[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN115204527B - Enterprise operation health index evaluation system based on big data - Google Patents

Enterprise operation health index evaluation system based on big data Download PDF

Info

Publication number
CN115204527B
CN115204527B CN202211118153.7A CN202211118153A CN115204527B CN 115204527 B CN115204527 B CN 115204527B CN 202211118153 A CN202211118153 A CN 202211118153A CN 115204527 B CN115204527 B CN 115204527B
Authority
CN
China
Prior art keywords
project
conversion rate
actual
day
per day
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.)
Active
Application number
CN202211118153.7A
Other languages
Chinese (zh)
Other versions
CN115204527A (en
Inventor
谭丽霞
贾庆佳
李瑞敏
王仕林
张志勇
李琛琛
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.)
Wanlian Index Qingdao Information Technology Co ltd
Original Assignee
Wanlian Index Qingdao 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 Wanlian Index Qingdao Information Technology Co ltd filed Critical Wanlian Index Qingdao Information Technology Co ltd
Priority to CN202211118153.7A priority Critical patent/CN115204527B/en
Publication of CN115204527A publication Critical patent/CN115204527A/en
Application granted granted Critical
Publication of CN115204527B publication Critical patent/CN115204527B/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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • 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
    • G06Q10/10—Office automation; Time management
    • G06Q10/103—Workflow collaboration or project management
    • 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
    • G06Q30/0206—Price or cost determination based on market factors

Landscapes

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

Abstract

The invention relates to the field of enterprise operation evaluation, in particular to an enterprise operation health index evaluation system based on big data, which comprises a database module, an input module, an analysis processing module and a display module, wherein the database module comprises: the operation records are used for storing the finished projects of various scales and types acquired by utilizing big data; an input module: the system is used for inputting the operation record of each project of the enterprise and sending the operation record to the analysis processing module; an analysis processing module: the method comprises the steps of selecting a reference operation record of each project, calculating the actual productivity conversion rate of each project every day, obtaining the theoretical productivity conversion rate of each project every day according to the influence factor and the actual productivity conversion rate every day, calculating the health degree of each project, obtaining the operation health index of each project according to the health degree of each project and the variance of the theoretical productivity conversion rate every day, and sending the operation health index of each project to a display module for displaying.

Description

Enterprise operation health index evaluation system based on big data
Technical Field
The application relates to the field of enterprise operation evaluation, in particular to an enterprise operation health index evaluation system based on big data.
Background
The evaluation of the enterprise operation health index is an important link for timely evaluating and summarizing the current situation of the existing operation mode of the enterprise, taking relevant measures for subsequent operation and improving efficiency, and is also a source and a basis for long-term development and continuous competition of the enterprise. The evaluation index of the enterprise operation health is very complex, and often comprises five large indexes and numerous small indexes through projects, capital, technologies, markets and management, so that the processing and analysis of enterprise operation data are more difficult, different large data analysis tools and analysis models are often required for operation, multidimensional data are difficult to convert into business values, the operation decision of an enterprise cannot be fed back and evaluated, and the practical value of the large data is greatly reduced.
Disclosure of Invention
Aiming at the problems that the credibility of enterprise operation health index evaluation is low only through financial profit and an effective basis cannot be provided for adjustment of subsequent operation strategies, the invention provides an enterprise operation health index evaluation system based on big data, which comprises a database module, an input module, an analysis processing module and a display module, wherein the input module comprises a data processing module and a display module, and the display module comprises a display module, a display module and a display module, wherein the display module is used for displaying the following operation strategies:
the database module is as follows: the system comprises a data storage module, a data processing module and a data processing module, wherein the data storage module is used for storing operation records of finished projects of various scales and types acquired by big data, and the operation records comprise predicted cost, predicted total energy, predicted daily capacity and predicted operation duration;
the input module is used for: the system comprises an analysis processing module, a storage module and a display module, wherein the analysis processing module is used for inputting operation records of each project of an enterprise, including actual cost and actual operation duration of each day in actual operation and sending the operation records of each project of the enterprise to the analysis processing module;
the analysis processing module: receiving the operation record of each project of the enterprise sent by the input module, selecting the operation record of the completed project with the same scale and the same type as each project from the database module, and taking the operation record as the reference operation record of each project;
obtaining the actual productivity conversion rate of each project per day according to the predicted cost, the predicted total productivity and the predicted daily productivity of each project in the reference operation record and the actual cost of each project per day in the actual operation;
acquiring an influence factor of the actual productivity conversion rate of each project per day, and acquiring a theoretical productivity conversion rate of each project per day according to the influence factor of the actual productivity conversion rate of each project per day and the actual productivity conversion rate of each day;
obtaining the health degree of each project according to the theoretical productivity conversion rate of each project per day, the actual productivity conversion rate of each day, the predicted operation duration and the actual operation duration;
obtaining an operation health index of each project according to the health degree of each project and the variance of the theoretical productivity conversion rate of each day, and sending the operation health index of each project to a display module for displaying;
the display module: and receiving and displaying the operation health index sent by the analysis processing module.
The method for obtaining the actual productivity conversion rate of each project per day according to the predicted cost, the predicted total productivity and the predicted daily productivity of each project in the reference operation record and the actual cost of each project per day in the actual operation comprises the following steps:
and obtaining the ratio of the predicted cost and the predicted total production energy of each project in the reference operation record, multiplying the ratio and the predicted daily production energy of the project to obtain the predicted daily investment of the project, and taking the ratio of the predicted daily investment of the project and the actual cost of the project in each day of actual operation as the actual production energy conversion rate of the project each day.
The method for acquiring the influence factors of the actual productivity conversion rate of each project per day comprises the following steps:
setting characteristic data influencing actual productivity conversion rate, including weather, holidays and market environment;
and evaluating the influence probability of the feature data influencing the actual productivity conversion rate every day, and taking the probability value of the feature data with the maximum probability as an influence factor influencing the actual productivity conversion rate every day.
The specific method for obtaining the theoretical productivity conversion rate of each project per day according to the influence factor of the actual productivity conversion rate of each project per day and the actual productivity conversion rate of each day is as follows:
multiplying the influence factor of the actual productivity conversion rate of each project per day with the actual productivity conversion rate per day, and taking the result value added with the actual productivity conversion rate as the theoretical productivity conversion rate of each project per day.
The method for obtaining the health degree of each project according to the theoretical capacity conversion rate of each project per day, the actual capacity conversion rate of each day, the predicted operation duration and the actual operation duration comprises the following steps:
Figure 48882DEST_PATH_IMAGE001
in the formula (I), the compound is shown in the specification,
Figure 632310DEST_PATH_IMAGE002
is a first
Figure 209922DEST_PATH_IMAGE003
The degree of health of the individual item(s),
Figure 195196DEST_PATH_IMAGE004
to be composed of
Figure 973796DEST_PATH_IMAGE005
An exponential function of the base is used,
Figure 44520DEST_PATH_IMAGE006
is a natural constant and is a natural constant,
Figure 425823DEST_PATH_IMAGE007
is as follows
Figure 265603DEST_PATH_IMAGE008
The actual running time of the individual items, i.e. the total number of days,
Figure 215104DEST_PATH_IMAGE009
for reference in operation record
Figure 507546DEST_PATH_IMAGE010
The predicted operation time period of each item,
Figure 364643DEST_PATH_IMAGE011
is a first
Figure 386826DEST_PATH_IMAGE011
The number of days is,
Figure 38387DEST_PATH_IMAGE012
is as follows
Figure 411599DEST_PATH_IMAGE013
An item is at
Figure 806809DEST_PATH_IMAGE014
The theoretical capacity of a day is the conversion rate,
Figure 824443DEST_PATH_IMAGE015
for reference in operation record
Figure 912485DEST_PATH_IMAGE008
Average of the daily capacity conversion for each project.
The method for obtaining the operation health index of each project according to the health degree of each project and the variance of the theoretical productivity conversion rate of each day comprises the following steps:
and e is taken as a base number, the variance of the theoretical productivity conversion rate of each day is taken as an index to obtain an exponential power, and the product of the reciprocal of the exponential power and the health degree of the project is taken as the operation health index of each project.
The invention has the beneficial effects that:
(1) Acquiring a reference operation record of each project of an enterprise project by utilizing big data, and obtaining the actual productivity conversion rate of the project each day according to the predicted cost, the predicted total energy, the predicted daily productivity and the actual cost of the project each day in the actual operation; the method can definitely, continuously and effectively reflect the conversion rate of the daily input conversion energy production of the enterprise on each project;
(2) Obtaining an influence factor of the actual productivity conversion rate of each project per day, and obtaining a theoretical productivity conversion rate of each project per day according to the influence factor and the actual productivity conversion rate per day; the method eliminates the negative influence of the ineffectiveness factor on the daily productivity conversion rate, and obtains the accurate theoretical daily productivity conversion rate;
(3) Obtaining the health degree of each project according to the theoretical productivity conversion rate of each project per day, the actual productivity conversion rate of each day, the predicted operation duration and the actual operation duration; the length of the project period and the actual energy production conversion rate in the method are direct representations of whether the project is efficient or not and whether the project is qualified or not, so that the obtained health degree can accurately reflect the state of the project in actual operation, the reliability is high, and effective basis can be provided for subsequent strategy adjustment.
Drawings
In order to more clearly illustrate the embodiments of the present invention 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, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a block diagram of a big data-based enterprise operation health index evaluation system according to the present invention;
FIG. 2 is a schematic diagram of clustering items according to time periods in the big data-based enterprise operation health index evaluation system.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, 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 invention.
An embodiment of the enterprise operation health index evaluation system based on big data of the present invention, as shown in fig. 1, includes:
s100, a database module: the system is used for storing operation records of finished projects of various scales and types obtained by utilizing big data, wherein the operation records comprise predicted cost, predicted total energy, predicted daily capacity and predicted operation duration;
it should be noted that, the module obtains the operation records of the same type and same specification project cases of each project of the enterprise by using the big data, and obtains the reference operation records of each project of the enterprise by project planning, because the current market environment and industry type tend to be more and more perfect, and a closed loop is formed between related industry chains, namely a supply-demand relationship network formed between enterprises, when an enterprise takes over a project from a project company, the big data is often used to obtain the same type and same specification projects in the industry, and capital, personnel, equipment, period, profit data and the like are invested, and then professional personnel draw up project plans and reference operation records, for example, a bid document belongs to one of the reference operation records, so that the enterprise evaluates the projects, determines bid values, and estimates the final profit condition by taking over the operation plans after the projects.
Therefore, in the module, the reference operation record of each item of the enterprise in the current year is obtained, and the reference operation record comprises information such as total energy, daily capacity, actual completion period, predicted completion period and predicted cost of each item.
S101, an input module: the system is used for inputting the operation record of each project of the enterprise and sending the operation record of each project of the enterprise to the analysis processing module S102;
s102, an analysis processing module specifically executes the following contents:
(1) Receiving the operation record of each project of the enterprise sent by the input module, selecting the operation record of the completed project with the same scale and the same type as the project from the database module, and taking the operation record as the reference operation record of the project;
(2) According to the predicted cost, the predicted total capacity and the predicted daily capacity of each project in the reference operation record and the actual cost of each day of the project in actual operation, the actual capacity conversion rate of each day of the project is obtained, and the specific method comprises the following steps:
obtaining the ratio of the predicted cost and the predicted total production energy of each project in the reference operation record, namely the predicted cost of each unit production energy of the project, obtaining the predicted daily investment of the project according to the predicted cost of each unit production energy of the project and the predicted daily production energy of the project, and taking the ratio of the predicted daily investment of the project and the actual cost of each day of the project in the actual operation as the actual production energy conversion rate of each day of the project, wherein the calculation formula is as follows:
Figure 507414DEST_PATH_IMAGE016
in the formula (I), the compound is shown in the specification,
Figure 706315DEST_PATH_IMAGE017
is as follows
Figure 109614DEST_PATH_IMAGE018
An item is at
Figure 962032DEST_PATH_IMAGE019
The conversion rate of the actual production capacity of the day,
Figure 716362DEST_PATH_IMAGE020
is as follows
Figure 656636DEST_PATH_IMAGE021
The number of the items is one,
Figure 180021DEST_PATH_IMAGE022
is as follows
Figure 203341DEST_PATH_IMAGE023
The predicted cost of an item in the reference operating record,
Figure 179387DEST_PATH_IMAGE024
is as follows
Figure 47986DEST_PATH_IMAGE023
The total energy of an item in the reference operating record,
Figure 691457DEST_PATH_IMAGE025
is a first
Figure 495465DEST_PATH_IMAGE026
The item is in the reference operation record
Figure 224387DEST_PATH_IMAGE027
The capacity produced by the solar cell is the capacity,
Figure 303201DEST_PATH_IMAGE028
is as follows
Figure 635142DEST_PATH_IMAGE030
An item is at
Figure 179256DEST_PATH_IMAGE031
Actual cost input of days;
wherein:
Figure 61761DEST_PATH_IMAGE032
represents the cost of the enterprise to operate the project per unit capacity;
Figure 883087DEST_PATH_IMAGE033
represents the project to operate
Figure 825635DEST_PATH_IMAGE027
Output of the day
Figure 591466DEST_PATH_IMAGE034
The cost theoretically paid by the capacity;
Figure 12083DEST_PATH_IMAGE035
is divided by
Figure 484652DEST_PATH_IMAGE036
The value of (a) represents the ratio of the theoretical daily input cost to the actual input cost for the project, and also reflects the conversion rate of the daily input cost of the enterprise into the productivity on the project.
The formula obtains the cost input of the unit production energy in the reference operation record according to the known project cost and the project total energy in the reference operation record, and the cost input is multiplied by the daily production energy and is compared with the actual input cost to obtain the production energy conversion rate;
(3) Obtaining an influence factor of the actual productivity conversion rate of each project per day, and obtaining a theoretical productivity conversion rate of each project per day according to the influence factor and the actual productivity conversion rate per day;
for each project, the daily capacity conversion rate is counted, the change of the daily capacity conversion rate in one year is analyzed, the capacity is accumulated to be profitable, the capacity and the capacity conversion rate are reduced due to the influence of a plurality of interference factors, the ineligible capacity factors and negative operation factors are included, the ineligible capacity factors include random variables which have negative influence on the production capacity of the enterprise, such as weather factors, industry changes and holidays, the random variables cannot be determined and changed by the enterprise, the daily capacity conversion rate needs to be free of the influence caused by the ineligible capacity factors, and the rest is the capacity conversion rate produced by the operation efficiency and the health degree of the enterprise.
The specific method for acquiring the influence factors of the actual productivity conversion rate of each project per day comprises the following steps:
setting characteristic data influencing actual productivity conversion rate, including weather, holidays and market environment;
estimating the influence probability of the feature data influencing the actual capacity conversion rate every day, and taking the probability value of the feature data with the maximum probability as an influence factor influencing the actual capacity conversion rate every day;
specifically, the method comprises the following steps of acquiring the influence factors of the actual productivity conversion rate of each project per day through a training classification network:
firstly, selecting characteristics of inelasticity factors, namely characteristic data influencing actual productivity conversion rate: data such as historical weather information, holiday information, and large market environment assessment values;
then, the enterprise and the project company simultaneously evaluate the influence of the force irresistible factors in 4-quarter data of historical data every day, namely, actually evaluating the influence probability value of the characteristic data of the force irresistible factors on production work every day, namely, manually scoring, evaluating the characteristic data of the force irresistible factors in each day, and evaluating the influence probability value of the production work every day, wherein the two companies simultaneously evaluate the force irresistible factors in each day to overcome the evaluation subjectivity of the company and the project company in different standings, so that the two companies average the influence evaluation results of the force irresistible factors in each day, and taking the average value as the influence value of the force irresistible factors in each day;
finally, the historical data, namely the influence value of force-inefficacy factors in 4-quarter data every day is used as the historical data, and the proportion of the training set to the test set in the historical data is set to be 7:3, taking 70% of historical data as a training set and taking 30% of historical data as a test set;
training the classification network through training set data, wherein the input of the classification network is as follows: the output of the inequality factor characteristic data in the training data is as follows: the actual capacity conversion per day for each project. In the classification network training process, training is carried out through a gradient descent method until a loss function is converged, and classification network training is finished, wherein the classification network structure is Encoder-FC, and the loss function is a cross entropy function;
further, the existing inelasticity factor data are classified by utilizing a trained classification network, the influence factor of the actual productivity conversion rate of each project per day is output by inputting the inelasticity factor data per day, and the influence factor of the actual productivity conversion rate of each project per day is outputSeed of Japanese apricot
Figure 801364DEST_PATH_IMAGE037
The essence of (a) is the classification probability output by the classification network,
Figure 726595DEST_PATH_IMAGE038
the value of (a) is between 0 and 1,
Figure 302237DEST_PATH_IMAGE039
is as follows
Figure 629313DEST_PATH_IMAGE040
The actual capacity conversion per day per project per day.
The method for obtaining the theoretical productivity conversion rate of each project per day according to the influence factor of the actual productivity conversion rate of each project per day and the productivity conversion rate of each project per day in actual operation comprises the following steps:
multiplying the actual capacity conversion rate of each project per day by the influence factor of the actual capacity conversion rate of each project per day, and taking the result value added with the actual capacity conversion rate as the theoretical capacity conversion rate of each project per day, wherein the calculation method comprises the following steps:
Figure 507139DEST_PATH_IMAGE041
in the above formula, the first and second carbon atoms are,
Figure 919666DEST_PATH_IMAGE042
represents the first
Figure 885348DEST_PATH_IMAGE043
The influence factor of the conversion rate of the actual production capacity of the day,
Figure 66930DEST_PATH_IMAGE044
represents the item of
Figure 115658DEST_PATH_IMAGE045
The conversion rate of the daily productivity is improved,
Figure 15481DEST_PATH_IMAGE046
represents the first
Figure 909487DEST_PATH_IMAGE043
Daily production work at a theoretical daily energy conversion rate that is not affected by the impact of the actual energy conversion rate.
Purposes and effects of this step: the force-ineligible factors cause loss of daily productivity and productivity conversion rate, and the enterprises cannot avoid the force-ineligible factors, so that the negative influence of random events of the force-ineligible factors on the daily productivity conversion rate has to be eliminated or reduced in order to accurately evaluate the operation health indexes of the enterprises and projects.
For example, if the daily capacity conversion rate of a project is 30%, and the weather condition of the day is very poor, and the influence factor of the actual capacity conversion rate is 0.4, then we consider that the project may be influenced by the weather condition to cause the daily capacity conversion rate to be low, and without the influence of the weather condition, the daily capacity conversion rate of the project should be: 30 percent of
Figure 945576DEST_PATH_IMAGE047
(1 + 0.4) =42%. The 42% is the theoretical daily energy conversion rate which is possessed by enterprises, teams and groups of projects, technologies, decisions, equipment and the like and can produce.
(4) Obtaining the health degree of each project according to the theoretical capacity conversion rate of each project per day, the actual capacity conversion rate of each day, the predicted operation duration and the actual operation duration;
the method for obtaining the health degree of each project according to the theoretical capacity conversion rate of each project per day, the actual capacity conversion rate of each day, the predicted operation duration and the actual operation duration comprises the following steps:
Figure 571730DEST_PATH_IMAGE048
in the formula (I), the compound is shown in the specification,
Figure 162111DEST_PATH_IMAGE049
is as follows
Figure 266333DEST_PATH_IMAGE050
The degree of health of the individual item(s),
Figure 15984DEST_PATH_IMAGE051
to be composed of
Figure 813038DEST_PATH_IMAGE052
An exponential function of the base is used,
Figure 749770DEST_PATH_IMAGE052
is a natural constant and is a natural constant,
Figure 923263DEST_PATH_IMAGE053
is as follows
Figure 137206DEST_PATH_IMAGE013
The actual running time of the individual items, i.e. the total number of days,
Figure 105162DEST_PATH_IMAGE054
for reference in operation record
Figure 201294DEST_PATH_IMAGE055
The predicted operation time period of each item,
Figure 240794DEST_PATH_IMAGE056
is a first
Figure 371561DEST_PATH_IMAGE056
The number of days is,
Figure 838315DEST_PATH_IMAGE057
is a first
Figure 421743DEST_PATH_IMAGE058
An item is at
Figure 140300DEST_PATH_IMAGE056
The theoretical capacity per day is the conversion rate,
Figure 125574DEST_PATH_IMAGE059
for reference in operation record
Figure 763229DEST_PATH_IMAGE050
Average of the daily capacity conversion for each project.
In this formula:
Figure 833953DEST_PATH_IMAGE060
on behalf of the duration of the operation of the project,
Figure 356201DEST_PATH_IMAGE061
representing the sequence number of the target item,
Figure 195981DEST_PATH_IMAGE062
represents
Figure 4537DEST_PATH_IMAGE063
A reference operating record for the item is recorded,
Figure 296978DEST_PATH_IMAGE064
represents the first
Figure 154076DEST_PATH_IMAGE065
The difference between the actual operation duration of each project and the operation duration of the reference operation record represents the overdue degree of the actual operation duration of the project;
Figure 441837DEST_PATH_IMAGE066
converse for inverse proportionality:
namely, it is
Figure 93399DEST_PATH_IMAGE067
When the number is negative, the project is completed in advance,
Figure 341977DEST_PATH_IMAGE068
is taken along with
Figure 737187DEST_PATH_IMAGE069
The smaller the value of (c) is, the more [1, + ∞]The larger the inner;
Figure 613876DEST_PATH_IMAGE070
when the number is positive, it represents that the item is overdue,
Figure 701918DEST_PATH_IMAGE071
is taken as follows
Figure 562426DEST_PATH_IMAGE072
The larger the value of (A) is, the more the value of (B) is in [0,1 ]]The smaller the inner, i represents any day in the operation cycle of the project,
Figure 230168DEST_PATH_IMAGE073
representing the theoretical capacity of the project after removing the force factor,
Figure 633467DEST_PATH_IMAGE074
representing the average daily energy production conversion rate found by reference to the operating record,
Figure 485886DEST_PATH_IMAGE075
represents the maximum number of days of operation for the project,
Figure 709057DEST_PATH_IMAGE076
it represents the cumulative sum of the differences between the theoretical daily energy-to-production conversion rate for each day and the average daily energy-to-production conversion rate obtained from the reference operational record for the operational cycle of the project.
Figure 446069DEST_PATH_IMAGE077
For direct proportional transformation, constraint
Figure 703875DEST_PATH_IMAGE078
Make it and
Figure 727194DEST_PATH_IMAGE079
the dimension is removed and the unification is carried out,
Figure 703240DEST_PATH_IMAGE080
is a positive number, and the larger it is
Figure 978364DEST_PATH_IMAGE081
In [1, + ∞ ]]The larger the interior, the healthier the project operation
Figure 356256DEST_PATH_IMAGE082
Is negative, and the smaller the number
Figure 957001DEST_PATH_IMAGE083
In the [0,1 ]]The smaller the interior, the healthier the project operation is;
Figure 748240DEST_PATH_IMAGE084
and
Figure 92633DEST_PATH_IMAGE085
the meaning of the multiplication is that after the unification of the dimensions, the item overdue degree is multiplied by the cumulative sum of the difference between the theoretical daily energy conversion rate and the average daily energy conversion rate obtained by referring to the operation records, the healthier the item is, the product is a positive number which is more than or equal to 1, and the bigger the item is, the worse the item is, the product is a decimal number which is more than 0 and less than 1.
The beneficial effect of this step: the length of the project period and the daily energy conversion rate are direct representations for judging whether the project is efficient or not and qualified or not, and the reference operation records are obtained by utilizing big data and combining the self-ability cognition of enterprises, so that the state of the project in actual operation can be reflected better by comparing with the reference operation records.
(5) Obtaining an operation health index of each project according to the health degree of each project and the variance of the theoretical productivity conversion rate of each day, and sending the operation health index of each project to the display module S103 for display;
the method for obtaining the operation health index of each project according to the health degree of each project and the variance of the theoretical productivity conversion rate of each day comprises the following steps:
e is taken as the base number, and the variance of the theoretical productivity conversion rate per day is taken as the base number
Figure 59452DEST_PATH_IMAGE086
Is an exponent to obtain an exponential power
Figure 565520DEST_PATH_IMAGE087
The inverse of the exponential power
Figure 109634DEST_PATH_IMAGE088
Health degree of conversion rate of actual production capacity per day
Figure 585615DEST_PATH_IMAGE089
As an operation health index of each project, the calculation formula is:
Figure 938099DEST_PATH_IMAGE090
in the formula (I), the compound is shown in the specification,
Figure 83909DEST_PATH_IMAGE091
is as follows
Figure 521844DEST_PATH_IMAGE092
The operational health index of an individual project,
Figure 535936DEST_PATH_IMAGE093
to be composed of
Figure 742927DEST_PATH_IMAGE094
An exponential function of the base (A) is,
Figure 325218DEST_PATH_IMAGE095
has the meaning of
Figure 250448DEST_PATH_IMAGE096
，
Figure 802652DEST_PATH_IMAGE094
Is a natural constant and is a natural constant,
Figure 129728DEST_PATH_IMAGE097
is as follows
Figure 414079DEST_PATH_IMAGE098
Theoretical capacity conversion per day for each project
Figure 154502DEST_PATH_IMAGE099
The variance of (c).
It should be noted that the stability of the daily productivity conversion rate also reflects the health degree of the project operation, and the dispersion of the data, i.e., the variance, is used to characterize the stability of the daily productivity conversion rate, and the health degree of the daily productivity conversion rate and the stability of the daily productivity conversion rate are combined to obtain the operation health index of the project.
S103, a display module: receiving and displaying the operation health index sent by the analysis processing module S102;
furthermore, the operation health indexes displayed by the module are obtained, each project operation health index is used as a reference of an operation decision, the operation decision can be traced, and strategic adjustment is carried out, wherein the specific method comprises the following steps:
setting a project operation health index threshold of 1 when
Figure 182501DEST_PATH_IMAGE100
Project operation health index of individual project
Figure 567346DEST_PATH_IMAGE101
At least when the value is greater than or equal to item 1, item 1
Figure 22598DEST_PATH_IMAGE102
The operation of each project is healthy, otherwise, the number is more than 0 and less than 1
Figure 250317DEST_PATH_IMAGE103
There are operational problems with individual projects.
Further, all the projects of the enterprise in one year are obtained
Figure 816428DEST_PATH_IMAGE104
According to the operation health degrees of all projects, the change of the enterprise operation health index in different time periods and different decisions is calculated, and the specific method comprises the following steps:
carrying out supervised clustering on all projects according to the similarity of operation time periods, namely inputting a plurality of groups of manually divided time periods, and clustering projects which are overlapped in a large range and relatively concentrated on a time sequence through machine learning, for example, if the operation time period of a project A is 8 months 1-7 days, the operation time periods of projects B and C are 8 months 1-8 months 8 and 8 months 2-8 months 10, the three project time sequences are considered to be almost parallel and divided into a cluster, so each cluster is a project with parallel simultaneous periods, and it needs to be noted that time overlapping and project overlapping are allowed to exist between the clusters, as shown in FIG. 2;
statistics of all items per cluster, i.e. per simultaneous segment in parallel
Figure 445992DEST_PATH_IMAGE104
And (4) value, extracting features in the cluster, namely mean value, discreteness and unhealthy item ratio. And screening the time period when the operation problem occurs in the project set. This step is relatively conventional, and allows direct observation within each cluster, even without computing any features
Figure 72146DEST_PATH_IMAGE105
The number of the value exceptions, and the time period in which the more problematic items are concentrated is screened out;
setting the operation decision made by the enterprise operator in turn throughout the year as
Figure 193685DEST_PATH_IMAGE106
The decisions are distributed on a time sequence, the time period with operation problems is matched with the operation decisions, and bad decisions can be corrected in time and strategic directions can be adjusted.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (6)

1. The utility model provides an enterprise operation health index evaluation system based on big data which characterized in that includes database module, input module, analysis processing module and display module:
the database module is as follows: the system comprises a data storage module, a data processing module and a data processing module, wherein the data storage module is used for storing operation records of finished projects of various scales and types acquired by big data, and the operation records comprise predicted cost, predicted total energy, predicted daily capacity and predicted operation duration;
the input module is used for: the system comprises an analysis processing module, a storage module and a display module, wherein the analysis processing module is used for inputting operation records of each project of an enterprise, including actual cost and actual operation duration of each day in actual operation and sending the operation records of each project of the enterprise to the analysis processing module;
the analysis processing module: receiving the operation record of each project of the enterprise sent by the input module, selecting the operation record of the completed project with the same scale and the same type as each project from the database module, and taking the operation record as the reference operation record of each project;
obtaining the actual productivity conversion rate of each project per day according to the predicted cost, the predicted total productivity and the predicted daily productivity of each project in the reference operation record and the actual cost of each project per day in the actual operation;
acquiring an influence factor of the actual productivity conversion rate of each project per day, and acquiring a theoretical productivity conversion rate of each project per day according to the influence factor of the actual productivity conversion rate of each project per day and the actual productivity conversion rate of each day;
obtaining the health degree of each project according to the theoretical productivity conversion rate of each project per day, the actual productivity conversion rate of each day, the predicted operation duration and the actual operation duration;
obtaining an operation health index of each project according to the health degree of each project and the variance of the theoretical productivity conversion rate of each day, and sending the operation health index of each project to a display module for displaying;
the display module: and receiving and displaying the operation health index sent by the analysis processing module.
2. The big-data-based enterprise operation health index evaluation system as claimed in claim 1, wherein the method for obtaining the actual productivity conversion rate of each project per day according to the predicted cost, the predicted total energy, the predicted daily productivity of each project in the reference operation record and the actual cost of each project per day in the actual operation comprises:
and obtaining the ratio of the predicted cost and the predicted total production energy of each project in the reference operation record, multiplying the ratio and the predicted daily production energy of the project to obtain the predicted daily investment of the project, and taking the ratio of the predicted daily investment of the project and the actual cost of the project in each day of actual operation as the actual production energy conversion rate of the project each day.
3. The big-data based enterprise operation health index evaluation system as claimed in claim 1, wherein the method for obtaining the impact factors of the actual capacity conversion rate of each project per day comprises:
setting characteristic data influencing actual productivity conversion rate, including weather, holidays and market environment;
and evaluating the influence probability of the feature data influencing the actual capacity conversion rate every day, and taking the probability value of the feature data with the maximum probability as an influence factor influencing the actual capacity conversion rate every day.
4. The big-data-based enterprise operation health index evaluation system as claimed in claim 1, wherein the specific method for obtaining the theoretical capacity conversion rate per day of each project according to the impact factor of the actual capacity conversion rate per day of each project and the actual capacity conversion rate per day of each project comprises:
multiplying the influence factor of the actual productivity conversion rate of each project per day with the actual productivity conversion rate per day, and taking the result value added with the actual productivity conversion rate as the theoretical productivity conversion rate of each project per day.
5. The big-data-based enterprise operation health index evaluation system as claimed in claim 1, wherein the method for obtaining the health degree of each project according to the theoretical capacity conversion rate of each project per day, the actual capacity conversion rate of each day, the predicted operation duration and the actual operation duration comprises:
Figure 944612DEST_PATH_IMAGE001
in the formula (I), the compound is shown in the specification,
Figure 134285DEST_PATH_IMAGE002
is a first
Figure 502949DEST_PATH_IMAGE003
The degree of health of the individual item,
Figure 69060DEST_PATH_IMAGE004
to be composed of
Figure 698624DEST_PATH_IMAGE005
An exponential function of the base (A) is,
Figure 652674DEST_PATH_IMAGE006
is a natural constant and is a natural constant,
Figure 39793DEST_PATH_IMAGE007
is a first
Figure 612857DEST_PATH_IMAGE008
The actual running time of the individual items, i.e. the total number of days,
Figure 96928DEST_PATH_IMAGE009
for reference in operation record
Figure 221878DEST_PATH_IMAGE010
The predicted operation time period of each item,
Figure 33977DEST_PATH_IMAGE011
is as follows
Figure 800944DEST_PATH_IMAGE012
The number of days is,
Figure 811626DEST_PATH_IMAGE013
is as follows
Figure 779582DEST_PATH_IMAGE014
An item is in
Figure 203610DEST_PATH_IMAGE015
The theoretical capacity per day is the conversion rate,
Figure 915214DEST_PATH_IMAGE016
for reference in operation record
Figure 249243DEST_PATH_IMAGE017
Average of the daily capacity conversion for each project.
6. The big-data-based enterprise operation health index evaluation system as claimed in claim 1, wherein the method for obtaining the operation health index of each project according to the health degree of each project and the variance of the theoretical capacity-to-conversion rate per day comprises:
and taking e as a base number, taking the variance of the theoretical productivity conversion rate of each day as an exponent to obtain an exponential power, and taking the product of the reciprocal of the exponential power and the health degree of the project as the operation health index of each project.
CN202211118153.7A 2022-09-15 2022-09-15 Enterprise operation health index evaluation system based on big data Active CN115204527B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211118153.7A CN115204527B (en) 2022-09-15 2022-09-15 Enterprise operation health index evaluation system based on big data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211118153.7A CN115204527B (en) 2022-09-15 2022-09-15 Enterprise operation health index evaluation system based on big data

Publications (2)

Publication Number Publication Date
CN115204527A CN115204527A (en) 2022-10-18
CN115204527B true CN115204527B (en) 2022-11-18

Family

ID=83572837

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211118153.7A Active CN115204527B (en) 2022-09-15 2022-09-15 Enterprise operation health index evaluation system based on big data

Country Status (1)

Country Link
CN (1) CN115204527B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2006004132A1 (en) * 2004-07-05 2006-01-12 Intellectual Property Bank Corp. Device for specifying company evaluation contribution factor and/or index, specifying program, and specifying method
CN109657887A (en) * 2017-10-10 2019-04-19 爱信诺征信有限公司 A kind of enterprise operation health Evaluation method and system
KR20190134309A (en) * 2018-05-25 2019-12-04 전자부품연구원 Method and System for Supporting Outsourcing Company Reliability Evaluation
CN110826923A (en) * 2019-11-09 2020-02-21 中国海洋大学 Enterprise management comprehensive evaluation system
CN110942242A (en) * 2019-11-22 2020-03-31 吉林省创业孵化投资管理有限公司 Method for evaluating operation performance of incubator of scientific and technological enterprise
CN111861537A (en) * 2020-05-24 2020-10-30 上海维信荟智金融科技有限公司 Operation analysis method and system
CN112836922A (en) * 2020-12-08 2021-05-25 江苏经贸职业技术学院 Evaluation system based on enterprise management
CN114186760A (en) * 2022-02-17 2022-03-15 北京融信数联科技有限公司 Analysis method and system for stable operation of enterprise and readable storage medium

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11954003B2 (en) * 2020-03-20 2024-04-09 UncommonX Inc. High level analysis system with report outputting

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2006004132A1 (en) * 2004-07-05 2006-01-12 Intellectual Property Bank Corp. Device for specifying company evaluation contribution factor and/or index, specifying program, and specifying method
CN109657887A (en) * 2017-10-10 2019-04-19 爱信诺征信有限公司 A kind of enterprise operation health Evaluation method and system
KR20190134309A (en) * 2018-05-25 2019-12-04 전자부품연구원 Method and System for Supporting Outsourcing Company Reliability Evaluation
CN110826923A (en) * 2019-11-09 2020-02-21 中国海洋大学 Enterprise management comprehensive evaluation system
CN110942242A (en) * 2019-11-22 2020-03-31 吉林省创业孵化投资管理有限公司 Method for evaluating operation performance of incubator of scientific and technological enterprise
CN111861537A (en) * 2020-05-24 2020-10-30 上海维信荟智金融科技有限公司 Operation analysis method and system
CN112836922A (en) * 2020-12-08 2021-05-25 江苏经贸职业技术学院 Evaluation system based on enterprise management
CN114186760A (en) * 2022-02-17 2022-03-15 北京融信数联科技有限公司 Analysis method and system for stable operation of enterprise and readable storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
基于DEA的光伏企业经营绩效评价指数研究;罗珏;《武汉理工大学学报》;20180630;第40卷(第3期);第341-346页 *
基于关键流程的公司运营指数理论模型与应用研究;魏敏兰等;《软件》;20160615;第37卷(第06期);第105-112页 *

Also Published As

Publication number Publication date
CN115204527A (en) 2022-10-18

Similar Documents

Publication Publication Date Title
CN108388974A (en) Top-tier customer Optimum Identification Method and device based on random forest and decision tree
CN108389069A (en) Top-tier customer recognition methods based on random forest and logistic regression and device
Taraniuk et al. Estimation of the marketing potential of industrial enterprises in the period of re-engineering of business processes
CN116307928A (en) Object supervision management system
CN116843378A (en) Hardware fitting supply prediction method and system based on deep learning
CN118350611B (en) Enterprise resource comprehensive integrated intelligent management system and method
CN112001551B (en) Ground and commercial power grid sales electricity quantity prediction method based on large-user electricity quantity information
CN115204527B (en) Enterprise operation health index evaluation system based on big data
CN117853072B (en) Supply chain management system and method
CN114139916A (en) Method and system for custom configuration of enterprise evaluation model
CN118428976A (en) Intangible asset value assessment method based on big data
CN114676931B (en) Electric quantity prediction system based on data center technology
CN113112362A (en) Bulk commodity price fluctuation risk situation evolution analysis method and system based on associated information
CN114119237A (en) Method and device for screening pension products
Zhang Application of data mining technology in financial risk management
WO2022227213A1 (en) Industry recommendation method and apparatus, computer device and storage medium
Zhang et al. Application of Adaboost Algorithm in Enterprise Financial Risk Analysis Model
CN112465381B (en) Building engineering construction progress data sharing scheduling management cloud platform based on cloud computing
CN116777379B (en) Intelligent operation management platform based on dynamic data
Wang Research on a Financial Crisis Early Warning Model Based on a Stochastic Forest Algorithm
CN117611364A (en) Input cost estimated deviation measuring and calculating method and system thereof
Wan et al. Equity incentive, heterogeneity of top management team and overinvestment
Ouyang Financial Risk Control of Listed Enterprises Based on Risk Warning Model
Naidovich et al. Survival analysis in credit scoring
CN118211692A (en) Electric power business expansion and installation inspection optimization method based on commercial environment state monitoring

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