CN116260666A

CN116260666A - Resource recommendation method and device

Info

Publication number: CN116260666A
Application number: CN202310019469.9A
Authority: CN
Inventors: 朱婉怡
Original assignee: Alibaba China Co Ltd
Current assignee: Alibaba China Co Ltd
Priority date: 2023-01-06
Filing date: 2023-01-06
Publication date: 2023-06-13

Abstract

The embodiment of the specification provides a resource recommendation method and a device, wherein the resource recommendation method comprises the following steps: predicting a flow value in a target time range according to a historical flow value of a user; determining a recommended bandwidth meeting a preset cost condition under the condition of carrying out cost calculation in a flow and bandwidth combined charging mode according to the flow value in the target time range; and recommending the recommended bandwidth to the user. The user purchases the CDN operators according to the recommended bandwidth, so that the cost of the user is minimized, the waste of resources is reduced, and the cost can be reduced.

Description

Resource recommendation method and device

Technical Field

The embodiment of the specification relates to the technical field of Internet, in particular to a resource recommendation method.

Background

With the vigorous development of the information content industry, video and streaming media become important carriers of internet content, and compared with traditional graphic content, video content can transmit more vivid information, and meanwhile, the data volume is larger, so that the content distribution needs to be accelerated through CDN technology.

Currently, CDN technologies are usually charged in a peak bandwidth manner, that is, a user can purchase peak bandwidths of different gears from a CDN operator to implement use of the CDN technologies. However, the flow attribute of the streaming media service itself makes the peak bandwidth generally exist only in a fixed time interval of each day, and the real-time flow at other times is far lower than the peak bandwidth. Therefore, an effective solution is needed to solve the above problems.

Disclosure of Invention

In view of this, the embodiments of the present disclosure provide a resource recommendation method. One or more embodiments of the present specification also relate to a resource recommendation apparatus, a computing device, a computer-readable storage medium, and a computer program that solve the technical drawbacks of the prior art.

According to a first aspect of embodiments of the present disclosure, there is provided a resource recommendation method, including: predicting a flow value in a target time range according to a historical flow value of a user; determining a recommended bandwidth meeting a preset cost condition under the condition of carrying out cost calculation in a flow and bandwidth combined charging mode according to the flow value in the target time range; and recommending the recommended bandwidth to the user.

According to a second aspect of embodiments of the present specification, there is provided a resource recommendation device, including: a prediction module configured to predict a flow value within a target time range based on a historical flow value of a user; the determining module is configured to determine a recommended bandwidth meeting a preset cost condition under the condition of performing cost calculation in a flow and bandwidth combined charging mode according to the flow value in the target time range; and the recommending module is configured to recommend the recommended bandwidth to the user.

According to a third aspect of embodiments of the present specification, there is provided a computing device comprising: a memory and a processor; the memory is configured to store computer-executable instructions that, when executed by the processor, perform the steps of the resource recommendation method described above.

According to a fourth aspect of embodiments of the present specification, there is provided a computer readable storage medium storing computer executable instructions which, when executed by a processor, implement the steps of the resource recommendation method described above.

According to a fifth aspect of embodiments of the present specification, there is provided a computer program, wherein the computer program, when executed in a computer, causes the computer to perform the steps of the resource recommendation method described above.

One embodiment of the present disclosure provides a resource recommendation method, which predicts a flow value within a target time range according to a historical flow value of a user; determining a recommended bandwidth meeting preset cost conditions under the condition of carrying out cost calculation in a flow and bandwidth combined charging mode according to the flow value in the target time range, wherein the preset cost conditions comprise conditions for flow cost and bandwidth cost; and recommending the recommended bandwidth to the user.

According to the method, the flow of the user in the target time range is predicted according to the historical flow value of the user, and the recommended bandwidth which can enable the cost to be the lowest is calculated according to the predicted flow value in the target time range under the condition that the cost calculation is carried out in a flow and bandwidth combined charging mode, so that the user can be recommended to the user, the user can purchase according to the recommended bandwidth to the CDN operator, the cost of the user is minimized, and therefore the waste of resources is reduced, and the cost can be reduced.

Drawings

Fig. 1 is an application scenario schematic diagram of a resource recommendation method according to an embodiment of the present disclosure;

FIG. 2 is a flow chart of a resource recommendation method provided by one embodiment of the present disclosure;

FIG. 3 illustrates a flow chart for determining recommended bandwidth in a resource recommendation method provided in accordance with one embodiment of the present disclosure;

FIG. 4 is a schematic diagram of objective functions in a resource recommendation method according to an embodiment of the present disclosure;

FIG. 5 shows a schematic flow chart of combined charging in a resource recommendation method provided in accordance with one embodiment of the present description;

FIG. 6 is a flowchart of a process of a resource recommendation method according to one embodiment of the present disclosure;

FIG. 7 is a schematic diagram of a resource recommendation device according to an embodiment of the present disclosure;

FIG. 8 is a block diagram of a computing device provided in one embodiment of the present description.

Detailed Description

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present description. This description may be embodied in many other forms than described herein and similarly generalized by those skilled in the art to whom this disclosure pertains without departing from the spirit of the disclosure and, therefore, this disclosure is not limited by the specific implementations disclosed below.

The terminology used in the one or more embodiments of the specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of the specification. As used in this specification, one or more embodiments and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present specification refers to and encompasses any or all possible combinations of one or more of the associated listed items.

It should be understood that, although the terms first, second, etc. may be used in one or more embodiments of this specification to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first may also be referred to as a second, and similarly, a second may also be referred to as a first, without departing from the scope of one or more embodiments of the present description. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.

First, terms related to one or more embodiments of the present specification will be explained.

CDN: content Delivery Network, a content distribution network. CDNs are a type of distributed content distribution network built on a data network. The CDN has the advantages that the server cluster technology is adopted, the defects of insufficient output bandwidth and concurrency capacity of a single-machine system are overcome, the number of concurrent flows supported by the system can be greatly increased, and adverse effects caused by single-point failure are reduced or avoided. For example, the CDN may employ a cluster of streaming servers to implement streaming media delivery.

SPO: smart prediction, the optimization, intelligent prediction and then optimization are structures of downstream optimization decision problems. It can directly use the structure of the optimization problem, i.e. its objectives and constraints, to design the predictive model.

Time sequence prediction algorithm: as a quantitative prediction algorithm, on one hand, statistical analysis can be performed by using past time sequence data to estimate the development trend of things; on the other hand, the randomness caused by the influence of accidental factors is fully considered, in order to eliminate the influence caused by random fluctuation, the historical data is utilized for carrying out statistical analysis, and the data is properly processed for carrying out trend prediction.

It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) according to the embodiments of the present disclosure are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region, and provide corresponding operation entries for the user to select authorization or rejection.

In the present specification, a resource recommendation method is provided, and the present specification relates to a resource recommendation apparatus, a computing device, and a computer-readable storage medium, which are described in detail in the following embodiments one by one.

Referring to fig. 1, fig. 1 shows an application scenario schematic diagram of a resource recommendation method according to an embodiment of the present disclosure.

Fig. 1 includes a client 102 and a server 104. Wherein, the user terminal 102 and the server terminal 104 are in communication connection. The client 102 may be a server of an enterprise user or a client of the enterprise user, where the client 102 is configured to store a historical flow value of the user. The server 104 may obtain the historical flow value recorded in the background of the user 102 after the user authorization, and of course, the user may upload the historical flow value by the user 102 as required, and the server 104 may execute the resource recommendation method after obtaining the historical flow value of the user, so as to determine the recommendation bandwidth.

In a specific implementation, the server 104 responds to a recommendation request of a user, obtains a historical flow value of the user through the user terminal 102, after the server 104 receives the historical flow value, predicts a flow value which is possibly consumed by the user in a target time range according to the historical flow value, determines a cost and a minimum recommended bandwidth which meet a flow cost and a bandwidth cost according to the flow value, and sends the recommended bandwidth to the user terminal 102, wherein the user terminal 102 can display the recommended bandwidth to the user, or can directly send the recommended bandwidth to a CDN operator, and purchases CDN services for the CDN operator according to the recommended bandwidth.

Referring to fig. 2, fig. 2 shows a flowchart of a resource recommendation method according to an embodiment of the present disclosure, which specifically includes the following steps.

Step 202: and predicting the flow value in the target time range according to the historical flow value of the user.

Specifically, the resource recommendation method provided in the embodiments of the present specification may be applied to CDN charging in a streaming media scenario, or may be applied to traffic charging in a telecom operation scenario, which is not limited in the embodiments of the present specification.

For easy understanding, in the embodiments of the present disclosure, the application of the resource recommendation method to the CDN billing scenario is described in detail, but the application of the resource recommendation method to other implementation scenarios is not affected.

The user may understand that the service side of the video and the streaming media, for example, may be a live broadcast platform in a live broadcast scenario, or may also be an e-commerce platform, where in the still picture service provided by the e-commerce platform, the browsing of the commodity downloads the still picture to generate the flow, so that the CDN technology is also required to be utilized. The historical flow value may be understood as a flow value consumed by a user in a historical period, where the flow value consumed in the historical period may include flow values corresponding to a plurality of time points in the historical period, for example, for a flow value consumed by the user in a certain day, may be a flow value consumed at time points separated by a preset period, for example, a time point may be determined at intervals of five minutes, that is, taking 1:00 in the day as a time point, then 1:05 can be a time point and 1:10 can be a time point. The target time frame may be understood as a future time period, such as a future month, or a future week, etc., which needs to be predicted. The flow value within the target time range may be understood as a flow value that needs to be predicted to be consumed by the user in a certain time period in the future, for example, may be a flow value that the user consumes in a certain month in the future, or may be a flow value that the user consumes in a certain day in the future. Also, the flow rate value consumed by the user in a certain time period in the future may include flow rate values consumed at a plurality of time points in the time period, that is, flow rate values consumed by the user at time points spaced apart from a preset time period in the time period.

Based on this, it is possible to predict the flow rate values that the user is likely to consume at a plurality of time points in a certain time period in the future, based on the flow rate values that the user is consuming at a plurality of time points in the history time period, respectively.

In practical application, the flow value of the user in the target time range can be predicted by using a prediction model or a prediction algorithm, and the flow value in the target time range comprises flow values corresponding to a plurality of time points, so that the flow value of the user in the target time range can be predicted according to a time sequence prediction method, and the specific implementation mode is as follows:

according to the historical flow value of the user, predicting a trend value and a variation value of the user in a target time range by using a time sequence prediction algorithm;

and predicting the flow value in the target time range according to the trend value and the variation value.

The basic principle of the method is that on one hand, the continuity of the development of things is admitted, and the past time series data is used for statistical analysis to estimate the development trend of the things; on the other hand, the randomness caused by the influence of accidental factors is fully considered, in order to eliminate the influence caused by random fluctuation, the historical data is utilized for carrying out statistical analysis, and the data is properly processed for carrying out trend prediction. The trend value of the user in the target time range may be understood as a trend of the user in the target time range. The variance value may be understood as an access behavior of the consumer of the user within the target time range, and the access behavior may be, for example, a browsing behavior of the consumer or a consuming behavior of the consumer. For example, in the e-commerce platform scenario, the trend value can be understood as whether the e-commerce platform is developed smoothly, whether consumers in the market have confidence consumption, and the like. The variance represents the periodic or aperiodic consumer behavior of the consumer.

Based on the above, the time sequence prediction method can be used for predicting the development trend of the user in the target time range and the access behavior of the consumer according to the flow value corresponding to each time point of the user in the historical time period, and predicting the flow value of the user in the target time range according to the development trend and the access behavior of the consumer.

For example, a time point may be determined every 5 minutes in the 11 months of a year according to a certain e-commerce platform, a development trend of the 11 months of the year and a consumption behavior of a consumer in the e-commerce platform may be predicted according to a flow value corresponding to each time point, and a flow value corresponding to each time point may be determined every 5 minutes in the 11 months of the year according to a prediction result.

In addition, the historical flow value of the user may be uploaded to the server side executing the resource recommendation method by the user, or may be automatically obtained after the server side executing the resource recommendation method is authorized by the user, which is not limited herein.

In sum, the flow value of the user in the target time range is predicted according to the historical flow value of the user, and the historical condition of the user is considered, so that the prediction result is more accurate, and the accuracy of determining the recommended bandwidth according to the prediction result is further improved.

Step 204: and determining the recommended bandwidth meeting the preset cost condition under the condition of carrying out cost calculation in a flow and bandwidth combined charging mode according to the flow value in the target time range.

Specifically, after the flow value of the user in the target time range is obtained through prediction, the recommended bandwidth meeting the preset cost condition under the condition that the cost calculation is performed in a flow and bandwidth combined charging mode can be determined.

The charging mode of combining flow and bandwidth can be understood as a charging mode of combining flow charging and peak bandwidth charging.

Alternatively, the preset cost condition includes a condition for traffic cost and bandwidth cost, and the preset cost condition may be understood as a cost and a minimum condition of traffic cost and bandwidth cost.

Based on this, in the case of performing cost calculation in a combined traffic and bandwidth charging manner, it is possible to calculate a cost and the lowest recommended bandwidth that satisfy the traffic cost and the bandwidth cost, based on the traffic value corresponding to each time point within the target time range.

In practical application, the flow value consumed by the user in the target month may be predicted according to the obtained historical minute-level flow value of the user, and referring to fig. 3, fig. 3 shows a flowchart for determining the recommended bandwidth in a resource recommendation method provided according to an embodiment of the present disclosure, which specifically includes the following steps.

Step 302: the minute-level flow value of the user in the historical time period is obtained.

The minute-level flow value may be understood as a flow value of a minute level, for example, a flow value corresponding to a time point of 5 minutes, a flow value of other time granularity, for example, a flow value corresponding to a time point of 1 hour, or a flow value corresponding to a time point of 1 day. It will be appreciated that the result of the flow value prediction from the minute level is also more accurate, as the number of minute level flow values is greater.

Step 304: and predicting the flow value of the user in the target month.

Step 306: and calculating the recommended bandwidth according to the predicted flow value.

The recommended bandwidth is understood to be the bandwidth that meets the cost and minimum cost of traffic and bandwidth costs. Correspondingly, calculating a recommended bandwidth according to the predicted flow value, namely determining the recommended bandwidth meeting the preset cost condition under the condition of carrying out cost calculation in a flow and bandwidth combined charging mode according to the flow value in the target time range.

In summary, through the algorithm technical means of combining prediction and decision optimization, the respective advantages of two modes of bandwidth peak charging and flow charging and the service flow demand characteristics of the user are fully integrated, the flow demand trend prediction and bandwidth resource water level recommendation service is established, and through combination of charging recommendation, the total cost and the service flow demand are considered, so that the total cost is reduced while the service flow demand can be met.

Specifically, when determining the recommended bandwidth meeting the preset cost condition, iterative processing may be performed according to the traffic cost and the bandwidth cost until a recommended bandwidth that minimizes the traffic cost and the bandwidth cost is obtained, where the specific implementation manner is as follows:

calculating an initial cost corresponding to a flow value in the target time range under the condition that a user uses an initial recommended bandwidth and adopts a flow and bandwidth combined charging mode to perform cost calculation;

and determining the initial recommended bandwidth as a recommended bandwidth recommended to the user under the condition that the initial cost reaches a preset cost range.

Under the condition that the initial cost does not reach the preset cost range, determining an updated recommended bandwidth corresponding to the current iterative process according to the initial recommended bandwidth;

in the current iteration process, calculating the update cost corresponding to the flow value in the target time range under the condition that the user uses the update recommended bandwidth and adopts a flow and bandwidth combination charging mode to perform cost calculation;

determining a target cost from the initial cost and the update cost calculated during each iteration;

judging whether the target cost converges to the minimum;

If so, determining the recommended bandwidth corresponding to the target cost as the recommended bandwidth recommended to the user;

if not, determining an updated recommended bandwidth corresponding to the next iteration process according to the recommended bandwidth corresponding to the target cost, entering the next iteration process, and returning to the step of calculating the updated cost corresponding to the flow value in the target time range under the condition that the user uses the updated recommended bandwidth and adopts a flow and bandwidth combined charging mode to perform cost calculation in the current iteration process.

The initial recommended bandwidth may be understood as a bandwidth actually purchased by a preset user. The preset cost range may be understood as a range of a sum of costs of a preset traffic cost and a bandwidth cost, the costs are within the preset cost range, the costs may be a cost which is smaller for a user and acceptable to the user, and the recommended bandwidth corresponding to the cost may be recommended to the user.

Based on this, under the condition that the user uses the initial recommended bandwidth and performs cost calculation by adopting a flow and bandwidth combined charging mode, the initial cost required to be consumed by the flow value in the predicted target time range can be calculated, whether the initial cost reaches the preset cost range or not is judged, if yes, the recommended bandwidth corresponding to the cost can be directly recommended to the user, if not, the updated recommended bandwidth corresponding to the current iteration process is required to be determined according to the initial recommended bandwidth, specifically, the updated time point can be determined in the upper and lower floating ranges of the initial time point corresponding to the initial recommended bandwidth, and the updated recommended bandwidth corresponding to the updated time point is determined. And calculating the update cost corresponding to the flow value in the target time range when the user uses the updated recommended bandwidth and adopts a flow and bandwidth combination charging mode to calculate the cost again, determining the target cost with the minimum cost value from the initial cost and the update cost calculated in each iteration process, judging whether the target cost is converged to the minimum, so that the cost is minimized through multiple iterations, and determining the recommended bandwidth corresponding to the target cost as the recommended bandwidth recommended to the user when the user uses the recommended bandwidth corresponding to the target cost when the user is judged to be converged to the minimum. And under the condition that the target cost is not converged to the minimum, the recommended bandwidth corresponding to the target cost at the moment is indicated, the cost consumed by the flow value in the predicted target time range cannot be minimized, the recommended bandwidth is required to be redetermined at the moment, and the step of calculating the updated cost is continuously executed until the target cost with the minimum cost value is converged to the minimum, so that the cost of the flow value consumed by the user in the target time range is minimized.

After two iterations, an initial cost, a first update cost in the first iteration process, and a second update cost in the second iteration process are calculated, where the initial cost corresponds to an initial recommended bandwidth, the first update cost corresponds to an update recommended bandwidth in the first iteration process, and the second update cost corresponds to a second recommended bandwidth in the second iteration process, and then when determining the target cost with the smallest cost value, the target cost is determined from the three costs of the initial cost, the first update cost, and the second update cost. And so on, after three iterations, the target cost with the smallest cost value is determined from the four costs of the initial cost, the first update cost, the second update cost, and the third update cost.

In summary, by combining the costs calculated in each iteration process, the target cost with the smallest cost value is determined, and then whether the target cost converges to the minimum is judged, so that the efficiency of determining the recommended bandwidth can be improved.

In practical application, the flow value in the target time range includes the flow value corresponding to the time point in the target time range, for example, the flow value corresponding to the time point in the target time range at intervals of a preset time period, and before calculating the initial cost, in order to facilitate the subsequent determination of the recommended bandwidth meeting the preset cost, an objective function may be constructed, and the objective function is used to provide the flow value corresponding to any time point in the target time range, where the specific implementation manner is as follows:

And constructing an objective function by taking a time point in the objective time range as an abscissa and a flow value corresponding to the time point in the objective time range as an ordinate, wherein the objective function is used for providing a flow value corresponding to any time point in the objective time range in the process of calculating the initial cost or the update cost.

Referring to fig. 4, fig. 4 is a schematic diagram illustrating an objective function in a resource recommendation method according to an embodiment of the present disclosure. The curve in fig. 4 is an objective function, where the abscissa of the objective function is a time point within the objective time range, and the ordinate is a flow value corresponding to the time point, that is, a predicted flow value that may be consumed at the time point.

In practical application, a general SPO optimization structure can be utilized to construct an objective function and determine a recommended bandwidth. Or the general SPO optimization structure may be improved according to a specific implementation scenario, and the improved SPO optimization structure is used to construct an objective function, which is not limited herein in this embodiment.

In summary, by constructing the objective function according to the flow value in the objective time range, a basis can be provided for the follow-up determination of the recommended bandwidth meeting the preset cost, and the flow value in the predicted objective time range can be visually displayed, so that flexible and accurate cost calculation is realized.

In the specific implementation, when the user uses the initial recommended bandwidth and performs cost calculation by adopting a flow and bandwidth combined charging mode, calculating the initial cost corresponding to the flow value in the target time range includes:

determining an initial time point in the target time range and a flow value corresponding to the initial time point, and taking the flow value as an initial recommended bandwidth;

according to the initial time point and the initial recommended bandwidth corresponding to the initial time point, calculating initial bandwidth cost and initial flow cost corresponding to the flow value in the target time range under the condition that the user uses the initial recommended bandwidth;

and calculating initial cost according to the initial bandwidth cost and the initial traffic cost.

Specifically, an initial time point may be determined in the objective function shown in fig. 4, a flow value corresponding to the initial time point may be determined according to the objective function, the flow value is used as an initial recommended bandwidth, the initial recommended bandwidth is a straight line intersecting the objective function in fig. 4, and an intersection point of the objective function and the straight line is the initial time point. And calculating the initial bandwidth cost and the initial flow cost corresponding to the flow value in the target time range under the condition that the user uses the initial bandwidth. The initial bandwidth cost corresponding to the flow value in the target time range is the A-bandwidth cost corresponding to the straight line in fig. 4, namely the cost of the initial recommended bandwidth, and the initial flow cost corresponding to the flow value in the target time range is the area of the shadow part between the objective function and the straight line in fig. 4, namely the B-flow cost.

In summary, by calculating the initial cost according to the initial recommended bandwidth, subsequent iterations can be performed by using the initial cost until the initial cost reaches the minimum, thereby realizing the recommendation of the recommended bandwidth resource water level and further realizing the minimum overall cost.

In a specific implementation, the calculating, according to the initial time point and the initial recommended bandwidth corresponding to the initial time point, an initial bandwidth cost and an initial traffic cost corresponding to a traffic value in the target time range when the user uses the initial recommended bandwidth includes:

calculating initial bandwidth cost corresponding to a flow value in the target time range under the condition that a user uses the initial recommended bandwidth according to the initial recommended bandwidth and the price corresponding to the initial recommended bandwidth;

and determining a target time point exceeding a flow value corresponding to the initial time point in the target time range according to the initial time point, and calculating initial flow cost corresponding to the flow value of the target time point under the condition that the user uses the initial recommended bandwidth.

Specifically, the price of the initial recommended bandwidth may be determined in the bandwidth gradient price of the CDN operator according to the initial recommended bandwidth, so as to determine the initial bandwidth cost corresponding to the traffic value in the target time range when the user uses the initial recommended bandwidth. Moreover, a target time point exceeding the flow value corresponding to the initial time point in the target time range may be determined according to the initial time point, as shown in fig. 4, all time points above the straight line are the target time point, and the initial flow cost is calculated according to the flow value and the price of the flow corresponding to the target time point.

In summary, by calculating the initial traffic cost and the initial bandwidth cost respectively, the calculation of the initial cost, that is, the overall cost, can be realized, and a basis is provided for the subsequent iterative processing.

In the implementation, when the initial cost does not converge to the minimum, the updated recommended bandwidth can be determined continuously according to the initial recommended bandwidth, and the implementation is as follows:

and determining an updating time point in the target time range and a flow value corresponding to the updating time point according to the initial time point corresponding to the initial recommended bandwidth, and taking the flow value as the updated recommended bandwidth.

Specifically, the update time point may be determined according to an initial time point corresponding to the peak bandwidth and the initial recommended bandwidth, where the peak bandwidth is the maximum value of the allowed instantaneous flow, and the peak position of the objective function in fig. 4 is the corresponding peak bandwidth, and the update time point may be determined between the initial time point corresponding to the initial recommended bandwidth and the time point corresponding to the peak bandwidth by using the peak bandwidth.

Based on this, an update time point in the target time range can be determined between the time point corresponding to the peak bandwidth and the initial time point corresponding to the initial recommended bandwidth, and a charging point of the update recommended bandwidth when the initial cost is minimum is calculated by using a preset function, wherein the charging point is the update time point, and a flow value corresponding to the update time point is determined and used as the update recommended bandwidth.

In practical applications, the preset function may be, for example, a function for calculating a variable value that makes the function take a minimum value, for example, an argmin function, which is a commonly used mathematical function and may be used for calculating the minimum value.

Accordingly, when determining the updated recommended bandwidth corresponding to the next iteration process according to the recommended bandwidth corresponding to the target cost, the updated time point in the target time range and the flow value corresponding to the updated time point may be redetermined between the updated time point and the time point corresponding to the peak bandwidth according to the updated time point corresponding to the updated recommended bandwidth, and the flow value is used as the redetermined updated recommended bandwidth.

In summary, when the initial cost does not converge to the minimum, continuously determining to update the recommended bandwidth according to the initial cost, and iterating until the initial cost converges to the minimum, thereby realizing the recommended bandwidth with the minimum determined cost.

When the method is implemented, the calculating the update cost corresponding to the flow value in the target time range under the condition that the user uses the update recommended bandwidth and adopts the flow and bandwidth combination charging mode to calculate the cost comprises the following steps:

calculating the update bandwidth cost corresponding to the flow value in the target time range under the condition that the user uses the update recommended bandwidth according to the update recommended bandwidth and the price corresponding to the update recommended bandwidth;

And determining a target time point exceeding a flow value corresponding to the update time point in the target time range according to the update time point, and calculating update flow cost corresponding to the flow value of the target time point under the condition that the user uses the update recommended bandwidth.

And calculating the update cost according to the update bandwidth cost and the update flow cost.

It should be noted that, the method for calculating the update cost is similar to the method for calculating the initial cost, and the description thereof will not be repeated here.

Step 206: and recommending the recommended bandwidth to the user.

Specifically, after determining the recommended bandwidth meeting the preset cost condition, the recommended bandwidth can be recommended to the user, so that the user can purchase the CDN service according to the determined recommended bandwidth when purchasing the CDN service from the CDN operator, and cost saving is realized.

In addition, after determining the recommended bandwidth meeting the preset cost condition, the recommended flow value can be determined according to the flow value in the predicted target time range, and the recommended flow value is recommended to the user, so that the user can purchase the bandwidth and the flow at the same time when buying, and the specific implementation mode is as follows:

determining a recommended flow value according to the recommended bandwidth and the flow value in the target time range;

And recommending the recommended flow value to the user.

In sum, through confirming bandwidth and flow that the user needs in target time range to recommend to the user, make the user can purchase according to recommended bandwidth and flow, can also maximize to satisfy the flow demand when saving the cost, when guaranteeing that the visitor number of user reaches the peak bandwidth, visit user's experience.

In practical applications, after recommending the recommended bandwidth to the user, the recommended bandwidth may also be provided to the CDN operator, and when the user accesses the CDN generated traffic, charging is performed according to the combined charging manner. Referring to fig. 5, fig. 5 shows a schematic flow chart of combined charging in a resource recommendation method according to an embodiment of the present disclosure, and specific steps are as follows.

Step 502: the determined recommended bandwidth is provided to the CDN operator.

Step 504: when a user accesses the CDN, determining the traffic consumed by the user to access the CDN.

Step 506: the CDN operator charges the user for accessing the CDN according to the combined charging rule.

Specifically, in the bandwidth part, the bandwidth is charged according to the price of the recommended bandwidth. When the real-time flow is above the recommended bandwidth, the current flow value needs to subtract the recommended bandwidth according to the current used bandwidth value, and the flow charging is carried out according to the obtained result.

In summary, according to the method, the flow of the user in the target time range is predicted according to the historical flow value of the user, and the recommended bandwidth with the lowest cost can be calculated according to the predicted flow value in the target time range under the condition of calculating the cost in a flow and bandwidth combined charging mode, so that the recommended bandwidth can be recommended to the user, the user can purchase according to the recommended bandwidth to the CDN operator, the cost of the user is minimized, and therefore the waste of resources is reduced, and the cost is also reduced.

The following describes, with reference to fig. 6, an example of application of the resource recommendation method provided in the present disclosure to CDN charging, which further describes the resource recommendation method. Fig. 6 is a flowchart of a processing procedure of a resource recommendation method according to an embodiment of the present disclosure, which specifically includes the following steps.

Step 602: and predicting the trend value and the variation value of the user in the target time range by using a time sequence prediction algorithm according to the historical flow value of the user.

Specifically, when the resource recommendation method is applied to CDN charging of a live platform, a development trend of the live platform in a target time range, an access behavior of a consumer, and the like can be predicted according to a flow value corresponding to each time point of the live platform in a historical time period.

Step 604: and predicting the flow value in the target time range according to the trend value and the variation value.

Specifically, the flow value possibly consumed by the live broadcast platform at each time point in the target time range can be predicted according to the predicted development trend of the live broadcast platform in the target time range, the access behaviors of consumers and the like.

Step 606: and constructing an objective function by taking a time point in the objective time range as an abscissa and a flow value corresponding to the time point in the objective time range as an ordinate.

Step 608: and determining an initial time point in the target time range and a flow value corresponding to the initial time point according to the target function, and taking the flow value as an initial recommended bandwidth.

Specifically, one of the time points in the target time range may be used as an initial time point according to the objective function, a flow value corresponding to the initial time point may be determined according to the objective function, and the flow value may be used as an initial recommended bandwidth.

Step 610: and calculating initial bandwidth cost and initial flow cost corresponding to the flow value in the target time range under the condition that the user uses the initial recommended bandwidth according to the initial time point and the initial recommended bandwidth corresponding to the initial time point.

Specifically, according to the initial recommended bandwidth and the price corresponding to the initial recommended bandwidth, calculating an initial bandwidth cost corresponding to a flow value in the target time range under the condition that the user uses the initial recommended bandwidth; and determining a target time point exceeding a flow value corresponding to the initial time point in the target time range according to the initial time point, and calculating initial flow cost corresponding to the flow value of the target time point under the condition that the user uses the initial recommended bandwidth.

Step 612: and calculating initial cost according to the initial bandwidth cost and the initial traffic cost.

Specifically, the initial bandwidth cost and the initial traffic cost may be added to obtain the initial cost.

Step 614: and judging whether the initial cost reaches a preset cost range or not. If yes, go to step 616; if not, go to step 618.

The preset cost range may be understood as a range of a sum of cost of preset traffic cost and bandwidth cost, and if the cost is within the preset cost range, the recommended bandwidth corresponding to the cost may be directly recommended to the user.

Step 616: and determining the initial recommended bandwidth as a recommended bandwidth recommended to the user.

Step 618: and determining an updated recommended bandwidth corresponding to the current iteration process according to the initial recommended bandwidth.

Specifically, an update time point in the target time range may be determined according to a time point corresponding to the peak bandwidth and an initial time point corresponding to the initial recommended bandwidth, and a flow value corresponding to the update time point is used as the update recommended bandwidth.

Step 620: in the current iteration process, calculating the updating cost corresponding to the flow value in the target time range under the condition that the user uses the updated recommended bandwidth and adopts a flow and bandwidth combined charging mode to perform cost calculation.

Step 622: a target cost having a minimum cost value is determined from the initial cost and the update cost calculated during each iteration.

Step 624: it is determined whether the target cost converges to a minimum, if so, step 626 is executed, and if not, step 628 is executed.

Step 626: and determining the recommended bandwidth corresponding to the target cost as the recommended bandwidth recommended to the user.

Specifically, the recommended bandwidth can meet a preset cost condition, that is, the sum of the flow cost and the bandwidth cost corresponding to the recommended bandwidth is the lowest.

Step 628: and re-determining the updated recommended bandwidth according to the recommended bandwidth corresponding to the target cost, and continuing to execute step 620.

Step 630: and determining a recommended flow value according to the recommended bandwidth and the flow value in the target time range.

Step 632: and recommending the recommended bandwidth and the recommended flow value to the user.

Corresponding to the method embodiment, the present disclosure further provides an embodiment of a resource recommendation device, and fig. 7 shows a schematic structural diagram of a resource recommendation device provided in one embodiment of the present disclosure. As shown in fig. 7, the apparatus includes:

a prediction module 702 configured to predict a flow value within a target time range based on a historical flow value of a user;

A determining module 704, configured to determine, according to the flow value in the target time range, a recommended bandwidth that meets a preset cost condition in the case of performing cost calculation in a combined charging manner of flow and bandwidth;

a recommendation module 706 configured to recommend the recommended bandwidth to the user.

In an alternative embodiment, the determining module 704 is further configured to:

judging whether the initial cost reaches a preset cost range or not;

judging whether the target cost converges to the minimum;

if not, determining an updated recommended bandwidth corresponding to the next iteration process according to the recommended bandwidth corresponding to the target cost, entering the next iteration process, and returning to the step of executing the updated cost corresponding to the flow value in the target time range under the condition that the user uses the updated recommended bandwidth and adopts a flow and bandwidth combined charging mode to perform cost calculation in the current iteration process.

In an optional embodiment, the flow value in the target time range includes a flow value corresponding to a time point in the target time range; the apparatus further includes a build module configured to:

In an alternative embodiment, the prediction module 702 is further configured to:

and recommending the recommended flow value to the user.

In summary, the device predicts the flow of the user in the target time range according to the historical flow value of the user, and can calculate the recommended bandwidth with the lowest cost according to the flow value in the predicted target time range under the condition of calculating the cost in a flow and bandwidth combined charging mode, so that the recommended bandwidth can be recommended to the user, the user can buy according to the recommended bandwidth to the CDN operator, the cost of the user is minimized, and therefore the waste of resources is reduced, and the cost is also reduced.

The foregoing is a schematic scheme of a resource recommendation device in this embodiment. It should be noted that, the technical solution of the resource recommendation device and the technical solution of the resource recommendation method belong to the same concept, and details of the technical solution of the resource recommendation device, which are not described in detail, can be referred to the description of the technical solution of the resource recommendation method.

Fig. 8 illustrates a block diagram of a computing device 800 provided in accordance with one embodiment of the present description. The components of computing device 800 include, but are not limited to, memory 810 and processor 820. Processor 820 is coupled to memory 810 through bus 830 and database 850 is used to hold data.

Computing device 800 also includes access device 840, access device 840 enabling computing device 800 to communicate via one or more networks 860. Examples of such networks include public switched telephone networks (PSTN, public Switched Telephone Network), local area networks (LAN, local Area Network), wide area networks (WAN, wide Area Network), personal area networks (PAN, personal Area Network), or combinations of communication networks such as the internet. Access device 840 may include one or more of any type of network interface, wired or wireless, such as a network interface card (NIC, network interface controller), such as an IEEE802.11 wireless local area network (WLAN, wireless Local Area Network) wireless interface, a worldwide interoperability for microwave access (Wi-MAX, worldwide Interoperability for Microwave Access) interface, an ethernet interface, a universal serial bus (USB, universal Serial Bus) interface, a cellular network interface, a bluetooth interface, a near field communication (NFC, near Field Communication) interface, and so forth.

In one embodiment of the present application, the above-described components of computing device 800, as well as other components not shown in FIG. 8, may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device illustrated in FIG. 8 is for exemplary purposes only and is not intended to limit the scope of the present application. Those skilled in the art may add or replace other components as desired.

Computing device 800 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), mobile phone (e.g., smart phone), wearable computing device (e.g., smart watch, smart glasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or personal computer (PC, personal Computer). Computing device 800 may also be a mobile or stationary server.

Wherein the processor 820 is configured to execute computer-executable instructions that, when executed by the processor, perform the steps of the resource recommendation method described above.

The foregoing is a schematic illustration of a computing device of this embodiment. It should be noted that, the technical solution of the computing device and the technical solution of the resource recommendation method belong to the same concept, and details of the technical solution of the computing device, which are not described in detail, can be referred to the description of the technical solution of the resource recommendation method.

An embodiment of the present disclosure also provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the resource recommendation method described above.

The above is an exemplary version of a computer-readable storage medium of the present embodiment. It should be noted that, the technical solution of the storage medium and the technical solution of the resource recommendation method belong to the same concept, and details of the technical solution of the storage medium, which are not described in detail, can be referred to the description of the technical solution of the resource recommendation method.

An embodiment of the present disclosure further provides a computer program, where the computer program, when executed in a computer, causes the computer to perform the steps of the resource recommendation method described above.

The above is an exemplary version of a computer program of the present embodiment. It should be noted that, the technical solution of the computer program and the technical solution of the resource recommendation method belong to the same concept, and details of the technical solution of the computer program, which are not described in detail, can be referred to the description of the technical solution of the resource recommendation method.

The foregoing describes specific embodiments of the present disclosure. 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.

The computer instructions include computer program code that may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of combinations of actions, but it should be understood by those skilled in the art that the embodiments are not limited by the order of actions described, as some steps may be performed in other order or simultaneously according to the embodiments of the present disclosure. Further, those skilled in the art will appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily all required for the embodiments described in the specification.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.

The preferred embodiments of the present specification disclosed above are merely used to help clarify the present specification. Alternative embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the teaching of the embodiments. The embodiments were chosen and described in order to best explain the principles of the embodiments and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. This specification is to be limited only by the claims and the full scope and equivalents thereof.

Claims

1. A resource recommendation method, comprising:

predicting a flow value in a target time range according to a historical flow value of a user;

determining a recommended bandwidth meeting a preset cost condition under the condition of carrying out cost calculation in a flow and bandwidth combined charging mode according to the flow value in the target time range;

and recommending the recommended bandwidth to the user.

2. The method according to claim 1, wherein determining, according to the flow value in the target time range, the recommended bandwidth satisfying the preset cost condition in the case of cost calculation in a combined charging manner of flow and bandwidth, comprises:

3. The method according to claim 2, wherein determining, according to the flow value in the target time range, the recommended bandwidth satisfying the preset cost condition in the case of cost calculation in a combined charging manner of flow and bandwidth, further comprises:

judging whether the target cost converges to the minimum;

4. The method of claim 2, wherein the flow value within the target time range includes a flow value corresponding to a point in time within the target time range;

the calculating, when the user uses the initial recommended bandwidth and adopts the flow and bandwidth combined charging mode to perform cost calculation, further includes, before the initial cost corresponding to the flow value in the target time range:

5. The method according to claim 2, wherein the calculating the initial cost corresponding to the flow value in the target time range in the case that the user uses the initial recommended bandwidth and uses the flow and bandwidth combined charging method to perform the cost calculation includes:

6. The method according to claim 5, wherein the calculating, according to the initial time point and the initial recommended bandwidth corresponding to the initial time point, an initial bandwidth cost and an initial traffic cost corresponding to traffic values in the target time range in the case that the user uses the initial recommended bandwidth includes:

7. A method according to claim 3, wherein the determining, according to the initial recommended bandwidth, an updated recommended bandwidth corresponding to the current iterative process includes:

8. The method according to claim 7, wherein the calculating the update cost corresponding to the flow value in the target time range in the case that the user uses the update recommended bandwidth and uses the flow and bandwidth combined charging method to perform the cost calculation includes:

Determining a target time point which exceeds a flow value corresponding to the update time point in the target time range according to the update time point, and calculating update flow cost corresponding to the flow value of the target time point under the condition that a user uses the update recommended bandwidth;

9. The method of claim 1, the predicting flow values within a target time range based on historical flow values of a user, comprising:

10. The method of claim 1, further comprising, after determining the recommended bandwidth that meets the preset cost condition:

and recommending the recommended flow value to the user.

11. The method of claim 1, the preset cost condition comprising a condition for traffic cost and bandwidth cost.

12. A computing device, comprising:

a memory and a processor;

the memory is configured to store computer executable instructions, the processor being configured to execute the computer executable instructions, which when executed by the processor, implement the steps of the method of any one of claims 1 to 11.

13. A computer readable storage medium storing computer executable instructions which when executed by a processor implement the steps of the method of any one of claims 1 to 11.

14. A computer program, wherein the computer program, when executed in a computer, causes the computer to perform the steps of the method of any of claims 1 to 11.