Enterprise important index monitoring system and method

Abstract

The invention relates to the technical field of intelligent enterprise management, in particular to an enterprise important index monitoring method, which comprises the following steps: constructing a budget list; obtaining the proportion of the quota of each budget item in the total budget, and then constructing an original monitoring index set; setting a plurality of # imgabs0 # dimension budget target vectors, and forming a budget target matrix through the budget target vectors; dividing the original monitoring index set into monitoring index subsets related to each budget target vector according to the dimensions of the budget target vectors; establishing a prediction model I through a machine learning algorithm, wherein the prediction model I is used for monitoring budget items in the monitoring index subset; screening a plurality of key monitoring indexes according to association degrees of elements in different monitoring index subsets, and constructing a key index list; and a second prediction model is constructed, and key monitoring indexes are monitored through the second prediction model. According to the method, the proportion (important indexes) of key budget items in the budget in the total budget is monitored, the prediction result is output, and enterprise managers are helped to make decisions.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent enterprise management, and in particular to a system and method for monitoring important indicators of an enterprise. Background Art

[0002] A financial budget is a financial plan that a company develops to achieve its stated goals. It involves forecasts of revenue, expenditure, capital use, and expected results. The purpose of a budget is to ensure the effective use of a company's resources and to provide financial guidance for future production and operations. Budgets can be divided into direct production-related budgets, which are directly related to production activities, including raw material procurement, production costs, labor costs, etc. and R&D-related budgets, which are used to support the development of new products or technologies, including researcher salaries, experimental material costs, etc.

[0003] Budget indicator monitoring helps companies to identify cost overruns or resource waste in a timely manner, so that they can take measures to adjust their production and operation strategies. By monitoring R&D budgets, companies can predict the progress and effectiveness of R&D projects and ensure that R&D activities are consistent with corporate strategic goals. Budget indicator monitoring provides management with important decision-making support information, helping them make more informed choices in resource allocation and strategic planning. Summary of the invention

[0004] The present invention selects key budget items for monitoring through the correlation between various budget items, monitors the proportion (important indicators) of key budget items in the total budget through an artificial algorithm model, and outputs prediction results to help enterprise managers make decisions.

[0005] The technical solution provided by the present invention is: a method for monitoring important indicators of an enterprise, the method comprising: Build a budget list; Get the ratio of each budget item to the total budget, and then construct the original monitoring indicator set; A plurality of n-dimensional budget target vectors are set, and a budget target matrix is ​​formed by the budget target vectors; the dimension n of the budget target vectors is greater than 2; According to the dimension of the budget target vector, the original monitoring indicator set is divided into monitoring indicator subsets related to each budget target vector; Establishing a prediction model 1 through a machine learning algorithm to monitor budget items within a subset of monitoring indicators; According to the correlation of elements in different monitoring indicator subsets, multiple key monitoring indicators are screened and a key indicator list is constructed; Prediction model 2 is constructed through machine learning algorithm, and key monitoring indicators are monitored through prediction model 2.

[0006] Preferably, the step of constructing a budget list and obtaining a plurality of budget items from the budget list includes: Export historical budget data from the company's financial system or budgeting tool; Extract budget items and corresponding amounts from the company's historical budget data and generate a budget list including all budget items; Extracting budget targets and budget target achievement rates from the company's historical budget data, wherein the budget target achievement rates include multiple sub-target achievement rates and a comprehensive target achievement rate; The budget items include one or more of energy consumption budget, raw material procurement budget, consumables procurement budget, equipment maintenance budget, labor cost budget, R&D capital investment budget, R&D personnel training budget, scientific research equipment procurement budget, R&D personnel recruitment budget and floating budget.

[0007] Preferably, obtaining the ratio of the amount of each budget item to the total budget amount and then constructing the original monitoring indicator set includes: Convert the amount data of each budget item into a numeric type, then sum the amounts of all budget items to obtain the total budget amount; Calculate the budget ratio of each budget item to the total budget ; Set the ratio threshold , if the proportion of budget items meets the following target screening conditions: , then the budget item is used as a monitoring item, where , , ; Multiple monitoring items that meet the target filtering conditions form the original monitoring indicator set ;in, Indicates the number of monitored items.

[0008] Preferably, the setting of multiple Dimensional budget target vector, including: Set the budget target vector: ;in Respectively represent the first to the budget targets; Set the watch item vector ,in, Indicates The name of the monitored item. Indicates The budget ratio corresponding to each monitoring item; From the original monitoring indicator set Winning The first A monitoring item vector associated with a budget target: , then The budget target is expressed as: ,in, , ; Convert the budget target into a budget target matrix consisting of monitoring items: .

[0009] Preferably, the setting of multiple time periods and setting different weights according to different time periods include: According to the dimension of the budget target vector, the original monitoring indicator set is divided into a plurality of monitoring indicator subsets related to the corresponding budget target vectors, including: Will be with Budget Targets The associated monitoring item vectors constitute a monitoring indicator subset , ={ }, ; Combine multiple monitoring indicator subsets into a monitoring indicator set: .

[0010] Preferably, the method of establishing a prediction model 1 by a machine learning algorithm for monitoring budget items within a subset of monitoring indicators includes: Building a prediction model 1: ,in , is the intercept, is the error term, is the regression coefficient; The prediction model 1 is trained by a linear regression algorithm so that the prediction model 1 learns the relationship between the budget quota ratio and the budget target achievement rate; Through the trained prediction model 1, after inputting multiple new budget quota ratios, the corresponding sub-goal achievement rate prediction value is output; Set the achievement rate threshold ,if , then the budget target achievement rate is considered unsatisfactory and warning information 1 is output.

[0011] Preferably, the step of screening multiple key monitoring indicators according to the correlation of elements in different monitoring indicator subsets and constructing a key indicator list includes: from Extract the budget amount corresponding to each monitoring item to build a ratio set 1: , from Extract the budget amount corresponding to each monitoring item to build the ratio set 2: ; Construct event set 1 by taking each event in which the budget amount in ratio set 1 changes, that is: {event 1, event 2, ..., event }; Construct event set 2 by taking each budget change event in ratio set 2, that is: {event ,event ,......,event }; Obtain statistics from historical budget data on the number of times each event in event set 2 causes all events in event set 1 to occur, and determine the degree of correlation between the events in event set 2 and those in event set 1 by comparing the lifts. The multiple events associated with event set 1 and event set 2 constitute a monitoring event set, and the monitoring item names corresponding to the events in the monitoring event set and the budget quota ratios corresponding to the monitoring item names constitute a key indicator list.

[0012] Preferably, a second prediction model is constructed by a machine learning algorithm, and key monitoring indicators are monitored by the second prediction model, including: Building prediction model 2: ,in, Indicates the number of monitored items in the terminal indicator list; Training prediction model 2; Input the budget quota ratio in the newly obtained key indicator list into the forecast model 2, and output the forecast value of the comprehensive target achievement rate; Set the achievement rate threshold ,if , then the comprehensive target achievement rate is considered unsatisfactory and the second warning information is output.

[0013] The present invention also provides a system for monitoring important indicators of an enterprise, and the system is used to execute the method for monitoring important indicators of an enterprise.

[0014] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method for monitoring important enterprise indicators.

[0015] Beneficial effects of the present invention: 1. The present invention exports budget data from the enterprise's financial system or budget preparation tool, organizes the exported data into a budget list, sums the amounts of all budget items, calculates the proportion of the amount of each budget item to the total budget amount, screens out key monitoring indicators by analyzing the correlation of elements in the monitoring indicator subset, organizes the screened key indicators into a list, and uses the second prediction model to continuously monitor the actual indicators of the enterprise. Enterprises can establish an effective budget management system to help enterprises better control costs, optimize resource allocation, and carry out financial planning and decision support.

[0016] 2. In the present invention, when training prediction model 1, the budget quota ratio is selected as the independent variable (explanatory variable), and the budget target achievement rate is set as the dependent variable (response variable). Use a linear regression algorithm to train prediction model 1 so that it learns the relationship between the budget quota ratio and the budget target achievement rate. Input the new budget quota ratio into the trained prediction model 1. Prediction model 1 outputs the corresponding sub-target achievement rate prediction value. According to the management needs of the enterprise and historical data analysis, a reasonable achievement rate threshold is set. If the predicted sub-target achievement rate is lower than the set threshold, the budget target achievement rate is considered unqualified. When the predicted sub-target achievement rate is lower than the threshold, the system automatically outputs warning information 1. The warning information can help the enterprise management to understand the potential risks of budget execution in a timely manner and take corresponding countermeasures.

[0017] 3. In the present invention, historical data is obtained from the financial database of the enterprise, including the budget quota ratio and the corresponding comprehensive target achievement rate, the budget quota ratio is selected as the independent variable, and the comprehensive target achievement rate is set as the dependent variable. The existing linear model training method is used to train the prediction model 2 so that it can learn the relationship between the budget quota ratio and the comprehensive target achievement rate, and the budget quota ratio in the newly obtained key indicator list (including production-related and R&D-related budgets) is input into the trained prediction model 2, and the prediction model 2 outputs the predicted value of the comprehensive target achievement rate. According to the management needs of the enterprise and historical data analysis, a reasonable achievement rate threshold is set. If the predicted comprehensive target achievement rate is lower than the set threshold, it is considered that the comprehensive target achievement rate is unqualified. When the predicted comprehensive target achievement rate is lower than the threshold, the system automatically outputs early warning information 2 to realize the monitoring of several important indicators. Early warning information 2 can help the management of the enterprise to understand the comprehensive effect of budget execution in a timely manner and take corresponding measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The present invention is a flow chart of a method for monitoring important indicators of an enterprise. DETAILED DESCRIPTION

[0019] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0020] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0021] Because production efficiency and scientific research capabilities directly constitute the competitiveness of an enterprise, the main goal of an enterprise's budget management and monitoring is to ensure that the invested budget can achieve the purpose of enhancing the competitiveness of the enterprise.

[0022] Please combine Figure 1 The present invention provides a method for monitoring important indicators of an enterprise, comprising the following steps: Step 1: Build a budget list, specifically: Export historical budget data from the company's financial system or budgeting tool; Extract budget items and corresponding amounts from the company's historical budget data and generate a budget list including all budget items; A budget target and a budget target achievement rate are extracted from the historical budget data of the enterprise, wherein the budget target achievement rate includes a plurality of sub-target achievement rates and a comprehensive target achievement rate.

[0023] The budget items usually include energy consumption budget, raw material procurement budget, consumables procurement budget, equipment maintenance budget, labor cost budget, R&D capital investment budget, R&D personnel training budget, scientific research equipment procurement budget, R&D personnel recruitment budget and floating budget. Among them, energy consumption budget, raw material procurement budget, consumables procurement budget, equipment maintenance budget, and labor cost budget as part of the budget will affect the company's production efficiency goals; while R&D capital investment budget, R&D personnel training budget, scientific research equipment procurement budget, R&D personnel recruitment budget, etc. as another part of the budget will affect the company's R&D progress goals. Among them, R&D progress will have an impact on production efficiency.

[0024] In this embodiment, the sub-goals include production benefit goals and R&D progress goals, and the achievement rates of the sub-goals include the achievement rates of production benefit goals and R&D progress goals, specifically: The production efficiency target can be set as a production increase target or a profit increase target. After the budget is invested each year, the actual production increase and profit increase are counted to obtain the production increase achievement rate and profit increase achievement rate, which is the sub-target achievement rate. Similarly, by comparing the formulated R&D progress target with the actual R&D progress, the sub-R&D base target achievement rate is obtained. The above is the sub-target achievement rate.

[0025] In this embodiment, the comprehensive target achievement rate is an indicator used to reflect the competitiveness of the enterprise. The so-called competitiveness includes the market share of the product, etc. By comparing the formulated market share target with the actual market share, the target achievement rate, that is, the comprehensive target achievement rate, is calculated.

[0026] Step 2: Get the ratio of each budget item to the total budget, and then construct the original monitoring indicator set, including the following steps: Convert the amount data of each budget item into a numeric type, then sum the amounts of all budget items to obtain the total budget amount; Calculate the budget ratio of each budget item to the total budget ; Set the ratio threshold , if the proportion of budget items meets the following target screening conditions: , then the budget item is used as a monitoring item, where , , ; Multiple monitoring items that meet the target filtering conditions form the original monitoring indicator set ;in, Indicates the number of monitored items.

[0027] Step 3: Set a plurality of n-dimensional budget target vectors, and form a budget target matrix through the budget target vectors; the dimension n of the budget target vectors is greater than 2, and the steps include: Set the budget target vector: ;in Respectively represent the first to the budget targets; Set the watch item vector ,in, Indicates The name of the monitored item. Indicates The budget ratio corresponding to each monitoring item; From the original monitoring indicator set Winning The first A monitoring item vector associated with a budget target: , then The budget target is expressed as: ,in, , ; Convert the budget target into a budget target matrix consisting of monitoring items: .

[0028] In this embodiment, since there are only two sub-goals (production efficiency goal and R&D progress goal), ; The budgets related to production efficiency goals include: energy consumption budget, raw material procurement budget, consumables procurement budget, and equipment maintenance budget. Combining the budget ratio of each budget in the total budget, we can know that: ; ; ; ; The budgets related to R&D progress goals include: R&D capital investment budget, R&D personnel training budget, scientific research equipment procurement budget, and R&D personnel recruitment budget. Combining the budget proportion of each budget in the total budget, we can know: , , , .

[0029] Step 4: According to the dimension of the budget target vector, the original monitoring indicator set is divided into monitoring indicator subsets related to each budget target vector, including the following steps: Will be with Budget Targets The associated monitoring item vectors constitute a monitoring indicator subset , ={ }, ; Combine multiple monitoring indicator subsets into a monitoring indicator set: .

[0030] Step 5: Establish a prediction model 1 through a machine learning algorithm to monitor the budget items within the monitoring indicator subset, including the following steps: The first prediction model is established by a machine learning algorithm to monitor the budget items in the monitoring indicator subset, including: Building a prediction model 1: ,in , is the intercept, is the error term, is the regression coefficient; The prediction model 1 is trained by a linear regression algorithm so that the prediction model 1 learns the relationship between the budget quota ratio and the budget target achievement rate; Through the trained prediction model 1, after inputting multiple new budget quota ratios, the corresponding sub-goal achievement rate prediction value is output; Set the achievement rate threshold ,if , then the budget target achievement rate is considered unsatisfactory and warning information 1 is output.

[0031] Step 6: According to the correlation between the elements in different monitoring indicator subsets, multiple key monitoring indicators are screened and a key indicator list is constructed, including the following steps: from Extract the budget amount corresponding to each monitoring item to build a ratio set 1: , from Extract the budget amount corresponding to each monitoring item to build the ratio set 2: ; Construct event set 1 by taking each event in which the budget amount in ratio set 1 changes, that is: {event 1, event 2, ..., event }; Construct event set 2 by taking each budget change event in ratio set 2, that is: {event ,event ,......,event };

[0032] In this embodiment, the occurrence of each event in the event set 2 is identified from the historical budget data. The number of times that each event in the event set 2 causes all events in the event set 1 to occur is counted. That is to say, after the scientific research funds in the budget are invested, production efficiency will be improved, the consumption of raw materials will be reduced, etc., so it will affect the changes in the raw material procurement budget and the equipment maintenance budget. The available capital investment is taken as an event in the event set 2, which will affect multiple events in the event set 1. The number of times the scientific research funds investment and the procurement budget changes and the equipment maintenance budget changes occur at the same time is obtained by statistics to calculate the promotion degree between the events. Because the promotion degree is an indicator to measure the degree of association between the events in the event set 2 and the events in the event set 1. The promotion degree is calculated by comparing the probability of the occurrence of the event set 1 event in the case of the occurrence of the event set 2 event and the probability of the event set 1 event occurring naturally. The promotion degree is used to judge the degree of association between the events in the event set 2 and the events in the event set 1. According to the analysis results of the promotion degree, the events in the event set 2 that are associated with the events in the event set 1 are selected. These associated events are combined into a monitoring event set.

[0033] Step 7: Construct prediction model 2 through machine learning algorithm, and monitor key monitoring indicators through prediction model 2, including the following steps: The second prediction model is constructed through the machine learning algorithm, and the key monitoring indicators are monitored through the second prediction model, including: Building prediction model 2: ,in, Indicates the number of monitored items in the terminal indicator list; To train the second prediction model, the prediction model 2 can be trained by using the existing linear model training method, and historical data can be obtained from the financial database of the enterprise.

[0034] Input the budget quota ratio in the newly obtained key indicator list into the forecast model 2, and output the forecast value of the comprehensive target achievement rate; Set the achievement rate threshold ,if , then the comprehensive target achievement rate is considered unsatisfactory and the second warning information is output.

[0035] The present invention also provides a system for monitoring important indicators of an enterprise, and the system is used to execute the method for monitoring important indicators of an enterprise.

[0036] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method for monitoring important enterprise indicators.

[0037] The embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by the central processing unit (CPU), the above-mentioned functions defined in the method of the present application are executed. It should be noted that the above-mentioned computer-readable medium of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of an electrical, magnetic, optical, electromagnetic, infrared segment, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wire segments, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, electrical wire, optical cable, RF, etc., or any suitable combination of the foregoing.

[0038] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0039] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be deformed or modified in any way.

Claims

1. A method for monitoring important indicators of an enterprise, characterized in that: The method comprises: Build a budget list; Get the ratio of each budget item to the total budget, and then construct the original monitoring indicator set; A plurality of n-dimensional budget target vectors are set, and a budget target matrix is ​​formed by the budget target vectors; the dimension n of the budget target vectors is greater than 2; According to the dimension of the budget target vector, the original monitoring indicator set is divided into monitoring indicator subsets related to each budget target vector; Establishing a prediction model 1 through a machine learning algorithm to monitor budget items within a subset of monitoring indicators; According to the correlation of elements in different monitoring indicator subsets, multiple key monitoring indicators are screened and a key indicator list is constructed; Prediction model 2 is constructed through machine learning algorithm, and key monitoring indicators are monitored through prediction model 2.

2. A method for monitoring important indicators of an enterprise according to claim 1, characterized in that: The step of constructing a budget list and obtaining multiple budget items from the budget list includes: Export historical budget data from the company's financial system or budgeting tool; Extract budget items and corresponding amounts from the company's historical budget data and generate a budget list including all budget items; Extracting budget targets and budget target achievement rates from the company's historical budget data, wherein the budget target achievement rates include multiple sub-target achievement rates and a comprehensive target achievement rate; The budget items include one or more of energy consumption budget, raw material procurement budget, consumables procurement budget, equipment maintenance budget, labor cost budget, R&D capital investment budget, R&D personnel training budget, scientific research equipment procurement budget, R&D personnel recruitment budget and floating budget.

3. The method for monitoring important indicators of an enterprise according to claim 1, characterized in that: The ratio of the amount of each budget item to the total budget amount is obtained, and then the original monitoring indicator set is constructed, including: Convert the amount data of each budget item into a numeric type, then sum the amounts of all budget items to obtain the total budget amount; Calculate the budget ratio of each budget item to the total budget ; Set the ratio threshold , if the proportion of budget items meets the following target screening conditions: , then the budget item is used as a monitoring item, where , , ; Multiple monitoring items that meet the target filtering conditions form the original monitoring indicator set ;in, Indicates the number of monitored items.

4. A method for monitoring important indicators of an enterprise according to claim 3, characterized in that: The setting multiple Dimensional budget target vector, including: Set the budget target vector: ;in Respectively represent the first to the budget targets; Set the watch item vector ,in, Indicates The name of the monitored item. Indicates The budget ratio corresponding to each monitoring item; From the original monitoring indicator set Winning The first A monitoring item vector associated with a budget target: , then The budget target is expressed as: ,in, , ; Convert the budget target into a budget target matrix consisting of monitoring items: .

5. A method for monitoring important indicators of an enterprise according to claim 4, characterized in that: The setting of multiple time periods and setting different weights according to different time periods include: According to the dimension of the budget target vector, the original monitoring indicator set is divided into a plurality of monitoring indicator subsets related to the corresponding budget target vectors, including: Will be with Budget Targets The associated monitoring item vectors constitute a monitoring indicator subset , ={ }, ; Combine multiple monitoring indicator subsets into a monitoring indicator set: .

6. A method for monitoring important indicators of an enterprise according to claim 5, characterized in that: The first prediction model is established by a machine learning algorithm to monitor the budget items in the monitoring indicator subset, including: Building a prediction model 1: ,in , is the intercept, is the error term, is the regression coefficient; The prediction model 1 is trained by a linear regression algorithm so that the prediction model 1 learns the relationship between the budget quota ratio and the budget target achievement rate; Through the trained prediction model 1, after inputting multiple new budget quota ratios, the corresponding sub-goal achievement rate prediction value is output; Set the achievement rate threshold ,if , then the budget target achievement rate is considered unsatisfactory and warning information 1 is output.

7. A method for monitoring important indicators of an enterprise according to claim 4, characterized in that: The method of screening multiple key monitoring indicators according to the correlation of elements in different monitoring indicator subsets and constructing a key indicator list includes: from Extract the budget amount corresponding to each monitoring item to build a ratio set 1: ， from Extract the budget amount corresponding to each monitoring item to build the ratio set 2: ； Construct event set 1 by taking each event in which the budget amount in ratio set 1 changes, that is: {event 1, event 2, ..., event }; Construct event set 2 by taking each budget change event in ratio set 2, that is: {event ,event ,......,event }; Obtain statistics from historical budget data on the number of times each event in event set 2 causes all events in event set 1 to occur, and determine the degree of correlation between the events in event set 2 and those in event set 1 by comparing the lifts; The multiple events associated with event set 1 and event set 2 constitute a monitoring event set, and the monitoring item names corresponding to the events in the monitoring event set and the budget quota ratios corresponding to the monitoring item names constitute a key indicator list.

8. A method for monitoring important indicators of an enterprise according to claim 7, characterized in that: The second prediction model is constructed through the machine learning algorithm, and the key monitoring indicators are monitored through the second prediction model, including: Building prediction model 2: ,in, Indicates the number of monitored items in the terminal indicator list; Training prediction model 2; Input the budget quota ratio in the newly obtained key indicator list into the forecast model 2, and output the forecast value of the comprehensive target achievement rate; Set the achievement rate threshold ,if , then the comprehensive target achievement rate is considered unsatisfactory and the second warning information is output.

9. An enterprise important indicator monitoring system, characterized in that: The system is used to execute a method for monitoring important enterprise indicators as described in any one of claims 1 to 8 above.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement a method for monitoring important enterprise indicators as described in any one of claims 1 to 8.

Images