Method and apparatus for controlling flow progress

Abstract

Embodiments of the present disclosure disclose a method and device for controlling traffic progress. A specific embodiment of the method comprises: obtaining current traffic and current ranking of each to-be-regulated commodity corresponding to a target condition, the current traffic representing the cumulative traffic of the to-be-regulated commodity from an initial time to a current time; determining an increment total amount of the traffic of each to-be-regulated commodity based on the current traffic and the current ranking of each to-be-regulated commodity and a pre-determined traffic regulation factor of the current time; determining an increment component of the traffic of each to-be-regulated commodity based on the increment total amount and a pre-determined increment distribution weight, the increment distribution weight being positively correlated with a click-through rate and a conversion rate of the to-be-regulated commodity; and adjusting the ranking of each to-be-regulated commodity based on a pre-determined correspondence between the traffic increment and the commodity ranking and the increment component of each to-be-regulated commodity. The method combines the feature attributes of commodities to distribute traffic, thereby improving the pertinence and accuracy of traffic progress control.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the technical field of computer, in particular, to the technical field of Internet, and more particularly to a method and device for controlling traffic progress. BACKGROUND

[0002] In the field of e-commerce, e-commerce platforms often need to give certain traffic incentives and support to specific goods, for example, to meet the marketing demands of customers or mobilize the interaction of merchants participating in the e-commerce platform. The e-commerce platform usually makes accurate estimates based on the sales ability of customers and the purchase demand of users, and combines a multi-level central control algorithm to regulate the traffic of specific goods on the basis of ensuring the overall traffic utilization rate and conversion rate.

[0003] Common traffic control methods include two kinds. One is to obtain a regulation factor that can achieve the traffic regulation target through a double bucket experiment, and directly apply the regulation factor to the ranking weight of all to-be-regulated goods to control the traffic of the goods by changing the ranking of the goods. The other is to fit the relationship between the regulation factor and the traffic regulation target (such as an exponential relationship or a linear relationship) through big data, and calculate the regulation factor combined with the offline obtained traffic regulation target. The regulation factor is also directly applied to the ranking of all to-be-regulated goods. SUMMARY

[0004] Embodiments of the present disclosure provide a method and device for controlling traffic progress.

[0005] In a first aspect, embodiments of the present disclosure provide a method for controlling traffic progress, the method comprising: obtaining a current traffic and a current ranking of each to-be-regulated good corresponding to a target condition, the current traffic representing the cumulative traffic of the to-be-regulated good from an initial time to a current time; determining a total amount of increments of the traffic of each to-be-regulated good based on the current traffic and the current ranking of each to-be-regulated good and a pre-determined traffic regulation factor at the current time; determining an increment component of the traffic of each to-be-regulated good based on the total amount of increments and a pre-determined increment allocation weight, the increment allocation weight being positively correlated with a click-through rate and a conversion rate of the to-be-regulated good; and adjusting the ranking of each to-be-regulated good based on a pre-determined correspondence between the traffic increment and the ranking of the good and the increment component of each to-be-regulated good.

[0006] In some embodiments, the traffic regulation factor is determined via the following steps: obtaining real-time traffic data of each to-be-regulated commodity in each period in a control bucket and an experiment bucket based on a pre-configured double-bucket experiment, wherein the ranking of each to-be-regulated commodity in the control bucket is a preset initial ranking, the ranking of each to-be-regulated commodity in the experiment bucket is adjusted based on a corresponding relationship and an incremental component of each to-be-regulated commodity, and the real-time traffic data includes traffic in a single period and cumulative traffic from an initial time to a cutoff period; estimating actual cumulative traffic of each to-be-regulated commodity from the initial time to each period and actual traffic in each period based on the real-time traffic data of each to-be-regulated commodity in each period in the control bucket and the experiment bucket and a preset traffic distribution strategy; determining an initial traffic regulation factor of the t period by using a PID algorithm represented by the following formula:

[0007]

[0008] wherein, α t，pid represents the initial traffic regulation factor of the t period, F P , F I , and F D are preset hyperparameters, dist t-1 (G) represents a preset traffic distribution target of the t-1 period, g t-1，a represents actual traffic of each to-be-regulated commodity in the t-1 period, dist i (G) represents a preset traffic distribution target of the i period, g i，a represents actual traffic of each to-be-regulated commodity in the i period, N is a preset positive integer, g t-1，c represents actual cumulative traffic of each to-be-regulated commodity from the initial time to the t-1 period, g t-2，c represents actual cumulative traffic of each to-be-regulated commodity from the initial time to the t-2 period; and determining the initial traffic regulation factor as the traffic regulation factor of the t period.

[0009] In some embodiments, the initial traffic regulation factor is determined as the traffic regulation factor of the t period, and the foregoing method further includes: estimating a traffic proportion of the t period in the entire regulation period based on a pre-determined distribution characteristic of commodity traffic in the regulation period; and determining a traffic distribution target of the t period by using the following formula:

[0010]

[0011] wherein, T t，dist represents the traffic distribution target of the t period, T t，a，test represents traffic of each to-be-regulated commodity in the t period in the experiment bucket, r t represents the traffic proportion of the t period, and T t，a，basedenotes the flow of each commodity to be regulated in the control barrel in the t period, r buck denotes the preset ratio of the experimental barrel flow to the total flow; the initial flow regulation factor is corrected by using the following formula:

[0012]

[0013] wherein, α t is the corrected flow regulation factor, K C is a predetermined flow progress estimation parameter, T t，ach is the flow obtained by each commodity to be regulated in the experimental barrel in the t period, α t-1 is the flow regulation factor in the t-1 period; the corrected flow regulation factor is determined as the flow regulation factor in the t period.

[0014] In some embodiments, the initial flow regulation factor in the t period is determined by using the PID algorithm, and the previous method further comprises: based on a preset smoothing processing strategy, respectively smoothing the actual cumulative flow of each commodity to be regulated from the initial time to each period and the actual flow in each period.

[0015] In some embodiments, if the flow distribution strategy is a relative quantity distribution strategy, the actual flow of each commodity to be regulated in each period is positively correlated with the difference between the flow of each commodity to be regulated in the experimental barrel in the period and the flow of each commodity to be regulated in the control barrel in the period, and is negatively correlated with the flow of each commodity to be regulated in the control barrel in the period; and the actual cumulative flow of each commodity to be regulated in each period is positively correlated with the difference between the cumulative flow of each commodity to be regulated in the experimental barrel in the period and the cumulative flow of each commodity to be regulated in the control barrel in the period, and is negatively correlated with the cumulative flow of each commodity to be regulated in the control barrel in the period.

[0016] In some embodiments, if the flow distribution strategy is an absolute quantity distribution strategy, the actual flow of each commodity to be regulated in each period is positively correlated with the flow of each commodity to be regulated in the experimental barrel in the period, and is negatively correlated with the preset ratio of the experimental barrel flow to the total flow.

[0017] In a second aspect, embodiments of the present disclosure provide a device for controlling traffic progress, the device comprising: a traffic data acquisition unit configured to acquire current traffic and current ranking of each to-be-regulated commodity corresponding to a target condition, the current traffic representing cumulative traffic of the to-be-regulated commodity from an initial time to a current time; an increment total amount determination unit configured to determine an increment total amount of traffic of each to-be-regulated commodity based on the current traffic and the current ranking of each to-be-regulated commodity and a pre-determined traffic regulation factor at the current time; an increment component determination unit configured to determine an increment component of traffic of each to-be-regulated commodity based on the increment total amount and a pre-determined increment allocation weight, the increment allocation weight being positively correlated with a click-through rate and a conversion rate of the to-be-regulated commodity; and a traffic progress control unit configured to adjust the ranking of each to-be-regulated commodity based on a pre-determined correspondence between traffic increment and commodity ranking and the increment component of each to-be-regulated commodity.

[0018] In some embodiments, the device further comprises a regulation factor determination unit, the regulation factor determination unit comprising: a real-time data acquisition module configured to acquire real-time traffic data of each to-be-regulated commodity in each time period in a control bucket and an experimental bucket based on a pre-configured double-bucket experiment, wherein the ranking of each to-be-regulated commodity in the control bucket is a pre-set initial ranking, the ranking of each to-be-regulated commodity in the experimental bucket is adjusted based on the pre-determined correspondence and the increment component of each to-be-regulated commodity, and the real-time traffic data comprises traffic in a single time period and cumulative traffic from an initial time to a cutoff time period; an actual traffic estimation module configured to estimate actual cumulative traffic of each to-be-regulated commodity from the initial time to each time period and actual traffic in each time period based on the real-time traffic data of each to-be-regulated commodity in each time period in the control bucket and the experimental bucket and a pre-set traffic distribution strategy; and a PID calculation module configured to determine an initial traffic regulation factor at a t time period using a PID algorithm represented by the following formula:

[0019]

[0020] wherein, α t，pid represents the initial traffic regulation factor at the t time period, F P , F I , and F D are pre-set hyperparameters, dist t-1 (G) represents a pre-set traffic distribution target at a t-1 time period, g t-1，a represents actual traffic of each to-be-regulated commodity in the t-1 time period, dist i (G) represents a pre-set traffic distribution target at an i time period, g i，a represents actual traffic of each to-be-regulated commodity in the i time period, and N is a pre-set positive integer, g t-1，cdenotes the actual cumulative flow of each commodity to be regulated from the initial time to the t-1 period, g t-2，c denotes the actual cumulative flow of each commodity to be regulated from the initial time to the t-2 period; the regulating factor determination module is configured to determine the initial flow regulating factor as the flow regulating factor of the t period.

[0021] In some embodiments, the regulating factor determination unit further comprises a regulating factor correction module configured to estimate the flow proportion of the t period in the entire regulating period based on the distribution characteristics of the predetermined commodity flow in the regulating period; and determine the flow distribution target of the t period using the following formula:

[0022]

[0023] wherein, T t，dist denotes the flow distribution target of the t period, T t，a，test denotes the flow of each commodity to be regulated in the t period in the experimental barrel, r t denotes the flow proportion of the t period, T t，a，base denotes the flow of each commodity to be regulated in the t period in the control barrel, r buck denotes the preset ratio of the experimental barrel flow to the total flow; and the initial flow regulating factor is corrected using the following formula:

[0024]

[0025] wherein, a t is the corrected flow regulating factor, K C is the predetermined flow progress estimation parameter, T t，ach is the flow of each commodity to be regulated in the t period in the experimental barrel, a t-1 is the flow regulating factor of the t-1 period; and the regulating factor determination module is configured to determine the corrected flow regulating factor as the flow regulating factor of the t period.

[0026] In some embodiments, the regulating factor determination unit further comprises a smoothing processing module configured to perform smoothing processing on the actual cumulative flow of each commodity to be regulated from the initial time to each period and the actual flow in each period based on a preset smoothing processing strategy.

[0027] In some embodiments, if the traffic distribution strategy is a relative quantity distribution strategy, the actual traffic of each to-be-regulated commodity in each time period is positively correlated with the difference between the traffic of each to-be-regulated commodity in the experimental bucket and the traffic of each to-be-regulated commodity in the control bucket in the time period, and negatively correlated with the traffic of each to-be-regulated commodity in the control bucket in the time period; and the actual cumulative traffic of each to-be-regulated commodity in each time period is positively correlated with the difference between the cumulative traffic of each to-be-regulated commodity in the experimental bucket in the time period and the cumulative traffic of each to-be-regulated commodity in the control bucket in the time period, and negatively correlated with the cumulative traffic of each to-be-regulated commodity in the control bucket in the time period.

[0028] In some embodiments, if the traffic distribution strategy is an absolute quantity distribution strategy, the actual traffic of each to-be-regulated commodity in each time period is positively correlated with the traffic of each to-be-regulated commodity in the experimental bucket in the time period, and negatively correlated with the preset ratio of the traffic of the experimental bucket to the overall traffic.

[0029] In a third aspect, the embodiments of the present disclosure further provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, when the one or more programs are executed by the one or more processors, the one or more processors implement the method for controlling traffic progress in any of the above embodiments.

[0030] In a fourth aspect, the embodiments of the present disclosure further provide a computer readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method for controlling traffic progress in any of the above embodiments.

[0031] The method and device for controlling traffic progress provided by the embodiments of the present disclosure determine the total increment of the traffic of each to-be-regulated commodity based on the current traffic and the current ranking of each to-be-regulated commodity corresponding to the target condition obtained and the traffic regulation factor of the current time point, then determine the increment component of the traffic of each to-be-regulated commodity based on the total increment and the pre-determined increment allocation weight, and adjust the ranking of each to-be-regulated commodity based on the pre-determined correspondence between the traffic increment and the commodity ranking and the increment component of each to-be-regulated commodity. Since the increment allocation weight is positively correlated with the click-through rate and the conversion rate of the to-be-regulated commodity, the traffic is allocated in combination with the characteristic attributes of the to-be-regulated commodity, thereby improving the pertinence and accuracy of the traffic progress control. BRIEF DESCRIPTION OF DRAWINGS

[0032] Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments made with reference to the accompanying drawings:

[0033] Figure 1 is an exemplary system architecture diagram in which some embodiments of the present disclosure can be applied;

[0034] Figure 2 is a flowchart of one embodiment of a method for controlling traffic progress according to the present disclosure;

[0035] Figure 3 is Figure 2 is a scenario diagram of a method for controlling traffic progress according to the present disclosure;

[0036] Figure 4 is a flowchart of determining a traffic regulation factor in one embodiment of a method for controlling traffic progress according to the present disclosure;

[0037] Figure 5 is a flowchart of revising a traffic regulation factor in one embodiment of a method for controlling traffic progress according to the present disclosure;

[0038] Figure 6 is a structural diagram of one embodiment of an apparatus for controlling traffic progress according to the present disclosure;

[0039] Figure 7 is a structural diagram of an electronic device suitable for implementing embodiments of the present disclosure. DETAILED DESCRIPTION

[0040] The present disclosure will be further described by embodiments with reference to the drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the present disclosure and are not to be used to limit the present disclosure in any manner. It is also to be understood that, for the purpose of clarity, only related parts of the drawings are shown.

[0041] It is to be understood that the embodiments in the present disclosure and the features in the embodiments can be combined if there is no conflict. The present disclosure will be described in detail with reference to the drawings and embodiments.

[0042] Figure 1 An exemplary system architecture 100 for a method for controlling traffic progress or an apparatus for controlling traffic progress to which embodiments of the present disclosure can be applied is shown.

[0043] As shown in Figure 1 , the system architecture 100 can include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is a medium to provide a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0044] The server 105 can be a business server of an e-commerce platform. The user can use the terminal device 101, 102, or 103 to interact with the server 105 through the network 104, for example, can send a target condition to the server 105, and receive the product information under the target condition returned by the server 105, and then can click, browse, or purchase the goods presented in the server 105. The terminal device 101, 102, or 103 can be hardware or software. When the terminal device 101, 102, or 103 is hardware, it can be an electronic device with communication function, including but not limited to a smart phone, a tablet computer, an electronic book reader, a laptop computer, and a desktop computer, etc. When the terminal device 101, 102, or 103 is software, it can be installed in the above-mentioned electronic devices. It can be implemented as a plurality of software or software modules for providing distributed services, or as a single software or software module. No specific limitation is made herein.

[0045] The server 105 can be provided with a traffic monitoring module to obtain the traffic data of the goods in the e-commerce platform, and control the traffic of the to-be-regulated goods according to the obtained traffic data.

[0046] It should be noted that the method for controlling traffic progress provided by the embodiments of the present disclosure can be executed by the server 105. Accordingly, the device for controlling traffic progress can be provided in the server 105.

[0047] It should be noted that the server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or as a single server. When the server is software, it can be implemented as a plurality of software or software modules for providing distributed services, or as a single software or software module. No specific limitation is made herein.

[0048] With reference to Figure 2 , a flowchart 200 of one embodiment of the method for controlling traffic progress according to the present disclosure is shown. The method for controlling traffic progress includes the following steps:

[0049] In step 201, the current traffic and the current ranking of each to-be-regulated good corresponding to the target condition are obtained.

[0050] In the present embodiment, the current traffic represents the cumulative traffic of the to-be-regulated goods from the initial time to the current time. The initial time can be the starting time of the traffic control period, for example, the regulation period of the method for controlling traffic progress in the present embodiment is one day, and the initial time can be set as 0 o'clock every day. The traffic can be represented in various data forms, for example, the click volume or the browsing volume of the goods.

[0051] The target condition is used to perform the scope of the subject determining the traffic progress control, which can be, for example, the category of the to-be-regulated goods, the characteristics or the supplier to which the goods belong, and the like. The current ranking represents the arrangement order of each to-be-regulated good under the target condition at the current time.

[0052] As an example, the execution subject can be a server as shown in FIG. 1, and the execution subject can call the current traffic and the current ranking of various goods under the target condition from the business service of the e-commerce platform. Figure 1

[0053] Step 202, based on the current traffic and the current ranking of each to-be-regulated good and the pre-determined traffic regulation factor at the current time, the total amount of the increment of the traffic of each to-be-regulated good is determined.

[0054] In this embodiment, the traffic regulation factor at the current time can represent the adjustment strategy for the traffic of the to-be-regulated goods, which can be directly obtained through a double bucket experiment, for example, and then based on the historical traffic data, the relationship between the traffic regulation factor and the traffic distribution target can be fitted, and then according to the traffic distribution target at the current time, the corresponding traffic regulation factor is determined.

[0055] The total amount of the increment of the traffic of each to-be-regulated good represents the expected value of the increase of the traffic of each to-be-regulated good at the next time.

[0056] In one specific example, the execution subject can perform formulas (1) and (2) to determine the total amount of the increment of the traffic of each to-be-regulated good.

[0057]

[0058] T skul = a * e b*pos+c (2)

[0059] In the formula, T query，inc represents the total amount of the increment of the traffic of each to-be-regulated good, a t represents the traffic regulation factor at the current time, T skul represents the lth to-be-regulated good, n represents the number of to-be-regulated goods under the target condition, pos represents the position of the to-be-regulated good in the current ranking, and a, b, and c represent parameters determined through offline fitting.

[0060] Step 203, based on the total amount of the increment and the pre-determined increment allocation weight, the increment component of the traffic of each to-be-regulated good is determined.

[0061] ​In the embodiment, the increment allocation weight is positively correlated with the click arrival rate and the conversion rate of the commodity to be regulated. The increment component of the traffic of the commodity to be regulated represents the expected value of the increase of the traffic of the commodity to be regulated at the next moment, and the sum of the increment components of the traffic of the commodities to be regulated is the total increment.

[0062] The click arrival rate of the commodity to be regulated represents the number of times that a user arrives at the information page of the commodity to be regulated by clicking, and the conversion rate represents the number of times of completing a conversion behavior (for example, ordering or collecting).

[0063] In step 204, the ranking of each commodity to be regulated is adjusted based on the predetermined correspondence between the traffic increment and the commodity ranking and the increment component of each commodity to be regulated.

[0064] In the embodiment, the correspondence between the traffic increment and the commodity ranking can be obtained by big data analysis.

[0065] As an example, the execution subject can pre-store the correspondence between the traffic increment and the commodity ranking, and then determine the ranking of each commodity to be regulated at the next moment according to the increment component of each commodity to be regulated, and adjust the ranking of the commodity to be regulated with a larger increment component to a position closer to the front, so as to improve the traffic obtained by the commodity to be regulated at the next moment.

[0066] Continuing to refer to Figure 3 , Figure 3 is a schematic diagram of one scenario of the method shown in 2. In Figure 3 the scenario 300 shown, the execution subject 301 can be a traffic monitoring server, the server 302 can be a business server of an e-commerce platform, and the commodity category for which the traffic is to be regulated is a clothing commodity. The execution subject sends the target condition "clothing" to the business server, and calls the current traffic and the current ranking of the clothing commodities from the business server. As shown in data 303, the commodities under the target condition include, in turn, a shirt, an underwear, and a pair of trousers, and the respective current traffic is 10, 5, and 3 (the traffic values here are only exemplary). Then, the execution subject determines the total increment of the commodities to be regulated based on the pre-set traffic regulation factor, which can be 15, for example. Then, the execution subject determines the increment component of the traffic of each commodity to be regulated in combination with the pre-determined increment allocation weight, which are 3, 8, and 4 in turn, to obtain data 304. Then, the ranking of each commodity to be regulated is adjusted in combination with the pre-determined correspondence between the commodity ranking and the traffic increment, to obtain the adjusted commodity ranking 305. Finally, 305 is sent to the business server to instruct the business server to adopt the commodity ranking shown in 305 at the next moment. Thus, the traffic progress control of the clothing commodities is completed.

[0067] The method and device for controlling traffic progress provided by the embodiments of the present disclosure determine the total increment of traffic of each to-be-regulated commodity based on the current traffic and current ranking of each to-be-regulated commodity corresponding to the target condition obtained and the traffic regulation factor of the current time point determined in advance, then determine the increment component of the traffic of each to-be-regulated commodity based on the total increment and the increment allocation weight determined in advance, and adjust the ranking of each to-be-regulated commodity based on the correspondence between the traffic increment and the commodity ranking and the increment component of each to-be-regulated commodity determined in advance. Since the increment allocation weight is positively correlated with the click-through rate and conversion rate of the to-be-regulated commodity, the traffic is allocated in combination with the characteristic attributes of the to-be-regulated commodity, thereby improving the pertinence and accuracy of traffic progress control.

[0068] Reference is made next to Figure 4 which shows a flow 400 for determining a traffic regulation factor in one embodiment of the method for controlling traffic progress. The flow 400 includes the following steps:

[0069] In step 401, real-time traffic data of each to-be-regulated commodity in each time period in the control bucket and the experimental bucket is obtained based on a pre-configured double bucket experiment.

[0070] In the present embodiment, the ranking of each to-be-regulated commodity in the control bucket is the preset initial ranking, the ranking of each to-be-regulated commodity in the experimental bucket is the adjusted ranking based on the correspondence and the increment component of each to-be-regulated commodity, and the real-time traffic data includes the traffic in a single time period and the cumulative traffic from the initial time point to the cutoff time period.

[0071] As an example, the time period can be a traffic collection period of the double bucket experiment, for example, the execution subject can collect the real-time traffic data of each to-be-regulated commodity in the experimental bucket and the control bucket every 10 minutes, and the time period for collecting data each time is the time period of 10 minutes before the collection point. The time period can also be set to a time period less than the traffic collection period, for example, it can be 5 minutes, the execution subject can collect the real-time traffic data of each to-be-regulated commodity in the experimental bucket and the control bucket every 10 minutes, and the time period for collecting data each time is the time period of 5 minutes before the collection point. As another example, the time period can also be set to a time period greater than the traffic collection period, for example, it can be 15 minutes, and the time period for collecting data each time is the time period of 15 minutes before the collection point, so that the real-time traffic data in each time period intersects with the real-time traffic data in the previous time period.

[0072] It can be understood that the shorter the flow collection period and the longer the time period, the higher the coverage of data, and the higher the accuracy of the flow control factor determined thereby, but the larger the amount of data and the amount of calculation, and the higher the performance requirement of the execution subject, and thus the flow collection period and the time period of the double-barrel experiment can be set according to actual requirements, in a balanced consideration of the control period, the accuracy and the efficiency. For example, the control period is a day, and then the flow collection period and the time period are set to 1 minute, so as to realize day-level flow control at the minute level.

[0073] In step 402, based on the real-time flow data of each to-be-controlled commodity in the control barrel and the experimental barrel in each time period and the preset flow distribution strategy, the actual cumulative flow of each to-be-controlled commodity from the initial time to each time period and the actual flow in each time period are estimated.

[0074] In this embodiment, the flow distribution strategy can represent the flow distribution target of each to-be-controlled commodity at each time in the control period. For example, it can be preset that the cumulative flow of the to-be-controlled commodity from 0 o'clock to 8 o'clock reaches 1000 clicks, and then the click volume reaches 20000 at 24 o'clock. For another example, it can be preset that in the control period from 0 o'clock to 24 o'clock, the flow of each to-be-controlled commodity in the experimental barrel is increased by 10% relative to the flow of each to-be-controlled commodity in the control barrel in each hour.

[0075] The execution subject can estimate the actual cumulative flow of each to-be-controlled commodity from the initial time to each time period and the actual flow in each time period based on the flow distribution strategy, the real-time flow data in the control barrel and the experimental barrel, and the preset configuration parameters of the double-barrel experiment (for example, the ratio of the flow of the experimental barrel to the actual flow).

[0076] In some optional implementation manners of this embodiment, if the flow distribution strategy is a relative amount distribution strategy, the actual flow of each to-be-controlled commodity in each time period is positively correlated with the difference between the flow of each to-be-controlled commodity in the experimental barrel and the flow of each to-be-controlled commodity in the control barrel in the time period, and negatively correlated with the flow of each to-be-controlled commodity in the control barrel in the time period; and the actual cumulative flow of each to-be-controlled commodity in each time period is positively correlated with the difference between the cumulative flow of each to-be-controlled commodity in the experimental barrel and the cumulative flow of each to-be-controlled commodity in the control barrel in the time period, and negatively correlated with the cumulative flow of each to-be-controlled commodity in the control barrel in the time period.

[0077] In this implementation manner, the relative amount distribution strategy can represent the proportion of the flow of each to-be-controlled commodity in the experimental barrel relative to the flow of each to-be-controlled commodity in the control barrel at the current time. For example, the flow of each to-be-controlled commodity in the experimental barrel can be increased by 1% relative to the flow of each to-be-controlled commodity in the control barrel in each hour.

[0078] Preferably, the relative amount distribution strategy can be used to detect the upper limit of the increase of the to-be-regulated commodity through a double-barrel experiment, and then the data obtained by multiplying the upper limit of the increase with a preset coefficient is determined as the proportion of the flow increase in the relative amount distribution strategy.

[0079] As an example, when the execution subject determines that the flow distribution strategy is the relative amount distribution strategy, formula (3) and (4) can be used to determine the actual flow and the actual cumulative flow of the to-be-regulated commodity in the m period.

[0080]

[0081]

[0082] In the formula, g m，a represents the actual flow of each to-be-regulated commodity in the m period, g m，c represents the actual cumulative flow of each to-be-regulated commodity from the initial time to the m period, T m，a，test represents the actual flow of each to-be-regulated commodity in the m period in the experimental barrel, T m，a，base represents the actual flow of each to-be-regulated commodity in the m period in the control barrel, T m，c，test represents the actual cumulative flow of each to-be-regulated commodity from the initial time to the m period in the experimental barrel, T m，c，base represents the actual cumulative flow of each to-be-regulated commodity from the initial time to the m period in the control barrel.

[0083] In some other optional implementations of the embodiment, if the flow distribution strategy is the absolute amount distribution strategy, the actual flow of each to-be-regulated commodity in each period is positively correlated with the flow of each to-be-regulated commodity in the experimental barrel in the period, and is negatively correlated with the preset ratio of the flow of the experimental barrel to the total flow.

[0084] In the implementation, the absolute amount distribution strategy represents the absolute value of the increase of the flow of the to-be-regulated commodity. As an example, the absolute value of the flow increase can be estimated based on historical flow data through a pre-constructed flow estimation model.

[0085] As an example, when the execution subject determines that the flow distribution strategy is the absolute amount distribution strategy, formula (5) and (6) can be used to determine the actual flow and the actual cumulative flow of the to-be-regulated commodity in the m period.

[0086] g m，a = T m，a，test / r buck (5)

[0087] g m，c = T m，c，test / r buck (6)

[0088] In the formula, r buck represents the ratio of the preset experimental barrel flow to the total flow.

[0089] Step 403, using the PID (proportion, integral, and differential) algorithm represented by formula (7), determine the initial flow control factor of the t period:

[0090]

[0091] In the formula, a t，pid represents the initial flow control factor of the t period, F P , F I , and F D are preset hyperparameters, dist t-1 (G) represents the preset flow distribution target of the t-1 period, g t-1，a represents the actual flow of each to-be-controlled commodity in the t-1 period, dist i (G) represents the preset flow distribution target of the i period, g i，a represents the actual flow of each to-be-controlled commodity in the i period, and N is a preset positive integer, g t-1，c represents the actual cumulative flow of each to-be-controlled commodity from the initial time to the t-1 period, g t-2，c represents the actual cumulative flow of each to-be-controlled commodity from the initial time to the t-2 period.

[0092] In practice, at the initial time of the flow control period, the actual flow accumulation time of the to-be-controlled commodity is short, and the data sparsity leads to large flow control fluctuations. In order to avoid this phenomenon, in some optional implementation manners of the embodiment, before the PID algorithm is used to determine the initial flow control factor of the t period, the following steps can also be used: based on a preset smoothing strategy, the actual cumulative flow of each to-be-controlled commodity from the initial time to each period and the actual flow in each period are smoothed, respectively.

[0093] As an example, the execution subject can use the wilson interval in the CTR (Click-Through-Rate, click-through rate) estimation to smooth the actual cumulative flow of each to-be-controlled commodity from the initial time to each period and the actual flow in each period obtained in step 402. Then, the smoothed data is input into the PID algorithm in step 403 to avoid large data fluctuations caused by short flow accumulation time at the initial time.

[0094] Step 404, determine the initial flow control factor as the flow control factor of the t period.

[0095] As can be seen from Figure 4 Figure 4 ​The flowchart shown in the figure embodies the steps of obtaining real-time traffic data based on a double-barrel experiment and determining a traffic regulation factor using a PID algorithm. The actual achievement rate of the traffic distribution target in the historical period, the total deviation, and the trend of completing the traffic distribution target in the recent period can be introduced into the determination process of the traffic regulation factor, thereby improving the accuracy and stability of traffic progress control.

[0096] Reference will now be made to Figure 5 , Figure 5 A flowchart for correcting a traffic regulation factor in one embodiment of the method for controlling traffic progress of the present disclosure is shown. In Figure 5 The flowchart 500 shown includes the following steps:

[0097] Step 501, based on the distribution characteristics of the commodity traffic in the regulation period, estimate the traffic proportion of the t period in the entire regulation period.

[0098] In this embodiment, the distribution characteristics of the commodity traffic in the regulation period are used to represent the law of the commodity traffic changing with time in the regulation period. As an example, the method of big data analysis can be used to analyze the correspondence between the commodity traffic and the time from the historical traffic data of the commodity, so as to determine the distribution characteristics of the commodity traffic in the regulation period.

[0099] In one specific example, the regulation period is one day and the t period is from 9:00 to 10:00. Based on the distribution characteristics of the commodity traffic in the regulation period, it can be determined that the total amount of traffic obtained by the commodity to be regulated in one day is 1000, and the traffic obtained in the period from 9:00 to 10:00 is 100, then the execution subject can determine that the traffic proportion of the t period in the entire regulation period is 10%.

[0100] Step 502, determine the traffic distribution target of the t period using formula (8):

[0101]

[0102] In the formula, T t，dist represents the traffic distribution target of the t period, T t，a，test represents the traffic of each commodity to be regulated in the t period in the experimental barrel, r t represents the traffic proportion of the t period, T t，a，base represents the traffic of each commodity to be regulated in the t period in the control barrel, r buck represents the preset ratio of the experimental barrel traffic to the total traffic.

[0103] In this embodiment, the traffic distribution target of the t period represents the expected traffic obtained by each commodity to be regulated in the t period.

[0104] Step 503, the initial flow regulation factor is corrected by formula (9):

[0105]

[0106] In the formula, a t is the corrected flow regulation factor, K C is a predetermined flow progress estimation parameter, T t，ach is the flow obtained by each commodity to be regulated in the experimental barrel at time t, a t-1 is the flow regulation factor at time t-1.

[0107] Step 504, the corrected flow regulation factor is determined as the flow regulation factor at time t.

[0108] As can be seen from Figure 5 , Figure 5 The flow 500 shown embodies the step of correcting the flow regulation factor based on the flow distribution characteristics, and the overall characteristics of the flow distribution can be introduced into the control process of the flow progress, thereby improving the stability of the flow progress control.

[0109] Further referring to Figure 6 , as an implementation of the method shown in the above figures, the present disclosure provides an embodiment of an apparatus for controlling flow progress, which corresponds to the method embodiment shown in Figure 2 , and the apparatus can be specifically applied to various electronic devices.

[0110] As shown in Figure 6 , the apparatus 600 for controlling flow progress of the present embodiment comprises: a flow data acquisition unit 601 configured to acquire the current flow and the current ranking of each commodity to be regulated corresponding to the target condition, the current flow representing the cumulative flow of the commodity to be regulated from the initial time to the current time; an increment total amount determination unit 602 configured to determine the increment total amount of the flow of each commodity to be regulated based on the current flow and the current ranking of each commodity to be regulated and the predetermined flow regulation factor at the current time; an increment component determination unit 603 configured to determine the increment component of the flow of each commodity to be regulated based on the increment total amount and the predetermined increment allocation weight, the increment allocation weight being positively correlated with the click-through rate and the conversion rate of the commodity to be regulated; and a flow progress control unit 604 configured to adjust the ranking of each commodity to be regulated based on the predetermined correspondence between the flow increment and the commodity ranking and the increment component of each commodity to be regulated.

[0111] In the embodiment, the device 600 further comprises a regulation factor determination unit, which comprises: a real-time data acquisition module configured to acquire real-time traffic data of each to-be-regulated commodity in each time period in the control bucket and the experiment bucket based on a preconfigured double-bucket experiment, wherein the ranking of each to-be-regulated commodity in the control bucket is a preset initial ranking, the ranking of each to-be-regulated commodity in the experiment bucket is adjusted based on the corresponding relationship and the ranking of each to-be-regulated commodity after the increment component, and the real-time traffic data comprises traffic in a single time period and cumulative traffic from an initial time to a cutoff time period; an actual traffic estimation module configured to estimate actual cumulative traffic of each to-be-regulated commodity from an initial time to each time period and actual traffic in each time period based on the real-time traffic data of each to-be-regulated commodity in each time period in the control bucket and the experiment bucket and a preset traffic distribution strategy; and a PID calculation module configured to determine an initial traffic regulation factor of the t time period by using a PID algorithm represented by the following formula:

[0112]

[0113] wherein, α t，pid represents the initial traffic regulation factor of the t time period, F P , F I , and F D are preset hyperparameters, dist t-1 (G) represents a preset traffic distribution target of the t-1 time period, g t-1，a represents actual traffic of each to-be-regulated commodity in the t-1 time period, dist i (G) represents a preset traffic distribution target of the i time period, g i，a represents actual traffic of each to-be-regulated commodity in the i time period, N is a preset positive integer, g t-1，c represents actual cumulative traffic of each to-be-regulated commodity from an initial time to the t-1 time period, g t-2，c represents actual cumulative traffic of each to-be-regulated commodity from an initial time to the t-2 time period; and a regulation factor determination module configured to determine the initial traffic regulation factor as a traffic regulation factor of the t time period.

[0114] In the embodiment, the regulation factor determination unit further comprises a regulation factor correction module configured to estimate a traffic proportion of the t time period in the entire regulation period based on a pre-determined distribution characteristic of commodity traffic in the regulation period, and determine a traffic distribution target of the t time period by using the following formula:

[0115]

[0116] wherein, T t，dist represents the traffic distribution target of the t time period, T t，a，testrepresents the flow rate of each commodity to be regulated in the experimental barrel at time t, r t represents the proportion of the flow rate at time t, T t，a，base represents the flow rate of each commodity to be regulated in the control barrel at time t, r buck represents the preset ratio of the flow rate of the experimental barrel to the total flow rate; the initial flow rate regulation factor is corrected by using the following formula:

[0117]

[0118] In the formula, a t is the corrected flow rate regulation factor, K C is a predetermined flow rate progress estimation parameter, T t，ach is the flow rate of each commodity to be regulated in the experimental barrel at time t, a t-1 is the flow rate regulation factor at time t-1; and the regulation factor determination module is configured to determine the corrected flow rate regulation factor as the flow rate regulation factor at time t.

[0119] In this embodiment, the regulation factor determination unit further includes a smoothing processing module configured to respectively smooth the actual cumulative flow rate of each commodity to be regulated from the initial time to each time period and the actual flow rate in each time period based on a preset smoothing processing strategy.

[0120] In this embodiment, if the flow rate distribution strategy is a relative quantity distribution strategy, the actual flow rate of each commodity to be regulated in each time period is positively correlated with the difference between the flow rate of each commodity to be regulated in the experimental barrel and the flow rate of each commodity to be regulated in the control barrel in the time period, and is negatively correlated with the flow rate of each commodity to be regulated in the control barrel in the time period; and the actual cumulative flow rate of each commodity to be regulated in each time period is positively correlated with the difference between the cumulative flow rate of each commodity to be regulated in the experimental barrel and the cumulative flow rate of each commodity to be regulated in the control barrel in the time period, and is negatively correlated with the cumulative flow rate of each commodity to be regulated in the control barrel in the time period.

[0121] In this embodiment, if the flow rate distribution strategy is an absolute quantity distribution strategy, the actual flow rate of each commodity to be regulated in each time period is positively correlated with the flow rate of each commodity to be regulated in the experimental barrel in the time period, and is negatively correlated with the preset ratio of the flow rate of the experimental barrel to the total flow rate.

[0122] Reference is made below to Figure 7 which shows an electronic device (e.g., a mobile phone) suitable for use to implement embodiments of the present disclosure. Figure 1The diagram below shows the structure of the server or terminal device 700. The terminal device in the embodiments of this disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The terminal device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0123] like Figure 7 As shown, the electronic device 700 may include a processing unit (e.g., a central processing unit, a graphics processor, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage device 708 into a random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the electronic device 700. The processing unit 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0124] Typically, the following devices can be connected to I / O interface 705: input devices 706 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 707 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 708 including, for example, magnetic tapes, hard disks, etc.; and communication devices 709. Communication device 709 allows electronic device 700 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 7 An electronic device 700 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 7 Each box shown can represent a device or multiple devices as needed.

[0125] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program comprising program code for executing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication device 709, or installed from the storage device 708, or installed from the ROM 702. When the computer program is executed by the processing device 701, the above-mentioned functions defined in the methods of embodiments of the present disclosure are executed. It should be noted that the computer readable medium of embodiments of the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, be, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In embodiments of the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device. In embodiments of the present disclosure, the computer readable signal medium can include a data signal carried in a baseband or as part of a carrier wave, in which the computer readable program code is carried. Such a propagated data signal can take any of a variety of forms, including but not limited to electro-magnetic, optical, or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate or transport a program for use by or in connection with an instruction execution system, apparatus or device. Program code contained in the computer readable medium can be transmitted by any suitable medium, including but not limited to wire, cable, RF, etc., or any suitable combination of the above.

[0126] The computer readable medium can be included in the electronic device; or can exist independently of the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquire a current flow and a current ranking of each to-be-regulated commodity corresponding to a target condition, the current flow representing a cumulative flow of the to-be-regulated commodity from an initial time to a current time; determine a total increment of the flow of each to-be-regulated commodity based on the current flow and the current ranking of each to-be-regulated commodity and a flow regulation factor of the current time determined in advance; determine an increment component of the flow of each to-be-regulated commodity based on the total increment and an increment allocation weight determined in advance, the increment allocation weight being positively correlated with a click-through rate and a conversion rate of the to-be-regulated commodity; and adjust the ranking of each to-be-regulated commodity based on a predetermined correspondence between the flow increment and the commodity ranking and the increment component of each to-be-regulated commodity.

[0127] Computer program code for carrying out operations of embodiments of the present disclosure can be written in any of one or more programming languages or combinations of languages including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0128] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of present disclosure. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations of blocks in the block diagrams and / or flow diagrams, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0129] The units described in the embodiments of the present disclosure can be implemented in the form of software or in the form of hardware. The units described can also be arranged in a processor, for example, a processor can be described as including a flow data acquisition unit, an incremental total amount determination unit, an incremental component determination unit, and a flow progress control unit. In some cases, the names of these units do not constitute a limitation on the units themselves, for example, the flow data acquisition unit can also be described as a unit that "acquires the current flow and the current ranking of each to-be-regulated commodity corresponding to a target condition".

[0130] The above description is merely preferred embodiments of the present disclosure and a description of the principles of the technology used. Those skilled in the art should understand that the scope of the application involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or equivalent features without deviating from the above inventive concept. For example, the above features are replaced with each other to form technical solutions with similar functions disclosed in the embodiments of the present disclosure (but not limited to).

Claims

1. A method for controlling the progress of traffic, wherein, The method comprises: obtaining current traffic and current ranking of each to-be-controlled commodity corresponding to a target condition, wherein the current traffic represents cumulative traffic of the to-be-controlled commodity from an initial time to a current time, and the target condition indicates a commodity category of traffic progress control effect; obtaining a traffic control factor of the commodity category corresponding to the current time through a double bucket experiment, determining an increment total amount of traffic of each to-be-controlled commodity based on the current traffic and the current ranking of each to-be-controlled commodity and the traffic control factor, and the traffic control factor can represent an adjustment strategy for the traffic of the to-be-controlled commodity; determining an increment component of traffic of each to-be-controlled commodity based on the increment total amount and a pre-determined increment allocation weight, wherein the increment allocation weight is positively correlated with a click-through rate and a conversion rate of the to-be-controlled commodity, the increment component is used to represent an expected value of an increase in traffic of the to-be-controlled commodity at a next time, and the increment total amount is a sum of the increment components of the to-be-controlled commodities; adjusting the ranking of each to-be-controlled commodity based on a pre-determined correspondence between traffic increment and commodity ranking and the increment component of each to-be-controlled commodity.

2. The method of claim 1, wherein, The traffic control factor is determined through the following steps: obtaining real-time traffic data of each to-be-controlled commodity in each period in a control bucket and an experimental bucket based on a pre-configured double bucket experiment, wherein the ranking of each to-be-controlled commodity in the control bucket is a pre-set initial ranking, the ranking of each to-be-controlled commodity in the experimental bucket is adjusted based on the correspondence and the increment component of each to-be-controlled commodity, and the real-time traffic data includes traffic in a single period and cumulative traffic from an initial time to a cutoff period; estimating actual cumulative traffic of each to-be-controlled commodity from an initial time to each period and actual traffic in each period based on the real-time traffic data of each to-be-controlled commodity in each period in the control bucket and the experimental bucket and a pre-set traffic distribution strategy, wherein the traffic distribution strategy represents a traffic distribution target of each to-be-controlled commodity at each time in a control period; PID algorithm characterized by the following formula, determine the t Initial flow control factor of time period: In the formula, express t Initial flow control factor for the time period , and These are preset hyperparameters. Indicates preset t- Traffic distribution target for time period 1 This indicates that each of the commodities to be regulated is in t- Actual traffic flow within a time period 1 Indicates preset i Traffic distribution targets for different time periods This indicates that each of the commodities to be regulated is in i Actual traffic flow during the time period N It is a preset positive integer. This indicates that each of the commodities to be regulated has changed from the initial time to... t- Actual cumulative traffic volume for period 1 This indicates that each of the commodities to be regulated has changed from the initial time to... t- Actual cumulative traffic flow in two time periods; determining the initial flow regulation factor as t the flow regulation factor for the period.

3. The method of claim 2, determining the initial flow regulation factor as t the flow regulation factor for the period, the method further comprising: Based on the predetermined distribution characteristics of commodity traffic in the regulation period, the traffic in the time period is estimated t The traffic proportion of the time period in the entire regulation period; The following formula is used to determine t Traffic distribution targets for time periods: In the formula, represents t the flow distribution target of the time period, represents the flow of each of the to-be-regulated commodities in the experimental barrel in the time period, t represents the flow of each of the to-be-regulated commodities in the control barrel in the time period, represents t the flow proportion of the time period, represents the flow of each of the to-be-regulated commodities in the experimental barrel in the time period, t represents the flow of each of the to-be-regulated commodities in the control barrel in the time period, represents the preset ratio of the experimental barrel flow to the total flow; modifying the initial traffic control factor by using the following formula: In the formula, is the modified flow control factor, is a predetermined flow progress estimation parameter, is the flow obtained by each of the to-be-controlled commodities in the experimental barrel at t is the flow obtained by each of the to-be-controlled commodities in the experimental barrel at is t- 1 is the flow control factor of the period; The modified flow regulation factor is determined as t the flow regulation factor for the period.

4. The method according to claim 2, wherein a PID algorithm is used to determine the... t The initial flow control factor for the time period, as described in the previously mentioned method, also includes: respectively smoothing the actual cumulative traffic of each to-be-controlled commodity from an initial time to each period and the actual traffic in each period based on a pre-set smoothing strategy.

5. The method of claim 2, wherein, if the traffic distribution strategy is a relative amount distribution strategy, the actual traffic of each to-be-controlled commodity in each period is positively correlated with a difference between the traffic of each to-be-controlled commodity in the experimental bucket and the traffic of each to-be-controlled commodity in the control bucket in the period, and negatively correlated with the traffic of each to-be-controlled commodity in the control bucket in the period; and the actual cumulative traffic of each to-be-controlled commodity in each period is positively correlated with a difference between the cumulative traffic of each to-be-controlled commodity in the experimental bucket and the cumulative traffic of each to-be-controlled commodity in the control bucket in the period, and negatively correlated with the cumulative traffic of each to-be-controlled commodity in the control bucket in the period.

6. The method of claim 5, wherein, if the flow distribution strategy is an absolute amount distribution strategy, the actual flow of each commodity to be regulated in each time period is positively correlated with the flow of each commodity to be regulated in the experiment bucket in the time period, and negatively correlated with the preset ratio of the experiment bucket flow to the overall flow.

7. An apparatus for controlling the progress of traffic, wherein, Comprise: a flow data acquisition unit configured to acquire current flow and current ranking of each commodity to be regulated corresponding to a target condition, the current flow representing the cumulative flow of the commodity to be regulated from an initial time to a current time, and the target condition indicating the commodity category of flow progress control action; an incremental total amount determination unit configured to acquire a flow regulation factor corresponding to the commodity category at the current time through a double bucket experiment, and determine an incremental total amount of flow of each commodity to be regulated based on the current flow and the current ranking of each commodity to be regulated and the flow regulation factor, the flow regulation factor representing an adjustment strategy for the flow of the commodity to be regulated; an incremental component determination unit configured to determine an incremental component of the flow of each commodity to be regulated based on the incremental total amount and a pre-determined incremental allocation weight, the incremental allocation weight being positively correlated with the click-through rate and conversion rate of the commodity to be regulated, the incremental component representing an expected value of the increase of the flow of the commodity to be regulated at the next time, and the incremental total amount being the sum of the incremental components of the commodities to be regulated; a flow progress control unit configured to adjust the ranking of each commodity to be regulated based on a pre-determined correspondence between flow increment and commodity ranking and the incremental component of each commodity to be regulated.

8. The apparatus of claim 7, wherein, The device further comprises a regulation factor determination unit, which comprises: a real-time data acquisition module configured to acquire real-time flow data of each commodity to be regulated in each time period in a control bucket and an experiment bucket based on a pre-configured double bucket experiment, wherein the ranking of each commodity to be regulated in the control bucket is a pre-set initial ranking, the ranking of each commodity to be regulated in the experiment bucket is adjusted based on the correspondence and the incremental component of each commodity to be regulated, and the real-time flow data includes flow in a single time period and cumulative flow from an initial time to a cutoff time period; an actual flow estimation module configured to estimate actual cumulative flow from an initial time to each time period and actual flow in each time period of each commodity to be regulated based on real-time flow data of each commodity to be regulated in each time period in the control bucket and the experiment bucket and a pre-set flow distribution strategy, the flow distribution strategy representing the flow distribution target of each commodity to be regulated at each time in the regulation period; PID calculation module, configured to determine the PID algorithm using the following formula t initial flow control factor of the period: In the formula, denotes t the initial flow control factor of the time period, , and is a preset hyperparameter, denotes a preset t- flow distribution target of the time period 1, denotes the actual flow of the respective to-be-controlled commodity in the time period 1, t- denotes the actual flow of the respective to-be-controlled commodity in the time period 1, denotes a preset i flow distribution target of the time period 1, denotes the actual flow of the respective to-be-controlled commodity in the time period 1, i denotes the actual flow of the respective to-be-controlled commodity in the time period 1, N is a preset positive integer, denotes the actual cumulative flow of the respective to-be-controlled commodity from the initial time to the time period 1, t- denotes the actual cumulative flow of the respective to-be-controlled commodity from the initial time to the time period 1, denotes the actual cumulative flow of the respective to-be-controlled commodity from the initial time to the time period 1, and t- denotes the actual cumulative flow of the respective to-be-controlled commodity from the initial time to the time period 1. a regulatory factor determination module configured to determine the initial flow regulatory factor as t a flow regulatory factor for the period.

9. The apparatus of claim 8, wherein, The regulation factor determination unit further comprises a regulation factor correction module configured to: Based on the predetermined distribution characteristics of commodity flow in the regulation period, the flow in the time period is estimated t The flow proportion of the time period in the entire regulation period; The following formula is used to determine t Traffic distribution targets for time periods: In the formula, representing t the flow distribution target of the time period, representing the flow of each of the to-be-regulated commodities in the experimental bucket in the time period, t representing the flow of each of the to-be-regulated commodities in the control bucket in the time period, representing t the flow proportion of the time period, representing the flow of each of the to-be-regulated commodities in the experimental bucket in the time period, t representing the flow of each of the to-be-regulated commodities in the control bucket in the time period, representing the preset ratio of the experimental bucket flow to the total flow; correct the initial flow regulation factor using the following formula: In the formula, is the modified flow control factor, is a predetermined flow progress estimation parameter, is the flow obtained by each of the to-be-controlled commodities in the experimental barrel in the period, t is the flow obtained by each of the to-be-controlled commodities in the experimental barrel in the period, is t- 1 the flow control factor of the period; and, The control factor determination module is configured to determine the modified flow control factor as t a flow control factor for the period. 10.The apparatus of claim 8, wherein the regulation factor determination unit further comprises a smoothing processing module configured to perform smoothing processing on the actual cumulative flow of each commodity to be regulated from an initial time to each time period and the actual flow of each commodity to be regulated in each time period based on a preset smoothing processing strategy.

11. The apparatus of claim 8, wherein, If the flow distribution strategy is a relative amount distribution strategy, the actual flow of each commodity to be regulated in each time period is positively correlated with the difference between the flow of each commodity to be regulated in the experimental bucket and the flow of each commodity to be regulated in the control bucket in the time period, and negatively correlated with the flow of each commodity to be regulated in the control bucket in the time period; and the actual cumulative flow of each commodity to be regulated in each time period is positively correlated with the difference between the cumulative flow of each commodity to be regulated in the experimental bucket and the cumulative flow of each commodity to be regulated in the control bucket in the time period, and negatively correlated with the cumulative flow of each commodity to be regulated in the control bucket in the time period.

12. The apparatus of claim 11, wherein, If the flow distribution strategy is an absolute amount distribution strategy, the actual flow of each commodity to be regulated in each time period is positively correlated with the flow of each commodity to be regulated in the experimental bucket in the time period, and negatively correlated with the preset ratio of the flow of the experimental bucket to the total flow. 13.An electronic device, comprising: one or more processors; a memory device having one or more programs stored thereon, when the one or more programs are executed by the one or more processors, the one or more processors implement the method for controlling flow progress according to any one of claims 1-6.

14. A computer readable medium having stored thereon a computer program, wherein, the program, when executed by a processor, implements the method for controlling flow progress according to any one of claims 1-6.

Images