CN111461775A - Method and device for determining influence of event on traffic - Google Patents

Method and device for determining influence of event on traffic Download PDF

Info

Publication number
CN111461775A
CN111461775A CN202010238059.XA CN202010238059A CN111461775A CN 111461775 A CN111461775 A CN 111461775A CN 202010238059 A CN202010238059 A CN 202010238059A CN 111461775 A CN111461775 A CN 111461775A
Authority
CN
China
Prior art keywords
event
analyzed
day
service data
traffic
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010238059.XA
Other languages
Chinese (zh)
Other versions
CN111461775B (en
Inventor
王健
徐进澎
李俊
黄芳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alipay Hangzhou Information Technology Co Ltd
Original Assignee
Alipay Hangzhou Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Alipay Hangzhou Information Technology Co Ltd filed Critical Alipay Hangzhou Information Technology Co Ltd
Priority to CN202010238059.XA priority Critical patent/CN111461775B/en
Publication of CN111461775A publication Critical patent/CN111461775A/en
Application granted granted Critical
Publication of CN111461775B publication Critical patent/CN111461775B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data

Landscapes

  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The embodiment of the specification provides a method and a device for determining the influence of an event on traffic, wherein the method comprises the following steps: acquiring historical service data corresponding to a target service from a database; acquiring basic service data of the day of the event to be analyzed according to the historical service data; determining a business data fluctuation item corresponding to the occurrence day of the event to be analyzed according to historical business data and a first set rule; determining a service data random disturbance item corresponding to the occurrence day of the event to be analyzed according to the historical service data and a second set rule; and determining the influence of the event on the service volume of the event occurrence day to be analyzed by using a set influence determination algorithm according to the basic service data, the service data fluctuation item and the service data random disturbance item.

Description

Method and device for determining influence of event on traffic
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for determining an influence of an event on a traffic volume.
Background
Generally, when the indexes of services (such as telephone traffic services, air ticket selling services, and the like) do not reach the standard, reason positioning is required to be performed, the indexes of the services can be divided into a service deployment rate, a acceptance achievement rate, a prediction deviation rate, and the like, and the prediction deviation rate can be divided into a reference prediction deviation rate, an event prediction deviation rate, and the like. In order to obtain the event prediction deviation rate, the actual impact of the event on the service needs to be located.
At present, when a positioning event actually affects a service, positioning is mostly performed by a manual analysis method, so that a large amount of human resources are consumed, time consumption is long, efficiency is low, service prediction updating is possibly affected, data assistance cannot be timely provided for a service party, and a service index is still continuously affected due to the fact that sufficient data support is not available when next service prediction is performed.
Therefore, it is necessary to provide a technical solution to achieve reliable and efficient actual impact of positioning events on services.
Disclosure of Invention
The embodiment of the specification provides a method for determining the influence of an event on traffic. The method for determining the influence of the event on the traffic comprises the following steps:
and acquiring historical service data corresponding to the target service from the database. Wherein the historical traffic data comprises actual traffic volume per day for the target traffic. And acquiring basic service data of the day of the event to be analyzed according to the historical service data. And the basic service data is the service data after the influences of the events and the special days are eliminated. The special days comprise holidays and key days, and the key days are the occurrence days of the periodic events. Determining a business data fluctuation item corresponding to the occurrence date of the event to be analyzed according to the historical business data and a first set rule; and determining a service data random disturbance item corresponding to the occurrence day of the event to be analyzed according to the historical service data and a second set rule. And determining the influence of the event on the traffic of the day of the event to be analyzed by using a set influence determination algorithm according to the basic service data, the service data fluctuation item and the service data random disturbance item.
The embodiment of the specification also provides a device for determining the influence of the event on the traffic. The device for determining the influence of the event on the traffic comprises:
the first acquisition module acquires historical service data corresponding to the target service from the database. Wherein the historical traffic data comprises actual traffic volume per day for the target traffic. And the second acquisition module is used for acquiring basic service data of the day of the event to be analyzed according to the historical service data. And the basic service data is the service data after the influences of the events and the special days are eliminated. The special days comprise holidays and key days, and the key days are the occurrence days of the periodic events. The first determining module is used for determining a business data fluctuation item corresponding to the occurrence day of the event to be analyzed according to the historical business data and a first set rule; and determining a service data random disturbance item corresponding to the occurrence day of the event to be analyzed according to the historical service data and a second set rule. And the second determining module is used for determining the influence of the event on the traffic of the day of the event to be analyzed by using a set influence determining algorithm according to the basic service data, the service data fluctuation item and the service data random disturbance item.
The embodiment of the specification also provides a device for determining the influence of the event on the traffic. The apparatus comprises: a processor; and a memory arranged to store computer executable instructions. The executable instructions, when executed, cause the processor to:
and acquiring historical service data corresponding to the target service from the database. Wherein the historical traffic data comprises actual traffic volume per day for the target traffic. Acquiring basic service data of the day of the event to be analyzed according to the historical service data; the basic service data are service data after the influences of events and special days are eliminated; the special days comprise holidays and key days, and the key days are the occurrence days of the periodic events. Determining a business data fluctuation item corresponding to the occurrence date of the event to be analyzed according to the historical business data and a first set rule; and determining a service data random disturbance item corresponding to the occurrence day of the event to be analyzed according to the historical service data and a second set rule. And determining the influence of the event on the traffic of the day of the event to be analyzed by using a set influence determination algorithm according to the basic service data, the service data fluctuation item and the service data random disturbance item.
The embodiment of the specification also provides a storage medium. The storage medium is used for storing computer executable instructions, and the executable instructions realize the following processes when executed:
and acquiring historical service data corresponding to the target service from the database. Wherein the historical traffic data comprises actual traffic volume per day for the target traffic. Acquiring basic service data of the day of the event to be analyzed according to the historical service data; and the basic service data is the service data after the influences of the events and the special days are eliminated. The special days comprise holidays and key days, and the key days are the occurrence days of the periodic events. Determining a business data fluctuation item corresponding to the occurrence date of the event to be analyzed according to the historical business data and a first set rule; and determining a service data random disturbance item corresponding to the occurrence day of the event to be analyzed according to the historical service data and a second set rule. And determining the influence of the event on the traffic of the day of the event to be analyzed by using a set influence determination algorithm according to the basic service data, the service data fluctuation item and the service data random disturbance item.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a method for determining an influence of an event on traffic according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a method for determining a business data fluctuation item in a method for determining an influence of an event on a business volume provided by an embodiment of the present specification;
FIG. 3 is a second flowchart of a method for determining an impact of an event on traffic according to an embodiment of the present disclosure;
fig. 4 is a third flowchart of a method of determining an influence of an event on traffic according to an embodiment of the present disclosure;
FIG. 5 is a flowchart of a fourth method of determining an impact of an event on traffic provided by an embodiment of the present specification;
fig. 6 is a schematic block diagram of a device for determining an influence of an event on traffic according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of a device for determining an influence of an event on traffic provided in an embodiment of the present specification.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The idea of the embodiment of the specification is that the influence of the event on the traffic of the event occurrence day is determined by a set influence determination algorithm through basic service data, a service data fluctuation item and a random disturbance item, so that the automatic determination of the influence of the event on the traffic is realized, the influence of the event on the traffic can be determined without a large amount of human resources, a large amount of human resources can be reduced, the time consumption is short, and the efficiency is high; based on this, embodiments of the present specification provide a method, an apparatus, a device, and a storage medium for determining an influence of an event on traffic, which will be described in detail below.
Fig. 1 is a flowchart of a method for determining an influence of time on traffic according to an embodiment of the present disclosure, where the method shown in fig. 1 at least includes the following steps:
102, acquiring historical service data corresponding to a target service from a database; wherein the historical service data comprises actual daily traffic of the target service.
The target service can be a telephone traffic service, an air ticket selling service, a product selling service and the like of a client center; correspondingly, if the target service is a telephone traffic service, the historical service data may be actual telephone traffic of each day within a first set time length; if the target service is an air ticket selling service, the historical service data can be the actual selling amount of the air tickets every day in a first set time length. The value of the first set time length may be one month, two months, or the like, and the specific value may be set according to an actual service scenario, which is not limited in the embodiments of the present specification.
In specific implementation, the historical service data within a first set time length before the event occurrence date can be acquired by taking the event occurrence date as a reference. For example, in one embodiment, assuming that the incident day is 3/11/2020, historical business data for a month prior to 3/11/2020 may be obtained. One possible form of the acquired historical traffic data is shown in table 1.
TABLE 1
Date Actual traffic volume
Day1 2800
Day2 1500
… …
DayN 1800
Where N is a positive integer, Day1 may be understood as the Day before the event to be analyzed, Day2 may be understood as the Day after the event to be analyzed, and Day N may be understood as the Day before the event to be analyzed. Of course, the actual traffic in table 1 is exemplary and should not be construed as a limitation of the embodiments of the present disclosure.
In addition, it should be noted that, in this embodiment of the present specification, the database may be a database corresponding to a target service platform.
And 104, determining basic service data of the event occurrence day to be analyzed according to the historical service data.
The basic service data are service data after the influences of events and special days are eliminated; the special days comprise holidays and key days, and the key days are the occurrence days of the periodic events.
The event occurrence date refers to the date of occurrence of the event, and the event generally refers to the event which has some relation with the target service and may affect the service volume of the target service.
Optionally, in the step 104, the basic service data of the event to be analyzed is determined according to the historical service data, which may be actually understood as inferring the basic service data of the event to be analyzed according to the historical service data. The basic service data refers to traffic data after the influence of an event and a special day. I.e., basic service data, can be understood as service data that is neither a special day nor a general day of an event occurrence day. In the embodiment of the present specification, after removing the service data corresponding to the event occurrence date and the special date in the historical service data, the obtained remaining historical service data determines the basic service data corresponding to the event occurrence date to be analyzed.
The holiday may be a legal holiday, such as a year, a spring festival, a national day, and the like, the key day is a day of occurrence of a periodic event, and the periodic event may be understood as an event that occurs on the same day in each period, for example, if the period of the periodic event is one month, the periodic event may be an event that occurs on a certain day in each month. For example, in one embodiment, the periodic event may be a monthly credit deduction event No. 1; also for example, the periodic event may be a monthly fixed-date credit card payment event, or the like.
106, determining a business data fluctuation item corresponding to the occurrence day of the event to be analyzed according to the historical business data and a first set rule; and determining a random disturbance item corresponding to the occurrence day of the event to be analyzed according to the historical service data and a second set rule.
The service data fluctuation item refers to natural fluctuation of service data and is used for representing natural fluctuation conditions of service volume corresponding to target services every day, and the random disturbance item can be understood as a random error item.
And step 108, determining the influence of the event on the traffic of the event day to be analyzed by using a set influence determination algorithm according to the basic service data, the service data fluctuation item and the service data random disturbance item.
In step 108, the influence of the event on the traffic of the day of the event to be analyzed is determined, which is actually the traffic caused by the occurrence of the event in the actual traffic of the day of the event to be analyzed.
In order to facilitate understanding of the methods provided by the embodiments of the present disclosure, the following detailed description will discuss specific implementation processes of the above steps.
Optionally, in step 104, determining the basic service data corresponding to the event occurrence date to be analyzed according to the historical service data, specifically including the following steps:
service data of an event occurrence day and a special day in the historical service data are removed; determining the average value of the service data corresponding to all dates which are positioned in a time node before the date of the event to be analyzed and belong to the same week number as the date of the event to be analyzed from the remaining historical service data after the elimination; and determining the average value of the service data as basic service data.
The previous time node of the event day to be analyzed may be a month, two months, and the like before the event day to be analyzed, and specifically, the specific duration of the time node may be set according to a specific service scenario, which is not limited in this embodiment of the present specification.
Optionally, in a specific implementation, all dates belonging to the same week number as the event occurrence date to be analyzed in a previous time node of the event occurrence date to be analyzed may be event occurrence dates, holidays or key dates, and in this case, the service data of the date is already removed, so that the basic service data of the event occurrence date to be analyzed cannot be determined according to the service data of the date. In this case, the basic traffic data may be determined using an average of traffic data of the day before and the day after the date. For example, if the day of the event to be analyzed is wednesday, and if all wednesdays in the previous time node of the day of the event to be analyzed are either the event day, the holiday, or the key day, in this case, when determining the basic service data, it is necessary to use the average value of the services of tuesday and thursday in the previous period as the service data of wednesday for determining the basic service data of the day to be analyzed.
For ease of understanding, the following will exemplify the determination process of the basic service data.
For example, in a specific embodiment, the date of the event to be analyzed is 3/11/2020, the number of corresponding weeks is wednesday, the dates corresponding to all wednesdays in a month before the date of the event to be analyzed (the previous period is one month) are 2/5/2020/2/12/2020/2/19/2020/26/2020, and if none of the 2/5/2020/2/12/2020/2/19/2020/2/26 is a holiday or a key day, the average value of the service data of 2/5/2020/2/12/2020/2/19/2020/2/26/2020 needs to be calculated, and the average value is used as the basic service data of 3/11/2020/3; if the data of 12 days in month 2 in 2020 is the key day, the service data of 12 days in month 2 in year 2020 has been removed, and in this case, the average value of the service data of 5 days in month 2 in year 2020, 19 days in month 2 in year 2020, and 26 days in month 2 in year 2020 can be used as the basic service data of 11 days in month 3 in year 2020; if it is determined that 5/2020/2/12, 2/19 and 26/2020/2 are key days, the service data corresponding to 5/2020/2/12, 2/19 and 26/2020/2 are all removed, and at this time, it is necessary to use the average value of the service data corresponding to 4/2/2020 and 6/2/2020 as the service data for 5/2/2020, use the average value of the service data corresponding to 11/2/2020 and 13/2/2020 as the service data for 12/2/2020, use the average value of the service data corresponding to 18/2/18 and 20/2/2020 as the service data for 19/2/2020, use the average value of the service data corresponding to 25/2/27/2020 as the service data for 26/2/26, and then determine the service data based on the determined 2/5/2/26, The business data of 12 days 2/2020, 19 days 2/2020, and 26 days 2/2020 calculate the basic business data corresponding to 11 days 3/2020. Of course, the description is only exemplary and should not be construed as limiting the embodiments of the present disclosure.
Optionally, in a specific embodiment, the day of the event to be analyzed may be a critical day or a non-critical day, the day of the event to be analyzed is a critical day or a non-critical day, and the determining manner of the business data fluctuation item is different, so in a specific embodiment, step 106 determines, according to the historical business data and according to a first set rule, the business data fluctuation item corresponding to the day of the event to be analyzed, and specifically includes the following processes:
judging whether the day of the event to be analyzed is a key day; if so, searching a business data fluctuation item corresponding to the occurrence date of the event to be analyzed from a pre-established first fluctuation item library according to date information corresponding to the occurrence date of the event to be analyzed and week information corresponding to the occurrence date of the event to be analyzed; otherwise, searching a business data fluctuation item corresponding to the occurrence day of the event to be analyzed from a pre-established second fluctuation item library according to the month information corresponding to the occurrence day of the event to be analyzed; the first fluctuation item stores the mapping relation of date information, week information and business data fluctuation items of each key day; the second fluctuation item library stores the mapping relationship between the month information and the business data fluctuation items.
In specific implementation, if the date of the event to be analyzed is the key date, the date information and the week information corresponding to the date of the event to be analyzed are matched with the first fluctuation item library, and the business data fluctuation items corresponding to the date information and the week information are searched from the first fluctuation item library and serve as the business data fluctuation items corresponding to the date of the event to be analyzed. The date information may include only date attribute information, such as number 1, number 2, and the like. For example, if the occurrence day of the event to be analyzed is No. 1 and monday, the business data fluctuation items corresponding to No. 1 and monday in the first fluctuation item library need to be used as the business data fluctuation items corresponding to the occurrence day of the event to be analyzed.
If the date of the event to be analyzed is a non-critical date, the month information corresponding to the date of the event to be analyzed needs to be matched with the second fluctuation item library, and the business data fluctuation item corresponding to the month information is searched from the second fluctuation item library and serves as the business data fluctuation item corresponding to the date of the event to be analyzed. For example, if the month corresponding to the occurrence day of the event to be analyzed is january, the service data fluctuation item corresponding to january in the second fluctuation item library needs to be used as the service data fluctuation item corresponding to the occurrence day of the event to be analyzed.
Specifically, in the embodiment of the present specification, the first fluctuation item library may be created by:
calculating the mean value of basic service data of all dates which are located in a time node before the key date and belong to the same week number with the key date aiming at each key date corresponding to the target service; calculating the ratio of the basic service data of the key day to the average value, and taking the ratio as a service data fluctuation item corresponding to the key day; and storing the date information of the key days, the week information corresponding to the key days and the business data fluctuation items into a first fluctuation item library correspondingly.
The previous time node may be a previous month, a previous two months, and the like, and the specific time length may be set according to an actual application scenario, which is not limited in the embodiment of the present specification.
To facilitate understanding of the above-described first fluctuation term library creation process, the following description will be given by way of example.
For example, in one specific embodiment, if the date of a certain key day is 3/11/2020, and wednesday, all dates which are within the previous month of the key day and belong to the same week number as the key day are 2/5/2020/2/12/2020/2/19/2020/2/26/2020, it is necessary to calculate the average value of the basic service data corresponding to the key day (i.e., 3/11/2020) and calculate the ratio of the basic service data corresponding to the key day (i.e., 3/11/2020) to the average value, and use the ratio as the service data fluctuation item corresponding to the key day (11/3/2020). The method for determining the basic service data corresponding to each date may refer to the method for determining the basic service data in step 104 in this embodiment, and details are not repeated here.
Wherein, one possible form of the first fluctuation item library is established as shown in table 2.
TABLE 2
Key day Week Business data fluctuation item
Number 1 Monday 1.01
… … …
Number 9 Tuesday 1.02
Of course, table 2 is only exemplary and should not be construed as limiting the embodiments of the present disclosure.
Specifically, in the embodiment of the present specification, the second fluctuation item library may be created by:
eliminating the business data of the holidays in the historical business data; calculating the average value of daily actual business volume corresponding to each month according to the remaining historical business data after elimination; determining the ratio of the average value of the actual daily traffic corresponding to the current month to the average value of the actual daily traffic corresponding to the previous month as a business data fluctuation item corresponding to the current month; and correspondingly storing the month information and the service data fluctuation items into the second fluctuation item library.
Optionally, the average of the daily actual traffic volume corresponding to each month may be calculated by dividing the actual total traffic volume corresponding to the month by the number of days corresponding to the month.
To facilitate understanding of the above-described process of creating the second fluctuation term library, the following description will be given by way of example.
For example, in a specific embodiment, the service data fluctuation item corresponding to the 3 months in 2020 needs to be calculated, the daily actual traffic average value corresponding to the 2 months in 2020 needs to be calculated, and the ratio of the daily actual traffic average value corresponding to the 3 months in 2020 to the daily actual traffic average value corresponding to the 2 months in 2020 is used as the service data fluctuation item corresponding to the 3 months in 2020 milky milk.
One possible form of the second fluctuation term library is shown in table 3.
TABLE 3
Month information Business data fluctuation item
1 month 1.01
2 month 1.02
… …
12 month 1.03
Of course, table 3 is only exemplary and should not be construed as limiting the embodiments of the present disclosure.
In addition, it should be noted that, in the embodiment of the present specification, in order to improve the accuracy of the determined service data fluctuation item, a month may be sliced, and the month is divided into two time periods, which are respectively denoted as a first time period and a second time period. Wherein the previous week of each date in the first time period is a date of the previous month and the previous week of each date in the second time period is a date of the present month. For example, in one embodiment, the first time period may be from 1 to 11 days of each month, and the second time period may be from 12 to the last day of each month. Of course, this is only an exemplary illustration, and does not constitute a limitation of the embodiments of this specification.
Therefore, in the embodiment of the present specification, in the step 106, the business data fluctuation item corresponding to the occurrence day of the event to be analyzed is determined according to the first set rule based on the historical business data, and may also be implemented by the following steps, as shown in fig. 2.
Step 202, judging whether the occurrence day of the event to be analyzed is a key day; if yes, go to step 204; otherwise, go to step 206;
and 204, searching a business data fluctuation item corresponding to the occurrence date of the event to be analyzed from a pre-established first fluctuation item library according to the date information corresponding to the occurrence date of the event to be analyzed and the week information corresponding to the occurrence date of the event to be analyzed.
The first fluctuation item library stores the mapping relation of date information, week information and business data fluctuation items of each key day;
step 206, judging whether the occurrence day of the event to be analyzed is positioned in the first time period of the month to which the occurrence day of the event to be analyzed belongs; if yes, go to step 208; otherwise, go to step 210;
wherein the previous week of each date in the first time period includes a date of a month previous to the current month.
And step 208, searching a business data fluctuation item corresponding to the occurrence day of the event to be analyzed from a pre-established second fluctuation item library according to the month information to which the occurrence day of the event to be analyzed belongs.
And the second fluctuation item library stores the mapping relation between the month information and the business data fluctuation items.
Step 210, determining a first basic service data mean value corresponding to a period before the occurrence date of the event to be analyzed, determining a second basic service data mean value corresponding to a period before the same date as the occurrence date of the event to be analyzed in the last month, and determining a ratio of the first basic service data mean value to the second basic service data mean value as a service data fluctuation item corresponding to the occurrence date of the event to be analyzed.
The previous cycle in step 210 may be the previous week, the previous two weeks, and the like, and specific values of the above cycles may be set according to an actual application scenario, which is not limited in this specification.
That is, in the embodiment of the present specification, if the event to be analyzed is not a key day, and the occurrence day of the event to be analyzed belongs to the first time period of the current month, directly searching the business data fluctuation item corresponding to the month from the second fluctuation item library according to the month to which the event to be analyzed belongs, and using the business data fluctuation item corresponding to the occurrence day of the event to be analyzed; if the event to be analyzed is not the key day and the occurrence day of the event to be analyzed does not belong to the first time period of the current month, calculating the business data fluctuation item corresponding to the occurrence day of the event to be analyzed in the following manner.
For example, assume that the event day to be analyzed is 26/2/2020, and the event day to be analyzed is not a key day and does not belong to the first time period of the current month, and therefore, when calculating the business data fluctuation item corresponding to the occurrence day of the event to be analyzed, firstly determining that the week before the occurrence day of the event to be analyzed is from 2020, 2 and 19 days to 2020, 2 and 25 days, the average value of the first basic service data corresponding to the week needs to be calculated, the last january of 26 days 2/2020 is 26 days 1/2020, the week before 16 days 1/2020 is 19 days 1/2020 to 25 days 1/2020, therefore, it is necessary to calculate a second basic service data mean value corresponding to the week, calculate a ratio of the first basic service data mean value and the second basic service data mean value, and determine the ratio as a service data fluctuation item corresponding to a time occurrence day to be analyzed.
Of course, in another embodiment, if the event to be analyzed is not a key day, directly determining a first basic service data mean value of a week before the occurrence day of the event to be analyzed, and determining a second basic service data mean value of a week before the same date as the occurrence day of the event to be analyzed in the previous month, and determining a ratio of the first basic service data mean value to the second basic service data mean value as the service data fluctuation item corresponding to the occurrence day of the event to be analyzed.
Optionally, in step 106, determining, according to the historical service data and according to a second set rule, a service data random disturbance item corresponding to the occurrence day of the event to be analyzed, specifically including:
removing holiday business data in the historical business data; determining all the traffic of the days which are in the second set time period before the occurrence date of the event to be analyzed and are the same as the week number of the occurrence date of the event to be analyzed from the remaining historical service data after the elimination; and determining the standard deviation of all the traffic in the day period as a random disturbance item of the traffic data.
In the embodiment of the present specification, since the holiday has a larger fluctuation compared with the ordinary day, in order to better obtain a reasonably stable random disturbance item, the holiday data in the historical service data needs to be removed.
In addition, the value of the second set time period may be two months, three months, or the like, and may be specifically set according to an actual application scenario, and the embodiment of this specification does not limit the specific value of the second set time period.
Optionally, in an embodiment of the present specification, after all days which are within a second set time period before the occurrence date of the time to be analyzed and which have the same number of weeks as the occurrence date of the event to be analyzed are acquired, extreme values in all the days are removed. And then calculating the standard deviation of the rest samples as a random disturbance item of the service data.
Optionally, in the step 108, determining, by using a set influence determination algorithm, an influence of the event on the traffic of the event day to be analyzed according to the basic service data, the service data fluctuation item, and the service data random disturbance item, where the step includes the following steps (1), (2), and (3):
step (1), detecting whether the predicted reference traffic of the day of the event to be analyzed is in the actual reference traffic range; the reference traffic is traffic without influence generated by an event; if yes, executing the step (2); otherwise, executing the step (3);
step (2), according to the actual traffic of the event to be analyzed on the day, the predicted reference traffic and the random disturbance item of the traffic data, determining a traffic influence range generated by the traffic of the event to be analyzed on the day according to a first influence range determining algorithm;
and (3) determining a traffic influence range generated by the traffic of the event to be analyzed on the occurrence day according to the actual traffic of the event to be analyzed on the occurrence day, the basic traffic data, the traffic data fluctuation item and the traffic data random disturbance item and a second influence range determining algorithm.
The predicted reference traffic is the traffic of the event occurrence day to be analyzed after the influence of the event is predicted and eliminated through historical service data; and the actual reference traffic is the traffic of the day of the event to be analyzed after the influence of the event is eliminated.
Specifically, in the step (1), detecting whether the predicted reference traffic of the day of the event to be analyzed is within the actual reference traffic range may be implemented through the following processes:
service data corresponding to all event occurrence days in the historical service data are removed, and prediction reference service volume corresponding to the event occurrence days to be analyzed is determined according to the remaining historical service data after removal; determining an actual reference traffic range corresponding to the day of the event to be analyzed according to the basic service data, the service data fluctuation item and the service data random disturbance item of the day of the event to be analyzed; and comparing the predicted reference traffic with the actual reference traffic range to judge whether the predicted reference traffic is in the actual reference traffic range.
Specifically, in the embodiment of the present specification, the acquired historical service data is actually formed by actual traffic volume of each day — for example, if the acquired historical service data is historical service data of a month before the occurrence date of the event to be analyzed, the actually acquired historical service data is actual traffic volume corresponding to each day in the month before the occurrence date of the event to be analyzed. And if the historical service data has the event occurrence date, removing the actual service volume corresponding to each event occurrence date in the historical service data. For example, if the actual traffic volume is acquired 30 days before the occurrence date of the event to be analyzed and there are three event occurrence dates in the previous 30 days, the remaining historical traffic data after being removed is the actual traffic volume corresponding to each of the remaining 27 days.
Alternatively, in the embodiment of the present specification, the predicted reference traffic of the occurrence day of the event to be analyzed may be predicted according to the remaining historical traffic data by using a prediction algorithm existing in the prior art, such as a linear regression algorithm, a logistic regression algorithm, a K-nearest neighbor algorithm, and the like.
Specifically, in the embodiment of the present specification, the determining an actual reference service range corresponding to an event occurrence day to be analyzed according to basic service data, a service data fluctuation item, and a service data random disturbance item of the event occurrence day to be analyzed specifically includes the following processes:
calculating the product of the basic service data and the service data fluctuation item; determining the difference value of the product and the service data random disturbance item as the minimum value of an actual reference service volume range, and determining the sum value of the product and the service data random disturbance item as the maximum value of the actual reference service volume range; and determining the actual reference traffic range according to the minimum value of the actual reference traffic range and the maximum value of the actual reference traffic range.
That is, in the embodiment of the present specification, the actual reference traffic volume range corresponding to the occurrence day of the event to be analyzed may be calculated by the following formula:
basic service data business data fluctuation item +/-service data random disturbance item
And the basic service data fluctuation item and the service data random disturbance item are used as the maximum value of the actual reference traffic range.
After the prediction reference traffic and the actual reference traffic range corresponding to the date of the event to be analyzed are determined, judging whether the prediction reference traffic corresponding to the date of the event to be analyzed is in the actual reference traffic range, if so, indicating that the predicted reference traffic is reasonable; otherwise, it is not reasonable to consider predicting the reference traffic.
In the embodiment of the present specification, if the predicted reference traffic is reasonable, the traffic impact range generated by the event on the day of the event to be analyzed is determined according to the first impact range determination algorithm, otherwise, the traffic impact range generated by the event on the day of the event to be analyzed is determined according to the second impact range determination algorithm.
Specifically, in the embodiment of the present specification, determining, according to a first influence range determining algorithm, a traffic influence range generated by the event on the occurrence day of the event to be analyzed according to the actual traffic, the predicted reference traffic, and the random disturbance item of the traffic data of the event to be analyzed, specifically includes the following processes:
calculating the difference value between the actual traffic of the day of the event to be analyzed and the predicted reference traffic; determining the difference between the difference and the service data random disturbance item as the minimum value of the service volume influence range, and determining the sum of the difference and the service data random disturbance item as the maximum value of the service volume influence range; and determining the traffic influence range according to the minimum value of the traffic influence range and the maximum value of the traffic influence range.
That is, in the embodiment of the present specification, the influence of an event on the traffic of the event occurrence day to be analyzed can be calculated by the following formula:
industryThe traffic influence range (actual traffic-predicted reference traffic) ± service data random disturbance item
The method comprises the following steps that (actual service volume-predicted reference service volume) -service data random disturbance items are used as the minimum value of a service volume influence range, and (actual service volume-predicted reference service volume) + service data random disturbance items are used as the maximum value of the service volume influence range.
Optionally, in this embodiment of the present specification, the method for determining the service volume influence range generated by the event on the event occurrence day according to the second influence range determining algorithm, according to the actual service volume, the basic service data, the service data fluctuation item, and the service data random disturbance item on the event occurrence day to be analyzed, specifically includes the following steps:
calculating the product of basic service data and the service data fluctuation item, and calculating the difference value between the actual service volume and the product; determining the difference between the difference and the service data random disturbance item as the minimum value of the service volume influence range, and determining the sum of the difference and the service data random disturbance item as the maximum value of the service volume influence range; and determining the traffic influence range according to the minimum value of the traffic influence range and the maximum value of the traffic influence range.
That is, in the embodiment of the present specification, the influence of an event on the traffic of the event occurrence day to be analyzed can be calculated by the following formula:
traffic impact range (actual traffic-basic traffic data business data fluctuation item) ± random traffic data disturbance item
Wherein, (actual traffic-basic traffic data-traffic data fluctuation item) -traffic data random disturbance item is used as the minimum value of the traffic influence range,
and (actual traffic-basic traffic data-traffic data fluctuation item) + traffic data random disturbance item is used as the maximum value of the traffic influence range.
For the convenience of understanding the method provided by the embodiments of the present specification, the following description will take the target service as the traffic service as an example.
Fig. 3 is a second flowchart of a method for determining an influence of an event on traffic according to an embodiment of the present disclosure, where the method shown in fig. 3 at least includes the following steps:
step 302, obtaining historical traffic data corresponding to the traffic service from a database.
Wherein the historical traffic data comprises actual traffic volume per day.
And step 304, eliminating the traffic data of the incident day, the holiday and the key day in the historical traffic data.
And step 306, determining the actual traffic average value corresponding to all dates which are located in the previous month of the day of the event to be analyzed and belong to the same week number as the day of the event to be analyzed from the remaining historical traffic data after the elimination.
And 308, determining the average value of the actual telephone traffic as the basic telephone traffic of the day of the event to be analyzed.
Step 310, judging whether the occurrence day of the event to be analyzed is a key day; if yes, go to step 312; otherwise, step 314 is performed.
Step 312, according to the date information and the week information corresponding to the occurrence date of the event to be analyzed, searching the traffic data fluctuation item corresponding to the event to be analyzed from the pre-established first fluctuation item library.
Step 314, judging whether the occurrence day of the event to be analyzed is positioned in the first time period of the month to which the occurrence day of the event to be analyzed belongs; if yes, go to step 316; otherwise, step 318 is performed.
And step 316, searching the traffic data fluctuation item corresponding to the event occurrence day to be analyzed from a pre-established second fluctuation item library according to the month information to which the event occurrence day to be analyzed belongs.
Step 318, determining a first basic traffic volume average value corresponding to a week before the occurrence day of the event to be analyzed, and determining a second basic traffic volume average value corresponding to a week before the same date as the occurrence day of the event to be analyzed in the previous month.
And step 320, calculating the ratio of the first basic traffic volume average value to the second basic traffic volume average value, and determining the ratio as a traffic data fluctuation item corresponding to the day of the event to be analyzed.
Step 322, removing the holiday telephone traffic data in the historical telephone traffic data.
And step 324, determining all day telephone traffic which is positioned in two months before the occurrence date of the event to be analyzed and has the same week number as the occurrence date of the event to be analyzed from the remaining historical telephone traffic data after the elimination.
And step 326, eliminating the maximum value and the minimum value in the telephone traffic of all days, and determining the standard deviation of the telephone traffic of the remaining days as the telephone traffic data random disturbance item corresponding to the occurrence day of the event to be analyzed.
Step 328, detecting whether the predicted reference telephone traffic of the day of the event to be analyzed is within the actual reference telephone traffic range; if yes, go to step 330; otherwise, step 332 is performed.
And 330, determining a telephone traffic influence range generated by the event to the event occurrence day according to the actual telephone traffic of the event to be analyzed occurrence day, the predicted reference telephone traffic and the telephone traffic data random disturbance item and a first influence range determination algorithm.
And 332, determining a telephone traffic influence range generated by the telephone traffic of the event to be analyzed on the day of the event to be analyzed according to the second influence range determining algorithm according to the actual service volume of the day of the event to be analyzed, the basic telephone traffic data, the telephone traffic data fluctuation item and the telephone traffic data random disturbance item.
In the embodiment shown in fig. 3, steps 304 to 320 and steps 322 to 326 may be executed simultaneously, or may be executed in sequence, where steps 304 to 320 are executed first, and then steps 322 to 326 are executed, or steps 322 to 326 are executed first, and then steps 304 to 322 are executed. Fig. 3 is an exemplary illustration only of performing steps 304 to 320 and then performing steps 322 to 326, and does not limit the embodiments of the present disclosure.
Fig. 4 is a third flowchart of a method for determining an influence of an event on traffic according to an embodiment of the present disclosure, where the method shown in fig. 4 at least includes the following steps:
step 402, obtaining historical traffic data corresponding to traffic service from a database.
Wherein the historical traffic data comprises actual traffic volume per day.
And step 404, eliminating the traffic data of the incident day, the holiday and the key day in the historical traffic data.
And step 406, determining the actual traffic average value corresponding to all dates which are located in the previous month of the day of the event to be analyzed and belong to the same week number as the day of the event to be analyzed from the remaining historical traffic data after the elimination.
And step 408, determining the average value of the actual telephone traffic as the basic telephone traffic of the day of the event to be analyzed.
Step 410, judging whether the occurrence day of the event to be analyzed is a key day; if yes, go to step 412; otherwise, step 414 is performed.
Step 412, searching the traffic data fluctuation item corresponding to the event to be analyzed from the pre-established first fluctuation item library according to the date information and the week information corresponding to the occurrence date of the event to be analyzed.
And step 414, searching the traffic data fluctuation item corresponding to the event occurrence day to be analyzed from a pre-established second fluctuation item library according to the month information to which the event occurrence day to be analyzed belongs.
And step 416, removing the holiday traffic data in the historical traffic data.
And 418, determining all day telephone traffic which is positioned in two months before the occurrence date of the event to be analyzed and has the same week number as the occurrence date of the event to be analyzed from the remaining historical telephone traffic data after the elimination.
And step 420, eliminating the maximum value and the minimum value in the telephone traffic of all days, and determining the standard deviation of the telephone traffic of the remaining days as the telephone traffic data random disturbance item corresponding to the occurrence day of the event to be analyzed.
Step 422, detecting whether the predicted reference telephone traffic of the day of the event to be analyzed is within the actual reference telephone traffic range; if yes, go to step 424; otherwise, step 426 is performed.
Step 424, according to the actual telephone traffic of the event to be analyzed, the predicted reference telephone traffic and the random telephone traffic disturbance item, determining the traffic influence range of the event to be analyzed according to the first influence range determining algorithm.
And 426, determining a traffic influence range generated by the event on the service volume on the day of the event to be analyzed according to the second influence range determining algorithm according to the actual traffic volume on the day of the event to be analyzed, the basic traffic data, the traffic data fluctuation item and the traffic data random disturbance item.
The steps 404 to 414 and the steps 416 to 420 may be executed simultaneously, or may be executed in sequence, where the steps 404 to 414 may be executed first, and then the steps 416 to 420 may be executed, or the steps 416 to 420 may be executed first, and then the steps 404 to 414 may be executed. Fig. 4 is only an exemplary illustration of performing steps 404 to 414 first and then performing steps 416 to 420, and does not limit the embodiments of the present disclosure.
Fig. 5 is a fourth flowchart of a method for determining an influence of an event on traffic according to an embodiment of the present disclosure, where the method shown in fig. 5 at least includes the following steps:
step 502, obtaining historical traffic data corresponding to the traffic service from a database.
Wherein the historical traffic data comprises actual traffic volume per day.
And step 504, eliminating the traffic data of the incident day, the holiday and the key day in the historical traffic data.
Step 506, determining the actual traffic average value corresponding to all dates which are located in the previous month of the day of the event to be analyzed and belong to the same week number as the day of the event to be analyzed from the remaining historical traffic data after the elimination.
And step 508, determining the average value of the actual telephone traffic as the basic telephone traffic of the day of the event to be analyzed.
Step 510, judging whether the occurrence day of the event to be analyzed is a key day; if yes, go to step 512; otherwise, step 514 is performed.
And step 512, searching the traffic data fluctuation item corresponding to the event to be analyzed from a pre-established first fluctuation item library according to the date information and the week information corresponding to the occurrence date of the event to be analyzed.
Step 514, determining a first basic traffic volume average value corresponding to a week before the occurrence day of the event to be analyzed, and determining a second basic traffic volume average value corresponding to a week before the same date as the occurrence day of the event to be analyzed in the previous month.
And 516, calculating the ratio of the first basic traffic volume average value to the second basic traffic volume average value, and determining the ratio as a traffic data fluctuation item corresponding to the day of the event to be analyzed.
And step 518, removing the holiday traffic data in the historical traffic data.
And step 520, determining all day telephone traffic which is positioned in two months before the occurrence date of the event to be analyzed and has the same week number as the occurrence date of the event to be analyzed from the remaining historical telephone traffic data after the elimination.
And 522, eliminating the maximum value and the minimum value in the telephone traffic of all days, and determining the standard deviation of the telephone traffic of the remaining days as the telephone traffic data random disturbance item corresponding to the occurrence day of the event to be analyzed.
Step 524, detecting whether the predicted reference telephone traffic of the day of the event to be analyzed is within the actual reference telephone traffic range; if yes, go to step 526; otherwise, step 528 is performed.
Step 526, determining a telephone traffic influence range generated by the event to the event occurrence day according to the first influence range determining algorithm according to the actual telephone traffic, the predicted reference telephone traffic and the telephone traffic data random disturbance item of the event to be analyzed occurrence day.
And step 528, determining a telephone traffic influence range generated by the event to the telephone traffic of the event occurrence day to be analyzed according to the second influence range determining algorithm according to the actual service volume of the event occurrence day to be analyzed, the basic telephone traffic data, the telephone traffic data fluctuation item and the telephone traffic data random disturbance item.
The steps 504 to 516 and the steps 518 to 522 may be executed simultaneously, or may be executed in sequence, where the steps 504 to 516 are executed first, and then the steps 518 to 522 are executed, or the steps 518 to 522 are executed first, and then the steps 504 to 516 are executed. Fig. 5 is an exemplary illustration only of performing steps 504 to 516 first and then performing steps 518 to 522, and does not limit the embodiments of the present disclosure.
Determining basic service data, a service data fluctuation item and a service data random disturbance item corresponding to the date of the event to be analyzed according to the acquired historical service data, and then determining the influence of the event on the traffic of the date of the event to be analyzed by using a set influence determination algorithm based on the basic service data, the service data fluctuation item and the service data random disturbance item; according to the scheme of the embodiment, only historical service data are acquired from the database, the influence of events on the service volume can be determined according to the historical service data, a large amount of resources are not required to be consumed, various data are acquired from various channels, and the operation is simple and convenient; in addition, the influence of the event on the service volume is automatically determined through the set influence algorithm, a large amount of human resources do not need to be consumed, the efficiency and the accuracy are high, the influence generated by the event can be quickly positioned, data assistance can be timely provided for a service party, correction can be conveniently carried out in the next service prediction, and the influence on service indexes due to service prediction deviation is reduced.
Corresponding to the method provided by the embodiments shown in fig. 1 to fig. 5 in the embodiments of the present specification, based on the same idea, an embodiment of the present specification further provides a device for determining an influence range of an event on traffic, for performing the method provided by the embodiments shown in fig. 1 to fig. 5 in the present specification, fig. 6 is a schematic diagram of module composition of the device for determining an influence range of an event on traffic provided by the embodiments of the present specification, and the device shown in fig. 6 at least includes:
a first obtaining module 602, configured to obtain historical service data corresponding to a target service from a database; wherein the historical traffic data comprises actual traffic volume per day for the target traffic;
a second obtaining module 604, configured to obtain basic service data of a day of an event to be analyzed according to the historical service data; the basic service data are service data after the influences of events and special days are eliminated; the special days comprise holidays and key days; the key day is the occurrence day of a periodic event;
a first determining module 606, configured to determine, according to the historical service data and according to a first set rule, a service data fluctuation item corresponding to the occurrence day of the event to be analyzed; determining a service data random disturbance item corresponding to the occurrence day of the event to be analyzed according to the historical service data and a second set rule;
the second determining module 608 determines, according to the basic service data, the service data fluctuation item, and the service data random disturbance item, an influence of the event on the traffic of the event occurrence day to be analyzed by using a set influence determining algorithm.
Optionally, the second determining module 608 includes:
the detection unit is used for detecting whether the predicted reference traffic of the day of the event to be analyzed is within the actual reference traffic range; the reference traffic is traffic after eliminating the influence generated by the event;
a first determining unit, configured to determine, according to a first influence range determining algorithm, a traffic influence range, generated by the event on traffic of the event to be analyzed on the occurrence day of the event, if the predicted reference traffic of the event to be analyzed on the occurrence day is within an actual reference traffic range, according to the actual traffic of the event to be analyzed on the occurrence day, the predicted reference traffic, and the traffic data random disturbance item;
and if the predicted reference quantity of the day of the event to be analyzed is not within the actual reference traffic range, determining a traffic influence range of the event on the traffic of the day of the event to be analyzed according to a second influence range determination algorithm according to the actual traffic of the day of the event to be analyzed, the basic traffic data, the traffic data fluctuation item and the traffic data random disturbance item.
Optionally, the detection unit is specifically configured to:
service data corresponding to all event occurrence days in the historical service data are removed, and prediction reference service volume corresponding to the event occurrence days to be analyzed is determined according to the remaining historical service data after removal; determining an actual reference traffic volume range corresponding to the day of the event to be analyzed according to the basic service data of the day of the event to be analyzed, the service data fluctuation item and the service data random disturbance item; and comparing the predicted reference traffic with the actual reference traffic range to judge whether the predicted reference traffic is in the actual reference traffic range.
Optionally, the detection unit is specifically configured to:
calculating the product of the basic service data and the service data fluctuation item; determining the difference value of the product and the service data random disturbance item as the minimum value of the actual reference service volume range, and determining the sum value of the product and the service data random disturbance item as the maximum value of the actual reference service volume range; and determining the actual reference service volume range according to the minimum value of the actual reference service volume range and the maximum value of the actual reference service volume range.
Optionally, the first determining unit is specifically configured to:
calculating the difference value between the actual traffic and the predicted reference traffic of the day of the event to be analyzed; determining the difference value of the difference value and the service data random disturbance item as the minimum value of the service volume influence range, and determining the sum value of the difference value and the service data random disturbance item as the maximum value of the service volume influence range; and determining the business volume influence range according to the minimum value of the business volume influence range and the maximum value of the business volume influence range.
Optionally, the second determining unit is specifically configured to:
calculating a product of the basic service data and the service data fluctuation item, and calculating a difference value between the actual service volume and the product; determining the difference value of the difference value and the service data random disturbance item as the minimum value of the service volume influence range, and determining the sum value of the difference value and the service data random disturbance item as the maximum value of the service volume influence range; and determining the business volume influence range according to the minimum value of the business volume influence range and the maximum value of the business volume influence range.
Optionally, the second obtaining module 604 includes:
the first removing unit is used for removing the service data of the event occurrence date and the special date in the historical service data;
a third determining unit, configured to determine, from the remaining historical service data after the elimination, a service data mean value corresponding to all dates which are located in a time node before the occurrence date of the event to be analyzed and have the same week number as the occurrence date of the event to be analyzed;
and the fourth determining unit is used for determining the average value of the service data as the basic service data.
Optionally, the first determining module 606 includes:
the first judging unit is used for judging whether the occurrence day of the event to be analyzed is the key day;
a first searching unit, configured to search, if the event to be analyzed occurs on the key day, a service data fluctuation item corresponding to the event to be analyzed on the day from a pre-established first fluctuation item library according to date information corresponding to the event to be analyzed and week information corresponding to the event to be analyzed; the first fluctuation item library stores mapping relations of date information, week information and business data fluctuation items of each key day;
a second searching unit, configured to search, according to month information corresponding to the occurrence day of the event to be analyzed, a service data fluctuation item corresponding to the occurrence day of the event to be analyzed from a second fluctuation item library established in advance, if the occurrence day of the event to be analyzed is not the key day; and the second fluctuation item library stores the mapping relation between the month information and the business data fluctuation items.
Optionally, the first determining module 606 includes:
the second judging unit is used for judging whether the day of the event to be analyzed is the key day;
a third searching unit, configured to search, if the date of the event to be analyzed is the key date, a service data fluctuation item corresponding to the date of the event to be analyzed from a pre-established first fluctuation item library according to date information corresponding to the date of the event to be analyzed and week information corresponding to the date of the event to be analyzed; the first fluctuation item library stores mapping relations of date information, week information and business data fluctuation items of each key day;
a third judging unit, configured to judge whether the event day to be analyzed is located in the first time period of the month to which the event day to be analyzed belongs if the event day to be analyzed is not the key day; wherein a previous week of each date in the first time period contains a date of a month previous to the current month;
a fourth searching unit, configured to search, according to month information to which the to-be-analyzed event day belongs, a service data fluctuation item corresponding to the to-be-analyzed event day from a second fluctuation item library established in advance, if the to-be-analyzed event day is located in the first time period;
a fifth location determining unit, configured to determine, if the to-be-analyzed event occurrence day is not in the first time period, a first basic service data mean value corresponding to a previous period of the to-be-analyzed event occurrence day, and determine, in a previous month, a second basic service data mean value corresponding to a previous period of the same date as the to-be-analyzed event occurrence day, and determine a ratio of the first basic service data mean value to the second basic service data mean value as the service data fluctuation item corresponding to the to-be-analyzed event occurrence day; wherein, the second fluctuation item library stores the mapping relationship between the month information and the business data fluctuation items
Optionally, the apparatus provided in this specification further includes:
the first establishing module is used for calculating the mean value of basic service data of all days which are located in a time node before the key day and belong to the same week number as the key day aiming at each key day corresponding to the target service; calculating the ratio of the basic service data of the key day to the average value, and taking the ratio as a service data fluctuation item corresponding to the key day; and correspondingly storing the date information of the key days, the week information corresponding to the key days and the business data fluctuation items into the first fluctuation item library.
Optionally, the apparatus provided in this specification further includes:
the second establishing module is used for eliminating the business data of the holidays in the historical business data;
calculating the average value of daily actual business volume corresponding to each month according to the remaining historical business data after elimination;
determining the ratio of the average value of the actual daily traffic corresponding to the current month to the average value of the actual daily traffic corresponding to the previous month as a business data fluctuation item corresponding to the current month;
and correspondingly storing the month information and the service data fluctuation items into the second fluctuation item library.
Optionally, the first determining module 606 further includes:
the second eliminating unit is used for eliminating the holiday business data in the historical business data;
a sixth determining unit, configured to determine, from the remaining historical service data after the elimination, traffic volumes of all dates that are within a second set time period before the occurrence date of the event to be analyzed and are the same as the number of weeks of the occurrence date of the event to be analyzed; and determining the standard deviation of all the traffic in the day period as the random disturbance item of the traffic data.
In this specification, the provided device for determining the influence of the event on the traffic may also execute the method executed by the device for determining the influence of the event on the traffic in fig. 1 to 5, and implement the function of the device for determining the influence of the event on the traffic in the embodiment shown in fig. 1 to 5, which is not described herein again.
The device for determining the influence of an event on the traffic, which is provided in the embodiment of the present specification, determines, according to the obtained historical service data, basic service data, a service data fluctuation item, and a service data random disturbance item corresponding to an event occurrence day to be analyzed, and then determines, based on the basic service data, the service data fluctuation item, and the service data random disturbance item, the influence of the event on the traffic of the event occurrence day to be analyzed by using a set influence determination algorithm; according to the scheme of the embodiment, only historical service data are acquired from the database, the influence of events on the service volume can be determined according to the historical service data, a large amount of resources are not required to be consumed, various data are acquired from various channels, and the operation is simple and convenient; in addition, the influence of the event on the service volume is automatically determined through the set influence algorithm, a large amount of human resources do not need to be consumed, the efficiency and the accuracy are high, the influence generated by the event can be quickly positioned, data assistance can be timely provided for a service party, correction can be conveniently carried out in the next service prediction, and the influence on service indexes due to service prediction deviation is reduced.
Further, based on the methods shown in fig. 1 to fig. 5, an embodiment of the present specification further provides a device for determining an influence of an event on traffic, as shown in fig. 7.
The device for determining the influence of events on traffic may vary greatly due to different configurations or performances, and may include one or more processors 701 and a memory 702, where one or more stored applications or data may be stored in the memory 702. Memory 702 may be, among other things, transient storage or persistent storage. The application program stored in memory 702 may include one or more modules (not shown), each of which may include a series of computer-executable instruction information in a determining device for the impact of an event on traffic. Still further, the processor 701 may be configured to communicate with the memory 702 to execute a series of computer-executable instruction information in the memory 702 on a device that determines the impact of an event on traffic. The apparatus for determining the impact of events on traffic may also include one or more power supplies 703, one or more wired or wireless network interfaces 704, one or more input-output interfaces 705, one or more keyboards 706, and the like.
In a particular embodiment, an apparatus for determining an impact of an event on traffic comprises a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may comprise one or more modules, and each module may comprise a series of computer-executable instruction information in the apparatus for determining an impact of an event on traffic, and the one or more programs configured to be executed by one or more processors comprise computer-executable instruction information for:
acquiring historical service data corresponding to a target service from a database; wherein the historical traffic data comprises actual traffic volume per day for the target traffic;
acquiring basic service data of the day of the event to be analyzed according to the historical service data; the basic service data are service data after the influences of events and special days are eliminated; the special days comprise holidays and key days; the key day is the occurrence day of a periodic event;
determining a business data fluctuation item corresponding to the occurrence date of the event to be analyzed according to the historical business data and a first set rule; determining a service data random disturbance item corresponding to the occurrence day of the event to be analyzed according to the historical service data and a second set rule;
and determining the influence of the event on the traffic of the day of the event to be analyzed by using a set influence determination algorithm according to the basic service data, the service data fluctuation item and the service data random disturbance item.
Optionally, when executed, the determining, by using a set influence determination algorithm, an influence of the event on the traffic of the event day to be analyzed according to the basic service data, the service data fluctuation item, and the service data random disturbance item includes:
detecting whether the predicted reference traffic of the day of the event to be analyzed is within an actual reference traffic range; the reference traffic is traffic after eliminating the influence generated by the event;
if so, determining a traffic influence range of the event on the traffic of the event occurrence day to be analyzed according to the actual traffic of the event occurrence day to be analyzed, the predicted reference traffic and the traffic data random disturbance item and a first influence range determination algorithm;
otherwise, determining a traffic influence range of the event on the traffic of the event occurrence day to be analyzed according to a second influence range determining algorithm according to the actual traffic of the event occurrence day to be analyzed, the basic traffic data, the traffic data fluctuation item and the traffic data random disturbance item.
Optionally, when the computer-executable instruction information is executed, the detecting whether the predicted reference traffic of the day of the event to be analyzed is within an actual reference traffic range includes:
service data corresponding to all event occurrence days in the historical service data are removed, and prediction reference service volume corresponding to the event occurrence days to be analyzed is determined according to the remaining historical service data after removal;
determining an actual reference traffic volume range corresponding to the day of the event to be analyzed according to the basic service data of the day of the event to be analyzed, the service data fluctuation item and the service data random disturbance item;
and comparing the predicted reference traffic with the actual reference traffic range to judge whether the predicted reference traffic is in the actual reference traffic range.
Optionally, when the computer-executable instruction information is executed, the determining, according to the basic service data of the event to be analyzed on the occurrence day, the service data fluctuation item, and the service data random disturbance item, an actual reference traffic volume range corresponding to the event to be analyzed on the occurrence day includes:
calculating the product of the basic service data and the service data fluctuation item;
determining the difference value of the product and the service data random disturbance item as the minimum value of the actual reference service volume range, and determining the sum value of the product and the service data random disturbance item as the maximum value of the actual reference service volume range;
and determining the actual reference service volume range according to the minimum value of the actual reference service volume range and the maximum value of the actual reference service volume range.
Optionally, when executed, the determining, according to a first influence range determining algorithm, a traffic influence range of the event on the traffic of the event occurrence day to be analyzed according to the actual traffic of the event occurrence day to be analyzed, the predicted reference traffic, and the traffic data random disturbance item includes:
calculating the difference value between the actual traffic and the predicted reference traffic of the day of the event to be analyzed;
determining the difference value of the difference value and the service data random disturbance item as the minimum value of the service volume influence range, and determining the sum value of the difference value and the service data random disturbance item as the maximum value of the service volume influence range;
and determining the business volume influence range according to the minimum value of the business volume influence range and the maximum value of the business volume influence range.
Optionally, when the computer-executable instruction information is executed, the determining, according to the actual traffic of the event to be analyzed on the occurrence day, the basic service data, the service data fluctuation item, and the service data random disturbance item, a traffic influence range generated by the event on the traffic of the event to be analyzed on the occurrence day according to a second influence range determining algorithm includes:
calculating a product of the basic service data and the service data fluctuation item, and calculating a difference value between the actual service volume and the product;
determining the difference value of the difference value and the service data random disturbance item as the minimum value of the service volume influence range, and determining the sum value of the difference value and the service data random disturbance item as the maximum value of the service volume influence range;
and determining the business volume influence range according to the minimum value of the business volume influence range and the maximum value of the business volume influence range.
Optionally, when the computer-executable instruction information is executed, the obtaining, according to the historical service data, basic service data corresponding to an event occurrence day to be analyzed includes:
service data of an event occurrence day and a special day in the historical service data are removed;
determining the average value of the service data corresponding to all dates which are positioned in a time node before the occurrence date of the event to be analyzed and belong to the same week number as the occurrence date of the event to be analyzed from the remaining historical service data after the elimination;
and determining the average value of the service data as the basic service data.
Optionally, when the computer-executable instruction information is executed, the determining, according to the historical service data and according to a first set rule, a service data fluctuation item corresponding to the occurrence day of the event to be analyzed includes:
judging whether the occurrence day of the event to be analyzed is the key day;
if so, searching a business data fluctuation item corresponding to the occurrence date of the event to be analyzed from a pre-established first fluctuation item library according to date information corresponding to the occurrence date of the event to be analyzed and week information corresponding to the occurrence date of the event to be analyzed; the first fluctuation item library stores mapping relations of date information, week information and business data fluctuation items of each key day;
otherwise, searching a business data fluctuation item corresponding to the occurrence day of the event to be analyzed from a pre-established second fluctuation item library according to the month information corresponding to the occurrence day of the event to be analyzed; and the second fluctuation item library stores the mapping relation between the month information and the business data fluctuation items.
Optionally, when the computer-executable instruction information is executed, the determining, according to the historical service data and according to a first set rule, a service data fluctuation item corresponding to the occurrence day of the event to be analyzed includes:
judging whether the occurrence day of the event to be analyzed is the key day;
if the event occurrence day to be analyzed is the key day, searching a business data fluctuation item corresponding to the event occurrence day to be analyzed from a pre-established first fluctuation item library according to date information corresponding to the event occurrence day to be analyzed and week information corresponding to the event occurrence day to be analyzed; the first fluctuation item library stores mapping relations of date information, week information and business data fluctuation items of each key day;
if the to-be-analyzed event occurrence day is not the key day, judging whether the to-be-analyzed event occurrence day is located in a first time period of a month to which the to-be-analyzed event occurrence day belongs; wherein a previous week of each date in the first time period contains a date of a month previous to the current month;
if the occurrence day of the event to be analyzed is located in the first time period, searching a business data fluctuation item corresponding to the occurrence day of the event to be analyzed from a pre-established second fluctuation item library according to the month information to which the occurrence day of the event to be analyzed belongs; otherwise, determining a first basic service data mean value corresponding to a previous period of the day of the event to be analyzed, determining a second basic service data mean value corresponding to a previous period of the same day as the day of the event to be analyzed in the last month, and determining the ratio of the first basic service data mean value to the second basic service data mean value as the service data fluctuation item corresponding to the day of the event to be analyzed; wherein, the second fluctuation item library stores the mapping relationship between the month information and the business data fluctuation items
Optionally, the computer-executable instruction information, when executed, establishes the first fluctuation item library by:
calculating the average value of basic service data of all dates which are located in a time node before the key date and belong to the same week number with the key date aiming at each key date corresponding to the target service;
calculating the ratio of the basic service data of the key day to the average value, and taking the ratio as a service data fluctuation item corresponding to the key day;
and correspondingly storing the date information of the key days, the week information corresponding to the key days and the business data fluctuation items into the first fluctuation item library.
Optionally, the computer-executable instruction information, when executed, establishes the second fluctuation item library by:
eliminating the business data of the holidays in the historical business data;
calculating the average value of daily actual business volume corresponding to each month according to the remaining historical business data after elimination;
determining the ratio of the average value of the actual daily traffic corresponding to the current month to the average value of the actual daily traffic corresponding to the previous month as a business data fluctuation item corresponding to the current month;
and correspondingly storing the month information and the service data fluctuation items into the second fluctuation item library.
Optionally, when the computer-executable instruction information is executed, the determining, according to the historical service data and according to a second set rule, a service data random disturbance item corresponding to the occurrence day of the event to be analyzed includes:
removing holiday business data in the historical business data;
determining all daily traffic which is located in a second set time period before the occurrence date of the event to be analyzed and is the same as the week number of the occurrence date of the event to be analyzed from the remaining historical service data after the elimination;
and determining the standard deviation of all the traffic in the day period as the random disturbance item of the traffic data.
The device for determining the influence of the event on the traffic, which is provided in the embodiment of the present specification, determines, according to the obtained historical service data, basic service data, a service data fluctuation item, and a service data random disturbance item corresponding to an event occurrence day to be analyzed, and then determines, based on the basic service data, the service data fluctuation item, and the service data random disturbance item, the influence of the event on the traffic of the event occurrence day to be analyzed by using a set influence determination algorithm; according to the scheme of the embodiment, only historical service data are acquired from the database, the influence of events on the service volume can be determined according to the historical service data, a large amount of resources are not required to be consumed, various data are acquired from various channels, and the operation is simple and convenient; in addition, the influence of the event on the service volume is automatically determined through the set influence algorithm, a large amount of human resources do not need to be consumed, the efficiency and the accuracy are high, the influence generated by the event can be quickly positioned, data assistance can be timely provided for a service party, correction can be conveniently carried out in the next service prediction, and the influence on service indexes due to service prediction deviation is reduced.
Further, based on the methods shown in fig. 1 to fig. 5, in a specific embodiment, the storage medium may be a usb disk, an optical disk, a hard disk, or the like, and when executed by a processor, the storage medium stores computer-executable instruction information that implements the following processes:
acquiring historical service data corresponding to a target service from a database; wherein the historical traffic data comprises actual traffic volume per day for the target traffic;
acquiring basic service data of the day of the event to be analyzed according to the historical service data; the basic service data are service data after the influences of events and special days are eliminated; the special days comprise holidays and key days, and the key days are the occurrence days of the periodic events;
determining a business data fluctuation item corresponding to the occurrence date of the event to be analyzed according to the historical business data and a first set rule; determining a service data random disturbance item corresponding to the occurrence day of the event to be analyzed according to the historical service data and a second set rule;
and determining the influence of the event on the traffic of the day of the event to be analyzed by using a set influence determination algorithm according to the basic service data, the service data fluctuation item and the service data random disturbance item.
Optionally, when executed by a processor, the determining, by using a set influence determination algorithm, an influence of the event on the traffic of the event occurrence day to be analyzed according to the basic service data, the service data fluctuation item, and the service data random disturbance item includes:
detecting whether the predicted reference traffic of the day of the event to be analyzed is within an actual reference traffic range; the reference traffic is traffic after eliminating the influence generated by the event;
if so, determining a traffic influence range of the event on the traffic of the event occurrence day to be analyzed according to the actual traffic of the event occurrence day to be analyzed, the predicted reference traffic and the traffic data random disturbance item and a first influence range determination algorithm;
otherwise, determining a traffic influence range of the event on the traffic of the event occurrence day to be analyzed according to a second influence range determining algorithm according to the actual traffic of the event occurrence day to be analyzed, the basic traffic data, the traffic data fluctuation item and the traffic data random disturbance item.
Optionally, the computer-executable instruction information stored in the storage medium, when executed by the processor, detects whether the predicted reference traffic of the day of the event to be analyzed is within an actual reference traffic range, and includes:
service data corresponding to all event occurrence days in the historical service data are removed, and prediction reference service volume corresponding to the event occurrence days to be analyzed is determined according to the remaining historical service data after removal;
determining an actual reference traffic volume range corresponding to the day of the event to be analyzed according to the basic service data of the day of the event to be analyzed, the service data fluctuation item and the service data random disturbance item;
and comparing the predicted reference traffic with the actual reference traffic range to judge whether the predicted reference traffic is in the actual reference traffic range.
Optionally, when the computer-executable instruction information stored in the storage medium is executed by the processor, determining an actual reference traffic volume range corresponding to the occurrence day of the event to be analyzed according to the basic service data of the occurrence day of the event to be analyzed, the service data fluctuation item, and the service data random disturbance item, includes:
calculating the product of the basic service data and the service data fluctuation item;
determining the difference value of the product and the service data random disturbance item as the minimum value of the actual reference service volume range, and determining the sum value of the product and the service data random disturbance item as the maximum value of the actual reference service volume range;
and determining the actual reference service volume range according to the minimum value of the actual reference service volume range and the maximum value of the actual reference service volume range.
Optionally, when executed by a processor, the determining, according to a first influence range determining algorithm, a traffic influence range of the event on the traffic of the event occurrence day to be analyzed according to the actual traffic of the event occurrence day to be analyzed, the predicted reference traffic, and the traffic data random disturbance item, includes:
calculating the difference value between the actual traffic and the predicted reference traffic of the day of the event to be analyzed;
determining the difference value of the difference value and the service data random disturbance item as the minimum value of the service volume influence range, and determining the sum value of the difference value and the service data random disturbance item as the maximum value of the service volume influence range;
and determining the business volume influence range according to the minimum value of the business volume influence range and the maximum value of the business volume influence range.
Optionally, when executed by a processor, the determining, according to a second influence range determining algorithm, a traffic influence range of the event on the traffic of the event occurrence day to be analyzed according to the actual traffic of the event occurrence day to be analyzed, the basic traffic data, the traffic data fluctuation item, and the traffic data random disturbance item, includes:
calculating a product of the basic service data and the service data fluctuation item, and calculating a difference value between the actual service volume and the product;
determining the difference value of the difference value and the service data random disturbance item as the minimum value of the service volume influence range, and determining the sum value of the difference value and the service data random disturbance item as the maximum value of the service volume influence range;
and determining the business volume influence range according to the minimum value of the business volume influence range and the maximum value of the business volume influence range.
Optionally, when the computer-executable instruction information stored in the storage medium is executed by the processor, the obtaining, according to the historical service data, basic service data corresponding to an event occurrence day to be analyzed includes:
service data of an event occurrence day and a special day in the historical service data are removed;
determining the average value of the service data corresponding to all dates which are positioned in a time node before the occurrence date of the event to be analyzed and belong to the same week number as the occurrence date of the event to be analyzed from the remaining historical service data after the elimination;
and determining the average value of the service data as the basic service data.
Optionally, when the computer-executable instruction information stored in the storage medium is executed by the processor, the determining, according to the historical service data and according to a first set rule, a service data fluctuation item corresponding to the occurrence day of the event to be analyzed includes:
judging whether the occurrence day of the event to be analyzed is the key day;
if so, searching a business data fluctuation item corresponding to the occurrence date of the event to be analyzed from a pre-established first fluctuation item library according to date information corresponding to the occurrence date of the event to be analyzed and week information corresponding to the occurrence date of the event to be analyzed; the first fluctuation item library stores mapping relations of date information, week information and business data fluctuation items of each key day;
otherwise, searching a business data fluctuation item corresponding to the occurrence day of the event to be analyzed from a pre-established second fluctuation item library according to the month information corresponding to the occurrence day of the event to be analyzed; and the second fluctuation item library stores the mapping relation between the month information and the business data fluctuation items.
Optionally, when the computer-executable instruction information stored in the storage medium is executed by the processor, the determining, according to the historical service data and according to a first set rule, a service data fluctuation item corresponding to the occurrence day of the event to be analyzed includes:
judging whether the occurrence day of the event to be analyzed is the key day;
if the event occurrence day to be analyzed is the key day, searching a business data fluctuation item corresponding to the event occurrence day to be analyzed from a pre-established first fluctuation item library according to date information corresponding to the event occurrence day to be analyzed and week information corresponding to the event occurrence day to be analyzed; the first fluctuation item library stores mapping relations of date information, week information and business data fluctuation items of each key day;
if the to-be-analyzed event occurrence day is not the key day, judging whether the to-be-analyzed event occurrence day is located in a first time period of a month to which the to-be-analyzed event occurrence day belongs; wherein a previous week of each date in the first time period contains a date of a month previous to the current month;
if the occurrence day of the event to be analyzed is located in the first time period, searching a business data fluctuation item corresponding to the occurrence day of the event to be analyzed from a pre-established second fluctuation item library according to the month information to which the occurrence day of the event to be analyzed belongs; otherwise, determining a first basic service data mean value corresponding to a previous period of the day of the event to be analyzed, determining a second basic service data mean value corresponding to a previous period of the same day as the day of the event to be analyzed in the last month, and determining the ratio of the first basic service data mean value to the second basic service data mean value as the service data fluctuation item corresponding to the day of the event to be analyzed; wherein, the second fluctuation item library stores the mapping relationship between the month information and the business data fluctuation items
Optionally, the storage medium stores computer-executable instruction information that, when executed by the processor, establishes the first fluctuation item library by:
calculating the average value of basic service data of all dates which are located in a time node before the key date and belong to the same week number with the key date aiming at each key date corresponding to the target service;
calculating the ratio of the basic service data of the key day to the average value, and taking the ratio as a service data fluctuation item corresponding to the key day;
and correspondingly storing the date information of the key days, the week information corresponding to the key days and the business data fluctuation items into the first fluctuation item library.
Optionally, the storage medium stores computer-executable instruction information that, when executed by the processor, establishes the second fluctuation item library by:
eliminating the business data of the holidays in the historical business data;
calculating the average value of daily actual business volume corresponding to each month according to the remaining historical business data after elimination;
determining the ratio of the average value of the actual daily traffic corresponding to the current month to the average value of the actual daily traffic corresponding to the previous month as a business data fluctuation item corresponding to the current month;
and correspondingly storing the month information and the service data fluctuation items into the second fluctuation item library.
Optionally, when the computer-executable instruction information stored in the storage medium is executed by the processor, the determining, according to the historical service data and according to a second set rule, a service data random disturbance item corresponding to the day of the event to be analyzed includes:
removing holiday business data in the historical business data;
determining all daily traffic which is located in a second set time period before the occurrence date of the event to be analyzed and is the same as the week number of the occurrence date of the event to be analyzed from the remaining historical service data after the elimination;
and determining the standard deviation of all the traffic in the day period as the random disturbance item of the traffic data.
When the computer-executable instruction information stored in the storage medium provided in the embodiment of the present specification is executed by a processor, the basic service data, the service data fluctuation item, and the service data random disturbance item corresponding to the day of the event to be analyzed are determined according to the obtained historical service data, and then, based on the basic service data, the service data fluctuation item, and the service data random disturbance item, the influence of the event on the traffic of the day of the event to be analyzed is determined by using a set influence determination algorithm; according to the scheme of the embodiment, only historical service data are acquired from the database, the influence of events on the service volume can be determined according to the historical service data, a large amount of resources are not required to be consumed, various data are acquired from various channels, and the operation is simple and convenient; in addition, the influence of the event on the service volume is automatically determined through the set influence algorithm, a large amount of human resources do not need to be consumed, the efficiency and the accuracy are high, the influence generated by the event can be quickly positioned, data assistance can be timely provided for a service party, correction can be conveniently carried out in the next service prediction, and the influence on service indexes due to service prediction deviation is reduced.
In the 90 th generation of 20 th century, it is obvious that improvements in Hardware (for example, improvements in Circuit structures such as diodes, transistors and switches) or software (for improvement in method flow) can be distinguished for a technical improvement, however, as technology develops, many of the improvements in method flow today can be regarded as direct improvements in Hardware Circuit structures, designers almost all obtain corresponding Hardware Circuit structures by Programming the improved method flow into Hardware circuits, and therefore, it cannot be said that an improvement in method flow cannot be realized by Hardware entity modules, for example, Programmable logic devices (Programmable logic devices L organic devices, P L D) (for example, Field Programmable Gate Arrays (FPGAs) are integrated circuits whose logic functions are determined by user Programming of devices), and a digital system is "integrated" on a P L D "by self Programming of designers without requiring many kinds of integrated circuits manufactured and manufactured by special chip manufacturers to design and manufacture, and only a Hardware software is written in Hardware programs such as Hardware programs, software programs, such as Hardware programs, software, Hardware programs, software programs, Hardware programs, software, Hardware programs, software, Hardware programs, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software.
A controller may be implemented in any suitable manner, e.g., in the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, Application Specific Integrated Circuits (ASICs), programmable logic controllers (PLC's) and embedded microcontrollers, examples of which include, but are not limited to, microcontrollers 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone L abs C8051F320, which may also be implemented as part of the control logic of a memory.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may 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, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the specification. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instruction information. These computer program instruction information may 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 instruction information executed by the processor of the computer or other programmable data processing apparatus produce means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instruction information may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instruction information stored in the computer-readable memory produce an article of manufacture including instruction information means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instruction information may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instruction information executed on the computer or other programmable apparatus provides steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instruction information, data structures, modules of a program, 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 technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may 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, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instruction information, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims (21)

1. A method of determining the impact of an event on traffic, the method comprising:
acquiring historical service data corresponding to a target service from a database; wherein the historical traffic data comprises actual traffic volume per day for the target traffic;
acquiring basic service data of the day of the event to be analyzed according to the historical service data; the basic service data are service data after the influences of events and special days are eliminated; the special days comprise holidays and key days, and the key days are the occurrence days of the periodic events;
determining a business data fluctuation item corresponding to the occurrence date of the event to be analyzed according to the historical business data and a first set rule; determining a service data random disturbance item corresponding to the occurrence day of the event to be analyzed according to the historical service data and a second set rule;
and determining the influence of the event on the traffic of the day of the event to be analyzed by using a set influence determination algorithm according to the basic service data, the service data fluctuation item and the service data random disturbance item.
2. The method of claim 1, wherein the determining, according to the basic service data, the service data fluctuation item and the service data random disturbance item, the influence of the event on the traffic of the day of the event to be analyzed by using a set influence determination algorithm comprises:
detecting whether the predicted reference traffic of the day of the event to be analyzed is within an actual reference traffic range; the reference traffic is traffic after eliminating the influence generated by the event;
if so, determining a traffic influence range of the event on the traffic of the event occurrence day to be analyzed according to the actual traffic of the event occurrence day to be analyzed, the predicted reference traffic and the traffic data random disturbance item and a first influence range determination algorithm;
otherwise, determining a traffic influence range of the event on the traffic of the event occurrence day to be analyzed according to a second influence range determining algorithm according to the actual traffic of the event occurrence day to be analyzed, the basic traffic data, the traffic data fluctuation item and the traffic data random disturbance item.
3. The method of claim 2, wherein the detecting whether the predicted benchmark traffic for the day of the event to be analyzed is within an actual benchmark traffic range comprises:
service data corresponding to all event occurrence days in the historical service data are removed, and prediction reference service volume corresponding to the event occurrence days to be analyzed is determined according to the remaining historical service data after removal;
determining an actual reference traffic volume range corresponding to the day of the event to be analyzed according to the basic service data of the day of the event to be analyzed, the service data fluctuation item and the service data random disturbance item;
and comparing the predicted reference traffic with the actual reference traffic range to judge whether the predicted reference traffic is in the actual reference traffic range.
4. The method according to claim 3, wherein the determining an actual reference traffic volume range corresponding to the occurrence day of the event to be analyzed according to the basic traffic data, the traffic data fluctuation item, and the traffic data random disturbance item of the occurrence day of the event to be analyzed comprises:
calculating the product of the basic service data and the service data fluctuation item;
determining the difference value of the product and the service data random disturbance item as the minimum value of the actual reference service volume range, and determining the sum value of the product and the service data random disturbance item as the maximum value of the actual reference service volume range;
and determining the actual reference service volume range according to the minimum value of the actual reference service volume range and the maximum value of the actual reference service volume range.
5. The method of claim 2, wherein the determining, according to the actual traffic volume of the event to be analyzed on the occurrence day, the predicted reference traffic volume, and the traffic data random disturbance term, a traffic volume influence range of the event on the traffic volume of the event to be analyzed according to a first influence range determination algorithm comprises:
calculating the difference value between the actual traffic and the predicted reference traffic of the day of the event to be analyzed;
determining the difference value of the difference value and the service data random disturbance item as the minimum value of the service volume influence range, and determining the sum value of the difference value and the service data random disturbance item as the maximum value of the service volume influence range;
and determining the business volume influence range according to the minimum value of the business volume influence range and the maximum value of the business volume influence range.
6. The method of claim 2, wherein the determining, according to a second influence range determining algorithm, a traffic influence range of the event on the traffic of the event occurrence day to be analyzed according to the actual traffic of the event occurrence day to be analyzed, the basic traffic data, the traffic data fluctuation item, and the traffic data random disturbance item, comprises:
calculating a product of the basic service data and the service data fluctuation item, and calculating a difference value between the actual service volume and the product;
determining the difference value of the difference value and the service data random disturbance item as the minimum value of the service volume influence range, and determining the sum value of the difference value and the service data random disturbance item as the maximum value of the service volume influence range;
and determining the business volume influence range according to the minimum value of the business volume influence range and the maximum value of the business volume influence range.
7. The method according to claim 1, wherein the obtaining of the basic service data corresponding to the occurrence day of the event to be analyzed according to the historical service data comprises:
service data of an event occurrence day and a special day in the historical service data are removed;
determining the average value of the service data corresponding to all dates which are positioned in a time node before the occurrence date of the event to be analyzed and belong to the same week number as the occurrence date of the event to be analyzed from the remaining historical service data after the elimination;
and determining the average value of the service data as the basic service data.
8. The method according to claim 1, wherein the determining, according to the historical business data and according to a first set rule, a business data fluctuation item corresponding to the occurrence day of the event to be analyzed includes:
judging whether the occurrence day of the event to be analyzed is the key day;
if so, searching a business data fluctuation item corresponding to the occurrence date of the event to be analyzed from a pre-established first fluctuation item library according to date information corresponding to the occurrence date of the event to be analyzed and week information corresponding to the occurrence date of the event to be analyzed; the first fluctuation item library stores mapping relations of date information, week information and business data fluctuation items of each key day;
otherwise, searching a business data fluctuation item corresponding to the occurrence day of the event to be analyzed from a pre-established second fluctuation item library according to the month information corresponding to the occurrence day of the event to be analyzed; and the second fluctuation item library stores the mapping relation between the month information and the business data fluctuation items.
9. The method according to claim 1, wherein the determining, according to the historical business data and according to a first set rule, a business data fluctuation item corresponding to the occurrence day of the event to be analyzed includes:
judging whether the occurrence day of the event to be analyzed is the key day;
if the event occurrence day to be analyzed is the key day, searching a business data fluctuation item corresponding to the event occurrence day to be analyzed from a pre-established first fluctuation item library according to date information corresponding to the event occurrence day to be analyzed and week information corresponding to the event occurrence day to be analyzed; the first fluctuation item library stores mapping relations of date information, week information and business data fluctuation items of each key day;
if the to-be-analyzed event occurrence day is not the key day, judging whether the to-be-analyzed event occurrence day is located in a first time period of a month to which the to-be-analyzed event occurrence day belongs; wherein a previous week of each date in the first time period contains a date of a month previous to the current month;
if the occurrence day of the event to be analyzed is located in the first time period, searching a business data fluctuation item corresponding to the occurrence day of the event to be analyzed from a pre-established second fluctuation item library according to the month information to which the occurrence day of the event to be analyzed belongs; otherwise, determining a first basic service data mean value corresponding to a previous period of the day of the event to be analyzed, determining a second basic service data mean value corresponding to a previous period of the same day as the day of the event to be analyzed in the last month, and determining the ratio of the first basic service data mean value to the second basic service data mean value as the service data fluctuation item corresponding to the day of the event to be analyzed; and the second fluctuation item library stores the mapping relation between the month information and the business data fluctuation items.
10. The method of claim 8 or 9, wherein the first fluctuation term library is created by:
calculating the average value of basic service data of all dates which are located in a time node before the key date and belong to the same week number with the key date aiming at each key date corresponding to the target service;
calculating the ratio of the basic service data of the key day to the average value, and taking the ratio as a service data fluctuation item corresponding to the key day;
and correspondingly storing the date information of the key days, the week information corresponding to the key days and the business data fluctuation items into the first fluctuation item library.
11. The method of claim 8 or 9, wherein the second fluctuation term library is created by:
eliminating the business data of the holidays in the historical business data;
calculating the average value of daily actual business volume corresponding to each month according to the remaining historical business data after elimination;
determining the ratio of the average value of the actual daily traffic corresponding to the current month to the average value of the actual daily traffic corresponding to the previous month as a business data fluctuation item corresponding to the current month;
and correspondingly storing the month information and the service data fluctuation items into the second fluctuation item library.
12. The method according to claim 1, wherein the determining, according to the historical service data and according to a second set rule, a service data random disturbance item corresponding to the occurrence day of the event to be analyzed includes:
removing holiday business data in the historical business data;
determining all daily traffic which is located in a second set time period before the occurrence date of the event to be analyzed and is the same as the week number of the occurrence date of the event to be analyzed from the remaining historical service data after the elimination;
and determining the standard deviation of all the traffic in the day period as the random disturbance item of the traffic data.
13. An apparatus for determining an impact of an event on traffic, the apparatus comprising:
the first acquisition module is used for acquiring historical service data corresponding to the target service from the database; wherein the historical traffic data comprises actual traffic volume per day for the target traffic;
the second acquisition module is used for acquiring basic service data of the day of the event to be analyzed according to the historical service data; the basic service data are service data after the influences of events and special days are eliminated; the special days comprise holidays and key days, and the key days are the occurrence days of the periodic events;
the first determining module is used for determining a business data fluctuation item corresponding to the occurrence day of the event to be analyzed according to the historical business data and a first set rule; determining a service data random disturbance item corresponding to the occurrence day of the event to be analyzed according to the historical service data and a second set rule;
and the second determining module is used for determining the influence of the event on the traffic of the day of the event to be analyzed by using a set influence determining algorithm according to the basic service data, the service data fluctuation item and the service data random disturbance item.
14. The apparatus of claim 13, the second determination module, comprising:
the detection unit is used for detecting whether the predicted reference traffic of the day of the event to be analyzed is within the actual reference traffic range; the reference traffic is traffic after eliminating the influence generated by the event;
a first determining unit, configured to determine, according to a first influence range determining algorithm, a traffic influence range, generated by the event on traffic of the event to be analyzed on the occurrence day of the event, if the predicted reference traffic of the event to be analyzed on the occurrence day is within an actual reference traffic range, according to the actual traffic of the event to be analyzed on the occurrence day, the predicted reference traffic, and the traffic data random disturbance item;
and if the predicted reference quantity of the day of the event to be analyzed is not within the actual reference traffic range, determining a traffic influence range of the event on the traffic of the day of the event to be analyzed according to a second influence range determination algorithm according to the actual traffic of the day of the event to be analyzed, the basic traffic data, the traffic data fluctuation item and the traffic data random disturbance item.
15. The apparatus according to claim 14, wherein the first determining unit is specifically configured to:
calculating the difference value between the actual traffic and the predicted reference traffic of the day of the event to be analyzed; determining the difference value of the difference value and the service data random disturbance item as the minimum value of the service volume influence range, and determining the sum value of the difference value and the service data random disturbance item as the maximum value of the service volume influence range; and determining the business volume influence range according to the minimum value of the business volume influence range and the maximum value of the business volume influence range.
16. The apparatus according to claim 14, wherein the second determining unit is specifically configured to:
calculating a product of the basic service data and the service data fluctuation item, and calculating a difference value between the actual service volume and the product; determining the difference value of the difference value and the service data random disturbance item as the minimum value of the service volume influence range, and determining the sum value of the difference value and the service data random disturbance item as the maximum value of the service volume influence range; and determining the business volume influence range according to the minimum value of the business volume influence range and the maximum value of the business volume influence range.
17. The apparatus of claim 13, the second acquisition module, comprising:
the first removing unit is used for removing the service data of the event occurrence date and the special date in the historical service data;
a third determining unit, configured to determine, from the remaining historical service data after the elimination, a service data mean value corresponding to all dates which are located in a time node before the occurrence date of the event to be analyzed and have the same week number as the occurrence date of the event to be analyzed;
and the fourth determining unit is used for determining the average value of the service data as the basic service data.
18. The apparatus of claim 13, the first determining module comprising:
the first judging unit is used for judging whether the occurrence day of the event to be analyzed is the key day;
a first searching unit, configured to search, if the event to be analyzed occurs on the key day, a service data fluctuation item corresponding to the event to be analyzed on the day from a pre-established first fluctuation item library according to date information corresponding to the event to be analyzed and week information corresponding to the event to be analyzed; the first fluctuation item library stores mapping relations of date information, week information and business data fluctuation items of each key day;
a second searching unit, configured to search, according to month information corresponding to the occurrence day of the event to be analyzed, a service data fluctuation item corresponding to the occurrence day of the event to be analyzed from a second fluctuation item library established in advance, if the occurrence day of the event to be analyzed is not the key day; and the second fluctuation item library stores the mapping relation between the month information and the business data fluctuation items.
19. The apparatus of claim 13, the first determining module comprising:
the second judging unit is used for judging whether the day of the event to be analyzed is the key day;
a third searching unit, configured to search, if the date of the event to be analyzed is the key date, a service data fluctuation item corresponding to the date of the event to be analyzed from a pre-established first fluctuation item library according to date information corresponding to the date of the event to be analyzed and week information corresponding to the date of the event to be analyzed; the first fluctuation item library stores mapping relations of date information, week information and business data fluctuation items of each key day;
a third judging unit, configured to judge whether the event day to be analyzed is located in the first time period of the month to which the event day to be analyzed belongs if the event day to be analyzed is not the key day; wherein a previous week of each date in the first time period contains a date of a month previous to the current month;
a fourth searching unit, configured to search, according to month information to which the to-be-analyzed event day belongs, a service data fluctuation item corresponding to the to-be-analyzed event day from a second fluctuation item library established in advance, if the to-be-analyzed event day is located in the first time period;
a fifth location determining unit, configured to determine, if the to-be-analyzed event occurrence day is not in the first time period, a first basic service data mean value corresponding to a previous period of the to-be-analyzed event occurrence day, and determine, in a previous month, a second basic service data mean value corresponding to a previous period of the same date as the to-be-analyzed event occurrence day, and determine a ratio of the first basic service data mean value to the second basic service data mean value as the service data fluctuation item corresponding to the to-be-analyzed event occurrence day; and the second fluctuation item library stores the mapping relation between the month information and the business data fluctuation items.
20. A device for determining the impact of an event on traffic, comprising:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
acquiring historical service data corresponding to a target service from a database; wherein the historical traffic data comprises actual traffic volume per day for the target traffic;
acquiring basic service data of the day of the event to be analyzed according to the historical service data; the basic service data are service data after the influences of events and special days are eliminated; the special days comprise holidays and key days, and the key days are the occurrence days of the periodic events;
determining a business data fluctuation item corresponding to the occurrence date of the event to be analyzed according to the historical business data and a first set rule; determining a service data random disturbance item corresponding to the occurrence day of the event to be analyzed according to the historical service data and a second set rule;
and determining the influence of the event on the traffic of the day of the event to be analyzed by using a set influence determination algorithm according to the basic service data, the service data fluctuation item and the service data random disturbance item.
21. A storage medium storing computer-executable instructions that, when executed, implement the following:
acquiring historical service data corresponding to a target service from a database; wherein the historical traffic data comprises actual traffic volume per day for the target traffic;
acquiring basic service data of the day of the event to be analyzed according to the historical service data; the basic service data are service data after the influences of events and special days are eliminated; the special days comprise holidays and key days, and the key days are the occurrence days of the periodic events;
determining a business data fluctuation item corresponding to the occurrence date of the event to be analyzed according to the historical business data and a first set rule; determining a service data random disturbance item corresponding to the occurrence day of the event to be analyzed according to the historical service data and a second set rule;
and determining the influence of the event on the traffic of the day of the event to be analyzed by using a set influence determination algorithm according to the basic service data, the service data fluctuation item and the service data random disturbance item.
CN202010238059.XA 2020-03-30 2020-03-30 Method and device for determining influence of event on traffic Active CN111461775B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010238059.XA CN111461775B (en) 2020-03-30 2020-03-30 Method and device for determining influence of event on traffic

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010238059.XA CN111461775B (en) 2020-03-30 2020-03-30 Method and device for determining influence of event on traffic

Publications (2)

Publication Number Publication Date
CN111461775A true CN111461775A (en) 2020-07-28
CN111461775B CN111461775B (en) 2023-03-24

Family

ID=71680228

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010238059.XA Active CN111461775B (en) 2020-03-30 2020-03-30 Method and device for determining influence of event on traffic

Country Status (1)

Country Link
CN (1) CN111461775B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113254787A (en) * 2021-06-22 2021-08-13 中国平安人寿保险股份有限公司 Event analysis method and device, computer equipment and storage medium
CN113360757A (en) * 2021-06-04 2021-09-07 中国科学院计算机网络信息中心 Method and device for measuring influence of event on target service
CN113706098A (en) * 2021-08-05 2021-11-26 深圳集智数字科技有限公司 Deviation reason identification method and device based on service and electronic equipment
CN113705859A (en) * 2021-08-05 2021-11-26 深圳集智数字科技有限公司 Method and device for predicting influence value of deviation cause, electronic device and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101808351A (en) * 2009-02-17 2010-08-18 中兴通讯股份有限公司 Method and system for business impact analysis
CN104301137A (en) * 2014-09-23 2015-01-21 国家电网公司 Method and system for analyzing influences of electric power communication faults on services
CN105847598A (en) * 2016-04-05 2016-08-10 浙江远传信息技术股份有限公司 Method and device for call center multifactorial telephone traffic prediction
CN109598393A (en) * 2017-09-30 2019-04-09 北京国双科技有限公司 A kind of analysis method and device of the influence information that event generates enterprise
CN109829756A (en) * 2019-01-18 2019-05-31 北京中电普华信息技术有限公司 A kind of method and system of the influence of determining abnormal factors to electricity sales amount
CN110443451A (en) * 2019-07-03 2019-11-12 深圳壹师城科技有限公司 Event grading approach, device, computer equipment and storage medium
CN111209400A (en) * 2020-01-03 2020-05-29 北京明略软件***有限公司 Data analysis method and device

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101808351A (en) * 2009-02-17 2010-08-18 中兴通讯股份有限公司 Method and system for business impact analysis
CN104301137A (en) * 2014-09-23 2015-01-21 国家电网公司 Method and system for analyzing influences of electric power communication faults on services
CN105847598A (en) * 2016-04-05 2016-08-10 浙江远传信息技术股份有限公司 Method and device for call center multifactorial telephone traffic prediction
CN109598393A (en) * 2017-09-30 2019-04-09 北京国双科技有限公司 A kind of analysis method and device of the influence information that event generates enterprise
CN109829756A (en) * 2019-01-18 2019-05-31 北京中电普华信息技术有限公司 A kind of method and system of the influence of determining abnormal factors to electricity sales amount
CN110443451A (en) * 2019-07-03 2019-11-12 深圳壹师城科技有限公司 Event grading approach, device, computer equipment and storage medium
CN111209400A (en) * 2020-01-03 2020-05-29 北京明略软件***有限公司 Data analysis method and device

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113360757A (en) * 2021-06-04 2021-09-07 中国科学院计算机网络信息中心 Method and device for measuring influence of event on target service
CN113254787A (en) * 2021-06-22 2021-08-13 中国平安人寿保险股份有限公司 Event analysis method and device, computer equipment and storage medium
CN113254787B (en) * 2021-06-22 2023-07-21 中国平安人寿保险股份有限公司 Event analysis method, device, computer equipment and storage medium
CN113706098A (en) * 2021-08-05 2021-11-26 深圳集智数字科技有限公司 Deviation reason identification method and device based on service and electronic equipment
CN113705859A (en) * 2021-08-05 2021-11-26 深圳集智数字科技有限公司 Method and device for predicting influence value of deviation cause, electronic device and storage medium
CN113706098B (en) * 2021-08-05 2024-03-22 深圳须弥云图空间科技有限公司 Business-based deviation reason identification method and device and electronic equipment
CN113705859B (en) * 2021-08-05 2024-04-19 深圳须弥云图空间科技有限公司 Method and device for predicting influence value of deviation cause, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN111461775B (en) 2023-03-24

Similar Documents

Publication Publication Date Title
CN111461775B (en) Method and device for determining influence of event on traffic
CN107526667B (en) Index abnormality detection method and device and electronic equipment
CN108733825B (en) Object trigger event prediction method and device
CN108171267B (en) User group division method and device and message pushing method and device
CN110634030B (en) Method, device and equipment for mining service indexes of applications
CN109190007B (en) Data analysis method and device
CN107168977B (en) Data query optimization method and device
CN108243032B (en) Method, device and equipment for acquiring service level information
CN111985201B (en) Data processing rule generation method and device and electronic equipment
CN110751515A (en) Decision-making method and device based on user consumption behaviors, electronic equipment and storage medium
CN114708007A (en) Intelligent decomposition method and system for store sales plan
CN111680960A (en) Attendance statistical method and equipment
CN110175084B (en) Data change monitoring method and device
CN110766232A (en) Dynamic prediction method and system thereof
CN114943383A (en) Prediction method and device based on time series, computer equipment and storage medium
CN109118361B (en) Method, device and system for managing limit
CN107544753B (en) Data processing method and device and server
CN109829756A (en) A kind of method and system of the influence of determining abnormal factors to electricity sales amount
CN115935723A (en) Equipment combination analysis method and system for gallium nitride preparation scene
CN117435652A (en) Data checking method and device
CN110009391B (en) Periodic event information determining method and device
CN110321433B (en) Method and device for determining text category
CN110245136B (en) Data retrieval method, device, equipment and storage equipment
CN111967767A (en) Business risk identification method, device, equipment and medium
CN111047089A (en) Load prediction method and device and electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant