CN113765811B

CN113765811B - Flow control method, device, equipment and storage medium

Info

Publication number: CN113765811B
Application number: CN202010504584.1A
Authority: CN
Inventors: 吴新生
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2020-06-05
Filing date: 2020-06-05
Publication date: 2024-04-16
Anticipated expiration: 2040-06-05
Also published as: CN113765811A

Abstract

The application discloses a flow control method, a flow control device, flow control equipment and a storage medium, wherein the flow control method comprises the following steps: acquiring target parameters of a first number of target objects in a preset unit time period and target parameter fluctuation data in the preset time period; determining a first flow control proportion of each target object based on target parameters of the first number of target objects in a preset unit time period; determining a second flow control proportion of each target object based on target parameter fluctuation data of the first number of target objects in a preset time period; the flow rate of each target object is controlled based on the first flow rate control ratio and the second flow rate control ratio of each target object in the target period. By utilizing the technical scheme provided by the embodiment of the application, automatic flow control can be realized, the influence of human factors is avoided, and the effectiveness and rationality of flow control on a target object are improved.

Description

Flow control method, device, equipment and storage medium

Technical Field

The present disclosure relates to the field of information processing technologies, and in particular, to a flow control method, apparatus, device, and storage medium.

Background

Along with the daily and monthly variation of the internet, the functions of some internet platforms are more and more diversified, for example, some instant messaging platforms can provide communication functions and realize the flow control of various objects such as financial products, advertisement information and the like.

In the prior art, when performing flow control of objects, flow control is often performed in combination with the related parameter levels of the objects, for example, the parameter values of yesterday are used as the scale division of the flow control of today. However, in the prior art, only the parameter value of a certain day is used as the basis of flow control, so that certain limitation exists, and the actual parameter of the object in the current period of time cannot be accurately mastered during flow control, thereby causing the loss of users. For example, there are some cases where high relevant parameters are made by temporary personnel to obtain a relatively large flow, but later relevant parameters tend to return to low level again, resulting in unreasonable flow control. Thus, there is a need to provide more reliable or efficient solutions.

Disclosure of Invention

The application provides a flow control method, a flow control device, flow control equipment and a storage medium, which can realize automatic flow control, avoid the influence of human factors and further improve the effectiveness and the rationality of flow control on a target object.

In one aspect, the present application provides a flow control method, the method comprising:

acquiring target parameters of a first number of target objects in a preset unit time period and target parameter fluctuation data in the preset time period;

determining a first flow control proportion of each target object based on target parameters of the first number of target objects in a preset unit time period;

determining a second flow control proportion of each target object based on target parameter fluctuation data of the first number of target objects in a preset time period;

the flow rate of each target object is controlled based on the first flow rate control ratio and the second flow rate control ratio of each target object in the target period.

In another aspect, a flow control device is provided, the device comprising:

the target parameter acquisition module is used for acquiring target parameters of a first number of target objects in a preset unit time period;

the target parameter fluctuation data acquisition module is used for acquiring target parameter fluctuation data of a first number of target objects in a preset time period;

a first flow control proportion determining module, configured to determine a first flow control proportion of each target object based on target parameters of the first number of target objects in a preset unit time period;

A second flow control proportion determining module, configured to determine a second flow control proportion of each target object based on target parameter fluctuation data of the first number of target objects in a preset time period;

and the flow control module is used for controlling the flow of each target object based on the first flow control proportion and the second flow control proportion of each target object in the target time period.

In another aspect, a flow control device is provided, the device comprising a processor and a memory having at least one instruction or at least one program stored therein, the at least one instruction or at least one program loaded and executed by the processor to implement a flow control method as described above.

Another aspect provides a computer readable storage medium having stored therein at least one instruction or at least one program loaded and executed by a processor to implement a flow control method as described above.

The flow control method, the flow control device, the flow control equipment and the storage medium have the following technical effects:

according to the method and the device, the first flow control proportion and the second flow control proportion are respectively determined by combining the target parameter of the target object in the preset unit time period and the target parameter fluctuation data in the preset time period, so that the calculation of the comprehensive flow control proportion considering the condition of the target parameter and the target parameter fluctuation is realized, the prediction accuracy of the flow control related parameters (target parameters) of the target object is greatly improved, the flow control is performed based on the first flow control proportion and the second flow control proportion, the automatic flow control can be realized, the grasp of the actual flow control related parameters of the target object is greatly improved, and the effectiveness and the rationality of the flow control of the target object are greatly improved.

Drawings

In order to more clearly illustrate the technical solutions and advantages of embodiments of the present application or of the prior art, the following description will briefly introduce the drawings that are required to be used in the embodiments or the prior art descriptions, it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of an application environment provided by an embodiment of the present application;

FIG. 2 is a schematic flow chart of a flow control method according to an embodiment of the present disclosure;

fig. 3 is a schematic flow chart of obtaining target parameter fluctuation data of a first number of target objects in the preset time period according to an embodiment of the present application;

FIG. 4 is a schematic flow chart of a training method of a parameter fluctuation recognition model according to an embodiment of the present application;

fig. 5 is a schematic flow chart of determining a first flow control ratio of each target object based on target parameters of the first number of target objects in a preset unit time period according to an embodiment of the present application;

FIG. 6 is a schematic flow chart of determining a second flow control ratio of each target object based on target parameter fluctuation data of the first number of target objects in a preset time period according to an embodiment of the present application;

FIG. 7 is a schematic flow chart of controlling the flow rate of each target object based on the first flow control ratio and the second flow control ratio of each target object in a target time period according to the embodiment of the present application;

fig. 8 is a schematic flow chart of controlling the flow of each target object according to the mapping relationship in the target time period according to the embodiment of the present application;

FIG. 9 is a schematic flow chart of a flow control device according to an embodiment of the present disclosure;

fig. 10 is a block diagram of a hardware structure of a server implementing a flow control method according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present application based on the embodiments herein.

It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Artificial intelligence is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and expand human intelligence, sense the environment, acquire knowledge and use the knowledge to obtain optimal results. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

In recent years, with research and progress of artificial intelligence technology, the artificial intelligence technology is widely applied in a plurality of fields, and the scheme provided by the embodiment of the application relates to the technology of machine learning/deep learning and the like of artificial intelligence, and is specifically described by the following embodiments:

referring to fig. 1, fig. 1 is a schematic diagram of an application environment provided in an embodiment of the present application, and as shown in fig. 1, the application environment includes at least a server 01 and a client 02.

In this embodiment of the present disclosure, the server 01 may be used to control the flow of the target object, and specifically, the server 01 may be an independent physical server, or may be a server cluster or a distributed system formed by multiple physical servers, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network ), and basic cloud computing services such as big data and an artificial intelligent platform.

The client 02 in the embodiment of the present specification may be used to recommend an object to the accessed traffic. Specifically, the client 02 may include a smart phone, a desktop computer, a tablet computer, a notebook computer, a smart speaker, a digital assistant, an augmented reality (augmented reality, AR)/Virtual Reality (VR) device, a smart wearable device, or other type of physical device, and may also include software running on the physical device, such as an application, a web page, an applet, and the like. Operating systems running on the electronic device in embodiments of the present application may include, but are not limited to, android systems, IOS systems, linux, windows, and the like.

In the embodiment of the present disclosure, the server 01 and the client 02 may be directly or indirectly connected through a wired or wireless communication method, which is not limited herein.

In the embodiment of the present disclosure, in order to improve accuracy of identifying a fluctuation condition of a target parameter in a current time period of a target object in a process of controlling a flow rate of the target object, a deep learning algorithm may be combined, and a parameter fluctuation identification model that may combine parameter fluctuation influencing factors in a preset time period and identify parameter fluctuation data in a time period after the preset time period may be trained.

In particular, the training data for training the parameter fluctuation recognition model may be collected from a large number of network nodes, and accordingly, the system formed by these network nodes and the apparatus for training the parameter fluctuation recognition model may be a distributed system formed by connecting in the form of network communication. The distributed system may be a blockchain system.

In addition, it should be noted that the parameter fluctuation recognition model provided according to the embodiment of the present application may provide an artificial intelligence cloud Service, which is also commonly referred to as AIaaS (AI as a Service, chinese is "AI as a Service"). The service mode of the artificial intelligent platform is the mainstream at present, and particularly, the AIaaS platform can split several common AI services and provide independent or packaged services at the cloud. This service mode is similar to an AI theme mall: all developers can access one or more artificial intelligence services provided by the use platform through an API interface, and partial deep developers can also use an AI framework and AI infrastructure provided by the platform to deploy and operate and maintain self-proprietary cloud artificial intelligence services.

In the following description of a flow control method according to an embodiment of the present application, fig. 2 is a schematic flow chart of a flow control method according to an embodiment of the present application, where the method operation steps described in the examples or the flow chart are provided, but more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one way of performing the order of steps and does not represent a unique order of execution. When implemented in a real system or server product, the methods illustrated in the embodiments or figures may be performed sequentially or in parallel (e.g., in a parallel processor or multithreaded environment). As shown in fig. 2, the method may include:

s201: and acquiring target parameters of the first number of target objects in a preset unit time period and target parameter fluctuation data in the preset time period.

In the embodiment of the present disclosure, the target object may be an object with a traffic demand, such as a financial product, a delivery information (advertisement), and the like.

Specifically, the first number may be the total number of target objects. Specifically, the target parameter of each target object in the preset unit time period may be a parameter related to flow control of the target object in the preset unit time period. Specifically, the preset unit time period may be a last unit time period of the current unit time period determined in connection with the unit time of calculating the target parameter. For example, the unit time period for calculating the target parameter is one day, and correspondingly, the current unit time period may be the current date, and the preset unit time period may be the day before the current date. In a specific embodiment, when the target object is a financial product, the parameter related to flow control (target parameter) is a rate of return of the financial product, and specifically, the rate of return may include, but is not limited to, a 7-day annual rate of return (average level of return of last 7 days, data obtained after the annual is made), and the like. Specifically, the definition of the yield in the practical application can be combined to obtain the corresponding yield information of the target object so as to calculate the yield. In another specific embodiment, when the target object is the delivery information such as an advertisement, it is assumed that when the platform controls the flow of the delivery information, the click rate of the delivery information is combined, and accordingly, the parameter related to flow control may be the click rate of the delivery information.

In practical applications, the parameter fluctuation data may represent the fluctuation situation of the target parameter in a period of time, and in this embodiment of the present disclosure, the target parameter fluctuation data of each target object in the preset period of time may represent the fluctuation situation of the target parameter in the current period of time of the target object. In a specific embodiment, taking the above-mentioned rate of return as an example, the parameter fluctuation data may be fluctuation data of the rate of return.

In the embodiment of the present disclosure, the duration of the preset time period is greater than the duration of the preset unit time period, and specifically, when the preset unit time period is one day, the target parameter fluctuation data in the preset time period may be the fluctuation condition of the target parameter for multiple days; accordingly, when the preset unit time period is one month, the target parameter fluctuation data in the preset time period may be fluctuation conditions of target parameters of a plurality of months.

In a specific embodiment, the parameter fluctuation data in the last preset period of time before the current point in time may be taken as the target parameter fluctuation data. Correspondingly, acquiring the target parameter fluctuation data of the first number of target objects in the preset time period may include:

1) Acquiring target parameters of a first number of target objects in the preset time period;

2) And determining target parameter fluctuation data of each target object in the preset time period based on the target parameters of the target object in the preset time period.

Specifically, the preset time period may be a latest preset time period before the current time point. For example one month before the current point in time, etc. The target parameters of each target object in the preset time period can comprise target parameters corresponding to a plurality of preset unit time periods in the preset time period; correspondingly, the variance of the target parameters of each target object in a plurality of preset unit time periods in a preset time period can be calculated, and the variance is used as the target parameter fluctuation data of the target object in the preset time period;

in other embodiments, the target parameter fluctuation data of the target object in the preset time period is not limited to the variance of the target parameter in the preset time period, and may include standard deviation of the target parameter in the preset time period.

In practical application, the fact that the target parameter fluctuation data obtained by directly calculating the target parameter of the target object in the preset time period is used as the basis for controlling the flow of the target object is considered, so that the fluctuation condition of the target parameter of the target object in the next process can not be accurately reflected. Accordingly, in other embodiments, as shown in fig. 3, acquiring the target parameter fluctuation data of the first number of target objects within the preset time period may include:

S301: and acquiring target parameters of the first number of target objects in a preset time period before the target time period.

S303: and determining initial parameter fluctuation data of each target object in the preset time period based on the target parameters of the target object in the preset time period.

S305: and acquiring parameter fluctuation influence factors of each target object in the preset time period.

S307: and taking the parameter fluctuation influencing factors as the input of a parameter fluctuation recognition model, and performing parameter fluctuation recognition learning in the parameter fluctuation recognition model to obtain a parameter fluctuation recognition result corresponding to each target object.

S309: and determining the target parameter fluctuation data of each target object in a preset time period based on the initial parameter fluctuation data of each target object in the preset time period and the corresponding parameter fluctuation recognition result.

In the embodiment of the present specification, the initial parameter fluctuation data may include variances, standard deviations, or the like of the target parameters for a plurality of unit time periods within a preset time period.

In the embodiment of the present specification, the parameter fluctuation influencing factor may include data influencing the target parameter. Specifically, taking a target object as a fund as an example, the parameter fluctuation influencing factors may include a business level of an investment fund manager, a total holding amount of the fund held by the fund company (the higher the total holding amount is generally inversely proportional to the benefit, the lower the fund benefit will be), whether there is an action of doing a person doing a certain period of time higher (specifically, a determination of whether there is an action of doing a person doing a certain period of time higher may be made by a value of whether a certain period of time benefit rate is higher than a historical average benefit rate).

In the embodiment of the present disclosure, the parameter fluctuation recognition model may include a model obtained by performing parameter fluctuation recognition training on a preset neural network based on parameter fluctuation influencing factors marked with parameter fluctuation data. Specifically, as shown in fig. 4, the parameter fluctuation recognition model may be obtained by training in the following manner:

s401: acquiring parameter fluctuation influencing factors in a plurality of unit historical time periods;

s403: acquiring parameter fluctuation data in a unit historical time period after each unit historical time period;

s405: taking the parameter fluctuation data in the later unit history time period as the labeling information of the parameter fluctuation influence factors in each unit history time period;

s407: and taking parameter fluctuation influencing factors in a plurality of unit historical time periods with marking information as training data, and carrying out profit fluctuation rate prediction training on a preset neural network to obtain a parameter fluctuation identification model.

In the embodiment of the present specification, the unit history period may be a history period having a fixed duration. The plurality of unit history time periods are different time periods with the same duration, and in particular, the plurality of unit history time periods may or may not overlap. For example, the fixed duration is 20 days, a certain unit history period is from 3 months in 2020 to 20 days in 2020, another unit history period is from 3 months in 2020 to 24 days in 2020, and accordingly, there is an overlapping period between the two unit history periods.

In a specific embodiment, the fixed duration is 20 days, a certain unit history period is from 3 months in 2020 to 3 months in 2020, and the labeling information corresponding to the parameter fluctuation influencing factors from 1 month in 2020 to 20 months in 2020 may be: and the actual calculated parameter fluctuation data is from 10 days in the year 2020 to 29 days in the year 2020. The marking information corresponding to the parameter fluctuation influencing factors in each unit history time period is the parameter fluctuation data in one unit history time period after the unit history time period.

In the embodiment of the present disclosure, the preset neural network may include, but is not limited to, a deep learning model such as a convolutional neural network, a cyclic neural network, or a recurrent neural network. Taking a convolutional neural network as an example, carrying out parameter fluctuation identification training on the preset neural network based on parameter fluctuation influencing factors in a plurality of unit historical time periods with labeling information, adjusting parameters in the preset neural network in the parameter fluctuation identification training until a parameter fluctuation identification result output by the preset neural network is matched with parameter fluctuation data in the labeling information of the input parameter fluctuation influencing factors, and taking the preset neural network when the parameter fluctuation data is matched as a parameter fluctuation identification model.

Specifically, the parameter fluctuation data in the model training stage are matched, which may be that the parameter fluctuation recognition result output in the model training stage is the same as the parameter fluctuation data in the labeling information, or that the difference between the parameter fluctuation recognition result output in the model training stage and the parameter fluctuation data in the labeling information is smaller than a certain threshold value, or the like.

In the embodiment of the specification, the parameter fluctuation influencing factors marked with the parameter fluctuation data are used as training data, and the trained parameter fluctuation recognition model can be combined with the parameter fluctuation influencing factors in a certain unit historical time period to recognize the parameter fluctuation data in the unit time period after the unit historical time period through machine learning, so that the recognition of the fluctuation condition of the target parameter in the unit time period after the unit historical time period is realized.

In the embodiment of the present disclosure, the parameter fluctuation influencing factor of each target object in the preset time period is used as input of a parameter fluctuation recognition model, parameter fluctuation recognition learning is performed in the parameter fluctuation recognition model, and the obtained parameter fluctuation recognition result corresponding to each target object can represent parameter fluctuation data in a time period (the duration of the time period is consistent with the duration of the preset time period) after the preset time period, that is, prediction of the parameter fluctuation data in a time period after the preset time period is implemented.

Further, the initial parameter fluctuation data and the corresponding parameter fluctuation recognition result are obtained through actual calculation in a preset time period, and the target parameter fluctuation data are determined, so that the target parameter fluctuation data can reflect the fluctuation condition of the target parameter before the current time point and the fluctuation condition of the target parameter in a period of time after the current time point, and the accuracy of determining the target parameter fluctuation data in the preset time period is greatly improved.

Specifically, the target parameter fluctuation data can be obtained by performing modes such as weighted average on the initial parameter fluctuation data and the corresponding parameter fluctuation recognition result. Specifically, the initial parameter fluctuation data and the weight of the parameter fluctuation recognition result can respectively represent the influence degree of the fluctuation of the target parameter at the current time, and specifically, the initial parameter fluctuation data and the weight of the parameter fluctuation recognition result can be set in combination with practical application. In some embodiments, the weight of the parameter fluctuation recognition result may be greater than the weight of the initial parameter fluctuation data.

In the embodiment of the present disclosure, by determining the target parameter fluctuation data by combining the initial parameter fluctuation data capable of reflecting the fluctuation condition of the target parameter for a preset period of time before the current time point and the parameter fluctuation recognition result including the current time point and the fluctuation condition of the target parameter for a period of time after the current time point, the fluctuation condition of the target parameter for the current period of time of the target object can be reflected more accurately.

S203: and determining a first flow control proportion of each target object based on the target parameters of the first number of target objects in a preset unit time period.

In practical applications, when the first flow control proportion is determined for the first number of target objects based on the target parameters, the larger the target parameter is, the higher the corresponding first flow control proportion is, whereas the smaller the target parameter is, the lower the corresponding first flow control proportion is.

In some specific embodiments, as shown in fig. 5, determining the first flow control ratio of each target object based on the target parameters of the first number of target objects within the preset unit time period may include:

s2031: calculating a target parameter mean value by utilizing target parameters of the first number of target objects in the preset unit time period;

s2033: determining parameter offset data of each target object according to the target parameter mean value and the target parameter of each target object in the preset unit time period;

s2035: and determining a first flow control proportion of each target object according to the parameter offset data of each target object.

In this embodiment of the present disclosure, the parameter offset data of each target object may be a difference value obtained by subtracting a target parameter mean value from a target parameter of the target object in the preset unit time period. In a specific embodiment, determining the first flow control ratio of each target object according to the parameter offset data of each target object may specifically be combined with the following formula:

wherein phi is _ai A first flow control ratio representing an i-th target object; n represents the total number of target objects (first number); k (k) _ai Parameter offset data representing an i-th target object; α represents a first control coefficient, and specifically, α may be a fixed value or a variable value. In the embodiment of the present disclosure, in order to ensure that the first flow control proportion of each target object is greater than zero, the value of α satisfies the following condition:specifically, when α is a fixed value, a fixed value satisfying the above conditions may be set in association with the actual situation. When alpha is a variation value, in order to avoid that the target object with low target parameter is not divided into flow; and meanwhile, the target object with high target parameters is avoided, the flow is excessive, and the size of alpha can be inversely proportional to the target parameters.

S205: and determining a second flow control proportion of each target object based on the target parameter fluctuation data of the first number of target objects in a preset time period.

In practical application, when the second flow control proportion is determined for the first number of target objects based on the target parameter fluctuation data, the larger the target parameter fluctuation data rate is, the lower the corresponding second flow control proportion is, whereas the smaller the target parameter fluctuation data is, the higher the corresponding second flow control proportion is.

In some specific embodiments, as shown in fig. 6, determining the second flow control ratio of each target object based on the target parameter fluctuation data of the first number of target objects in the preset time period includes:

s2051: calculating a target parameter fluctuation mean value by utilizing target parameter fluctuation data of the first number of target objects in the preset time period;

s2053: determining the parameter discrete data of each target object according to the target parameter fluctuation mean value and the target parameter fluctuation data of each target object in the preset time period;

s2055: and determining a second flow control proportion of each target object according to the parameter discrete data of each target object.

In this embodiment of the present disclosure, the discrete parameter data of each target object may be a difference value obtained by subtracting the mean value of the target parameter fluctuation from the target parameter fluctuation data of the target object in the preset time period. In a specific embodiment, the determining the second flow control proportion of each target object according to the parameter discrete data of each target object may specifically be combined with the following formula:

Wherein phi is _vi A second flow control ratio representing an i-th target object; n represents the total number of target objects (first number); k (k) _vi Parameter discrete data representing an ith target object; beta represents the second control coefficient, and specifically, beta may be a fixed value or a variable value. In the embodiment of the present disclosure, in order to ensure that the second flow control proportion of each target object is greater than zero, the value of β satisfies the following condition:specifically, when β is a fixed value, a fixed value satisfying the above conditions may be set in combination with the actual situation. When beta is a variation value, the target object with low profit fluctuation rate is prevented from being separated into the flow; and meanwhile, a target object with high profit fluctuation rate is avoided, the flow is excessive, and the size of beta can be inversely proportional to the profit fluctuation rate.

S207: the flow rate of each target object is controlled based on the first flow rate control ratio and the second flow rate control ratio of each target object in the target period.

In the embodiment of the present specification, the target period may be a current unit period for calculating the target parameter. For example, the unit time period for calculating the target parameter is one day, and accordingly, the target time period may be the current date.

In a specific embodiment, as shown in fig. 7, controlling the flow rate of each target object based on the first flow control ratio and the second flow control ratio of each target object in the target period may include:

s2071: and carrying out weighted average on the first flow control proportion and the second flow control proportion of each target object to obtain the target request flow control proportion of each target object.

In the embodiment of the present disclosure, the sum of the weight corresponding to the first flow control ratio and the weight corresponding to the second flow control ratio is equal to one; specifically, the weights of the first flow control proportion and the second flow control proportion may be preset in combination with the target parameter and the influence degree of the target parameter fluctuation data on the actual target parameter of the target object in the target time period.

In some embodiments, to better avoid the inaccuracy of benefit of manually targeting high targets on a day (unit time period), before weighted averaging the first and second flow control ratios for each target object to obtain the target requested flow control ratio for each target object, the method further includes:

1) Acquiring a historical parameter mean value of each target object in a historical time period;

2) Calculating a difference value between a target parameter of each target object in the preset unit time period and a historical parameter mean value in a historical time period;

3) When the difference value is greater than or equal to a preset threshold value, the weight corresponding to the second flow control proportion is increased, and the weight corresponding to the first flow control proportion is decreased;

in the embodiment of the present disclosure, the difference between the target parameter of each target object in the preset unit time period and the average value of the historical parameter in the historical time period is the target parameter minus the average value of the historical parameter. In particular, the historical parameter mean may include the average value of the target parameter of the target object from the beginning to the end, or may be the average value of the target parameter in the last period of time (for example, the average value of the target parameter in one year). The preset threshold may be a value greater than 0 set in combination with the condition of the target parameter in the history period of the target object in the actual application, for example, may be 30% of the average value of the history parameter.

S2073: a second amount of target flow is obtained.

Specifically, the second number may be the total number of target traffic, which in this embodiment of the present disclosure may include, but is not limited to, a user flow (access account) or a resource (application) to which object recommendation may be made.

S2075: and determining the target flow number of each target object according to the second quantity and the target request flow control proportion of each target object.

S2077: and determining the flow corresponding to each target object from the target flow based on a preset algorithm and the target flow number of each target object.

In the embodiment of the present disclosure, the preset algorithm may include, but is not limited to, a tail number control method, a random control method, etc., where the tail number control method selects a corresponding number of flows according to the tail number as the flows corresponding to a certain target object; the random control method is to randomly select a corresponding number of flows from the controllable flows as the flows corresponding to a certain target object.

S2079: and establishing a mapping relation between the object identifier of each target object and the flow identifier of the flow corresponding to the target object.

In the embodiment of the present disclosure, the object identifier may be information for distinguishing different target objects, and the object identifier in the mapping relationship may include one or more pieces of information that may be used as the target object identifier. Traffic identification of traffic may be information that distinguishes between different traffic.

In other embodiments, the mapping relationship may further include an update time of the mapping relationship. Specifically, as shown in table 1, a target object is taken as an example of a foundation. Table 1 is an example of a mapping relationship provided in the embodiment of the present specification.

TABLE 1

As can be seen from table 1, assuming that the total number of target objects is 4, the total target traffic is 10000, and the number of fund merchants, the number of funds, and the abbreviations of merchants can be used as the identification information of the target objects, the tail number of the allocated traffic is the tail 5-bit information of the traffic identification of the traffic allocated to the target objects. The tail numbers of the allocated traffic are left-closed and right-open, for example, the traffic allocated to the target object, which is called AAA for merchant, is the traffic from tail number 00000 to tail number 02000, wherein the traffic of tail number 00000 is included, but the traffic of tail number 02000 is not included.

S20711: and controlling the flow of each target object according to the mapping relation in the target time period.

In practical application, after establishing a mapping relationship between the object identifier of each target object and the flow identifier of the flow corresponding to the target object, the method further includes:

and storing the mapping relation into a cache.

In other embodiments, in order to save memory space, after the mapping is obtained, the mapping may be stored in the cache using a pb (Protocol Buff is a serialization Protocol pushed by Google) serialization format.

Accordingly, as shown in fig. 8, the controlling the flow of each target object according to the mapping relationship in the target time period includes:

S801: responding to an object recommendation request of a target request flow in a target time period, and acquiring a flow identifier of the target request flow;

s803: inquiring the mapping relation from the cache based on the flow identification, and determining a target recommended object;

s805: and recommending the target recommended object to the target request flow.

In practical application, in the target time period, the operation of controlling the flow of each target object according to the mapping relation can be triggered by whether an object recommendation request is received, and once the object recommendation request is received, the corresponding operation can be executed in response to the object recommendation request, so that object recommendation is realized.

In practical application, when the mapping relation cannot be queried in the cache, the mapping relation can be queried from the memory. Correspondingly, when the mapping relation is stored in a pb serialization form, deserialization processing can be performed on the queried mapping relation, and then the target recommended object is determined.

As can be seen from the technical solutions provided in the embodiments of the present disclosure, a first flow control proportion and a second flow control proportion are respectively determined in combination with a target parameter of a target object in the preset unit time period and target parameter fluctuation data in the preset time period, so as to implement calculation of a comprehensive flow control proportion considering both the level of the target parameter and the fluctuation condition of the target parameter, greatly improve the accuracy of predicting a flow control related parameter (target parameter) of the target object, and perform flow control based on the first flow control proportion and the second flow control proportion, so that automatic flow control can be implemented, and the grasping of an actual flow control related parameter of the target object is greatly improved, the effectiveness and the rationality of flow control of the target object are improved, user experience is improved, and sustainable development of a platform is implemented.

In practical application, the number of target objects is large, the existing manual updating of the flow control proportion often has the problems of low efficiency and easy error, and in the embodiment of the specification, the calculation of the flow control proportion can be automatically triggered by setting a timing task, and the mapping relationship between the object identifier of the target object and the flow identifier of the flow allocated to the target object is established and updated into a cache, so that when an object recommendation request is received, object recommendation can be performed based on the mapping relationship in the cache. In practical application, after a user triggers an object recommendation request, an FCGI (an intermediate layer, an interface provided for a client may be used to communicate with a back-end server), and the FCGI may be used to keep a CGI (Common Gateway Interface, public gateway interface) interpreter in a memory, so as to improve performance, and if a cache fails, a DB may be degraded if the cache fails, by running a target object corresponding to four bits after the traffic identifier. Accordingly, step S201 of obtaining the target parameters of the first number of target objects in the preset unit time period and the target parameter fluctuation data in the preset time period may include obtaining the target parameters of the first number of target objects in the preset unit time period and the target parameter fluctuation data in the preset time period when the preset time is reached.

In other embodiments, the number of users of the internet platform is often large, and correspondingly, a plurality of servers are deployed to respond to the object recommendation request; in the prior art, gray level release configuration is often adopted, correspondingly, before the total mapping relation is released to all servers, as the mapping relation determined based on the new target request flow control proportion is only released to part of servers, the users have two accesses, namely, the first access is the server for distributing the flow based on the mapping relation which is not updated, the second access is the server for distributing the flow based on the mapping relation which is updated, so that two recommended objects of the same user are inconsistent, idempotency is poor, user experience is poor, and platform development is also unfavorable. In the embodiment of the specification, by means of a timing task, the mapping relation between the object identifier of the target object and the flow identifier of the flow allocated to the target object can be updated timely, so that the flow can be allocated timely, and reasonable recommendation of the object is ensured.

The embodiment of the application also provides a flow control device, as shown in fig. 9, which comprises:

the target parameter obtaining module 910 may be configured to obtain target parameters of the first number of target objects in a preset unit time period;

The target parameter fluctuation data obtaining module 920 may be configured to obtain target parameter fluctuation data of the first number of target objects within a preset period of time;

a first flow control proportion determining module 930, configured to determine a first flow control proportion of each target object based on target parameters of the first number of target objects within a preset unit time period;

a second flow control proportion determining module 940, configured to determine a second flow control proportion of each target object based on target parameter fluctuation data of the first number of target objects in a preset time period;

the flow control module 950 may be configured to control the flow of each target object based on the first flow control ratio and the second flow control ratio of each target object during the target time period.

In some embodiments, the flow control module 950 may include:

the weighted average calculation unit is used for carrying out weighted average on the first flow control proportion and the second flow control proportion of each target object to obtain a target request flow control proportion of each target object;

a flow quantity acquisition unit configured to acquire a second quantity of the target flow;

A target flow rate number determining unit for determining a target flow rate number of each target object according to the second number and the target request flow rate control proportion of each target object;

the flow determining unit is used for determining the flow corresponding to each target object from the target flow based on a preset algorithm and the target flow number of each target object;

the mapping relation establishing unit is used for establishing a mapping relation between the object identifier of each target object and the flow identifier of the flow corresponding to the target object;

and the flow control unit is used for controlling the flow of each target object according to the mapping relation in the target time period.

In some embodiments, the apparatus further comprises:

the storage module is used for storing the mapping relation into a cache;

accordingly, the flow control unit includes:

the flow identification acquisition unit is used for responding to an object recommendation request of a target request flow in a target time period and acquiring a flow identification of the target request flow;

the target recommended object determining unit is used for querying the mapping relation from the cache based on the flow identification and determining a target recommended object;

and the object recommending unit is used for recommending the target recommended object to the target request flow.

In some embodiments, the flow control module 950 may further include:

the historical parameter average value acquisition unit is used for acquiring the historical parameter average value of each target object in a historical time period before carrying out weighted average on the first flow control proportion and the second flow control proportion of each target object to obtain the target request flow control proportion of each target object;

a parameter difference calculating unit, configured to calculate a difference between a target parameter of each target object in the preset unit time period and a historical parameter mean value in a historical time period;

the weight adjusting unit is used for adjusting the weight corresponding to the second flow control proportion to be larger and adjusting the weight corresponding to the first flow control proportion to be smaller when the difference value is larger than or equal to a preset threshold value;

wherein the sum of the weight corresponding to the first flow control proportion and the weight corresponding to the second flow control proportion is equal to one;

in some embodiments, the target parameter fluctuation data acquisition module 920 may include:

a target parameter obtaining unit, configured to obtain target parameters of a first number of target objects in a preset time period before the target time period;

An initial parameter fluctuation data determining unit for determining initial parameter fluctuation data of each target object in the preset time period based on the target parameter of the target object in the preset time period;

the parameter fluctuation influence factor acquisition unit is used for acquiring parameter fluctuation influence factors of each target object in the preset time period;

the parameter fluctuation recognition learning unit is used for taking the parameter fluctuation influence factors as the input of a parameter fluctuation recognition model, and performing parameter fluctuation recognition learning in the parameter fluctuation recognition model to obtain a parameter fluctuation recognition result corresponding to each target object;

the target parameter fluctuation data determining unit is used for determining target parameter fluctuation data of each target object in a preset time period based on initial parameter fluctuation data of each target object in the preset time period and a corresponding parameter fluctuation identification result;

the parameter fluctuation recognition model comprises a model obtained by performing parameter fluctuation recognition training on a preset neural network based on parameter fluctuation influence factors marked with parameter fluctuation data.

In some embodiments, the first flow control ratio determination module 930 may include:

The target parameter mean value calculation unit is used for calculating a target parameter mean value by utilizing target parameters of the first number of target objects in the preset unit time period;

the parameter offset data determining unit is used for determining parameter offset data of each target object according to the target parameter mean value and the target parameter of each target object in the preset unit time period;

and the first flow control proportion determining unit is used for determining the first flow control proportion of each target object according to the parameter offset data of each target object.

In some embodiments, the second flow control ratio determination module 940 may include:

the target parameter fluctuation mean value calculation unit is used for calculating a target parameter fluctuation mean value by utilizing target parameter fluctuation data of the first number of target objects in the preset time period;

the parameter discrete data determining unit is used for determining parameter discrete data of each target object according to the target parameter fluctuation mean value and the target parameter fluctuation data of each target object in the preset time period;

and the second flow control proportion determining unit is used for determining the second flow control proportion of each target object according to the parameter discrete data of each target object.

The device and method embodiments in the device embodiments described are based on the same application concept.

The present application provides a flow control device comprising a processor and a memory having at least one instruction, or at least one program, stored therein, loaded and executed by the processor to implement a flow control method as provided by the method embodiments described above.

The memory may be used to store software programs and modules that the processor executes to perform various functional applications and data processing by executing the software programs and modules stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, application programs required for functions, and the like; the storage data area may store data created according to the use of the device, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide access to the memory by the processor.

The method embodiments provided in the embodiments of the present application may be performed in a mobile terminal, a computer terminal, a server, or similar computing device. Taking the operation on the server as an example, fig. 10 is a block diagram of a hardware structure of a server implementing a flow control method according to an embodiment of the present application. As shown in fig. 10, the server 1000 may vary considerably in configuration or performance and may include one or more central processing units (Central Processing Units, CPU) 1010 (the processor 1010 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA), a memory 1030 for storing data, one or more storage mediums 1020 (e.g., one or more mass storage devices) for storing applications 1023 or data 1022. Wherein the memory 1030 and storage medium 1020 can be transitory or persistent storage. The program stored on the storage medium 1020 may include one or more ofThe above modules, each of which may include a series of instruction operations in a server. Still further, the central processor 1010 may be configured to communicate with a storage medium 1020 and execute a series of instruction operations in the storage medium 1020 on the server 1000. The Server 1000 may also include one or more power supplies 1060, one or more wired or wireless network interfaces 1050, one or more input/output interfaces 1040, and/or one or more operating systems 1021, such as Windows Server ^TM ，Mac OS X ^TM ，Unix ^TM ,Linux ^TM ，FreeBSD ^TM Etc.

Input-output interface 1040 may be used to receive or transmit data via a network. The specific example of the network described above may include a wireless network provided by a communication provider of the server 1000. In one example, input-output interface 1040 includes a network adapter (Network Interface Controller, NIC) that may be connected to other network devices via base stations to communicate with the internet. In one example, the input-output interface 1040 may be a Radio Frequency (RF) module for communicating with the internet wirelessly.

It will be appreciated by those of ordinary skill in the art that the configuration shown in fig. 10 is merely illustrative and is not intended to limit the configuration of the electronic device described above. For example, the server 1000 may also include more or fewer components than shown in fig. 10, or have a different configuration than shown in fig. 10.

Embodiments of the present application also provide a storage medium that may be disposed in an apparatus to store at least one instruction, or at least one program, for implementing a flow control method according to a method embodiment, where the at least one instruction, or the at least one program, is loaded and executed by the processor to implement the flow control method provided by the method embodiment.

Alternatively, in this embodiment, the storage medium may be located in at least one network server among a plurality of network servers of the computer network. Alternatively, in the present embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.

According to the embodiments of the flow control method, the device, the equipment, the server or the storage medium provided by the application, the first flow control proportion and the second flow control proportion are respectively determined by combining the target parameter of the target object in the preset unit time period and the target parameter fluctuation data in the preset time period, so that the calculation of the comprehensive flow control proportion considering the condition of the target parameter and the target parameter fluctuation is realized, the prediction accuracy of the flow control related parameter (target parameter) of the target object is greatly improved, the flow control is performed based on the first flow control proportion and the second flow control proportion, the automatic flow control can be realized, the grasp of the actual flow control related parameter of the target object is greatly improved, and the effectiveness and the rationality of the flow control of the target object are greatly improved.

It should be noted that: the foregoing sequence of the embodiments of the present application is only for describing, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, device, server and storage medium embodiments, the description is relatively simple as it is substantially similar to method embodiments, with reference to the description of method embodiments in part.

Those of ordinary skill in the art will appreciate that all or a portion of the steps implementing the above embodiments may be implemented by hardware, or may be implemented by a program indicating that the relevant hardware is implemented, where the program may be stored on a computer readable storage medium, where the storage medium may be a read only memory, a magnetic disk or optical disk, etc.

The foregoing description of the preferred embodiments of the present application is not intended to limit the invention to the particular embodiments of the present application, but to limit the scope of the invention to the particular embodiments of the present application.

Claims

1. A method of flow control, the method comprising:

2. The method of claim 1, wherein controlling the flow of each target object based on the first flow control ratio and the second flow control ratio of each target object during the target time period comprises:

Weighted average is carried out on the first flow control proportion and the second flow control proportion of each target object to obtain a target request flow control proportion of each target object;

acquiring a second quantity of the target flow;

determining the target flow number of each target object according to the second quantity and the target request flow control proportion of each target object;

determining the flow corresponding to each target object from the target flow based on a preset algorithm and the target flow number of each target object;

establishing a mapping relation between an object identifier of each target object and a flow identifier of a flow corresponding to the target object;

and controlling the flow of each target object according to the mapping relation in the target time period.

3. The method of claim 2, wherein after establishing a mapping relationship between the object identifier of each target object and the traffic identifier of the traffic corresponding to the target object, the method further comprises:

storing the mapping relation into a cache;

correspondingly, the controlling the flow of each target object according to the mapping relation in the target time period includes:

responding to an object recommendation request of a target request flow in a target time period, and acquiring a flow identifier of the target request flow;

Inquiring the mapping relation from the cache based on the flow identification, and determining a target recommended object;

and recommending the target recommended object to the target request flow.

4. The method of claim 2, wherein prior to weighted averaging the first flow control ratio and the second flow control ratio for each target object to obtain the target requested flow control ratio for each target object, the method further comprises:

acquiring a historical parameter mean value of each target object in a historical time period;

calculating a difference value between a target parameter of each target object in the preset unit time period and a historical parameter mean value in a historical time period;

when the difference value is greater than or equal to a preset threshold value, the weight corresponding to the second flow control proportion is increased, and the weight corresponding to the first flow control proportion is decreased;

wherein the sum of the weight corresponding to the first flow control proportion and the weight corresponding to the second flow control proportion is equal to one.

5. The method of claim 1, wherein the obtaining target parameter fluctuation data for the first number of target objects over the preset time period comprises:

Acquiring target parameters of a first number of target objects in a preset time period before the target time period;

determining initial parameter fluctuation data of each target object in the preset time period based on the target parameter of the target object in the preset time period;

acquiring parameter fluctuation influence factors of each target object in the preset time period;

taking the parameter fluctuation influencing factors as the input of a parameter fluctuation recognition model, and performing parameter fluctuation recognition learning in the parameter fluctuation recognition model to obtain a parameter fluctuation recognition result corresponding to each target object;

determining target parameter fluctuation data of each target object in a preset time period based on initial parameter fluctuation data of each target object in the preset time period and a corresponding parameter fluctuation recognition result;

6. The method of claim 1, wherein determining a first flow control ratio for each target object based on target parameters of the first number of target objects over a preset unit time period comprises:

Calculating a target parameter mean value by utilizing target parameters of the first number of target objects in the preset unit time period;

determining parameter offset data of each target object according to the target parameter mean value and the target parameter of each target object in the preset unit time period;

and determining a first flow control proportion of each target object according to the parameter offset data of each target object.

7. The method of claim 1, wherein determining the second flow control ratio for each target object based on the target parameter fluctuation data for the first number of target objects over a preset period of time comprises:

calculating a target parameter fluctuation mean value by utilizing target parameter fluctuation data of the first number of target objects in the preset time period;

determining the parameter discrete data of each target object according to the target parameter fluctuation mean value and the target parameter fluctuation data of each target object in the preset time period;

and determining a second flow control proportion of each target object according to the parameter discrete data of each target object.

8. A flow control device, the device comprising:

9. The apparatus of claim 8, wherein the flow control module comprises:

10. The apparatus of claim 9, wherein the apparatus further comprises:

the storage module is used for storing the mapping relation into a cache;

accordingly, the flow control unit includes:

11. The apparatus of claim 9, wherein the flow control module further comprises:

12. The apparatus of claim 8, wherein the target parameter fluctuation data acquisition module comprises:

13. The apparatus of claim 8, wherein the first flow control ratio determination module comprises:

14. The apparatus of claim 8, wherein the second flow control ratio determination module comprises:

15. A flow control device comprising a processor and a memory having at least one instruction or at least one program stored therein, the at least one instruction or the at least one program loaded and executed by the processor to implement the flow control method of any one of claims 1 to 7.

16. A computer readable storage medium having stored therein at least one instruction or at least one program loaded and executed by a processor to implement the flow control method of any of claims 1 to 7.