CN112734159A - Enterprise rework/rework rate calculation method and system - Google Patents

Enterprise rework/rework rate calculation method and system Download PDF

Info

Publication number
CN112734159A
CN112734159A CN202011409848.1A CN202011409848A CN112734159A CN 112734159 A CN112734159 A CN 112734159A CN 202011409848 A CN202011409848 A CN 202011409848A CN 112734159 A CN112734159 A CN 112734159A
Authority
CN
China
Prior art keywords
rework
rate
enterprise
linear regression
regression equation
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.)
Pending
Application number
CN202011409848.1A
Other languages
Chinese (zh)
Inventor
万凯
李宗朋
刘识
程志华
赵宇亮
赵加奎
王宏刚
林晓静
郭敏
杨志
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.)
Big Data Center Of State Grid Corp Of China
Original Assignee
Big Data Center Of State Grid Corp Of China
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 Big Data Center Of State Grid Corp Of China filed Critical Big Data Center Of State Grid Corp Of China
Priority to CN202011409848.1A priority Critical patent/CN112734159A/en
Publication of CN112734159A publication Critical patent/CN112734159A/en
Pending legal-status Critical Current

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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Operations Research (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computing Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Marketing (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a method and a system for calculating the rework/rework rate of an enterprise, comprising the following steps: acquiring the rework/rework rate and the corresponding date of the enterprise, determining the start date of the rework/rework, and constructing a rework/rework rate set; determining the rework/rework rate of the enterprise based on the relation among the start date, the rework/rework rate and the corresponding date in the rework/rework rate set of the enterprise, so that the technical scheme realizes the quantitative analysis of the high-dimensional data of the rework/rework rate; meanwhile, the rework/rework rate graph drawn in the technical scheme provided by the invention can realize visual display.

Description

Enterprise rework/rework rate calculation method and system
Technical Field
The invention relates to the technical field of enterprise rework and reproduction after holidays, in particular to a method and a system for calculating enterprise rework/reproduction rate.
Background
The enterprise rework and production recovery analysis is an important means for evaluating the recovery condition of the social and economic activities before and after the legal holidays (including shutdown caused by major influence), and the rework and production recovery rate is an important index for measuring the recovery speed of the social and economic activities. At present, the technical scheme of the analysis of the rework and production rate mainly comprises one of the following steps:
the rate of rework and production recovery under specific standards: the time from the beginning of the rework to the time when the rework and rework indicator reaches a certain specific threshold value of 30%, 50%, 80%, etc.
The rework and reproduction rate under a specific standard can only take effect on a specific threshold, and once the rework and reproduction index has no value completely equal to the threshold, the rework and reproduction rate cannot be obtained. Moreover, the original analysis of the rework and rework rate mainly aims at two major dimensions of rework (rework) rate and time, and if more data of other dimensions are provided, it is difficult to obtain an analysis value of the comprehensive rework and rework rate. Meanwhile, the original rework and production recovery rate analysis method cannot be visually displayed in a good visual mode, and is not beneficial to data display and analysis.
Disclosure of Invention
In order to solve the problems of difficulty in quantitative analysis, incapability of analyzing high-dimensional data, difficulty in visual display and the like in the conventional compound work and compound production rate calculation, the invention provides an enterprise compound work/compound production rate calculation method, which comprises the following steps of:
acquiring the rework/rework rate and the corresponding date of the enterprise, determining the start date of the rework/rework, and constructing a rework/rework rate set;
determining an enterprise rework/rework rate based on a relationship of a start date, rework/rework rates, and corresponding dates in the enterprise rework/rework rate set.
Preferably, the acquiring the rework/rework rate and the corresponding date of the enterprise, determining a start date of the rework/rework, and constructing a rework/rework rate set includes:
determining the date corresponding to the minimum rework/rework rate from the obtained enterprise rework/rework rates as the starting date of the enterprise rework/rework;
determining each rework/rework index value in turn from the start date and establishing a rework/rework rate sequence on the date corresponding to the index value reached for the first time;
forming a rework/rework rate set by all rework/rework rate sequences;
wherein the rework/rework index is rework/rework rate.
Preferably, the rework/rework rate is calculated according to various statistical data and rework/rework users;
wherein the statistical data comprises: power data, tax data, logistics data;
preferably, the rework user: the number of the corresponding users is greater than the threshold value in the statistical data;
preferably, the determining the enterprise rework/rework rate based on the relationship among the start date, rework/rework rate and corresponding date in the enterprise rework/rework rate set includes:
drawing a rework/rework rate graph according to the rework/rework rate in the rework/rework rate set M and the date corresponding to the index value reached for the first time;
determining a rework/rework rate versus days based on the rework/rework rate graph;
the relation between the rework and recovery rate and days comprises the following steps: a relationship determined by a unary linear regression equation when the variable affecting the rework and reproduction index is an independent variable; and when the variable influencing the repeated work and production index is a plurality of independent variables, the relationship is determined by a multivariate linear equation.
Preferably, the determining of the unary linear regression equation comprises:
constructing a unary linear equation based on the linear relation between the independent variable and the complex work yield;
revising the coefficient in the unary linear equation based on a complex work and complex production rate data set and a probability distribution function of the complex work and complex production rate to obtain a coefficient with the minimum error of the unary linear regression equation, and further constructing the unary linear regression equation; wherein the independent variable is rework time.
Preferably, the calculation formula of the unary linear regression equation is as follows:
Figure RE-GDA0002976556100000021
in the formula (I), the compound is shown in the specification,
Figure RE-GDA0002976556100000022
representing the rework and recovery rate of the enterprise, xiIndicating first arrival
Figure RE-GDA0002976556100000023
The number of days taken in the day,
Figure RE-GDA0002976556100000024
and
Figure RE-GDA0002976556100000025
respectively, represent the coefficients that minimize the error of the unary linear regression equation.
Preferably, the multiple linear regression equation determination includes:
constructing a multivariate linear equation corresponding to each variable data and the rework/rework rate based on the independent variable data;
solving the multiple linear equations based on pre-constructed constraint conditions and minimization functions to obtain all coefficients which enable the errors of the simultaneous multiple linear equations to be minimum, and further constructing multiple linear regression equations;
wherein the minimization function comprises parameters corresponding to all variable data; the variable data includes: time, oil consumption, gas consumption, coal consumption, railway passenger traffic, tax revenue, and water consumption.
Preferably, the calculation of the multiple linear equation is as follows:
y＝Xβ+ε
in the formula, y represents an enterprise rework complex yield matrix, X represents a plurality of independent variable matrixes related to the rework complex yield, beta represents a multivariate linear equation parameter matrix, and epsilon represents an error matrix;
the constraint conditions include:
r (x) p +1, x takes the value (x)1,…,xp)
Figure RE-GDA0002976556100000031
ε～N(0，σ2In)；
Wherein x represents a plurality of independent variable vectors related to the rework reproduction yield, I and j each represent a data point sequence number, p represents the length of the x sequence, n represents the length of the y sequence, σ represents the standard deviation of ε, and InRepresenting an n-order identity matrix;
the minimization function is calculated as follows:
Figure RE-GDA0002976556100000032
wherein Q represents a minimum function, βpThe p-th term, x, of the parameter matrix beta of the multivariate linear equationipItem i y of the matrix y representing the rework and production rate of the enterpriseiCorresponding to the pth item of the X quantity in the matrix, p represents the quantity of independent variables;
the minimum coefficient is calculated as follows:
Figure RE-GDA0002976556100000033
Figure RE-GDA0002976556100000034
wherein X represents a plurality of independent variable matrixes related to the complex yield of the rework;
the multiple linear regression equation is calculated as follows:
Figure RE-GDA0002976556100000035
in the formula (I), the compound is shown in the specification,
Figure RE-GDA0002976556100000036
representing the enterprise rework and production rate matrix corresponding to a plurality of variable data,
Figure RE-GDA0002976556100000037
representing a plurality of independent variable matrixes related to the rework complex yield,
Figure RE-GDA0002976556100000038
the coefficients that minimize the error of the multiple linear regression equation are represented.
Preferably, the starting point for determining the rework and reproduction index of each enterprise in the industry and at different time is as follows: and determining the minimum value in the rework and rework indexes corresponding to each rework day.
Preferably, after determining the rework and production rate of the enterprise, the method further comprises:
and calculating the difference of the multiple historical synchronous repeated production rates according to the historical synchronous repeated production rates of the enterprises in the multiple years.
Preferably, the calculating the difference between the plurality of historical synchronous repeated work and production rates according to the plurality of historical synchronous repeated work and production rates of the enterprise comprises:
based on one or more independent variables which influence the indexes of the complex work and the complex production, respectively selecting a unary linear regression equation or a multiple linear regression equation corresponding to each year;
respectively utilizing the unary linear regression equation or the multiple linear regression equation to calculate the number of days corresponding to the achievement of each re-work rate in each year based on a plurality of given re-work rates, and respectively calculating the difference value of the number of days corresponding to the achievement of the re-work rate in each year based on each re-work rate; or
Respectively utilizing the unary linear regression equation or the multiple linear regression equation to calculate the rework/rework rate corresponding to each day in each year based on a plurality of given rework/rework days, and respectively calculating the difference value of the rework/rework rate corresponding to the day in each year based on each day.
Based on the same inventive concept, the invention also provides an enterprise rework and production rate determination system, which comprises:
the acquisition module is used for acquiring the rework/rework rate and the corresponding date of the enterprise, determining the start date of the rework/rework, and constructing a rework/rework rate set;
and the calculation module is used for determining the enterprise rework/rework rate based on the relation among the start date, the rework/rework rate and the corresponding date in the enterprise rework/rework rate set.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a method and a system for calculating the rework/rework rate of an enterprise, comprising the following steps: acquiring the rework/rework rate and the corresponding date of the enterprise, determining the start date of the rework/rework, and constructing a rework/rework rate set; determining the rework/rework rate of the enterprise based on the relation among the start date, the rework/rework rate and the corresponding date in the rework/rework rate set of the enterprise, so that the technical scheme realizes the quantitative analysis of the high-dimensional data of the rework/rework rate;
the rework/rework rate graph drawn in the technical scheme provided by the invention can realize visual display.
Drawings
FIG. 1 is a schematic diagram of an enterprise rework/rework rate calculation method of the present invention;
FIG. 2 is a graph comparing the simultaneous resumption rates in example 1;
FIG. 3 is a graph comparing the in-phase rework rates after performing regression analysis in example 1;
FIG. 4 is a block diagram of an enterprise rework and rework rate calculation system of the invention.
Detailed Description
For a better understanding of the present invention, reference is made to the following description taken in conjunction with the accompanying drawings and examples.
In the case of the example 1, the following examples are given,
in this embodiment, taking the traditional spring festival in china and the first day of the chinese calendar (chinese calendar) every year as an example, the method for calculating the rework/rework rate of an enterprise according to the present invention is illustrated, as shown in fig. 1, and includes:
s1: acquiring the rework/rework rate and the corresponding date of the enterprise, determining the start date of the rework/rework, and constructing a rework/rework rate set;
s2: determining an enterprise rework/rework rate based on a relationship between a start date, rework/rework rate and a corresponding date in the enterprise rework/rework rate set;
the specific implementation method comprises the following steps:
variable definition
(1) Rework or rework index R
The rework or rework indicator is an indicator for quantitatively measuring the level of rework or rework, and may be a rework rate and a rework rate (for example, the rework rate and the rework rate characterized by electric power data, tax data, logistics data, etc.) calculated based on various data, or other values for measuring the level of rework and rework besides the rework rate and the rework rate.
The calculation method of the multiplex rate calculated by the power consumption data is as follows:
and (4) re-working user: the current day electric quantity/the last 12 months and days average electric quantity is more than or equal to the threshold value
The rework rate is 100 percent of the number of reworking users in the statistical range/the total number of users in the statistical range
The complex yield calculated from the electricity consumption data is calculated as follows:
the compound yield is the sum of the electric quantity of the user in the current day in the statistical range/the sum of the electric quantity of the user in the last 12 months in the statistical range is 100 percent
The rework and reproduction index value of the first month is R1
The rework and reproduction index value of the first two in the positive month is R2
The rework and reproduction index value of Zhengyue Junyi san is R3
The rework and reproduction index value of the first four months is R4
……
The rework and reproduction index value on day i from the beginning of the first due month is Ri
……
The rework and reproduction index value of the nth day from the beginning of the first due month is Rn
The rework and rework index value corresponding to the rework and rework starting point is Rs
(2) Set of maximum rework and rework yields M
Maximum rework and reproduction rate sequence MjAll of MjForming a set M.
(3) Time series and numerical series of rework and reproduction rate
In the rework and rework rate data, the time series is xiThe numerical sequence of the rework and rework rate is yi。
Origin screening algorithm for rework and reproduction index
The selected starting point of the rework and rework multiple production index has an important role in developing rework and rework multiple production rate analysis. Because the reworking and reworking indexes of different industries and different time may fluctuate, the calculation deviation may be caused by blindly taking the first time of the first month as the calculation starting point, and particularly, the reworking and reworking rate may be difficult to calculate when the reworking and reworking recovery is slow or even reversed. The invention selects the starting point R of the rework and reproduction indexsThe minimum value of the first to the first four reworking and production-resuming indexes is as follows:
Rs＝min(R1,R2,R3,R4)
full-time-period rework and production rate algorithm
Determination of RsAnd then, carrying out rework and production rate calculation on the full-time range of the data. From the first day of the normal month (i ═ 1) to the next time of workProduce data the last day (i ═ n), compare R day by dayiAnd Maxj(R1,…,Ri-1)
First, let Mj＝Maxj(R1,…,Ri-1) And M1＝R1Then i increases from 2 to n:
if R isi≤Maxj(R1,…,Ri-1) I is 2, …, n, then MjRemain unchanged.
If R isi＞Maxj(R1,…,Ri-1) I is 2, …, n, then Mj＝Ri。
Through the above operation, M is obtainedjSet M of (a).
In set M, take out MjCorresponding number of days, i.e. RiSubscript of as days xi。
In set M, take out MjCorresponding rework and reproduction index RiAs value yi。
With xiAnd yiAs the rework rate data set, a rework rate comparison graph of a large industrial enterprise can be drawn as shown in fig. 2 by taking the rework rate of the large industrial enterprise as an example.
The unitary linear reworking and production rate regression algorithm comprises the following steps:
due to the fact that the data points of the re-work and re-production rate are discrete, and multiple industries show obvious linear growth rules, the method is used for better analyzing and mining the mathematical problems existing in the re-work and re-production process. Suppose that the enterprise has a rework and rework recovery rate yiAnd days xiIn a linear relationship, a unary linear regression equation is given:
yi＝β0+β1xi+εi,i＝1,2,…,n
meanwhile, in order to solve the optimal parameters, the social application background can be assumed by combining the complex work and complex production analysis:
(1)
Figure RE-GDA0002976556100000071
(2)
Figure RE-GDA0002976556100000072
then a conclusion y can be reachedi～N(β0+β1xi，σ2)
Thus, yiIs a probability distribution function of
Figure RE-GDA0002976556100000073
Then get after multiplication
Figure RE-GDA0002976556100000074
Solving so that L (beta)0,β1,σ2) Taking the parameters of the maximum value, the following can be obtained:
Figure RE-GDA0002976556100000075
wherein the content of the first and second substances,
Figure RE-GDA0002976556100000076
and
Figure RE-GDA0002976556100000077
i.e., the coefficients that minimize the error of the unary linear regression equation.
Thus, it can be seen that the coefficients estimate the post-regression equation:
Figure RE-GDA0002976556100000078
in order to evaluate the quality of the regression equation, a determination coefficient is introduced
Figure RE-GDA0002976556100000079
Wherein the content of the first and second substances,
Figure RE-GDA00029765561000000710
Figure RE-GDA00029765561000000711
such as R in regression analysis2If the regression analysis is more than 0.9, the regression analysis is considered to be effective. Fig. 3 is drawn by taking the rework rate of a large industrial enterprise as an example.
In this embodiment, the axis of abscissas in fig. 2 and 3 represents the rework rate, the axis of ordinates represents the number of days taken to reach the rework rate threshold for the first time, and each coordinate point is the number of days that should reach a certain rework rate for the first time (if there are days that should reach the rework rate for the repetition, only the number of days that should reach the rework rate for the first time is reserved).
The rate of recurrence plot can also be plotted as described above.
The multiple linear multiple-work multiple-production rate regression algorithm comprises
If more multivariable data besides time and rework rate (rework rate) can be obtained in the actual rework and rework analysis, such as independent variables such as oil gas consumption and the like, the unary linear regression can be expanded to obtain the multivariate linear regression analysis method. Giving a multiple linear regression equation:
yi＝β0+β1xi1+…+βpxip+εi,i＝1,2,…,n
for convenience, remember
Figure RE-GDA0002976556100000081
At this time, the multiple linear regression becomes:
y＝Xβ+ε
meanwhile, in order to solve the optimal parameters, the social application background can be assumed by combining the complex work and complex production analysis:
(1) r (x) p +1, and x1,…,xpNot a random variable.
(2)
Figure RE-GDA0002976556100000082
(3)ε～N(0，σ2In)
Order minimization function
Figure RE-GDA0002976556100000083
Solving so that Q (beta)0,β1,…,βp) Taking the parameters of the minimum value, the following can be obtained:
Figure RE-GDA0002976556100000084
thus, it can be seen that the coefficients estimate the post-regression equation:
Figure RE-GDA0002976556100000085
example 2
In this embodiment, for unary linear regression and multiple linear regression with the rework rate difference algorithm between two years, the following general algorithm may be used:
if the two year regression equation is: y isa＝XaβaAnd yb＝Xbβb
If given a particular rework reproduction yield yd
The difference X of the independent variables including the number of daysd＝yd/βa-yd/βb
If each independent variable value X in given daysd＝[1 xd1 … xdp]
Then the difference y between the rework and the production rated＝ya-yb＝Xdβa-Xdβb
Example 3:
in order to implement the method, the present invention further provides an enterprise rework/rework rate determination system, as shown in fig. 4, including: the device comprises an acquisition module and a calculation module;
wherein the acquisition module is configured to: acquiring the rework/rework rate and the corresponding date of the enterprise, determining the start date of the rework/rework, and constructing a rework/rework rate set;
the calculation module is used for: determining an enterprise rework/rework rate based on a relationship of a start date, rework/rework rates, and corresponding dates in the enterprise rework/rework rate set.
The construction of the rework/rework rate set in the acquisition module comprises the following steps:
determining the date corresponding to the minimum rework/rework rate from the obtained enterprise rework/rework rates as the starting date of the enterprise rework/rework;
determining each rework/rework index value in turn from the start date and establishing a rework/rework rate sequence on the date corresponding to the index value reached for the first time;
forming a rework/rework rate set by all rework/rework rate sequences;
wherein the rework/rework index is rework/rework rate.
The rework/rework rate is calculated according to various statistical data and rework/rework users;
wherein the statistical data comprises: power data, tax data, logistics data;
and (4) re-working user: and the number of the corresponding users is greater than the threshold value in the statistical data.
The calculation module is specifically configured to:
drawing a rework/rework rate graph according to the rework/rework rate in the rework/rework rate set M and the date corresponding to the index value reached for the first time;
determining a rework/rework rate versus days based on the rework/rework rate graph;
the relation between the rework and recovery rate and days comprises the following steps: a relationship determined by a unary linear regression equation when the variable affecting the rework and reproduction index is an independent variable; and when the variable influencing the repeated work and production index is a plurality of independent variables, the relationship is determined by a multivariate linear equation.
The one-dimensional linear regression equation determination comprises:
constructing a unary linear equation based on the linear relation between the independent variable and the complex work yield;
revising the coefficient in the unary linear equation based on a complex work and complex production rate data set and a probability distribution function of the complex work and complex production rate to obtain a coefficient with the minimum error of the unary linear regression equation, and further constructing the unary linear regression equation; wherein the independent variable is rework time.
The unitary linear regression equation is calculated as follows:
Figure RE-GDA0002976556100000101
in the formula (I), the compound is shown in the specification,
Figure RE-GDA0002976556100000102
representing the rework and recovery rate of the enterprise, xiIndicating first arrival
Figure RE-GDA0002976556100000103
The number of days taken in the day,
Figure RE-GDA0002976556100000104
and
Figure RE-GDA0002976556100000105
respectively, represent the coefficients that minimize the error of the unary linear regression equation.
The multiple linear regression equation determination comprises:
constructing a multivariate linear equation corresponding to each variable data and the rework/rework rate based on the independent variable data;
solving the multiple linear equations based on pre-constructed constraint conditions and minimization functions to obtain all coefficients which enable the errors of the simultaneous multiple linear equations to be minimum, and further constructing multiple linear regression equations;
wherein the minimization function comprises parameters corresponding to all variable data; the variable data includes: time, oil consumption, gas consumption, coal consumption, railway passenger traffic, tax revenue, and water consumption.
The calculation of the multiple linear equation is as follows:
y＝Xβ+ε
in the formula, y represents an enterprise rework complex yield matrix, X represents a plurality of independent variable matrixes related to the rework complex yield, beta represents a multivariate linear equation parameter matrix, and epsilon represents an error matrix;
the constraint conditions include:
r (x) p +1, x takes the value (x)1,…,xp)
Figure RE-GDA0002976556100000106
ε～N(0，σ2In)；
Wherein x represents a plurality of independent variable vectors related to the rework reproduction yield, I and j each represent a data point sequence number, p represents the length of the x sequence, n represents the length of the y sequence, σ represents the standard deviation of ε, and InRepresenting an n-order identity matrix;
the minimization function is calculated as follows:
Figure RE-GDA0002976556100000111
wherein Q represents a minimum function, βpThe p-th term, x, of the parameter matrix beta of the multivariate linear equationipItem i y of the matrix y representing the rework and production rate of the enterpriseiCorresponding to the pth item of the X quantity in the matrix, p represents the quantity of independent variables;
the minimum coefficient is calculated as follows:
Figure RE-GDA0002976556100000112
Figure RE-GDA0002976556100000113
wherein X represents a plurality of independent variable matrixes related to the complex yield of the rework;
the multiple linear regression equation is calculated as follows:
Figure RE-GDA0002976556100000114
in the formula (I), the compound is shown in the specification,
Figure RE-GDA0002976556100000115
representing the enterprise rework and production rate matrix corresponding to a plurality of variable data,
Figure RE-GDA0002976556100000116
representing a plurality of independent variable matrixes related to the rework complex yield,
Figure RE-GDA0002976556100000117
the coefficients that minimize the error of the multiple linear regression equation are represented.
The starting point for determining the re-work and re-production indexes of the industries of the enterprises at different times is as follows: and determining the minimum value in the rework and rework indexes corresponding to each rework day.
After determining the rework and production rate of the enterprise, the method further comprises the following steps:
and calculating the difference of the multiple historical synchronous repeated production rates according to the historical synchronous repeated production rates of the enterprises in the multiple years.
The calculating the difference of the plurality of historical synchronous repeated work and production rates according to the plurality of historical synchronous repeated work and production rates of the enterprise comprises:
based on one or more independent variables which influence the indexes of the complex work and the complex production, respectively selecting a unary linear regression equation or a multiple linear regression equation corresponding to each year;
respectively utilizing the unary linear regression equation or the multiple linear regression equation to calculate the number of days corresponding to the achievement of each re-work rate in each year based on a plurality of given re-work rates, and respectively calculating the difference value of the number of days corresponding to the achievement of the re-work rate in each year based on each re-work rate; or respectively utilizing the unary linear regression equation or the multiple linear regression equation to calculate the rework/rework rate corresponding to each day in each year based on a plurality of given rework/rework days, and respectively calculating the difference value of the rework/rework rate corresponding to the day in each year based on each day.

Claims (10)

1. An enterprise rework/rework rate calculation method is characterized by comprising the following steps:
acquiring the rework/rework rate and the corresponding date of the enterprise, determining the start date of the rework/rework, and constructing a rework/rework rate set;
determining an enterprise rework/rework rate based on a relationship of a start date, rework/rework rates, and corresponding dates in the enterprise rework/rework rate set.
2. The computing method of claim 1, wherein the obtaining the rework/rework rates and corresponding dates of the enterprise, determining a start date of the rework/rework, and constructing a set of rework/rework rates comprises:
determining the date corresponding to the minimum rework/rework rate from the obtained enterprise rework/rework rates as the starting date of the enterprise rework/rework;
determining each rework/rework index value in turn from the start date and establishing a rework/rework rate sequence on the date corresponding to the index value reached for the first time;
forming a rework/rework rate set by all rework/rework rate sequences;
wherein the rework/rework index is rework/rework rate.
Preferably, the rework/rework rate is calculated according to various statistical data and rework/rework users;
wherein the statistical data comprises: power data, tax data, logistics data;
preferably, the rework user: and the number of the corresponding users is greater than the threshold value in the statistical data.
3. The computing method of claim 2, wherein determining an enterprise rework/rework rate based on a relationship of a start date, rework/rework rates, and corresponding dates in the set of enterprise rework/rework rates comprises:
drawing a rework/rework rate graph according to the rework/rework rate in the rework/rework rate set M and the date corresponding to the index value reached for the first time;
determining a rework/rework rate versus days based on the rework/rework rate graph;
the relation between the rework and recovery rate and days comprises the following steps: a relationship determined by a unary linear regression equation when the variable affecting the rework and reproduction index is an independent variable; and when the variable influencing the repeated work and production index is a plurality of independent variables, the relationship is determined by a multivariate linear equation.
4. The computing method of claim 3, wherein the one-dimensional linear regression equation determination comprises:
constructing a unary linear equation based on the linear relation between the independent variable and the complex work yield;
revising the coefficient in the unary linear equation based on a complex work and complex production rate data set and a probability distribution function of the complex work and complex production rate to obtain a coefficient with the minimum error of the unary linear regression equation, and further constructing the unary linear regression equation; wherein the independent variable is rework time.
5. The method of claim 4, wherein the unitary linear regression equation is calculated as follows:
Figure RE-FDA0002976556090000021
in the formula (I), the compound is shown in the specification,
Figure RE-FDA0002976556090000022
representing the rework and recovery rate of the enterprise, xiIndicating first arrival
Figure RE-FDA0002976556090000023
The number of days taken in the day,
Figure RE-FDA0002976556090000024
and
Figure RE-FDA0002976556090000025
respectively, represent the coefficients that minimize the error of the unary linear regression equation.
6. The computing method of claim 3, wherein the multiple linear regression equation determination comprises:
constructing a multivariate linear equation corresponding to each variable data and the rework/rework rate based on the independent variable data;
solving the multiple linear equations based on pre-constructed constraint conditions and minimization functions to obtain all coefficients which enable the errors of the simultaneous multiple linear equations to be minimum, and further constructing multiple linear regression equations;
wherein the minimization function comprises parameters corresponding to all variable data; the variable data includes: time, oil consumption, gas consumption, coal consumption, railway passenger traffic, tax revenue, and water consumption.
7. The method of claim 6, wherein the multivariate linear equation is calculated as follows:
y＝Xβ+ε
in the formula, y represents an enterprise rework complex yield matrix, x represents a plurality of independent variable matrixes related to the rework complex yield, beta represents a multivariate linear equation parameter matrix, and epsilon represents an error matrix;
the constraint conditions include:
r (x) p +1, x takes the value (x)1，…，xp)
Figure RE-FDA0002976556090000026
ε～N(0，σ2In)；
Wherein x represents a plurality of independent variable vectors related to the rework reproduction yield, I and j each represent a data point sequence number, p represents the length of the x sequence, n represents the length of the y sequence, σ represents the standard deviation of ε, and InRepresenting an n-order identity matrix;
the minimization function is calculated as follows:
Figure RE-FDA0002976556090000031
wherein Q represents a minimum function, βpThe p-th term, x, of the parameter matrix beta of the multivariate linear equationipItem i y of the matrix y representing the rework and production rate of the enterpriseiCorresponding to the pth item of the X quantity in the matrix, p represents the quantity of independent variables;
the minimum coefficient is calculated as follows:
Figure RE-FDA0002976556090000032
Figure RE-FDA0002976556090000033
wherein X represents a plurality of independent variable matrixes related to the complex yield of the rework;
the multiple linear regression equation is calculated as follows:
Figure RE-FDA0002976556090000034
in the formula (I), the compound is shown in the specification,
Figure RE-FDA0002976556090000035
representing the enterprise rework and production rate matrix corresponding to a plurality of variable data,
Figure RE-FDA0002976556090000036
representing a plurality of independent variable matrixes related to the rework complex yield,
Figure RE-FDA0002976556090000037
the coefficients that minimize the error of the multiple linear regression equation are represented.
8. The calculation method according to claim 2, wherein the starting point for determining the rework and production recovery index in the industry and at different times of each enterprise is as follows: and determining the minimum value in the rework and rework indexes corresponding to each rework day.
9. The computing method of claim 1, further comprising, after determining the rate of rework and return of the enterprise:
and calculating the difference of the multiple historical synchronous repeated production rates according to the historical synchronous repeated production rates of the enterprises in the multiple years.
Preferably, the calculating the difference between the plurality of historical synchronous repeated work and production rates according to the plurality of historical synchronous repeated work and production rates of the enterprise comprises:
based on one or more independent variables which influence the indexes of the complex work and the complex production, respectively selecting a unary linear regression equation or a multiple linear regression equation corresponding to each year;
respectively utilizing the unary linear regression equation or the multiple linear regression equation to calculate the number of days corresponding to the achievement of each re-work rate in each year based on a plurality of given re-work rates, and respectively calculating the difference value of the number of days corresponding to the achievement of the re-work rate in each year based on each re-work rate; or
Respectively utilizing the unary linear regression equation or the multiple linear regression equation to calculate the rework/rework rate corresponding to each day in each year based on a plurality of given rework/rework days, and respectively calculating the difference value of the rework/rework rate corresponding to the day in each year based on each day.
10. An enterprise rework/rework rate determination system, comprising:
the acquisition module is used for acquiring the rework/rework rate and the corresponding date of the enterprise, determining the start date of the rework/rework, and constructing a rework/rework rate set;
and the calculation module is used for determining the enterprise rework/rework rate based on the relation among the start date, the rework/rework rate and the corresponding date in the enterprise rework/rework rate set.
CN202011409848.1A 2020-12-04 2020-12-04 Enterprise rework/rework rate calculation method and system Pending CN112734159A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011409848.1A CN112734159A (en) 2020-12-04 2020-12-04 Enterprise rework/rework rate calculation method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011409848.1A CN112734159A (en) 2020-12-04 2020-12-04 Enterprise rework/rework rate calculation method and system

Publications (1)

Publication Number Publication Date
CN112734159A true CN112734159A (en) 2021-04-30

Family

ID=75598036

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011409848.1A Pending CN112734159A (en) 2020-12-04 2020-12-04 Enterprise rework/rework rate calculation method and system

Country Status (1)

Country Link
CN (1) CN112734159A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113935568A (en) * 2021-08-30 2022-01-14 国网江苏省电力有限公司物资分公司 Auxiliary decision-making method for making purchasing strategy in productivity recovery stage

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113935568A (en) * 2021-08-30 2022-01-14 国网江苏省电力有限公司物资分公司 Auxiliary decision-making method for making purchasing strategy in productivity recovery stage

Similar Documents

Publication Publication Date Title
CN109615226B (en) Operation index abnormity monitoring method
CN111582568B (en) Power data-based method for predicting reworking of enterprises in spring festival
CN110019401B (en) Method, device, equipment and storage medium for predicting part quantity
CN112734159A (en) Enterprise rework/rework rate calculation method and system
CN111008727A (en) Power distribution station load prediction method and device
CN111598475A (en) Power grid risk prediction method based on improved gray Markov model
Hepenstrick et al. Forecasting with Large Unbalanced Datasets: The Mixed Frequency Three-Pass Regression Filter
CN115271192A (en) Industrial production index prediction method and processor
CN113379336B (en) Intelligent manufacturing execution process data processing system and method based on MES system
CN115456260A (en) Customer service telephone traffic prediction method
CN115549082A (en) Power load prediction method based on load mining and LSTM neural network
CN113780655A (en) Steel multi-variety demand prediction method based on intelligent supply chain
CN115470970A (en) Electric quantity prediction method and system based on prophet-LightGBM combined model
CN106651056B (en) Energy prediction system based on equipment working condition combination
CN113780861A (en) Component index evaluation method and system based on user daily electric quantity adjustment value
CN106682840A (en) Short-term power sale quantity predicting method and system based on daily cumulative distributed electric quantity
CN110991698A (en) Seasonal traffic flow grey prediction method based on mixed processing
CN112330182A (en) Quantitative analysis method and device for economic operation condition
CN117575475B (en) Quick construction and display method for large-screen report based on data warehouse
Kumari Productivity in Public Sector: Analysis at Industrial Group Level
CN109614586A (en) Reliability confidence lower limit construction method based on Bayesian theory and linear fitting
CN114036762B (en) System and method for predicting load of power distribution network based on proportionality coefficient method
Nababan et al. Forecasting the Amount of Oil Palm Production in Simalungun Regency Based on Data for 2000-2019 Using Double Exponential Smoothing Method
CN117670000B (en) Pump station water supply quantity prediction method based on combined prediction model
Товма et al. Forecasting and analysis of energy consumption

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