Method, device and storage medium for predicting traffic of business system
By combining the correlation between order volume and traffic through a nonlinear time series forecasting model, the problem of inaccurate traffic forecasting in the insurance business system was solved, achieving accurate forecasting of order volume and total traffic, and supporting the stability management of the system.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- PEOPLE'S INSURANCE COMPANY OF CHINA
- Filing Date
- 2023-12-28
- Publication Date
- 2026-06-12
Smart Images
Figure CN117829887B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of insurance technology, and in particular to a method, apparatus, device, and storage medium for predicting business system traffic. Background Technology
[0002] With the online development of the insurance business, more and more insurance products are being sold directly online. For example, on the one hand, insurance companies can gradually convert offline customers into online customers through telemarketing, live streaming, and other activities; on the other hand, they can increase the number of policies sold (also known as the number of policies issued) by conducting promotional activities such as 618, Double 11, and Double 12. With the transformation of insurance sales methods and the internetization of the insurance business, the traffic of insurance business systems is fluctuating more and more significantly at different times.
[0003] In this context, predicting the traffic of the insurance business system becomes crucial: if the traffic of the insurance business system can be accurately predicted during a certain period, measures can be taken in advance to prevent the stability of the insurance business system from being reduced due to excessive traffic when the traffic is too high, or maintenance work can be carried out on the insurance business system during periods of low traffic, and so on.
[0004] Traditional traffic prediction methods for insurance business systems mainly consider that the number of policies issued and the traffic of insurance business systems often follow certain linear patterns. Based on the number of policies issued by the insurance business system in a historical period, linear models such as linear regression or mean-variance can be used to predict the traffic of the insurance business system in a future period.
[0005] However, current online marketing models in the insurance industry are causing increasing variance in the distribution of sales volume across different time periods. This means that sales volume often varies significantly across different time periods – for example, promotional activities targeting insurance products can lead to sudden increases or decreases in sales volume during those periods. In such cases, using linear models such as linear regression or mean-variance to fit the aforementioned linear relationships makes it difficult to accurately predict the traffic of the insurance business system in future time periods. Summary of the Invention
[0006] This application provides a method, apparatus, device, and storage medium for predicting traffic in a business system, addressing the problem in the prior art of accurately predicting traffic in an insurance business system.
[0007] This application embodiment also provides a method for predicting business system traffic, including: determining an activity tag corresponding to a specified time period to be predicted; predicting the total order volume of a target business system in the specified time period based on an order volume prediction model for predicting order volume in a time period with an activity tag, the specified prediction date, and the activity tag; the order volume prediction model is a nonlinear time series prediction model trained based on the order volume of the target business system in multiple time periods in a historical time period, and the activity tags corresponding to the multiple time periods; and predicting the total traffic generated by the target business system in the specified time period based on the correlation between traffic and order volume of the target business system in the same time period.
[0008] This application embodiment also provides a business system traffic prediction device, including: a tag determination module, used to determine the activity tag corresponding to a specified time period to be predicted; an order volume prediction module, used to predict the total order volume of the target business system in the specified time period based on an order volume prediction model for predicting the order volume of a time period with an activity tag, the specified prediction date, and the activity tag; the order volume prediction model is a nonlinear sequence prediction model trained based on the order volume of the target business system in multiple time periods in a historical time period and the activity tags corresponding to the multiple time periods; and a traffic prediction module, used to predict the total traffic generated by the target business system in the specified time period based on the correlation between the traffic and order volume of the target business system in the same time period.
[0009] This application embodiment also provides an electronic device, including: a memory and a processor; the memory is used to store a computer program; the processor, coupled to the memory, is used to execute the computer program to: determine an activity tag corresponding to a specified time period to be predicted; predict the total order volume of a target business system in the specified time period based on an order volume prediction model for predicting order volume in a time period with an activity tag, and the specified prediction date and the activity tag; the order volume prediction model is a nonlinear time series prediction model trained based on the order volume of the target business system in multiple time periods in a historical time period, and the activity tags corresponding to the multiple time periods; and predict the total traffic generated by the target business system to obtain the total order volume in the specified time period based on the correlation between traffic and order volume of the target business system in the same time period.
[0010] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to implement the steps of the business system traffic prediction method provided in this application.
[0011] One or more embodiments provided in this application can first determine the activity tag corresponding to a specified time period to be predicted, then predict the total order volume of the target business system in the specified time period based on the order volume prediction model for predicting the order volume of the time period with the activity tag, as well as the specified time period and the activity tag, and finally predict the total traffic generated by the target business system to obtain the total order volume in the specified time period based on the correlation between the traffic and the order volume of the target business system in the same time period. Since the order volume prediction model is a nonlinear time series prediction model trained based on the order volume of the target business system in multiple time periods in a historical time period and the activity tags corresponding to the multiple time periods, the model fully utilizes the changing trend of the order volume of the target business system in different time periods with the activity tag characteristics during the training phase, and can achieve accurate prediction of the order volume of the target business system in the specified time period. By utilizing the correlation between the order volume and the traffic of the target business system in the same time period, the purpose of obtaining the total traffic generated by the total order volume of the target business system in the specified time period can be accurately achieved. Attached Figure Description
[0012] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:
[0013] Figure 1 A schematic diagram illustrating the implementation process of a business system traffic prediction method provided for an exemplary embodiment of this application;
[0014] Figure 2 A schematic diagram of the order volume prediction process in the business system traffic prediction method provided for an exemplary embodiment of this application;
[0015] Figure 3 A schematic diagram of the structure of a business system traffic prediction device provided for an exemplary embodiment of this application;
[0016] Figure 4 This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of this application. Detailed Implementation
[0017] Many specific details are set forth in the following description to provide a full understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this application; therefore, this application is not limited to the specific embodiments disclosed below.
[0018] The terminology used in one or more embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the scope of one or more embodiments of this application. The singular forms “a,” “the,” and “the” used in one or more embodiments of this application and in the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” used in one or more embodiments of this application refers to and includes any or all possible combinations of one or more associated listed items.
[0019] It should be understood that although the terms first, second, etc., may be used to describe various information in one or more embodiments of this application, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first may also be referred to as second without departing from the scope of one or more embodiments of this application, and similarly, second may also be referred to as first. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."
[0020] To address the aforementioned problems in the existing technology, this application provides a method for predicting traffic in a business system. This method first determines the activity tag corresponding to a specified time period to be predicted. Then, based on an order volume prediction model used to predict order volume during time periods with activity tags, and the specified time period and activity tags, it predicts the total order volume of the target business system during the specified time period. Finally, based on the correlation between traffic and order volume of the target business system within the same time period, it predicts the total traffic generated by the target business system to obtain the total order volume during the specified time period. Since this order volume prediction model is a nonlinear time series prediction model trained based on the order volume of the target business system in multiple time periods throughout a historical period, and the corresponding activity tags for those multiple time periods, the model fully utilizes the changing trend of the target business system's order volume in different time periods with activity tag characteristics during the training phase. This enables accurate prediction of the target business system's order volume during the specified time period. By utilizing the correlation between the order volume and traffic of the target business system within the same time period, the method can accurately achieve the goal of obtaining the total traffic generated by the target business system to obtain the total order volume during the specified time period. Specifically, this application provides a method for predicting business system traffic. This application also relates to a business system traffic prediction device, electronic device, and computer-readable storage medium, which will be described in detail in the following embodiments.
[0021] Figure 1 This is a flowchart illustrating a method for predicting traffic in a business system, provided as an exemplary embodiment of this application. Figure 1 As shown, the method includes:
[0022] Step 110: Determine the activity label corresponding to the specified time period to be predicted.
[0023] The specified time period to be predicted can be a day, several days, or a month within a future time period. The activity tag corresponding to the specified time period to be predicted is used to indicate whether a marketing activity will be launched during the specified time period. The value of the activity tag can be represented by 0 and 1. When the value of the activity tag is 1, it indicates that a marketing activity will be launched during the specified time period, such as Double Eleven or Double Twelve. When the value of the activity tag is 0, it indicates that no marketing activity will be launched during the specified time period.
[0024] Step 120: Based on the order volume prediction model used to predict the order volume of time periods with activity tags, and the specified time period and activity tags, predict the total order volume of the target business system in the specified time period.
[0025] The order volume prediction model is a non-linear time series prediction model trained based on the order volume of the target business system in multiple time periods throughout history, as well as the activity tags corresponding to those time periods. The target business system can be an insurance business system.
[0026] Optionally, the training process of the order volume prediction model may include: obtaining training samples, wherein the training samples contain order volume information of the target business system in multiple historical time periods, and labeling information of activity tags based on the order volume information of the target business system in multiple historical time periods, and labeling information of activity tags based on the order volume information of the target business system in multiple historical time periods, to train a preset nonlinear time series prediction model and obtain the order volume prediction model.
[0027] As an example, the pre-defined nonlinear time series forecasting model could be a Prophet model based on an additive model, which decomposes a time series into a structure composed of four main components. These four main components may include: Trend: describing the long-term trend of the time series; Seasonal: reflecting the periodic pattern of the time series; Holiday Effect: indicating the impact of a specific date or time period on the time series; and Noise: containing unpredictable random variations.
[0028] Furthermore, the Prophet model can select different model forms based on the characteristics of the data, including additive and multiplicative models. These two models represent different mathematical expressions, but both can be used to capture different features of time series. Specifically, the additive model predicts the sum of trend, seasonality, and holiday effects. The multiplicative model predicts the product of trend, seasonality, and holiday effects.
[0029] like Figure 2 The diagram shown illustrates the application of the order volume prediction method provided in this embodiment of the application in a real-world scenario. This embodiment of the application, based on the Prophet model's ability to predict data trends caused by a combination of seasonality, holidays, and other factors, and recognizing that the order volume of an insurance business system is easily affected by seasonality, marketing activities, and other characteristics, uses the Prophet model to accurately predict the order volume of the insurance business system. Specifically, Figure 2 The implementation process may include: First, obtaining order volume data for the target business system across multiple historical time periods from its order volume database. This could be a time series of dates and order volumes: [D1, P1], [D2, P2], [D3, P3], ..., where D1, D2, ... are dates, P1 is the order volume of the target business system on date D1, P2 is the order volume of the target business system on date D2, and so on. Then, obtaining the activity tags for these multiple historical time periods, such as the dates on which marketing activities were launched [D1, D2, ...]. 3……]; Then, based on the order volume data of the target business system in multiple historical periods and the activity tags of these multiple historical periods, a preset nonlinear time series prediction model (e.g., a nonlinear Prophet time series model) is trained to obtain the order volume prediction model; Finally, the specified period to be predicted (e.g., the date of the future launch of the marketing campaign [Dx]) is input into the order volume prediction model to output the predicted order volume of the target business system in the specified period, thus obtaining the order volume of the target business system on the date of the future launch of the marketing campaign [Dx].
[0030] Step 130: Based on the correlation between traffic and order volume of the target business system in the same time period, predict the total traffic generated by the target business system in the specified time period when it obtains the total order volume.
[0031] Optionally, since there is usually a positive correlation between order volume and traffic in the target business system, the total traffic generated by the target business system to acquire total order volume within a specified time period can be determined based on this correlation and the predicted total order volume. Specifically, based on the correlation between traffic and order volume of the target business system in the same time period, the total traffic generated by the target business system to acquire total order volume within a specified time period is predicted, including:
[0032] Obtain the peak daily traffic and peak daily order volume of the target business system within a historical time period;
[0033] Based on the ratio of the peak daily traffic to the peak daily order volume of the target business system within a historical time period, the correlation between the traffic and order volume generated by the target business system in the same time period is determined.
[0034] Based on the correlation between traffic and order volume generated by the target business system in the same period, predict the total traffic generated by the target business system when it obtains the total order volume in a specified period.
[0035] As an example, the peak daily traffic of the target business system in a historical time period can be obtained as N0, and the peak daily order volume of the target business system in a historical time period can be obtained as P0. The total order volume predicted in step 120 is P1. Then, the total traffic N1 generated by the target business system in the specified time period is N1 = P1 * N0 / P0.
[0036] Optionally, the correlation between order volume and traffic in the target business system can also be obtained through linear fitting. Specifically, determining the correlation between traffic and order volume generated by the target business system in the same time period includes:
[0037] The peak daily traffic and peak daily order volume of the target business system are obtained in multiple historical time periods. The order volume of the target business system is used as the independent variable, and the traffic generated by the target business system in the same time period is used as the dependent variable. A straight line is fitted to characterize the linear relationship between the traffic generated by the target business system in the same time period and the order volume.
[0038] The correlation between traffic and order volume generated by the target business system in the same period is determined based on the slope of the straight line used to characterize the linear relationship between traffic and order volume generated in the same period.
[0039] Optionally, the target business system is the core business system of a specified business. The specified business includes multiple customer business systems. The core business system can aggregate the order volume of multiple business systems in the service architecture of the specified business within the same time period to obtain the total order volume for the same time period. The method further includes:
[0040] Determine the traffic correlation between the core business system and the target customer business system, where the target customer business system can be any one of multiple customer business systems;
[0041] Based on the traffic correlation between the core business system and the target customer's business system, as well as the total traffic, predict the traffic of the target customer's business system during a specified period.
[0042] The traffic of the target customer's business system during a specified period can be the total traffic of the front-end and back-end interactions with the target customer's business system, or it can be the total traffic of the front-end user interactions with the target customer's business system.
[0043] The target business system can be an insurance business system, which is typically designed with a distributed architecture and functionally divided into a core business system, a public business system, a policy issuance system, and a sales business system. The core business system aggregates policy issuance volumes from different types of insurance products and different sales channels, storing all policy issuance information. The public business system provides unified services to all business systems, while the policy issuance and sales business systems are further divided into different systems based on insurance product characteristics and sales channels. Insurance policy issuance volume directly corresponds to the traffic of the core business system, while the public business system, policy issuance system, and sales system have different correlations with the core business system. Based on this, the embodiments of this application first determine the traffic correlation between different types of customer business systems and the core business system, and then, based on this traffic correlation, predict the traffic of different types of customer business systems. The public business system, the policy issuance system for different insurance products, and the sales system for different insurance products can all be referred to as customer business systems.
[0044] Optionally, determine the traffic correlation between the core business system and the target customer's business system, including:
[0045] Obtain the average daily traffic and peak daily traffic of the core business system within a preset historical time period, as well as the average daily traffic and peak daily traffic of the target customer's business system within a preset historical time period;
[0046] Based on the average daily traffic and peak daily traffic of the core business system within a preset historical time period, and the average daily traffic and peak daily traffic of the target customer's business system within the preset historical time period, the traffic correlation between the core business system and the target customer's business system is determined.
[0047] Optionally, different types of customer business systems, due to their different functions, may have different correlations with the traffic generated by the order volume aggregated by the core business system, such as strong correlation, weak correlation, or no correlation. Based on this, this application embodiment can introduce the Pearson correlation coefficient to measure the correlation between the traffic generated by different customer business systems and the traffic generated by the core business system. Specifically, determining the traffic correlation between the core business system and the target customer business system includes:
[0048] Based on the quotient of the covariance and standard deviation between the average daily traffic of the core business system and the average daily traffic of the target customer business system within a preset historical period, the Pearson correlation coefficient between the traffic of the core business system and the target customer business system is determined.
[0049] Based on the ratio between the peak daily traffic of the core business system and the peak daily traffic of the target customer's business system within a preset historical time period, the peak traffic correlation coefficient between the core business system and the target customer's business system is determined.
[0050] Based on the Pearson correlation coefficient and peak traffic correlation coefficient, the traffic correlation between the core business system and the target customer's business system is determined.
[0051] The Pearson correlation coefficient between the traffic of the core business system and the target customer's business system can be the quotient of the covariance and standard deviation of the traffic of these two variables. Assuming the average daily traffic of the target customer's business system A over a preset historical period is X, and the average daily traffic of the core business system over the same period is Y, the formula for calculating the Pearson correlation coefficient is: The Pearson correlation coefficient, ranging from 0 to 1, reflects the correlation between two variables: the average daily traffic (X) of the target customer's business system A within a preset historical time period, and the average daily traffic (Y) of the core business system within the same historical time period. A Pearson correlation coefficient close to 1 indicates a perfectly positive linear relationship between the two variables; conversely, a coefficient close to 0 indicates no linear relationship between them.
[0052] As an example, the traffic correlation between the core business system and the target customer business system can be determined based on the Pearson correlation coefficient and the peak traffic correlation coefficient. Specifically, the product of the Pearson correlation coefficient and the peak traffic correlation coefficient can be used as a representation of the traffic correlation between the core business system and the target customer business system.
[0053] Optionally, embodiments of this application, based on the Pearson correlation coefficient being close to 1, indicating a perfectly positive linear relationship between the two variables, can predict the system traffic of the target customer's business system during a specified time period when the Pearson correlation coefficient between the traffic of the core business system and the target customer's business system is close to 1. Specifically, based on the traffic correlation between the core business system and the target customer's business system, and the total traffic, predicting the traffic of the target customer's business system during a specified time period includes:
[0054] When the Pearson correlation coefficient is greater than or equal to a preset threshold, the system traffic of the target customer business system during the specified period is predicted based on the traffic correlation between the core business system and the target customer business system in the target business, as well as the traffic generated by the core business system during the specified period.
[0055] The preset threshold is used to characterize the critical value at which the traffic of the target customer's business system is correlated with the traffic of the core system.
[0056] As an example, when the Pearson correlation coefficient is close to 1, it indicates that the increase or decrease in traffic to the target customer's business system is related to the increase in traffic to the core business system. In this case, the traffic to the target customer's business system can be predicted to allow for timely operational planning. Assume the historical peak traffic of the target customer's business system A is M0, the historical peak traffic of the core business system is N0, and the historical peak order volume is P0; the predicted order volume from the previous steps is P1, and the Pearson correlation coefficient between the traffic of the target customer's business system A and the core business system is W1. Then, the predicted traffic of the target customer's business system A within a specified time period can be: M1 = W1 * M0 * N1 / N0. Where N1 = P1 * N0 / P0, and W1 * M0 / N0 represents the traffic correlation between the core business system and the target customer's business system A.
[0057] If the Pearson correlation coefficient is close to 0, it indicates that the increase or decrease in traffic to the target customer's business system is unrelated to the increase in traffic to the core business system caused by marketing activities, and therefore no prediction is necessary.
[0058] The business system traffic prediction method provided in one or more embodiments of this application first determines the activity tag corresponding to a specified time period to be predicted. Then, based on the order volume prediction model for predicting the order volume of the time period with the activity tag, and the specified time period and activity tag, it predicts the total order volume of the target business system in the specified time period. Finally, based on the correlation between the traffic and order volume of the target business system in the same time period, it predicts the total traffic generated by the target business system to obtain the total order volume in the specified time period. Since the order volume prediction model is a nonlinear time series prediction model trained based on the order volume of the target business system in multiple time periods in a historical time period and the activity tags corresponding to the multiple time periods, the model fully utilizes the changing trend of the order volume of the target business system in different time periods with activity tag characteristics during the training phase. It can achieve accurate prediction of the order volume of the target business system in the specified time period. By utilizing the correlation between the order volume and traffic of the target business system in the same time period, the purpose of obtaining the total traffic generated by the total order volume of the target business system in the specified time period can be accurately achieved.
[0059] It should be noted that the execution subject of each step of the method provided in the above embodiments can be the same device, or the method can be executed by different devices. For example, the execution subject of steps 110 to 130 can be device A; or the execution subject of steps 110 to 120 can be device A, and the execution subject of step 130 can be device B; and so on.
[0060] Furthermore, some processes described in the above embodiments and accompanying drawings include multiple operations that appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or they may be executed in parallel. The operation numbers, such as 110, 120, etc., are merely used to distinguish different operations and do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel.
[0061] Figure 3 This is a schematic diagram of the structure of a business system traffic prediction device 300 provided for an exemplary embodiment of this application. Figure 3 As shown, the device 300 includes: a tag determination module 310, a single quantity prediction module 320, and a flow prediction module 330, wherein:
[0062] The label determination module 310 is used to determine the activity labels corresponding to the specified time period to be predicted;
[0063] The order volume prediction module 320 is used to predict the total order volume of the target business system in the specified period based on the order volume prediction model for predicting the order volume of the period with activity tags, the specified prediction date and the activity tags; the order volume prediction model is a nonlinear sequence prediction model trained based on the order volume of the target business system in multiple periods in the historical time period and the activity tags corresponding to the multiple periods.
[0064] The traffic prediction module 330 is used to predict the total traffic generated by the target business system when it obtains the total number of orders in the specified time period, based on the correlation between the traffic and the number of orders generated by the target business system in the same time period.
[0065] Optionally, the target business system is the core business system of a specified business, and the specified business includes multiple customer business systems. The core business system is capable of aggregating the order volume of the multiple business systems in the service architecture of the specified business within the same time period to obtain the total order volume within the same time period. The device further includes:
[0066] The association determination module is used to determine the traffic association degree between the core business system and the target customer business system, wherein the target customer business system is any one of the multiple customer business systems;
[0067] The first prediction module is used to predict the traffic of the target customer business system during the specified time period based on the traffic correlation between the core business system and the target customer business system, as well as the total traffic.
[0068] Optionally, the association determination module is used to:
[0069] Obtain the average daily traffic and peak daily traffic of the core business system within a preset historical time period, and the average daily traffic and peak daily traffic of the target customer business system within the preset historical time period;
[0070] Based on the average daily traffic and peak daily traffic of the core business system within a preset historical time period, and the average daily traffic and peak daily traffic of the target customer business system within the preset historical time period, the traffic correlation between the core business system and the target customer business system is determined.
[0071] Optionally, the association determination module is used to:
[0072] Based on the quotient of the covariance and standard deviation between the average daily traffic of the core business system and the average daily traffic of the target customer business system within the preset historical time period, the Pearson correlation coefficient between the traffic of the core business system and the target customer business system is determined.
[0073] Based on the ratio between the daily peak traffic of the core business system and the daily peak traffic of the target customer business system within the preset historical time period, the peak traffic correlation coefficient between the core business system and the target customer business system is determined.
[0074] Based on the Pearson correlation coefficient and the peak traffic correlation coefficient, the traffic correlation between the core business system and the target customer business system is determined.
[0075] Optionally, the first prediction module is configured to:
[0076] If the Pearson correlation coefficient is greater than or equal to a preset threshold, the system traffic of the target customer business system during the specified time period is predicted based on the traffic correlation between the core business system and the target customer business system in the target business, and the traffic generated by the core business system during the specified time period.
[0077] The preset threshold is used to characterize the critical value at which the traffic of the target customer's business system is correlated with the traffic of the core system.
[0078] Optionally, when the traffic prediction module predicts the total traffic generated by the target business system when it obtains the total number of orders in the specified time period based on the correlation between the traffic and order volume of the target business system in the same time period, it is specifically used for:
[0079] Obtain the peak daily traffic and peak daily order volume of the target business system within a historical time period;
[0080] Based on the ratio of the peak daily traffic to the peak daily order volume of the target business system within a historical time period, the correlation between the traffic and order volume generated by the target business system in the same time period is determined.
[0081] Based on the correlation between the traffic and order volume generated by the target business system in the same period, the total traffic generated by the target business system in the specified period when it obtains the total order volume is predicted.
[0082] Optionally, when determining the correlation between the traffic and order volume generated by the target business system in the same time period, the traffic prediction module is specifically used for:
[0083] The peak daily traffic and peak daily order volume of the target business system are obtained in multiple historical time periods. The order volume of the target business system is used as the independent variable, and the traffic generated by the target business system in the same time period is used as the dependent variable. A straight line is fitted to characterize the linear relationship between the traffic generated by the target business system in the same time period and the order volume.
[0084] The correlation between the traffic and order volume generated by the target business system in the same period is determined based on the slope of the straight line characterizing the linear relationship between the traffic and order volume generated in the same period.
[0085] The business system traffic prediction apparatus provided in one or more embodiments of this application can first determine the activity tag corresponding to a specified time period to be predicted, then predict the total order volume of the target business system in the specified time period based on the order volume prediction model for predicting the order volume of the time period with the activity tag, as well as the specified time period and the activity tag, and finally predict the total traffic generated by the target business system to obtain the total order volume in the specified time period based on the correlation between the traffic and the order volume of the target business system in the same time period. Since the order volume prediction model is a nonlinear time series prediction model trained based on the order volume of the target business system in multiple time periods in a historical time period and the activity tags corresponding to the multiple time periods, the model fully utilizes the changing trend of the order volume of the target business system in different time periods with the activity tag characteristics during the training phase, and can achieve accurate prediction of the order volume of the target business system in the specified time period. By utilizing the correlation between the order volume and the traffic of the target business system in the same time period, the purpose of obtaining the total traffic generated by the total order volume of the target business system in the specified time period can be accurately achieved.
[0086] The business system traffic prediction device 300 can achieve Figures 1-2 For details of the method implementation examples, please refer to [link / reference]. Figures 1-2 The method for predicting business system traffic in the illustrated embodiment will not be described in detail here.
[0087] Figure 4 This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of this application. For example... Figure 4 As shown, the device includes a memory 41 and a processor 42.
[0088] Memory 41 is used to store computer programs and can be configured to store various other data to support operation on the computing device. Examples of this data include instructions for any application or method used to operate on the computing device, contact data, phone book data, messages, pictures, videos, etc.
[0089] Processor 42, coupled to memory 41, is used to execute a computer program in memory 41 for: determining an activity tag corresponding to a specified time period to be predicted; predicting the total order volume of the target business system in the specified time period based on an order volume prediction model for predicting order volume in a time period with an activity tag, and the specified prediction date and the activity tag; the order volume prediction model is a nonlinear time series prediction model trained based on the order volume of the target business system in multiple time periods in a historical time period, and the activity tags corresponding to the multiple time periods; and predicting the total traffic generated by the target business system to obtain the total order volume in the specified time period based on the correlation between traffic and order volume of the target business system in the same time period.
[0090] The electronic device provided in one or more embodiments of this application can first determine the activity tag corresponding to a specified time period to be predicted, then predict the total order volume of the target business system in the specified time period based on the order volume prediction model for predicting the order volume of the time period with the activity tag, as well as the specified time period and the activity tag, and finally predict the total traffic generated by the target business system to obtain the total order volume in the specified time period based on the correlation between the traffic and the order volume of the target business system in the same time period. Since the order volume prediction model is a nonlinear time series prediction model trained based on the order volume of the target business system in multiple time periods in a historical time period and the activity tags corresponding to the multiple time periods, the model fully utilizes the changing trend of the order volume of the target business system in different time periods with the activity tag characteristics during the training phase, and can achieve accurate prediction of the order volume of the target business system in the specified time period. By utilizing the correlation between the order volume and the traffic of the target business system in the same time period, the purpose of obtaining the total traffic generated by the total order volume of the target business system in the specified time period can be accurately achieved.
[0091] Furthermore, such as Figure 4 As shown, the electronic device also includes other components such as a communication component 43, a display 44, a power supply component 45, and an audio component 46. Figure 4 The diagram only shows some components and does not mean that the electronic device includes only these components. Figure 4 The components shown. Additionally, depending on the implementation of the traffic playback device, Figure 4 The components within the dashed box are optional, not mandatory. For example, when an electronic device is implemented as a terminal device such as a smartphone, tablet, or desktop computer, it may include... Figure 4 The components within the dashed box; when the electronic device is implemented as a server-side device such as a conventional server, cloud server, data center, or server array, it may be excluded. Figure 4 The component within the dashed box.
[0092] Accordingly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to implement the steps in the above-described business system traffic prediction method embodiments.
[0093] Accordingly, this application also provides a computer program product, including a computer program / instructions, which, when executed, can implement the steps executable by an electronic device in the above-described processing method embodiment of the design drawing. Optionally, this computer program product, in addition to executing the steps in the above-described business system traffic prediction method embodiment, can also perform other steps.
[0094] The above Figure 4The communication component is configured to facilitate wired or wireless communication between the device containing the communication component and other devices. The device containing the communication component can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, the communication component receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component may further include a Near Field Communication (NFC) module, Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, etc.
[0095] The above Figure 4 The memory in the memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.
[0096] The above Figure 4 The display includes a screen, which may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can sense not only the boundaries of the touch or swipe action, but also the duration and pressure associated with the touch or swipe operation.
[0097] The above Figure 4 The power supply component provides power to the various components of the device in which it resides. The power supply component may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device in which it resides.
[0098] The above Figure 4 The audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC) configured to receive external audio signals when the device containing the audio component is in an operating mode, such as call mode, recording mode, or voice recognition mode. The received audio signals can be further stored in memory or transmitted via a communication component. In some embodiments, the audio component also includes a speaker for outputting audio signals.
[0099] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0100] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.
[0101] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0102] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0103] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0104] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0105] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0106] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0107] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0108] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A method for predicting traffic in a business system, characterized in that, include: Determine the activity tags corresponding to the specified time period to be predicted; Based on the order volume prediction model for predicting order volume during periods with activity tags, and the specified period and the activity tags, the total order volume of the target business system during the specified period is predicted; the order volume prediction model is a nonlinear time series prediction model trained based on the order volume of the target business system in multiple periods in a historical time period, and the activity tags corresponding to the multiple periods. Based on the correlation between the traffic and order volume of the target business system in the same time period, predict the total traffic generated by the target business system when it obtains the total order volume in the specified time period; The target business system is the core business system of a specified business. The specified business includes multiple customer business systems. The core business system can aggregate the order volume of the multiple business systems in the service architecture of the specified business within the same time period to obtain the total order volume for the same time period. The method further includes: determining the traffic correlation between the core business system and the target customer business system, where the target customer business system is any one of the multiple customer business systems; determining the traffic correlation between the core business system and the target customer business system includes: based on the average daily traffic of the core business system within a preset historical time period. The Pearson correlation coefficient between the traffic of the core business system and the target customer business system is determined by taking the volume of traffic and the quotient of the covariance and standard deviation between the daily average traffic of the target customer business system within the preset historical time period. The peak traffic correlation coefficient between the core business system and the target customer business system is determined by the ratio between the daily peak traffic of the core business system and the daily peak traffic of the target customer business system within the preset historical time period. Finally, the traffic correlation degree between the core business system and the target customer business system is determined based on the Pearson correlation coefficient and the peak traffic correlation coefficient. Based on the traffic correlation between the core business system and the target customer business system, and the total traffic, predict the traffic of the target customer business system during the specified time period.
2. The method as described in claim 1, characterized in that, Determining the traffic correlation between the core business system and the target customer's business system includes: Obtain the average daily traffic and peak daily traffic of the core business system within a preset historical time period, and the average daily traffic and peak daily traffic of the target customer business system within the preset historical time period; Based on the average daily traffic and peak daily traffic of the core business system within a preset historical time period, and the average daily traffic and peak daily traffic of the target customer business system within the preset historical time period, the traffic correlation between the core business system and the target customer business system is determined.
3. The method as described in claim 1, characterized in that, The method of predicting the traffic of the target customer's business system during the specified time period based on the traffic correlation between the core business system and the target customer's business system, and the total traffic, includes: If the Pearson correlation coefficient is greater than or equal to a preset threshold, the system traffic of the target customer business system during the specified time period is predicted based on the traffic correlation between the core business system and the target customer business system, and the traffic generated by the core business system during the specified time period. The preset threshold is used to characterize the critical value at which the traffic of the target customer business system is correlated with the traffic of the core business system.
4. The method according to any one of claims 1 to 3, characterized in that, The method of predicting the total traffic generated by the target business system in the specified time period based on the correlation between traffic and order volume in the same time period includes: Obtain the peak daily traffic and peak daily order volume of the target business system within a historical time period; Based on the ratio of the peak daily traffic to the peak daily order volume of the target business system within a historical time period, the correlation between the traffic and order volume generated by the target business system in the same time period is determined. Based on the correlation between the traffic and order volume generated by the target business system in the same period, the total traffic generated by the target business system in the specified period when it obtains the total order volume is predicted.
5. The method according to any one of claims 1 to 3, characterized in that, Determining the correlation between traffic and order volume generated by the target business system within the same time period includes: The peak daily traffic and peak daily order volume of the target business system are obtained in multiple historical time periods. The order volume of the target business system is used as the independent variable, and the traffic generated by the target business system in the same time period is used as the dependent variable. A straight line is fitted to characterize the linear relationship between the traffic generated by the target business system in the same time period and the order volume. The correlation between the traffic and order volume generated by the target business system in the same period is determined based on the slope of the straight line characterizing the linear relationship between the traffic and order volume generated in the same period.
6. A device for predicting traffic in a business system, characterized in that, include: The label determination module is used to determine the activity labels corresponding to the specified time period to be predicted; The order volume prediction module is used to predict the total order volume of the target business system in the specified period based on the order volume prediction model for predicting the order volume of the period with activity tags, the specified period and the activity tags; the order volume prediction model is a nonlinear time series prediction model trained based on the order volume of the target business system in multiple periods in the historical time period and the activity tags corresponding to the multiple periods. The traffic prediction module is used to predict the total traffic generated by the target business system when it obtains the total number of orders in the specified time period, based on the correlation between the traffic and the number of orders generated by the target business system in the same time period. The target business system is the core business system of a specified business. The specified business includes multiple customer business systems. The core business system can aggregate the order volume of the multiple business systems in the service architecture of the specified business within the same time period to obtain the total order volume within the same time period. The device further includes: a correlation determination module, used to determine the traffic correlation degree between the core business system and the target customer business system, wherein the target customer business system is any one of the multiple customer business systems; the correlation determination module is specifically used to: determine the Pearson correlation coefficient between the traffic of the core business system and the target customer business system based on the quotient of the covariance and standard deviation between the average daily traffic of the core business system within a preset historical time period and the average daily traffic of the target customer business system within the preset historical time period; determine the peak traffic correlation coefficient between the core business system and the target customer business system based on the ratio between the peak daily traffic of the core business system within the preset historical time period and the peak daily traffic of the target customer business system within the preset historical time period; and determine the traffic correlation degree between the core business system and the target customer business system based on the Pearson correlation coefficient and the peak traffic correlation coefficient. The first prediction module is used to predict the traffic of the target customer business system during the specified time period based on the traffic correlation between the core business system and the target customer business system, as well as the total traffic.
7. An electronic device, characterized in that, include: Memory and processor; The memory is used to store computer programs; The processor, coupled to the memory, is configured to execute the computer program for: Determine the activity tags corresponding to the specified time period to be predicted; Based on the order volume prediction model for predicting order volume during periods with activity tags, and the specified period and the activity tags, the total order volume of the target business system during the specified period is predicted; the order volume prediction model is a nonlinear time series prediction model trained based on the order volume of the target business system in multiple periods in a historical time period, and the activity tags corresponding to the multiple periods. Based on the correlation between the traffic and order volume of the target business system in the same time period, predict the total traffic generated by the target business system when it obtains the total order volume in the specified time period; The target business system is the core business system of the specified business. The specified business includes multiple customer business systems. The core business system can aggregate the order volume of the multiple business systems in the service architecture of the specified business in the same time period to obtain the total order volume in the same time period and determine the traffic correlation between the core business system and the target customer business system. The target customer business system is any one of the multiple customer business systems. Determining the traffic correlation between the core business system and the target customer business system includes: determining a Pearson correlation coefficient between the traffic of the core business system and the target customer business system based on the quotient of the covariance and standard deviation of the average daily traffic of the core business system and the average daily traffic of the target customer business system within the preset historical time period; determining a peak traffic correlation coefficient between the core business system and the target customer business system based on the ratio between the peak daily traffic of the core business system and the peak daily traffic of the target customer business system within the preset historical time period; and determining the traffic correlation between the core business system and the target customer business system based on the Pearson correlation coefficient and the peak traffic correlation coefficient. Based on the traffic correlation between the core business system and the target customer business system, and the total traffic, predict the traffic of the target customer business system during the specified time period.
8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it causes the processor to implement the steps of the business system traffic prediction method according to any one of claims 1 to 5.