JP2020071558A - Resource management support apparatus and resource management support method - Google Patents

Abstract

To efficiently and precisely control system resource management.SOLUTION: A resource management support apparatus stores the number of users in a target system, a data processing amount, a resource status, and past information of an external environment, executes machine learning using information on the number of users and the external environment in a predetermined past period of time as input so as to estimate the predicted number of users in a predetermined external environment in a predetermined future period of time, executes the machine learning using the data processing amount in the predetermined past period of time, the number of users and calendar characteristics of the past period of time as input so as to estimate the predicted data processing amount for the predicted number of users in a predetermined future period of time, determines whether a resource usage status and processing time are equal to or above the standard based on resource status information in the predetermined past period of time, estimates that a required allocation amount of the resource has been increased or decreased by a predetermined percentage from the current state according to a determination result, and executes machine learning using the required allocation amount of the resource and a peak value of the data processing amount as input so as to estimate a predicted required allocation amount with the predicted data processing amount in a predetermined future period of time.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a resource management support device and a resource management support method.

  In recent years, there has been a tendency for the system to become more complex and larger in scale, such as by increasing the number of device configurations and applications, and linking with various external systems.

  On the other hand, in such a system, resource management operations such as monitoring / analyzing the operation status of various resources, early detection of problems in the system, and planning of a reinforcement plan for future operation are becoming more important.

  As a conventional technique related to the operation analysis of such a system, for example, in an access number prediction system that predicts the number of accesses from a customer, the access history is recorded by dividing the accesses according to the access requirements, and When storing the access history for each predetermined period and predicting the number of accesses in the prediction target period using the access history, when the number of accesses for the access requirement increases or decreases, the increase or decrease is used as the access history. There has been proposed an access number prediction system (see Patent Document 1), which is provided with a prediction unit that reflects the access number and predicts the access number in the prediction target period based on the access history.

  A number-of-accesses estimation device for estimating the number of users' access to services in a communication network, which is a DNS query totalization unit that aggregates DNS (Domain Name System) queries for each domain at regular time intervals and records them in a communication log. And the number of accesses estimation for estimating the number of accesses for each domain based on a model formula expressed using the cumulative number of queries for each domain, the maximum TTL (Time-To-Live), and the number of potential users calculated from the communication log. An access number estimation device (see Patent Document 2) having a unit and an output unit that outputs the number of accesses for each domain has also been proposed.

JP, 2009-15415, A JP, 2008-32965, A

  In general, the system engineers in charge are in charge of each task of conventional system operation analysis and resource management based thereon.

In this case, the system engineer, for example, periodically acquires and analyzes the operation information of the relevant system, and uses the result to make a resource management judgment such as changing various settings.
However, as described above, the larger and more complicated the target system is, the more the man-hours and costs required for the corresponding work increase.

  In addition, since it is also a task with a strong personality, the above-mentioned resource management judgment accuracy differs depending on the system engineer. In addition, if the criteria for such a judgment are ambiguous in the first place and the system engineer's skills and experience values are insufficient, it is likely that the judgment result will cause a corresponding operational risk.

Performing system operation based on such accuracy may lead to cases in which the performance required for business cannot be exerted under heavy load, or cases where operating costs remain high due to excessively high-performance resource settings for load. Absent.
Then, the objective of this invention is providing the technique which makes the resource management of a system efficient and favorable.

  A resource management support device of the present invention for solving the above-mentioned problems is a storage unit that stores past information of the number of users, a data processing amount, a resource status, and an external environment in a system to be managed, and a past predetermined period. A first process for estimating a predicted number of users in a predetermined external environment at a predetermined time in the future from the predetermined period in the past by machine learning using the number of users and past information of the external environment in By machine learning with the past information of the data processing amount and the number of users in the past predetermined period and the calendar characteristic of the period as input, the predicted number of users at a predetermined time in the future from the past predetermined period Based on the second process of estimating the predicted data processing amount and the past information of the resource condition in the past predetermined period, the resource usage condition and the processing condition are processed. A third process of determining whether the time is equal to or longer than a predetermined criterion and estimating that the required allocation amount of the resource indicated by the past information is increased or decreased by a predetermined ratio from the current state according to the result of the determination; Predicted required allocation at the predicted data processing amount at a predetermined time in the future from the past predetermined period by machine learning using the estimated required resource amount for the predetermined period and the peak value of the data processing amount in the period as inputs. It is characterized by comprising a fourth processing for estimating the quantity, and a calculation section for executing the fourth processing.

  Further, in the resource management support method of the present invention, an information processing apparatus including a storage unit that stores past information on the number of users, the amount of data processing, the resource status, and the external environment in a system to be managed is First estimating the predicted number of users in a predetermined external environment at a predetermined time in the future from the past predetermined period by machine learning using the past number of users and the past information of the external environment as input. The predicted user at a predetermined time in the future from the past predetermined period by processing and machine learning using the past information of the data processing amount and the number of users in the past predetermined period and the calendar characteristic of the period as inputs. The second processing for estimating the predicted data processing amount in terms of the number of resources, and the resource usage status based on the past information of the resource status in the past predetermined period. And a third process for determining whether the processing time is equal to or longer than a predetermined criterion, and estimating that the required allocation amount of the resource indicated by the past information is increased or decreased by a predetermined ratio from the current state according to the result of the determination, Prediction at the predicted data processing amount at a predetermined time in the future from the past predetermined period by machine learning with the required allocation amount of the resource estimated for the past predetermined period and the peak value of the data processing amount in the period being input And a fourth process for estimating the required allocation amount.

  According to the present invention, system resource management can be efficiently and accurately performed.

It is a figure which shows the example of a network structure containing the resource management support apparatus of this embodiment. It is a figure which shows the hardware structural example of the resource management support apparatus of this embodiment. It is a figure which shows the data structural example of the number information of active contractors of this embodiment. It is a figure which shows the data structural example of the financial information of this embodiment. It is a figure which shows the data structural example of the sales promotion information of this embodiment. It is a figure which shows the data structural example of the resource relevant information of this embodiment. It is a figure which shows the example of a flow of the resource management support method in this embodiment. It is a figure which shows the structural example 1 of the objective variable and explanatory variable in this embodiment. It is a figure which shows the structural example 2 of the objective variable and explanatory variable in this embodiment. It is a figure which shows the structural example 3 of the objective variable and explanatory variable in this embodiment. It is a figure which shows the structural example 4 of the objective variable and explanatory variable in this embodiment. It is a figure which shows the example 2 of a flow of the resource management support method in this embodiment.

--- Network configuration ---

  Embodiments of the present invention will be described below in detail with reference to the drawings. FIG. 1 is a diagram showing a configuration example of a resource management support device 100 according to this embodiment. The resource management support device 100 shown in FIG. 1 is a computer device that enables efficient and accurate resource management of the system.

The resource management support device 100 is, for example, a server device operated by a vendor. This vendor is in charge of managing the business system of a financial institution, for example. Further, the business system is the target system 300 in FIG.
As an example of the target system 300, a business system such as an internet banking service provided by a financial institution can be assumed.
On the other hand, a user who uses the target system 300, that is, a terminal operated by a customer of the above-described financial institution is the user terminal 200.

  As a specific example of the user terminal 200, a smartphone, a PC, a tablet terminal, etc. can be assumed. In this case, the customer of the financial institution operates the user terminal 200 to use the internet banking service provided by the target system 300.

On the other hand, the resource management support device 100 operated by the vendor performs the resource management in the target system 300 efficiently and accurately based on various information such as the number of active contractors in the target system 300 and the daily transaction volume. It becomes a device.
--- Hardware configuration ---

The hardware configuration of the resource management support device 100 in this embodiment is as follows. As illustrated in FIG. 2, the resource management support device 100 includes an SSD (Solid).
A storage unit 101 configured by an appropriate non-volatile storage element such as a State Drive) or a hard disk drive, a memory 103 configured by a volatile storage element such as a RAM, a program 102 stored in the storage unit 101, and the like are read into the memory 103. And the like to perform overall control of the apparatus itself and to perform various judgments, calculations and control processes, an arithmetic unit 104 such as a CPU, an input unit 105 that receives a key input or a voice input from a user, a display that displays processing data, and the like. An output unit 106 and a communication unit 107 that is connected to the network 10 and is in charge of data communication with other devices such as the target system 300 described above are provided.
If the resource management support device 100 is a stand-alone machine, the communication unit 107 described above is unnecessary.

  In addition, in the storage device 101, in addition to the program 102 for implementing the functions required as the resource management support device of the present embodiment, the number 125 of active contractor information, the financial information 126, the sales promotion information 127, and the resource-related information. At least the information 128 is stored. However, details of these pieces of information will be described later.

Further, the program 102 is assumed to include a machine learning algorithm 1021. As the machine learning algorithm 1021, for example, an objective variable that is an item to be estimated (eg, the number of active contractors, daily transaction volume, allocated resource value, etc. described later) is used as an explanatory variable (eg, financial information or calendar described later). Characteristic, forecast active subscribers, forecast daily trading volume, etc.) are used to solve regression problems by so-called supervised learning, linear regression model, MARS, support vector regression, regression tree, model tree, genetic programming, etc. Should be adopted for.
--- Data structure example ---

Next, tables used by the resource management support device 100 of this embodiment will be described. FIG. 3 shows an example of the active contractor number information 125 in this embodiment.
The active contractor number information 125 of this embodiment is a table in which information on the daily active contractor number and the transaction amount in the target system 300 is accumulated.
The data structure is a set of records including data such as daily transaction volume on the day, the number of active contractors, year, month, day, and day of the week, with the day as a key.

Further, FIG. 4 shows an example of the financial information 126 in this embodiment. The financial information 126 of the present embodiment is a table that stores information such as monthly prices of financial products and interest rates.
The data structure is a set of records including data such as the previous month's average stock price and the previous month's interest rate, with the month as a key.

  Further, FIG. 5 shows an example of the sales promotion information 127 in this embodiment. The sales promotion information 127 of the present embodiment is a table in which, for each service provided by the target system 300, information on sales promotion performed by the financial institution or the like is accumulated for each month.

  The data structure is a set of records including data such as the number of CMs in the previous month and the number of DMs in the previous month with the month as a key. CM indicates a commercial film broadcast on mass media, and DM indicates a direct mail sent to each customer.

  Further, FIG. 6 shows an example of the resource-related information 129 according to this embodiment. The resource-related information 129 of this embodiment is a table in which the types and amounts of various resources set in the target system 300, the usage status of the resources in the period, and the like are accumulated for each month.

  The data structure is such that, with the month as a key, the type and amount of resources allocated to the target system 300 in the month, the maximum usage rate / usage amount at peak time in the target system 300, the average usage rate / usage amount at peak time, It is a collection of records consisting of data such as batch processing time and waiting time.

  Note that the batch processing time of the above is the time required for the batch processing in the target system 300 in the corresponding month (eg, daily processing regarding business data in the Internet banking service), and is the average in the target system 300. The ratio is shown when the batch processing time or the predetermined normal processing time is 1.0.

The waiting time is a waiting time (latency) that occurs when a user uses a service in the target system 300, and is an average waiting time in the target system 300 or is defined in advance. The ratio when the normal waiting time is 1.0 is shown.
--- Flow example ---

  The actual procedure of the resource management support method according to this embodiment will be described below with reference to the drawings. Various operations corresponding to the resource management support method described below are realized by a program which the resource management support apparatus 100 reads into a memory or the like and executes. The program is composed of codes for performing various operations described below.

  FIG. 7 is a diagram showing a flow example 1 of the resource management support method in the present embodiment. First, the resource management support apparatus 100 senses the arrival of a predetermined time with its own calendar function (a function naturally provided as a computer), or receives a user instruction from the input unit 105, and then the storage unit 101 stores it. Information (past information) in a predetermined past period is extracted from the active contractor number information 125, the financial information 126, and the sales promotion information 127 (s10).

  Here, as illustrated in the “learning time” table 150 in FIG. 8, the number of active contractors (for each month from “January 2018” to “April 2018”, which is a predetermined period in the past, Number of users: extracted from active contractor number information 125), average price of previous month and interest rate of previous month (external environment information: all extracted from financial information 126), CM number of previous month and DM number of previous month (external environment information: all) Extracted from the sales promotion information 127).

  Subsequently, the resource management support device 100 uses the number of active subscribers as the objective variable, of the information obtained in s10, the average price of the previous month and the interest rate of the previous month, the number of CMs of the previous month and the number of DMs of the previous month as explanatory variables, and the machine learning algorithm. This is input to 1021 and, for example, the active contractor in “May 2018”, which is the next month from the present time, is estimated (s11).

  At this time, the explanatory variables are the average stock price and interest rate of the previous month, which are the average stock price and the interest rate of “April 2018”, which is the closest to “May 2018”, as shown in the table 151 of “Forecast time” in FIG. The previous month's interest rate and the number of CMs and DMs of "April 2018" are the number of CMs and DMs of the previous month.

  Subsequently, the resource management support device 100 extracts the daily transaction amount (data processing amount) and the number of active contractors in the past predetermined period, and the calendar characteristic of the period from the active contractor number information 125 (s12). ..

  Here, as illustrated in the table 160 of “at the time of learning” in FIG. 9, for each day from “May 1, 2008” to “April 30, 2018”, which is a predetermined period in the past, Next transaction amount (data processing amount: extracted from active contractor number information 125), active contractor number (user number: extracted from active contractor number information 125), date, day of the week (calendar characteristics: all active contracts (Extracted from the number information 125) is obtained.

  Next, the resource management support apparatus 100 inputs the date and time and the daily transaction volume as the target variables and the number of active contractors, the date, the day of the week, and the day of the week as the explanatory variables to the machine learning algorithm 1021 among the information obtained in s12. However, for example, the daily trading volume on each day from “May 1, 2018” to “May 31, 2018”, which is tomorrow as viewed from the present time, is estimated (s13).

  The explanatory variables at this time include the number of active contractors estimated in s11 and “May 1, 2018” to “May 31, 2018” as shown in the table 161 of “at the time of prediction” in FIG. Each day of the week.

  Subsequently, the resource management support device 100, based on the resource-related information 128 of the storage unit 101, the past information of the resource status regarding each month from “May 2008” to “April 2018” which is a predetermined period in the past. As the maximum peak usage rate or average usage rate, and batch processing time or latency (both processing time) information is extracted (s14).

Here, as illustrated by a table 170 in FIG. 10, for each month from “May 2008” to “April 2018”, which is a predetermined period in the past, the resource type and its allocated amount,
It is assumed that the peak maximum usage rate / usage rate, average usage rate / usage rate, batch processing time, and latency (past resource status information: all extracted from the resource-related information 128) are obtained.

  Subsequently, the resource management support apparatus 100 has the peak maximum usage rate / usage rate or average usage rate / usage rate and the batch processing time or latency of the information obtained in s14, which are both equal to or greater than the first criterion. It is determined (s15).

  Here, the first criterion is, for example, “100%” for the peak maximum usage rate / usage amount, “100%” for the peak average usage rate / usage amount, and the batch processing time and latency. Is "1.3".

  As a result of the above determination, when neither the peak maximum usage rate / usage rate or average usage rate / usage rate nor the batch processing time or latency is equal to or higher than the first criterion (s16: No), the resource management support apparatus 100 Causes the process to transition to s18.

  On the other hand, as a result of the above determination, if the maximum usage rate / usage rate or average usage rate / usage at peak time and the batch processing time or latency are both equal to or greater than the first criterion (s16: Yes), resource management support The device 100 estimates that the required allocation amount of the resource indicated by the above-mentioned past information is increased by a predetermined percentage from the value of the corresponding period (which may include the current concept) (s17), and shifts the process to s22. ..

  As the “predetermined ratio” to be increased, for example, a ratio in which the batch processing time or the latency exceeds the first standard can be assumed. Therefore, when the batch processing time or the latency exceeds the first criterion by 10%, the required allocation amount of the resource is increased by 10% from the value of the corresponding period.

  On the other hand, as a result of the determination in step s15 described above, neither the maximum usage rate / usage rate or average usage rate / usage at peak time nor the batch processing time or latency is equal to or more than the first standard (s16: No). The resource management support apparatus 100 determines whether the peak maximum usage rate / usage rate or average usage rate / usage rate and the batch processing time or latency are both below the second criterion (s18).

  Here, the second criterion is, for example, “50%” for the maximum usage rate / usage amount at peak, “50%” for the average usage rate / usage amount at peak, and batch processing time and latency. Is "0.5".

  As a result of the above determination, when neither the maximum usage rate / usage amount or average usage rate / usage amount at the peak time nor the batch processing time or the latency is below the second standard (s19: No), the resource management support device 100 Estimates that the required allocation amount of the resource indicated by the above-mentioned past information is also valid as the value of the corresponding period (which may include the current concept) (s20), and shifts the processing to s22.

  On the other hand, as a result of the above determination, when the maximum usage rate / usage rate or average usage rate / usage at peak time and the batch processing time or latency are both below the second standard (s19: Yes), resource management support The device 100 estimates that the required allocation amount of the resource indicated by the past information is reduced by a predetermined ratio from the value of the corresponding period (which may include the current concept) (s21).

As the “predetermined ratio” to be reduced, for example, the batch processing time or the latency is
A rate below the second criterion can be assumed. Therefore, when the batch processing time or the latency exceeds the second criterion by 10%, the required allocation amount of the resource is reduced by 10% from the value of the corresponding period.

  Subsequently, the resource management support apparatus 100 sets the required allocation amount of each resource in the target system 300 estimated for at least one of the above-mentioned s17, s20, and s21 for the predetermined period as a target variable, and sets the data processing amount in the period. Of the peak value (maximum value of the daily trading volume on each day of the relevant period, estimated in s13) of FIG. 11 as an explanatory variable in the “learning time” table 180 and the “estimation time” table 181. As described above, it is input to the machine learning algorithm 1021 and, for example, the necessary allocation amount (“allocation resource value” in FIG. 11) in “May 2018” is estimated (s22).

  The resource management support apparatus 100 displays the required allocation amount (table 181 in FIG. 11) estimated for the resources of the target system 300 in this way, for example, on the output unit 106 (s23), and ends the process.

  Note that, as shown in the flow of FIG. 12, instead of steps s10 to s13 in the flow example 1 of FIG. 7, the number of active contractors, financial information, sales promotion information, and daily transaction volume in the past predetermined period are past. The information and the calendar characteristic of the period are acquired (s101), and the machine learning by the machine learning algorithm 1021 is executed by using the daily transaction volume as the objective variable, the number of active contractors and the calendar characteristic as explanatory variables, and the future The daily transaction volume in the number of active contractors on each day of each calendar characteristic at a predetermined time may be estimated (s102). In this case, the steps after step s14 are the same as in the flow example 1.

  The best mode for carrying out the present invention has been specifically described above, but the present invention is not limited to this, and various modifications can be made without departing from the scope of the invention.

According to the present embodiment as described above, it is possible to automate the periodical analysis of the operation information on the target system, and use the result to accurately determine the necessity of changing the resource settings. This leads to a reduction in the load on the system engineer or the like and a reduction in human costs, and also enables a resource configuration that can be appropriately dealt with at the peak of the future to be preset and dealt with. The end users of such a system also have the advantage of being able to use the service smoothly and comfortably without encountering unfavorable situations such as high access making it difficult to access and latency exceeding the allowable range.
That is, the resource management of the system can be efficiently and accurately performed.

  At least the following matters will be made clear by the description of the present specification. That is, in the resource management support apparatus according to the present embodiment, when the usage status and the processing time are equal to or more than the first criterion in the fourth processing, the calculation unit requires the necessary allocation of the resource indicated by the past information. It is estimated that the amount has been increased by a predetermined percentage from the current state, and when both the usage status and the processing time are below the second standard, the required allocation amount of the resource indicated by the past information is reduced by a predetermined percentage from the current state. It may be assumed that

  According to this, for example, when the resource usage is high (eg, 100%), it is completely used up but it is not an overload condition that adversely affects performance. Whether or not the situation is unclear in the past, such as the overload condition that adversely affects the performance, it is possible to appropriately make a decision using the processing time as a guide. As a result, system resource management can be made more efficient and accurate.

  Further, in the resource management support device of the present embodiment, the arithmetic unit, in the fourth processing, the maximum usage rate or average usage rate at the peak of the usage status, and the batch processing time or the processing time, or When both the latency and the first criterion are equal to or more than the first criterion, it is estimated that the required allocation amount of the resource indicated by the past information is increased by a predetermined ratio from the current state, and the maximum use rate or average use at the peak of the use state. If both the rate and the batch processing time or the latency that is the processing time are less than or equal to the second standard, it is estimated that the required allocation amount of the resource indicated by the past information is reduced by a predetermined ratio from the current state. There may be.

  According to this, for example, when the resource usage is high (eg, 100%), it is completely used up but it is not an overload condition that adversely affects performance. Whether it is an overload condition that adversely affects performance above, or a situation that was unclear in the past, it is possible to make appropriate decisions by taking appropriate measures based on the batch processing time or the excessive length of latency. Become. As a result, system resource management can be made more efficient and accurate.

  In addition, in the resource management support apparatus of the present embodiment, the arithmetic unit performs the first process, the number of users in a predetermined period in the past, and financial product information that is information on the external environment and sales promotion related to the system. By using machine learning with past information of activity information as input, it is possible to estimate the predicted number of users under predetermined circumstances of financial products and sales promotion activities at a predetermined time in the future from the predetermined time in the past. Good.

  According to this, for example, the number of users of financial services provided by financial institutions is sensitive to financial environment information such as stock prices and interest rates, that is, financial information, and sales promotion activities performed by the financial institutions (commercial media It is possible to accurately estimate the number of users in the future based on the situation that many people are affected by broadcasting, sending direct mail, etc.). As a result, system resource management can be made more efficient and accurate.

  Further, in the resource management support device of the present embodiment, the calculation unit merges the first process and the second process, and the number of users, the external environment, and the data processing amount in a past predetermined period. By using machine learning with the past information of and the calendar characteristic of the period as an input, it is assumed that the estimated data processing amount at a predetermined number of predicted users at a predetermined time in the future from the predetermined period in the past is estimated. Good.

  According to this, it is possible to more efficiently estimate the number of users in the future, and further, it is possible to further efficiently and accurately perform the resource management of the system.

    Further, in the resource management support method of the present embodiment, when the information processing device performs the fourth processing, when both the usage status and the processing time are equal to or more than a first reference, the resource information indicated by the past information is required. It is estimated that the allocated amount is increased by a predetermined ratio from the current state, and when both the usage status and the processing time are below the second standard, the required allocated amount of the resource indicated by the past information is decreased by the predetermined ratio from the current state. It may be assumed to be one.

Further, in the resource management support method of the present embodiment, the information processing device, in the fourth processing, the maximum usage rate or average usage rate at the peak of the usage status, and the batch processing time which is the processing time. Alternatively, when the latency is both equal to or greater than the first criterion, it is estimated that the required allocation amount of the resource indicated by the past information is increased by a predetermined ratio from the current state, and the maximum use rate or the average during the peak of the use state. If both the usage rate and the batch processing time or the latency, which is the processing time, are equal to or less than the second standard, it is estimated that the required allocation amount of the resource indicated by the past information is reduced by a predetermined ratio from the current state. May be

  Further, in the resource management support method according to the present embodiment, the information processing apparatus relates to the number of users in a predetermined period in the past and the information about the financial product, which is information about the external environment, and the system during the first processing. It is also possible to estimate the predicted number of users under the predetermined situation of the financial product and the sales promotion activity at a predetermined time in the future from the predetermined time period of the past by machine learning using past information of the sales promotion activity as input. ..

  Further, in the resource management support method of the present embodiment, the information processing apparatus merges the first processing and the second processing, and the number of users, the external environment, and the data processing in a past predetermined period. It is also possible to estimate the predicted data processing amount for a predetermined number of predicted users at a predetermined time point in the future from the predetermined time period in the past by machine learning using the past information of the amount and the calendar characteristic of the period. ..

10 network 100 resource management support device 101 storage unit 102 program 1021 machine learning algorithm 103 memory 104 arithmetic unit 105 input unit 106 output unit 107 communication unit 125 active contractor number information 126 financial information 127 sales promotion information 128 resource related information 200 user terminal 300 Target system

Claims (10)

A storage unit that stores past information of the number of users, the amount of data processing, the resource status, and the external environment in the managed system,
Estimating a predicted number of users in a predetermined external environment at a predetermined time in the future from the past predetermined period by machine learning using the number of users in the past predetermined period and past information of the external environment as input One process and machine learning using the past information of the data processing amount and the number of users in the past predetermined period and the calendar characteristic of the period as input, the predictive use in the predetermined period in the future from the past predetermined period. Based on the second process of estimating the predicted data processing amount in the number of users and the past information of the resource status in the past predetermined period, it is determined whether the resource usage status and the processing time are equal to or more than a predetermined reference, and the result of the determination is obtained. Accordingly, the third process of estimating that the required allocation amount of the resource indicated by the past information is increased or decreased by a predetermined ratio from the current state, Of the estimated amount of resources required for the predetermined period and the machine learning with the peak value of the amount of data processing in the period as input are used to predict the predicted amount of data processing at a predetermined time in the future from the predetermined period in the past. A fourth processing for estimating a quota, and a computing unit for executing
A resource management support device comprising: The arithmetic unit is
In the fourth processing, when both the usage status and the processing time are equal to or more than the first criterion, it is estimated that the required allocation amount of the resource indicated by the past information is increased by a predetermined ratio from the current status, and the usage status is calculated. If both the processing time and the processing time are equal to or less than the second criterion, it is estimated that the required allocation amount of the resource indicated by the past information is reduced by a predetermined ratio from the current state.
The resource management support apparatus according to claim 1, wherein: The arithmetic unit is
In the fourth processing,
If both the peak maximum usage rate or average usage rate that is the usage status and the batch processing time or latency that is the processing time are equal to or greater than the first criterion, the required allocation amount of the resource indicated by the past information Is estimated to have been increased by a predetermined percentage from the current status,
When both the maximum usage rate or the average usage rate at the peak time which is the usage status and the batch processing time or the latency which is the processing time are both below the second standard, the required allocation amount of the resource indicated by the past information. Is estimated to have been reduced by a predetermined percentage from the current state,
The resource management support device according to claim 2, wherein The arithmetic unit is
At the time of the first process, the past number of users in a predetermined period in the past, machine learning with the past information of the financial product information that is the information of the external environment and the information of the sales promotion activity related to the system as the input, the past The estimated number of users under predetermined circumstances of financial products and promotional activities at a predetermined time in the future from the predetermined period of
The resource management support apparatus according to claim 1, wherein: The arithmetic unit is
Machine learning in which the first process and the second process are merged, and the past information of the number of users, the external environment, and the data processing amount in the past predetermined period, and the calendar characteristic of the period are input. According to the above, the estimated data processing amount for a predetermined number of predicted users at a predetermined time in the future from the predetermined time in the past is estimated.
The resource management support apparatus according to claim 1, wherein: An information processing apparatus including a storage unit that stores past information on the number of users, data processing amount, resource status, and external environment in a managed system is
Estimating a predicted number of users in a predetermined external environment at a predetermined time in the future from the past predetermined period by machine learning using the number of users in the past predetermined period and past information of the external environment as input 1 process,
By machine learning with the past information of the data processing amount and the number of users in the past predetermined period and the calendar characteristics of the period as an input, the predicted number of users at a predetermined time in the future from the past predetermined period A second process for estimating a predicted data processing amount;
Based on the past information of the resource status in the past predetermined period, it is determined whether the resource usage status and the processing time are equal to or more than a predetermined standard, and the required allocation amount of the resource indicated by the past information is determined from the current status according to the result of the determination. A third process for estimating that the flow rate has been increased or decreased by a predetermined ratio,
By machine learning using the required allocation amount of the resource estimated for the past predetermined period and the peak value of the data processing amount in the period as an input, the predicted data processing amount in the predetermined time period in the future from the past predetermined period A fourth process for estimating a predicted required quota,
A resource management support method characterized by executing the following. The information processing device is
In the fourth processing, when both the usage status and the processing time are equal to or more than the first criterion, it is estimated that the required allocation amount of the resource indicated by the past information is increased by a predetermined ratio from the current status, and the usage status is calculated. If both the processing time and the processing time are less than or equal to the second criterion, it is estimated that the required allocation amount of the resource indicated by the past information is reduced by a predetermined ratio from the current state.
The resource management support method according to claim 6, wherein: The information processing device is
In the case of the fourth processing, if the peak maximum usage rate or average usage rate that is the usage status and the batch processing time or latency that is the processing time are both equal to or greater than the first reference, the past information indicates It is estimated that the required allocation amount of the resource is increased by a predetermined percentage from the current state, and the maximum usage rate or average usage rate at the peak of the usage status and the batch processing time or latency that is the processing time are both If it is equal to or less than the criterion of 2, it is estimated that the required allocation amount of the resource indicated by the past information is reduced by a predetermined ratio from the current state,
The resource management support method according to claim 7, wherein: The information processing device is
At the time of the first process, the past number of users in a predetermined period in the past, machine learning with the past information of the financial product information that is the information of the external environment and the information of the sales promotion activity related to the system as the input, the past Estimate the predicted number of users under certain circumstances of financial products and promotional activities at a predetermined time in the future from the predetermined period of
The resource management support method according to claim 6, wherein: The information processing device is
Machine learning in which the first process and the second process are merged, and the past information of the number of users, the external environment, and the data processing amount in the past predetermined period, and the calendar characteristic of the period are input. Thus, the estimated data processing amount for a predetermined number of predicted users at a predetermined time in the future from the predetermined time in the past is estimated,
The resource management support method according to claim 6, wherein: