allocation information and the adjustment information.

[0060] In an embodiment of the present application, the process of an information processing device determining the initial allocation data corresponding to the next time period from the expected data based on the historical data allocation information and the adjustment information includes: when the historical consumption information of the target object is less than or equal to the preset threshold, the information processing device determines the initial allocation data from the expected data according to the historical allocation information; when the historical consumption information is greater than the preset threshold, the preset adjustment coefficient of the target object is obtained; the information processing device determines the initial allocation data from the expected data based on the adjustment information, the historical data allocation information and the preset adjustment coefficient.

[0061] It should be noted that the preset threshold is a threshold preset in the information processing device, or it may be a threshold received by the information processing device before the information processing device allocates information and adjusts information based on historical data and determines the initial allocated data corresponding to the next time period from the expected data. It may also be a threshold configured in the information processing device. The specific threshold can be determined based on actual conditions, and the embodiments of the present application are not limited to this.

[0062] In an embodiment of the present application, when the historical consumption information is greater than a preset threshold, the information processing device determines the process of initial allocation data based on the adjustment information, expected data and historical data allocation information. The information processing device can first obtain the product of the preset adjustment coefficient and the adjustment information, and then the information processing device obtains the difference between the expected data and the product. Finally, the information processing device determines the product of the historical data allocation information and the difference to obtain the initial allocation data.

[0063] In the embodiment of the present application, the information processing device determines the process of initially allocating data according to the adjustment information, the expected data and the historical data allocation information, as shown in formula (4):

[0064] hour_target=(total_target-ADJUST_RATA*delta)*hour_rate (4)

[0065] Among them, total_target is the expected data of the target object; delta is the adjustment information of the target object, specifically the current cumulative delivery effect of the unit; hour_rate is the historical data allocation information of the target object, that is, the proportion of the hourly traffic of the market in the past n days; hour_target is the initial allocation data of the target object; ADJUST_RATA is the preset adjustment coefficient, that is, the preset hyperparameter, which is used to adjust the effect of the delivery effect on the preset adjustment. When it is expected that this unit will fluctuate more on the advertiser's budget (expected data), this preset hyperparameter takes a larger value. When it is expected that this unit will fluctuate less on the advertiser's budget (expected data), this hyperparameter takes a smaller value.

[0066] S103, determining the target competition probability of the target object in the next time period according to the adjustment information, the initial allocation data, the initial competition probability and the time period information; the initial competition probability is the competition probability of the target object in the current time period, and the time period information includes the current time period and the next time period; when the next time period arrives, the competition process of the target object is executed according to the target competition probability.

[0067] In an embodiment of the present application, after the information processing device determines the initial allocation data corresponding to the next time period from the expected data based on the historical data allocation information and adjustment information, the information processing device can determine the target competition probability of the target object in the next time period based on the adjustment information, the initial allocation data, the initial competition probability and the time period information.

[0068] It should be noted that the initial competition probability is the competition probability of the target object in the current time period; the time period information includes the current time period and the next time period.

[0069] In an embodiment of the present application, before the information processing device determines the target competition probability of the target object in the next time period based on the adjustment information, the initial allocation data, the initial competition probability and the time period information, the information processing device also obtains the time period information, the preset adjustment step and the initial competition probability of the target object; wherein the time period information includes the current consumption information of the target object in the current time period. Accordingly, the process of the information processing device determining the target competition probability of the target object in the next time period based on the adjustment information, the initial allocation data, the initial competition probability and the time period information includes: the information processing device adjusts the initial allocation data according to the current consumption information, the adjustment information and the preset adjustment step to obtain the adjusted allocation data; the information processing device determines the target competition probability according to the adjusted allocation data, the initial competition probability and the time period information.

[0070] In an embodiment of the present application, the information processing device adjusts the initial allocation data according to the current consumption information, adjustment information and preset adjustment step to obtain the adjusted allocation data, including: the information processing device first obtains the product of the preset adjustment step and the adjustment information, and then the information processing device obtains the difference between the value 1 and the product; the information processing device obtains the target competition probability by obtaining the product between the initial allocation data and the difference.

[0071] In the embodiment of the present application, the information processing device determines the process of adjusting the allocation data according to the current consumption information, the initial allocation data, the adjustment information and the preset adjustment step, as shown in formula (5):

[0072] new_target=old _target*(1-UPDATE_RATE*delta) (5)

[0073] Among them, new_target is the adjusted allocation data, that is, the budget after this adjustment; old_target is the initial allocation data, that is, the budget before this adjustment; delta is the adjustment information of the target object; UPDATE_RATE is the preset adjustment step, that is, the hyperparameter, which is the value configured in the information processing device.

[0074] It should be noted that UPDATE_RATE represents the adjustment step size, which is set separately in the cold start phase and the normal phase.

[0075] a. Initialization at 0:00 every day is based on the hourly target consumption generated by daily statistics. During normal operation (not cold start phase), it is based on the previous hourly target consumption.

[0076] b. When a new unit enters the hourly target consumption adjustment for the first time, it is adjusted based on the preset hourly target consumption.

[0077] c. UPDATE_RATE can be set separately for upward and downward adjustment, and can also be set separately in the cold start phase and the normal phase to adapt to different situations, UPDATE_RATE_INC (hourly target consumption upward adjustment step), UPDATE_RATE_DEC (hourly target consumption downward adjustment step).

[0078] d. To avoid drastic changes in the budget in adjacent time periods, this method sets the maximum range of a single adjustment, INCR_RATE_MAX (maximum range of a single upward adjustment of the hourly target consumption) and DECR_RATE_MAX (maximum range of a single downward adjustment of the hourly target consumption), and sets the upper and lower adjustment ranges in the cold start phase and the normal phase respectively.

[0079] In an embodiment of the present application, the information processing device adjusts the initial allocation data according to the current consumption information, the adjustment information and the preset adjustment step to obtain the adjusted allocation data, including: the information processing device filters out the target data with the largest data value from the initial allocation data and the current consumption information; the information processing device adjusts the target data using the adjustment information and the preset adjustment step to obtain the adjusted allocation data.

[0080] In an embodiment of the present application, the adjustment step includes a cold start adjustment step and a non-cold start adjustment step. The information processing device uses the adjustment information and the preset adjustment step to adjust the target data to obtain the adjusted allocation data. The process includes: when the historical consumption information of the target object is less than or equal to the preset threshold, the target data is adjusted using the adjustment information and the cold start adjustment step to obtain the adjusted allocation data; when the historical consumption information is greater than the preset threshold, the target data is adjusted using the adjustment information and the non-cold start adjustment step to obtain the adjusted allocation data.

[0081] It should be noted that the non-cold start adjustment step size is larger than the cold start adjustment step size.

[0082] In an embodiment of the present application, the process in which the information processing device determines the target competition probability based on the adjusted allocation data, the initial competition probability and the time period information includes: the information processing device determines the consumption error based on the time period information and the adjusted allocation data; the information processing device determines the target competition probability based on the initial competition probability, the consumption error and the current consumption information.

[0083] It should be noted that the time period information includes current consumption information, the time span of the current time period, the time span of the next time period and adjusted allocation data (target consumption of the next time period).

[0084] It should also be noted that the current consumption information is: when initialized at 0:00 every day: the consumption from 0:00 to the current time of the day. When running normally: the consumption from the timestamp of the last program run to the current time.

[0085] It should also be noted that the time span of the current time period is: when initialized at 0 o'clock every day: the timestamp of the latest data that can be obtained - 0 o'clock. During normal operation: the timestamp of the latest data that can be obtained - the timestamp of the last program run end.

[0086] It should also be noted that the adjusted allocation data is: current hour target consumption - current hour cumulative consumption; the time span of the next time period: the length from the current moment to the next nearest hour.

[0087] In an embodiment of the present application, the information processing device determines the process of consumption error based on time period information and adjusted allocation data, including the information processing device determining the ratio of the time span of the next time period to the time span of the current time period, and then the information processing device obtains the product of the current consumption information and the ratio, and finally the information processing device obtains the consumption error based on the difference between the adjusted allocation data and the product.

[0088] As shown in formula (6):

[0089] residual=c_next-c_last* (tm_next / tm_last) (6)

[0090] Among them, residual is the consumption error, c_next is the adjusted allocation data c_last, tm_next and tm_last are consumption information. Specifically, c_last is the current consumption information, that is, the actual cost of the current time window; tm_next is the time span of the next time period; tm_last is the time span of the current time period.

[0091] In the embodiment of the present application, the information processing device determines the first competition probability according to the initial competition probability, the consumption error and the current consumption information, as shown in formula (7):

[0092] r_next=r_last*(c_last+residual) / c_last (7)

[0093] Among them, r_last is the initial competition probability, residual is the consumption error, c_last is the current consumption information, and r_next is the first competition probability.

[0094] In an embodiment of the present application, the process of an information processing device determining a target competition probability based on an initial competition probability, a consumption error, and current consumption information includes the information processing device determining a first competition probability based on the initial competition probability, the consumption error, and current consumption information; when the historical consumption information of the target object is less than or equal to a preset threshold, screening the target competition probability with the largest competition probability value from the first competition probability and the initial competition probability; when the historical consumption information is greater than the preset threshold, using the first competition probability as the target competition probability.

[0095] It should be noted that when the information processing device determines that the historical consumption information of the target object is less than or equal to the preset threshold, the target object is in the cold start stage; when the information processing device determines that the historical consumption information of the target object is greater than the preset threshold, the target object is in the non-cold start stage, that is, the target object is in the normal delivery stage.

[0096] It can be understood that when the advertising unit is in the cold start stage, the information processing device selects the maximum bidding probability with the largest bidding probability value from the first bidding probability and the initial bidding probability as the target bidding probability, so that the target bidding probability is not adjusted downward, thereby accumulating data as soon as possible to enter the normal delivery stage.

[0097] It should be noted that the value range of the target competition probability is between 0 and 1. The information processing device will randomly discard traffic in the next time period according to the target competition probability to achieve the purpose of controlling cost protection effect.

[0098] For example, Figure 2 As shown, the present application embodiment provides an exemplary information processing method flow chart:

[0099] 1. The information processing device obtains the historical consumption information, historical feedback quantity and historical expected consumption information of the target object.

[0100] 2. The information processing device determines initial adjustment information based on historical consumption information, historical feedback quantity and historical expected consumption information.

[0101] 3. The information processing device performs proportional and differential processing on the initial adjustment information to obtain adjustment information.

[0102] 4. The information processing device obtains adjustment information of the target object in the current time period, historical data allocation information of the target object, and expected data of the target object.

[0103] 5. When the historical consumption information of the target object is less than or equal to a preset threshold, the information processing device determines the initial allocation data from the expected data according to the historical allocation information.

[0104] 6. When the historical consumption information is greater than a preset threshold, the information processing device obtains a preset adjustment coefficient of the target object.

[0105] It should be noted that after step 4, the information processing device may execute step 5 or step 6.

[0106] 7. The information processing device determines the initial allocation data from the expected data according to the adjustment information, the historical data allocation information and the preset adjustment coefficient.

[0107] 8. The information processing device obtains the time period information, preset adjustment step size, and initial competition probability of the target object.

[0108] It should be noted that step 8 can be directly executed after step 5; step 8 can also be executed after step 7.

[0109] It should be noted that the time period information includes the current consumption information of the target object in the current time period.

[0110] 9. The information processing device selects the target data with the largest data value from the initial allocation data and the current consumption information.

[0111] 10. When the historical consumption information of the target object is less than or equal to a preset threshold, the information processing device adjusts the target data using the adjustment information and the cold start adjustment step to obtain adjusted allocation data.

[0112] 11. When the historical consumption information is greater than a preset threshold, the information processing device uses the adjustment information and the non-cold start adjustment step to adjust the target data to obtain the adjusted allocation data.

[0113] It should be noted that after step 9, the information processing device may execute step 10 or step 11.

[0114] 12. The information processing device determines the consumption error based on the time period information and the adjusted allocation data.

[0115] It should be noted that step 12 may be directly executed after step 10; step 12 may also be executed after step 11.

[0116] 13. The information processing device determines the first competition probability based on the initial competition probability, the consumption error and the current consumption information.

[0117] 14. When the historical consumption information of the target object is less than or equal to a preset threshold, the information processing device selects a target competition probability with the largest competition probability value from the first competition probability and the initial competition probability.

[0118] 15. When the historical consumption information is greater than a preset threshold, the information processing device uses the first competition probability as the target competition probability.

[0119] It should be noted that after step 13, the information processing device may execute step 14 or step 15.

[0120] It can be understood that the adjustment information of the target object is offline data information, and the historical data allocation information of the target object, the expected data of the target object, the initial competition probability, time period information, etc. are real-time data information. The information processing device uses the offline data information and real-time data information to allocate the expected data of the target object, and determine the target competition probability of the target object in the next time period. When the next time period arrives, the competition process of the target object is executed according to the target competition probability, so that the information processing device can achieve minute-level effects and continuously process the target object in units of minutes.

[0121] The method of this application is verified online on the off-site advertising TCPA product, and the absolute value of the effect improvement on the unit consuming confidence is shown in Table 1:

[0122] Table 1 Test data comparison table

[0123] Unit Achievement Rate Consumption Achievement Rate Improved value 1.40% 4.80%

[0124] Among them, the improvement value = experimental group index - control group index. The experimental group adopts this method, while the control group does not. The flow rates of the experimental group and the control group are the same, and the other variables are the same.

[0125] Unit achievement rate = number of achieved units / total number of units, which is the indicator that advertisers are most concerned about.

[0126] Consumption achievement rate = achieved unit consumption / total consumption, which is the indicator that the platform cares most about.

[0127] It can be seen from the experimental results that the effect brought by the method of the present invention is positive, can be correctly implemented and used normally in an industrial-grade system, and has a positive effect on actual advertising delivery.

[0128] It can be understood that the information processing device obtains the adjustment information of the target object, determines the initial allocation data of the target object from the expected data of the target object according to the adjustment information and historical data allocation information of the target object, and determines the target competition probability of the target object in the next time period according to the adjustment information, the initial allocation data, the initial competition probability and the time period information, so as to execute the competition process of the target object in the next time period according to the target competition probability, thereby increasing the amount of user feedback data and improving the accuracy of the information processing device in processing the target object.

[0129] Embodiment 2

[0130] Based on the same inventive concept of the first embodiment, the embodiment of the present application provides an information processing device 1, corresponding to an information processing method; Figure 3 A schematic diagram of the structure of an information processing device provided in an embodiment of the present application Figure 1 , the information processing device 1 may include:

[0131] An acquisition unit 11 is used to acquire adjustment information of a target object in a current time period, historical data allocation information of the target object, and expected data of the target object;

[0132] The determination unit 12 is used to determine the initial allocation data corresponding to the next time period from the expected data according to the historical data allocation information and the adjustment information; determine the target competition probability of the target object in the next time period according to the adjustment information, the initial allocation data, the initial competition probability and the time period information of the target object; the initial competition probability is the competition probability of the target object in the current time period, and the time period information includes the current time period and the next time period; so that when the next time period arrives, the competition process of the target object is executed according to the target competition probability.

[0133] In some embodiments of the present application, the device further comprises a processing unit;

[0134] The acquisition unit 11 is used to acquire the historical consumption information, historical feedback quantity and historical expected consumption information of the target object;

[0135] The determining unit 12 is used to determine initial adjustment information according to the historical consumption information, the historical feedback quantity and the historical expected consumption information;

[0136] The processing unit is used to perform proportional and differential processing on the initial adjustment information to obtain the adjustment information.

[0137] In some embodiments of the present application, the device further comprises an adjustment unit;

[0138] The acquisition unit 11 is used to acquire the time period information, the preset adjustment step, and the initial competition probability of the target object, wherein the time period information includes the current consumption information of the target object in the current time period;

[0139] Correspondingly, the adjustment unit is used to adjust the initial allocation data according to the current consumption information, the adjustment information and the preset adjustment step to obtain adjusted allocation data;

[0140] The determining unit 12 is configured to determine the target competition probability according to the adjusted allocation data, the initial competition probability and the time period information.

[0141] In some embodiments of the present application, the device further comprises a screening unit;

[0142] The screening unit is used to screen out target data with the largest data value from the initial allocation data and the current consumption information;

[0143] The adjustment unit is used to adjust the target data using the adjustment information and the preset adjustment step to obtain the adjusted allocation data.

[0144] In some embodiments of the present application, the preset adjustment step size includes a cold start adjustment step size and a non-cold start adjustment step size;

[0145] The adjustment unit is used to adjust the target data using the adjustment information and the cold start adjustment step to obtain the adjusted allocation data when the historical consumption information of the target object is less than or equal to a preset threshold; and to adjust the target data using the adjustment information and the non-cold start adjustment step to obtain the adjusted allocation data when the historical consumption information of the target object is greater than the preset threshold; the non-cold start adjustment step is greater than the cold start adjustment step.

[0146] In some embodiments of the present application, the determination unit 12 is used to determine the consumption error based on the time period information and the adjusted allocation data; and determine the target competition probability based on the initial competition probability, the consumption error and the current consumption information.

[0147] In some embodiments of the present application, the determining unit 12 is used to determine a first competition probability according to the initial competition probability, the consumption error and the current consumption information;

[0148] The screening unit is used to screen the target competition probability with the largest competition probability value from the first competition probability and the initial competition probability when the historical consumption information of the target object is less than or equal to a preset threshold; and to use the first competition probability as the target competition probability when the historical consumption information is greater than the preset threshold.

[0149] In some embodiments of the present application, the acquisition unit 11 is used to acquire a preset adjustment coefficient of the target object when the historical consumption information of the target object is greater than a preset threshold;

[0150] The determination unit 12 is used to determine the initial allocation data from the expected data based on the adjustment information, the historical data allocation information and the preset adjustment coefficient; when the historical consumption information is less than or equal to the preset threshold, the initial allocation data is determined from the expected data according to the historical allocation information.

[0151] It should be noted that, in actual applications, the above-mentioned acquisition unit 11 and determination unit 14 can be implemented by a processor 13 on the information processing device 1, specifically a CPU (Central Processing Unit), an MPU (Microprocessor Unit), a DSP (Digital Signal Processing) or a field programmable gate array (FPGA); the above-mentioned data storage can be implemented by a memory 14 on the information processing device 1.

[0152] The embodiment of the present invention further provides an information processing device 1, such as Figure 4 As shown, the information processing device 1 includes: a processor 13, a memory 14 and a communication bus 15. The memory 14 communicates with the processor 13 via the communication bus 15. The memory 14 stores a program executable by the processor 13. When the program is executed, the information processing method described above is executed by the processor 13.

[0153] In practical applications, the memory 14 may be a volatile memory, such as a random access memory (RAM); or a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk (HDD) or a solid-state drive (SSD); or a combination of the above types of memory, and provide instructions and data to the processor 13.

[0154] An embodiment of the present invention provides a computer-readable storage medium having a computer program thereon, and when the program is executed by the processor 13, the information processing method as described above is implemented.

[0155] It can be understood that the information processing device obtains the adjustment information of the target object, determines the initial allocation data of the target object from the expected data of the target object according to the adjustment information and historical data allocation information of the target object, and determines the target competition probability of the target object in the next time period according to the adjustment information, the initial allocation data, the initial competition probability and the time period information, so as to execute the competition process of the target object in the next time period according to the target competition probability, thereby increasing the amount of user feedback data and improving the accuracy of the information processing device in processing the target object.

[0156] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0157] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0158] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0159] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0160] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. An information processing method, characterized in that: The method comprises: Acquire adjustment information of the target object in the current time period, historical data allocation information of the target object, and expected data of the target object; the adjustment information is information obtained based on the current historical expected data and current historical consumption information of the target object; the historical data allocation information is the ratio between the total value of the allocation information of the target object at the same time point in the past period of time and the total value of the expected data of the target object in the past period of time; the expected data is the estimated spending information of the target object on the day; Determining initial allocation data corresponding to a next time period from the expected data according to the historical data allocation information and the adjustment information; Determine the target competition probability of the target object in the next time period according to the adjustment information, the initial allocation data, the initial competition probability and the time period information; the initial competition probability is the competition probability of the target object in the current time period, and the time period information includes the current time period and the next time period; when the next time period arrives, execute the competition process of the target object according to the target competition probability; Before obtaining the adjustment information of the target object in the current time period, the method further includes: Obtaining historical consumption information, historical feedback quantity, and historical expected consumption information of the target object; Determining initial adjustment information according to the historical consumption information, the historical feedback quantity and the historical expected consumption information; Performing proportional and differential processing on the initial adjustment information to obtain the adjustment information; The determining, from the expected data according to the historical data allocation information and the adjustment information, the initial allocation data corresponding to the next time period comprises: In a case where the historical consumption information of the target object is less than or equal to a preset threshold, determining the initial allocation data from the expected data according to the historical data allocation information; When the historical consumption information is greater than a preset threshold, obtaining a preset adjustment coefficient of the target object; The initial allocation data is determined from the expected data according to the adjustment information, the historical data allocation information and the preset adjustment coefficient.

2. The method according to claim 1, characterized in that Before determining the target competition probability of the target object in the next time period according to the adjustment information, the initial allocation data, the initial competition probability and the time period information, the method further includes: Acquire the time period information, the preset adjustment step, and the initial competition probability of the target object, wherein the time period information includes the current consumption information of the target object in the current time period; Accordingly, determining the target competition probability of the target object in the next time period according to the adjustment information, the initial allocation data, the initial competition probability and the time period information includes: Adjusting the initial allocation data according to the current consumption information, the adjustment information and the preset adjustment step to obtain adjusted allocation data; The target competition probability is determined according to the adjusted allocation data, the initial competition probability and the time period information.

3. The method according to claim 2, characterized in that The adjusting the initial allocation data according to the current consumption information, the adjustment information and the preset adjustment step to obtain the adjusted allocation data includes: Filtering out target data with the largest data value from the initial allocation data and the current consumption information; The target data is adjusted using the adjustment information and the preset adjustment step to obtain the adjusted allocation data.

4. The method according to claim 3, characterized in that The preset adjustment step size includes a cold start adjustment step size and a non-cold start adjustment step size, and the adjusting the target data using the adjustment information and the preset adjustment step size to obtain the adjusted allocation data includes: When the historical consumption information of the target object is less than or equal to a preset threshold, adjusting the target data by using the adjustment information and the cold start adjustment step to obtain the adjusted allocation data; When the historical consumption information is greater than a preset threshold, the target data is adjusted using the adjustment information and the non-cold start adjustment step to obtain the adjusted allocation data; the non-cold start adjustment step is greater than the cold start adjustment step.

5. The method according to claim 2, characterized in that: The determining the target competition probability according to the adjusted allocation data, the initial competition probability and the time period information includes: determining a consumption error based on the time period information and the adjusted allocation data; The target competition probability is determined according to the initial competition probability, the consumption error and the current consumption information.

6. The method according to claim 5, characterized in that The determining the target competition probability according to the initial competition probability, the consumption error and the current consumption information includes: Determining a first competition probability according to the initial competition probability, the consumption error and the current consumption information; When the historical consumption information of the target object is less than or equal to a preset threshold, selecting the target competition probability with the largest competition probability value from the first competition probability and the initial competition probability; When the historical consumption information is greater than a preset threshold, the first competition probability is used as the target competition probability.

7. An information processing device, characterized in that: The device comprises: An acquisition unit is used to acquire adjustment information of a target object in a current time period, historical data allocation information of the target object, and expected data of the target object; the adjustment information is information obtained based on the current historical expected data and current historical consumption information of the target object; the historical data allocation information is a ratio between a total value of allocation information of the target object at a same time point in the past period of time and a total value of expected data of the target object in the past period of time; the expected data is the estimated spending information of the target object on the day; a determination unit, configured to determine, from the expected data, initial allocation data corresponding to a next time period according to the historical data allocation information and the adjustment information; determine, according to the adjustment information, the initial allocation data, the initial competition probability, and the time period information of the target object, a target competition probability of the target object in the next time period; the initial competition probability is the competition probability of the target object in the current time period, and the time period information includes the current time period and the next time period; so that when the next time period arrives, the competition process of the target object is executed according to the target competition probability; The acquisition unit is further used to acquire the historical consumption information, historical feedback quantity and historical expected consumption information of the target object; The determining unit is further configured to determine initial adjustment information according to the historical consumption information, the historical feedback quantity and the historical expected consumption information; a processing unit, configured to perform proportional and differential processing on the initial adjustment information to obtain the adjustment information; The determination unit is also used to determine the initial allocation data from the expected data according to the historical data allocation information when the historical consumption information of the target object is less than or equal to a preset threshold; to obtain the preset adjustment coefficient of the target object when the historical consumption information is greater than the preset threshold; and to determine the initial allocation data from the expected data based on the adjustment information, the historical data allocation information and the preset adjustment coefficient.

8. An information processing device, characterized in that: The device comprises: A memory, a processor and a communication bus, wherein the memory communicates with the processor via the communication bus, the memory stores an information processing program executable by the processor, and when the information processing program is executed, the method according to any one of claims 1 to 6 is performed by the processor.

9. A storage medium having a computer program stored thereon, applied to an information processing device, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.