CN115796585A - Enterprise operation risk assessment method and system - Google Patents
Enterprise operation risk assessment method and system Download PDFInfo
- Publication number
- CN115796585A CN115796585A CN202211501503.8A CN202211501503A CN115796585A CN 115796585 A CN115796585 A CN 115796585A CN 202211501503 A CN202211501503 A CN 202211501503A CN 115796585 A CN115796585 A CN 115796585A
- Authority
- CN
- China
- Prior art keywords
- risk
- enterprise
- indexes
- bottom layer
- index
- 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.)
- Withdrawn
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of enterprise security risk assessment, in particular to an enterprise operation risk assessment method and an enterprise operation risk assessment system, wherein the enterprise operation risk assessment method screens out corresponding risk indexes and makes corresponding risk assessment based on mass data of an enterprise to be assessed by using an artificial intelligence data processing technology in underlying indexes with potential risks in a qualitative and quantitative mode, visualizes a risk assessment result, prominently displays the influence degree and the risk value of the risk indexes of the enterprise to be assessed, assists an enterprise manager in analyzing and judging the risk of the enterprise to be assessed, and provides comprehensive and diversified risk index data reference for the risk control priority of the enterprise to be assessed for the enterprise manager.
Description
Technical Field
The invention relates to the technical field of enterprise security risk assessment, in particular to an enterprise operation risk assessment method and system.
Background
The identification of the enterprise operation risk can help the enterprise to carry out timely transformation, and reduce or avoid the major loss of various crises to the enterprise operation. With the interweaving and merging development of various industries, the risk of current enterprise operation gradually tends to complexity and diversity. In the prior art, the technology for identifying the enterprise operation risk is incomplete, the identified risk item is single, the comprehensiveness is not strong, the timeliness is low, and the requirements of monitoring and identifying the enterprise operation risk in the current general connection and multivariate development cannot be met, so that an enterprise operation risk evaluation method and an enterprise operation risk evaluation system are urgently needed to meet the current requirements of timely predicting and evaluating complex and multivariate enterprise risk places.
Disclosure of Invention
Aiming at the defects in the prior art and the requirement of the multivariate evaluation data of the enterprise operation risk, the invention provides an enterprise operation risk evaluation method in a first aspect, which comprises the following steps: selecting a bottom index of enterprise risk assessment; calibrating the balance base number of each bottom layer index; setting the initial weight of each bottom-layer index; establishing an enterprise risk assessment system by combining the bottom layer indexes with the corresponding balance base numbers and the initial weights; acquiring actual data corresponding to bottom indexes of an enterprise to be evaluated; predicting the single risk degree of the bottom layer index according to the actual data and the balance base number; screening risk indexes from the bottom layer indexes of the enterprise to be evaluated according to the single risk degree; drawing up a risk coefficient of the corresponding risk index by combining the initial weight and the individual risk degree of the risk index; setting up a risk evaluation subsystem of the enterprise to be evaluated by combining the risk indexes with the corresponding risk coefficients; visualizing the risk index and the corresponding risk coefficient of the enterprise risk evaluation subsystem to be evaluated; and evaluating the risk level of the enterprise to be evaluated through the visualized enterprise risk evaluation subsystem to be evaluated. The enterprise risk assessment system is set up by selecting diversified bottom layer indexes; meanwhile, an artificial intelligence data processing technology can be utilized, for example, a deep learning algorithm can be utilized to carry out deep excavation on actual data corresponding to bottom layer indexes of an enterprise to be evaluated in time, comprehensive risk indexes and corresponding risk coefficients of the enterprise to be evaluated are determined on the basis of an enterprise risk evaluation system through the excavated actual data with the breadth and the depth, an enterprise risk evaluation subsystem to be evaluated for the enterprise to be evaluated is constructed, the enterprise risk evaluation subsystem to be evaluated is visualized, the enterprise risk level can be expressed visually and accurately in the form of a map and the like, and the actual benefit of the method can be more highlighted. The enterprise operation risk assessment method screens out corresponding risk indexes and makes corresponding risk assessment and visualizes the risk assessment result by utilizing an artificial intelligence data processing technology based on mass data of an enterprise to be assessed in a qualitative and quantitative mode in a bottom layer index with potential risk, so that the influence degree and the risk value of the risk indexes of the enterprise to be assessed are prominently displayed, an enterprise manager is assisted to analyze and judge the risk of the enterprise to be assessed, and comprehensive and diversified risk index data reference is provided for the risk control priority of the enterprise to be assessed by the enterprise manager. Meanwhile, compared with the risk item assessment in the prior art, the enterprise operation risk assessment method provided by the invention is more complete, stronger in comprehensiveness and higher in timeliness, and can well meet the requirements of complex and multivariate enterprise operation risk assessment.
Optionally, the selecting the underlying index of the enterprise risk assessment includes the following steps: selecting underlying indexes with potential risks according to business processes of enterprises, wherein the underlying indexes comprise user quantity, new user growth quantity, user demand satisfaction ratio, user complaint ratio, product innovation, product market ratio, product demand quantity, product sales quantity, product retention quantity, product recovery rate, product quality, product price, product sales strategy, overall operation cost and income, comprehensive quality of sales staff, financing amount, financing state, financing difficulty degree, financial cost, enterprise credit rating, asset turnover rate, asset liability rate, intellectual protection degree, research and development capital investment, technical innovation degree, product iteration speed, current technical maturity, enterprise management efficiency, comprehensive quality of management personnel, management system health degree, macro economic growth rate, macro economic fluctuation condition, industry macro income, industry level, industry prospect, competition degree, social public opinion tendency, sudden public health event, natural environment disaster degree, state holding policy degree, government investment ratio, judicial quotation abnormal condition, income abnormal condition, business tax condition and operation condition. According to the method, the bottom-layer indexes with potential risks for enterprise operation are selected according to the enterprise business process, the pre-screening of the risk items is preliminarily completed, and a foundation is laid for the subsequent screening and evaluation of the risk items of the enterprise to be evaluated.
Optionally, the establishing of the enterprise risk assessment system by combining the bottom layer indexes with the corresponding balance cardinality and the initial weight includes the following steps: generating risk feature nodes by using the bottom layer indexes, and assigning corresponding balance base numbers to the risk feature nodes, wherein the risk nodes comprise user risk nodes, product operation risk nodes, financing risk nodes, financial risk nodes, innovation risk nodes, management risk nodes, macroscopic economic risk nodes, industry risk nodes, social public opinion risk nodes, natural disaster risk nodes, political risk nodes and law risk nodes; establishing a multi-dimensional risk network layer according to the corresponding initial weight through the risk feature nodes, wherein the multi-dimensional risk network layer comprises an internal risk one-way network, an external risk one-way network and internal and external risk associated networks; and establishing an enterprise risk evaluation system according to the multidimensional risk network layer.
Optionally, the predicting the single risk of the underlying indicator according to the actual data and the balance base number includes the following steps: quantifying actual data corresponding to any bottom-layer index by taking the balance base number as a median; constructing a single bottom layer index fluctuation function by using the actual data corresponding to the quantized bottom layer index and taking time as an independent variable; extracting actual data in a corresponding time period when the value of the secondary derivation result is minimum according to the secondary derivation result of the single bottom layer index fluctuation function; averaging actual data in a corresponding time period when the secondary derivation result value is minimum, and obtaining the current target value of the single bottom layer index; and obtaining the single risk degree of the bottom layer index by combining the current target value with the balance base number.
Optionally, the single-term risk satisfies the following formula:
wherein d is i Individual risk, H, representing the ith underlying indicator i Balance base, t, representing the i-th underlying index 0 The starting time t of the corresponding time period when the quadratic derivative result value of the single bottom layer index fluctuation function of the ith bottom layer index is minimum n The end time of the corresponding time period when the quadratic derivative result value of the single bottom layer index fluctuation function of the ith bottom layer index is minimum is represented by n, t is represented by t 0 To t n The number of the discrete actual data of the ith bottom index in the interval, C represents t 0 To t n The ith actual data with discrete bottom layer indexes in the time period, num [ C [)]Represents t 0 To t n The number of discrete actual data of the ith bottom index in the time period, and C' represents t 0 To t n In the ith discrete actual data of the bottom layer indexes in the time period, the data is more than H i Actual data of (2), num [ C']Represents t 0 To t n In the ith discrete actual data of the bottom layer indexes in the time period, the data is more than H i The amount of actual data.
Optionally, the screening of the risk indicators in the underlying indicators of the enterprise to be evaluated through the single risk includes the following steps: removing the bottom layer indexes with the single risk value of zero in all the bottom layer indexes; and defining the rest bottom layer indexes as risk indexes.
Optionally, the risk factor satisfies the following formula:
wherein D is q Individual risk degree, α, for the qth risk indicator q The risk factor, alpha, representing the qth risk indicator q0 Represents the initial weight of the q-th risk indicator, D represents the individual risk degree, [ D ]] max Represents the maximum value of the individual risks, [ alpha ] 0 ] max Representing the maximum value of the initial weight.
Optionally, the establishing of the enterprise risk assessment subsystem to be assessed by using the risk indexes and combining with the corresponding risk coefficients includes the following steps: removing bottom layer indexes without corresponding risk indexes in the enterprise risk assessment system; assigning the risk coefficients to corresponding risk indicators; and carrying out gradient layering on the risk indexes according to the risk coefficients to obtain an enterprise risk assessment subsystem.
Optionally, the method for evaluating the risk level of the enterprise to be evaluated through the visualized risk evaluation subsystem of the enterprise to be evaluated includes the following steps: according to the quantity of the risk indexes in the visualized enterprise risk assessment subsystem to be assessed, the risk coefficient range and the risk index gradient layering result, an enterprise risk level assessment model is constructed, the enterprise risk level is assessed by utilizing the enterprise risk level, and the enterprise risk level assessment model meets the following formula:
wherein E is 0 Indicating that the enterprise risk level to be assessed is normal, E 1 Indicating that the risk level of the enterprise to be assessed is slight, E 2 Indicating that the risk level of the enterprise to be evaluated is medium, E 3 Indicating that the risk level of the enterprise to be assessed is higher, E 4 Indicates that the risk level of the enterprise to be evaluated is high, alpha min Representing the minimum risk factor value, alpha max Value representing the maximum Risk coefficient, Q 0 Representing the value of the risk factor alpha e (alpha) min ，0.9α min +0.1α max ]Risk index corresponding to hour, num [ Q ] 0 ]Represents Q 0 Beta represents Q 0 Compensation coefficient of the amount of, Q 1 Value representing the risk factor alpha e (0.9 alpha) min +0.1α max ，0.8α min +0.2α max ]Risk index corresponding to hour, num [ Q ] 1 ]Represents Q 1 Gamma represents Q 1 Compensation coefficient of the amount of, Q 2 Representing the value of the risk factor alpha epsilon (0.8 alpha) min +0.2α max ，0.5α min +0.5α max ]Risk index corresponding to hour, num [ Q ] 2 ]Represents Q 2 Delta denotes Q 2 Compensation coefficient of the amount of, Q 3 Value representing the value of the risk factor alpha ∈ (0.5 alpha) min +0.5α max ，0.75α min +0.25α max ]Risk index corresponding to hour, num [ Q ] 3 ]Represents Q 3 The quantity of (e) represents Q 3 Compensation coefficient of the amount of, Q 4 Value representing the risk factor alpha e (0.75 alpha) min +0.25α max ，α max ]Risk index corresponding to hour, num [ Q ] 4 ]Represents Q 4 The number of (b), ζ represents Q 4 The amount of compensation factor.
In a second aspect, the present invention further provides an enterprise operation risk assessment system, where the enterprise operation risk assessment system includes a processor, an input device, an output device, and a memory, where the processor, the input device, the output device, and the memory are connected to each other, where the memory is used to store a computer program, and the computer program includes program instructions, and the processor is configured to call the program instructions to execute the enterprise operation risk assessment method according to the first aspect. The enterprise operation risk assessment system is compact in structure and stable in performance, and can efficiently execute the enterprise operation risk assessment method, so that the applicability and the practical application capability of the enterprise operation risk assessment system are improved.
Drawings
FIG. 1 is a flow chart of an enterprise operation risk assessment method of the present invention;
FIG. 2 is a schematic diagram of an enterprise risk assessment architecture of the present invention;
FIG. 3 is a schematic plan view of a three-dimensional visual assessment enterprise risk assessment subsystem of the present invention;
FIG. 4 is a perspective view of a three-dimensional visual assessment enterprise risk assessment subsystem of the present invention;
fig. 5 is a structural diagram of the enterprise operation risk assessment system of the present invention.
Detailed Description
Specific embodiments of the present invention will be described in detail below, and it should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that: it is not necessary to employ these specific details to practice the present invention. In other instances, well-known circuits, software, or methods have not been described in detail so as not to obscure the present invention.
Throughout the specification, reference to "one embodiment," "an embodiment," "one example," or "an example" means: the particular features, structures, or characteristics described in connection with the embodiment or example are included in at least one embodiment of the invention. Thus, the appearances of the phrases "in one embodiment," "in an embodiment," "one example" or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combination and/or sub-combination in one or more embodiments or examples. Further, those of ordinary skill in the art will appreciate that the illustrations provided herein are for illustrative purposes and are not necessarily drawn to scale.
Referring to fig. 1, in an embodiment, the present invention provides an enterprise operation risk assessment method, including the following steps:
and S01, selecting a bottom-layer index of enterprise risk assessment.
The bottom indexes of enterprise risk assessment are used as the basis for building an enterprise risk assessment system, and comprehensive analysis needs to be carried out on risk points existing in the existing environment. Therefore, the bottom layer indexes selected in the step S01 satisfy the comprehensive principle, the scientific principle, the operability principle and the acquirability principle. The comprehensive principle means that the selected overall bottom-level indexes take various factors causing enterprise risks into consideration, such as environmental factors, political factors, enterprise strategic factors, financial factors, social factors and the like; the scientific principle indicates that the characteristics and the conditions of the enterprise risk degree can be objectively and truly embodied by the underlying indexes; the operability principle represents the characteristics that the selected bottom layer indexes can be observed, quantized, measured and the like according to certain specifications and modes; the availability principle represents the characteristics of the underlying indexes themselves and the realistic feasibility of the underlying indexes in evaluating the risk of the enterprise.
In an optional embodiment, the selecting the underlying indicators of the enterprise risk assessment in step S01 includes the following steps: and selecting the underlying indexes with potential risks according to the business process of the enterprise. Specifically, according to the current enterprise business process and conventional business management processes and according to channels such as related academic papers, normal finance magazines, reports and the like for enterprise operation risk research, traditional enterprise operation risk indexes and new enterprise operation risk indexes are summarized into multi-element fused bottom indexes, and a foundation is laid for building an enterprise risk assessment system. In this embodiment, the selected bottom layer indicators include: the user quantity from the user level, the new user growth quantity, the user demand satisfaction ratio, the user complaint ratio and other indexes; product innovation, product market proportion, product demand, product sales, product retention, product recovery, product quality, product price and other indexes from the product level; indexes such as product sale strategies, overall operation and income, comprehensive quality of sales staff and the like from a product operation level; financing amount, financing state, financing difficulty level and other indexes from the financing level; financial cost, enterprise credit rating, asset turnover rate, asset liability rate and other indexes from the financial aspect; the indexes from the innovation level, such as intellectual property protection degree, research and development capital investment, technical innovation degree, product iteration speed, current technical maturity and the like; the enterprise management efficiency, comprehensive quality of management personnel, health degree of management system and other bottom layer indexes from the management level; macro-economic growth rate, macro-economic fluctuation condition, industry macro-income level and other indexes from a macro-economic level; indexes such as industry prospect and competitive degree from the industry level; indexes such as industry social public opinion tendency and sudden public health events from the social public opinion level; indexes such as natural environment disaster degree from a natural disaster level; indexes such as national support policy degree and government input proportion from political level; and the judicial law from the legal level relates to indexes such as complaint conditions, tax payment abnormal conditions, abnormal operation conditions, operation penalty conditions and the like. In this embodiment, the multidirectional indexes from 13 layers are selected as the basis of the enterprise risk assessment system, and the selected bottom layer indexes not only meet the comprehensive principle, the scientific principle, the operability principle and the acquirability principle, but also meet the requirement of a multidimensional data source of enterprise risk assessment. In the embodiment, the bottom-layer indexes are index items with potential risks in enterprise operation selected according to enterprise business processes and conventional business management processes, and the risk items and the risk evaluation results for the enterprise to be evaluated are selected by the bottom-layer indexes through a subsequent analysis method, so that an enterprise manager can manage and control the enterprise operation risks in time.
And S02, calibrating the balance base number of each bottom layer index.
In the construction of an enterprise risk assessment system, the balance base number of each bottom layer index meeting the operability principle and the acquirability principle needs to be calibrated, and the balance base number represents the minimum negative influence of data corresponding to the bottom layer index on conditions such as management, finance, growth and the like. The balance base number in step S02 is set such that, for the balance base number of an enterprise risk assessment system common to a certain industry, the specific quantitative value is related to macroscopic data such as the industry development state, government policy, social background, and the like. In an optional embodiment, regarding the bottom-level index of the user amount, if the average monthly user amount of a product operated by a company of 10-15 people in a certain industry is 20 ten thousand, the balance base of the bottom-level index is set to be 20 ten thousand, and meanwhile, for example, to avoid statistical errors, the tolerance of the balance base of the bottom-level index is set to be ± 5000. When a certain enterprise to be evaluated conforms to the industry background and the average user quantity in the month is 10 ten thousand, under a corresponding universal enterprise risk evaluation system, the user quantity is possibly used as a risk item of the enterprise to be evaluated to establish an enterprise risk evaluation sub-system to be evaluated; when another enterprise to be evaluated meets the industry background and the average user quantity in the month is 22 ten thousand, the user quantity is not taken as a risk item in the corresponding general enterprise risk evaluation system, namely the corresponding enterprise risk evaluation subsystem to be evaluated does not have the evaluation index of the user quantity.
In an alternative embodiment, the single-term risk degree of the underlying index calculated based on the balance base number is guaranteed to be unified into forward calculation, and the specific numerical value of the balance base number comprises the whole real number. When the actual meaning of the absolute balance base number of a certain bottom-layer index is that the actual data is larger than the balance base number, the balance base number is set to be a positive value when the bottom-layer index is used for evaluating the enterprise risk items to be evaluated by the risk items; when the actual meaning of the absolute balance base number of a certain bottom-layer index is that the actual data is smaller than the balance base number, the balance base number is set to be a negative value when the bottom-layer index can be used for carrying out risk item evaluation on the enterprise risk item to be evaluated, and the subsequent actual data is also subjected to inverse number processing when being imported. Through the processing, the single risk degree of the bottom layer index calculated based on the balance base number can be guaranteed to be calculated in the forward direction in a unified mode.
And S03, setting the initial weight of each bottom-layer index.
In the construction of an enterprise risk assessment system, the contribution weights of the enterprise risk evaluation system to the bottom layer indexes of different items are different, and on the premise that the overall bottom layer indexes meet the comprehensive requirement, the overall risk degree of the bottom layer indexes needs to be judged to ensure the reasonability of the enterprise risk assessment result. The initial weight in step S03 represents a degree of negative influence of the underlying indicator on the financial state and the growth state of the enterprise, that is, a risk degree of each underlying indicator in the general enterprise risk assessment system. In this embodiment, the initial weight may be set according to the existing conventional enterprise risk indicator occupation plan, and in this embodiment, the global initial weight range is set to (0,1), where the initial weight value is placed between (0,0.1 ] with a low risk level of the underlying indicator, the initial weight value is placed between (0.1,0.2) with a low risk level of the underlying indicator, the initial weight value is placed between (0.2,0.5 ] with a medium risk level of the underlying indicator, the initial weight value is placed between (0.5,0.75) with a high risk level of the underlying indicator, and the initial weight value is placed between (0.75,1) with a high risk level of the underlying indicator.
And S04, building an enterprise risk assessment system by combining the corresponding balance cardinality and the initial weight through the bottom layer indexes.
Referring to fig. 2, in an optional embodiment, the building of the enterprise risk assessment system by combining the corresponding balance cardinality and the initial weight through the bottom-layer indexes in step S04 includes the following steps: the enterprise risk assessment system is built by combining the corresponding balance cardinality and the initial weight through the bottom layer indexes, and the method comprises the following steps: generating risk feature nodes by using the bottom layer indexes, and assigning corresponding balance base numbers to the risk feature nodes, wherein the risk nodes comprise user risk nodes, product operation risk nodes, financing risk nodes, financial risk nodes, innovation risk nodes, management risk nodes, macroscopic economic risk nodes, industry risk nodes, social public opinion risk nodes, natural disaster risk nodes, political risk nodes and law risk nodes; establishing a multi-dimensional risk network layer according to the corresponding initial weight through the risk feature nodes, wherein the multi-dimensional risk network layer comprises an internal risk one-way network, an external risk one-way network and internal and external risk associated networks; and constructing an enterprise risk evaluation system according to the multi-dimensional risk network layer.
In this embodiment, the user risk nodes include bottom-layer indexes such as user amount, new user growth amount, user demand satisfaction ratio, user complaint ratio, and the like; the product risk nodes comprise bottom-layer indexes such as product innovation, product market proportion, product demand, product sales, product retention, product recovery, product quality, product price and the like; the product operation risk node comprises indexes such as product sale strategies, overall operation and income, comprehensive quality of sales staff and the like; the financing risk node comprises bottom-layer indexes such as financing amount, financing state, financing difficulty and the like; the financial risk nodes comprise bottom layer indexes such as financial cost, enterprise credit level, asset turnover rate, asset liability rate and the like; the innovation risk node comprises the bottom-layer indexes of intellectual property protection degree, research and development capital investment, technical innovation degree, product iteration speed, current technical maturity and the like; the management risk nodes comprise the bottom layer indexes such as enterprise management efficiency, comprehensive quality of management personnel, health degree of a management system and the like; the macro-economic risk node comprises bottom layer indexes such as a macro-economic growth rate, a macro-economic fluctuation condition, an industry macro-income level and the like; the industry risk node comprises bottom layer indexes such as industry prospect, competition degree and the like; the social public opinion risk node comprises bottom indexes such as industrial social public opinion tendency, sudden public health events and the like; the natural disaster risk nodes comprise bottom layer indexes such as natural environment disaster degree and the like; the political risk nodes comprise bottom layer indexes such as national support policy degree and government input proportion; the legal risk nodes comprise bottom-layer indexes such as judicial complaint conditions, tax payment abnormal conditions, abnormal operation conditions, operation penalty conditions and the like.
In this embodiment, the internal risk unidirectional network includes user risk nodes, product operation risk nodes, financing risk nodes, financial risk nodes, innovation risk nodes, management risk nodes, and other risk nodes; the external risk unidirectional network comprises risk nodes such as macro-economic risk nodes, industry risk nodes, social public opinion risk nodes, natural disaster risk nodes, political risk nodes and legal risk nodes; the internal and external risk association networks are formed by connecting risk nodes with common underlying indexes. The dimension in the multidimensional risk network layer is defined by the initial weight of the bottom layer indexes, and the risk degree of the bottom layer indexes is multidimensional through the initial weight range of the bottom layer indexes, wherein the bottom layer indexes with the initial weight between (0,0.1) are placed in the low risk dimension, the bottom layer indexes between (0.1,0.2) are placed in the low risk dimension, the bottom layer indexes between (0.2,0.5) are placed in the medium risk dimension, the bottom layer indexes between (0.5,0.75) are placed in the high risk dimension, and the bottom layer indexes between (0.75,1) are placed in the high risk dimension.
S05, acquiring actual data corresponding to bottom indexes of an enterprise to be evaluated;
the step S05 of obtaining actual data corresponding to the underlying indicators of the enterprise to be evaluated may be accomplished by using techniques such as data mining and processing in the field of artificial intelligence. In an optional embodiment, existing information mining and identifying technologies such as a convolutional neural network in the field of artificial intelligence are utilized to deeply mine and identify in a multi-source database including but not limited to an internal database of an enterprise to be evaluated, an information database related to the enterprise to be evaluated obtained through network crawling, and the obtained data is cleaned and screened, so that the format of the obtained data is unified. And matching the processed data with the corresponding bottom layer indexes and then performing further screening.
In yet another optional embodiment, the actual data corresponding to the underlying index of the enterprise to be evaluated is obtained in step S05, and the actual data information corresponding to the underlying index is entered and sorted by using data processing software such as an excel table and the like.
And S06, predicting the single risk degree of the bottom layer index according to the actual data and the balance base number.
In an optional embodiment, the step S06 of predicting the single risk of the underlying indicator according to the actual data and the balance base includes the following steps: and quantizing the actual data corresponding to any bottom-layer index by taking the balance base as a reference. The method comprises the steps of utilizing actual data corresponding to quantized bottom layer indexes and taking time as an independent variable to construct a single bottom layer index fluctuation function, selecting different time lengths as time units according to different bottom layer indexes due to discontinuous time of the actual data obtained through big data, and selecting continuous 5 or more than 5 actual data to construct the single bottom layer index fluctuation function under the time length units, so that the single bottom layer index fluctuation function can be a segmented function. And extracting actual data in a corresponding time period when the value of the secondary derivation result is minimum according to the secondary derivation result of the single bottom layer index fluctuation function. If the single bottom layer index fluctuation function is a continuous function, taking a corresponding time point when the secondary derivation result value is minimum as a center, respectively taking two time points in front and at back as actual data extraction points, and extracting 5 actual data in total for subsequent processing; if the single-term bottom-layer index fluctuation function is a piecewise function, the function after the quadratic derivation of the fluctuation function is also a piecewise function, the time period corresponding to the minimum value of the quadratic derivation is used as the actual data source time period, and specific actual data in the time period is extracted to ensure the stability and reliability of the data. And averaging actual data in a corresponding time period when the secondary derivation result value is minimum, and obtaining the current target value of the single bottom layer index. And obtaining the single risk degree of the bottom layer index by combining the current target value with the balance base number, wherein the single risk degree meets the following formula:
wherein d is i Individual risk, H, representing the ith underlying indicator i ∈R，H i Balance base, t, representing the i-th underlying index 0 The starting time t of the corresponding time period when the quadratic derivative result value of the single bottom layer index fluctuation function of the ith bottom layer index is minimum n The end time of the corresponding time period when the quadratic derivative result value of the single bottom layer index fluctuation function of the ith bottom layer index is minimum is represented by n, t is represented by t 0 To t n The number of the discrete actual data of the ith bottom index in the interval, C represents t 0 To t n The ith actual data with discrete bottom layer indexes in the time period, num [ C [)]≥5，num[C]Represents t 0 To t n The number of the ith discrete actual data of the underlying indexes in the time period, C' represents t 0 To t n In the ith discrete actual data of the bottom layer indexes in the time period, the data is more than H i Num [ C' + represents t 0 To t n In the ith discrete actual data of the bottom layer indexes in the time period, the data is more than H i The amount of actual data.
And S07, screening the risk indexes from the bottom indexes of the enterprise to be evaluated through the single risk degree.
The screening of the risk indexes in the bottom layer indexes of the enterprise to be evaluated through the single risk degree in the step S07 comprises the following steps: removing the bottom layer indexes with the single risk value of zero in all the bottom layer indexes; the remaining underlying indicators are defined as risk indicators. The general enterprise risk assessment system is subjected to targeted shrinkage through the related data of the enterprise to be assessed, so that interference risk items are removed, the definition degree of risk indexes in the subsequently constructed enterprise risk assessment subsystem to be assessed is ensured, the time for subsequent data processing is shortened, and the high efficiency of data processing is ensured.
And S08, drawing up a risk coefficient of the corresponding risk index by combining the initial weight and the individual risk degree of the risk index.
In an alternative embodiment, the risk factor in step S08 satisfies the following formula:
wherein alpha is q ∈(0,1)，α q Risk coefficient, D, representing the qth risk indicator q Individual risk degree, α, for the qth risk indicator q The risk factor, alpha, representing the qth risk indicator q0 Represents the initial weight of the q-th risk indicator, D represents the individual risk degree, [ D ]] max Represents the maximum of the individual risk degrees,
[α 0 ] max representing the maximum value of the initial weight.
And S09, building a risk evaluation sub-system of the enterprise to be evaluated by combining the risk indexes with the corresponding risk coefficients.
In an optional embodiment, the step S09 of building a risk assessment subsystem of the enterprise to be assessed by using the risk indexes in combination with the corresponding risk coefficients includes the following steps: removing bottom layer indexes without corresponding risk indexes in the enterprise risk assessment system; assigning the risk coefficients to corresponding risk indicators; and carrying out gradient layering on the risk indexes according to the risk coefficients to obtain an enterprise risk assessment subsystem. In this embodiment, the general enterprise risk assessment system is subjected to targeted shrinkage again through a single risk degree of a bottom layer index, and risk degree multidimensional processing is performed on the risk index again through a risk coefficient, wherein the bottom layer index with the risk coefficient between (0,0.1) is placed in a low risk dimension, the bottom layer index between (0.1,0.2) is placed in a low risk dimension, the bottom layer index between (0.2,0.5) is placed in a medium risk dimension, the bottom layer index between (0.5,0.75) is placed in a high risk dimension, and the bottom layer index between (0.75,1) is placed in a high risk dimension.
And S10, visualizing the risk indexes and the corresponding risk coefficients of the enterprise risk assessment subsystem to be assessed.
For the classified risk indexes and corresponding risk coefficients, a visualization target can be realized by using the prior art, in this embodiment, specific targets include that the risk indexes with different risk coefficients are represented by wire frames rendered in different colors, the risk indexes with the same dimension are set in the same plane, the risk indexes with different dimensions are set in different planes, and a three-dimensional visual assessment enterprise risk assessment subsystem is constructed according to the dimension of the risk degree. Referring to fig. 3 and 4, wherein 1 represents a low risk dimension, 2 represents a low risk dimension, 3 represents a medium risk dimension, 4 represents a high risk dimension, 5 represents a high risk dimension, and 6 represents a risk indicator, wherein fig. 2 is a plan view of a three-dimensional visual assessment enterprise risk assessment subsystem, and in fig. 3, the risk indicator 6 can be adjusted in size according to a plan space to load all risk indicators in the risk dimension; fig. 4 is a three-dimensional schematic view of a risk assessment subsystem of a three-dimensional visual assessment enterprise, and in fig. 4, the range size of each dimension may be adaptively adjusted according to the number of risk indicators entering the risk dimension, so as to load all risk indicators in the risk dimension.
And S11, evaluating the risk level of the enterprise to be evaluated through the visualized risk evaluation subsystem of the enterprise to be evaluated.
In an optional embodiment, the step S11 of evaluating the risk level of the enterprise to be evaluated through the visualized risk evaluation subsystem of the enterprise to be evaluated includes the following steps: according to the quantity of the risk indexes in the visualized enterprise risk assessment subsystem to be assessed, the risk coefficient range and the risk index gradient layering result, an enterprise risk level assessment model is constructed, the enterprise risk level is assessed by utilizing the enterprise risk level, and the enterprise risk level assessment model meets the following formula:
wherein, E 0 Indicating that the risk level of the enterprise to be assessed is low, E 1 Indicating that the enterprise to be assessed is at a lower risk level, E 2 Indicating that the risk level of the enterprise to be evaluated is medium, E 3 Indicating that the risk level of the enterprise to be assessed is higher, E 4 Indicates that the risk level of the enterprise to be evaluated is high, alpha min Represents the minimum risk factor value, alpha max Value representing the maximum Risk coefficient, Q 0 Representing the value of the risk factor alpha e (alpha) min ，0.9α min +0.1α max ]Risk index corresponding to hour, num [ Q ] 0 ]Represents Q 0 Beta represents Q 0 Compensation coefficient of quantity, Q 1 Value representing the risk factor alpha e (0.9 alpha) min +0.1α max ，0.8α min +0.2α max ]Risk index corresponding to hour, num [ Q ] 1 ]Represents Q 1 Gamma represents Q 1 Compensation coefficient of the amount of, Q 2 Representing the value of the risk factor alpha epsilon (0.8 alpha) min +0.2α max ，0.5α min +0.5α max ]Risk index corresponding to hour, num [ Q ] 2 ]Represents Q 2 Delta denotes Q 2 Compensation coefficient of the amount of, Q 3 Value representing the value of the risk factor alpha ∈ (0.5 alpha) min +0.5α max ，0.75α min +0.25α max ]Risk index corresponding to hour, num [ Q ] 3 ]Represents Q 3 The quantity of (e) represents Q 3 Compensation coefficient of the amount of, Q 4 Value representing the risk factor alpha e (0.75 alpha) min +0.25α max ，α max ]Risk index corresponding to hour, num [ Q ] 4 ]Represents Q 4 The number of (b), ζ represents Q 4 The amount of compensation factor.
In an alternative embodiment, the method of the present invention is used for evaluating the business risk of multiple enterprises in a certain area in 1 month to 7 months in 2022, and the specific results are shown in the following table:
statistical table for evaluating overall risk level in certain area
The invention can efficiently evaluate the operation risk of each enterprise to be evaluated, and can simultaneously summarize the evaluation results aiming at the total enterprises in the target area so as to know the current overall enterprise operation condition.
According to the method, an enterprise risk assessment system is established by selecting diversified bottom layer indexes; meanwhile, an artificial intelligence data processing technology can be utilized, for example, a deep learning algorithm can be utilized to carry out deep excavation on actual data corresponding to bottom layer indexes of an enterprise to be evaluated in time, comprehensive risk indexes and corresponding risk coefficients of the enterprise to be evaluated are determined on the basis of an enterprise risk evaluation system through the excavated actual data with the breadth and the depth, an enterprise risk evaluation subsystem to be evaluated for the enterprise to be evaluated is constructed, the enterprise risk evaluation subsystem to be evaluated is visualized, the enterprise risk level can be expressed visually and accurately in the form of a map and the like, and the actual benefit of the method can be more highlighted. The enterprise operation risk assessment method screens out corresponding risk indexes and makes corresponding risk assessment and visualizes the risk assessment result by utilizing an artificial intelligence data processing technology based on mass data of an enterprise to be assessed in a qualitative and quantitative mode in a bottom layer index with potential risk, so that the influence degree and the risk value of the risk indexes of the enterprise to be assessed are prominently displayed, an enterprise manager is assisted to analyze and judge the risk of the enterprise to be assessed, and comprehensive and diversified risk index data reference is provided for the risk control priority of the enterprise to be assessed by the enterprise manager. Meanwhile, compared with the risk item assessment in the prior art, the enterprise operation risk assessment method provided by the invention is more complete, stronger in comprehensiveness and higher in timeliness, and can well meet the requirements of complex and multivariate enterprise operation risk assessment.
Referring to fig. 5, in an embodiment, the present invention further provides an enterprise operation risk assessment system, where the enterprise operation risk assessment system includes a processor, an input device, an output device, and a memory, where the processor, the input device, the output device, and the memory are connected to each other, where the memory is used to store a computer program, where the computer program includes program instructions, and the processor is configured to call the program instructions to execute the enterprise operation risk assessment method provided by the present invention. The enterprise operation risk assessment system is compact in structure and stable in performance, and can efficiently execute the enterprise operation risk assessment method, so that the applicability and the practical application capability of the enterprise operation risk assessment system are improved.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (10)
1. An enterprise operation risk assessment method is characterized by comprising the following steps:
selecting a bottom index of enterprise risk assessment;
calibrating the balance base number of each bottom layer index;
setting the initial weight of each bottom-layer index;
establishing an enterprise risk assessment system by combining the corresponding balance cardinality and the initial weight through the bottom layer indexes;
acquiring actual data corresponding to bottom indexes of an enterprise to be evaluated;
predicting the single risk degree of the bottom layer index according to the actual data and the balance base number;
screening risk indexes from the bottom layer indexes of the enterprise to be evaluated according to the single risk degree;
drawing up a risk coefficient of the corresponding risk index by combining the initial weight and the individual risk degree of the risk index;
setting up a risk evaluation subsystem of the enterprise to be evaluated by combining the risk indexes with the corresponding risk coefficients;
visualizing the risk index and the corresponding risk coefficient of the enterprise risk evaluation subsystem to be evaluated;
and evaluating the risk level of the enterprise to be evaluated through the visualized risk evaluation subsystem of the enterprise to be evaluated.
2. The enterprise operation risk assessment method according to claim 1, wherein the selecting of the underlying indexes of the enterprise risk assessment comprises the following steps:
selecting the underlying indexes with potential risks according to business processes of the enterprise, wherein the underlying indexes comprise user quantity, new user growth quantity, user demand satisfaction ratio, user complaint ratio, product innovation, product market ratio, product demand quantity, product sales quantity, product retention quantity, product recovery rate, product quality, product price, product sales strategy, overall earning cost and income, comprehensive quality of sales staff, financing amount, financing state, financing difficulty degree, financial cost, enterprise credit rating, asset turnover rate, asset liability rate, intellectual protection degree, research and development capital investment, technical innovation degree, product iteration speed, current technical maturity, enterprise management efficiency, comprehensive quality of management personnel, management system health degree, macroscopic economic growth rate, macroscopic economic fluctuation condition, industry macroscopic income, industry level industry prospect, competition degree, social public opinion, sudden public health event, natural environment disaster degree, national support policy degree, government investment ratio, judicial law complaint condition, income abnormal condition, business tax condition and business penalty condition.
3. The enterprise operation risk assessment method according to claim 2, wherein the enterprise risk assessment system is built by combining the corresponding balance cardinality and the initial weight through the bottom layer indexes, and the method comprises the following steps:
generating risk feature nodes by using the bottom layer indexes, and assigning corresponding balance base numbers to the risk feature nodes, wherein the risk nodes comprise user risk nodes, product operation risk nodes, financing risk nodes, financial risk nodes, innovation risk nodes, management risk nodes, macroscopic economic risk nodes, industry risk nodes, social public opinion risk nodes, natural disaster risk nodes, political risk nodes and law risk nodes;
establishing a multi-dimensional risk network layer according to the corresponding initial weight through the risk feature nodes, wherein the multi-dimensional risk network layer comprises an internal risk one-way network, an external risk one-way network and internal and external risk associated networks;
and constructing an enterprise risk evaluation system according to the multi-dimensional risk network layer.
4. The enterprise business risk assessment method according to claim 2, wherein the step of predicting the individual risk degree of the underlying index based on the actual data in combination with the balance base number comprises the steps of:
quantifying actual data corresponding to any bottom-layer index by taking the balance base number as a median;
constructing a single bottom layer index fluctuation function by using the actual data corresponding to the quantized bottom layer index and taking time as an independent variable;
extracting actual data in a corresponding time period when the value of the secondary derivation result is minimum according to the secondary derivation result of the single bottom layer index fluctuation function;
averaging actual data in a corresponding time period when the secondary derivation result value is minimum, and obtaining the current target value of the single bottom layer index;
and obtaining the single risk degree of the bottom layer index by combining the current target value with the balance base number.
5. The enterprise operation risk assessment method according to claim 4, wherein the individual risk degree satisfies the following formula:
wherein d is i Individual risk, H, representing the ith underlying indicator i Balance base, t, representing the i-th underlying index 0 The starting time t of the corresponding time period when the quadratic derivative result value of the single bottom layer index fluctuation function of the ith bottom layer index is minimum n The end time of the corresponding time period when the quadratic derivative result value of the single bottom layer index fluctuation function of the ith bottom layer index is minimum is represented by n, t is represented by t 0 To t n The number of the discrete actual data of the ith bottom index in the interval, C represents t 0 To t n The ith actual data with discrete bottom layer indexes in the time period, num [ C [)]Represents t 0 To t n Number of actual data of i-th discrete base level indicator in time period, C ′ Represents t 0 To t n In the ith discrete actual data of the bottom layer indexes in the time period, the data is more than H i Actual data of (2), num [ C ] ′ ]Represents t 0 To t n In the ith discrete actual data of the bottom layer indexes in the time period, the data is more than H i The amount of actual data.
6. The enterprise business risk assessment method according to claim 4, wherein the screening of the risk indicators from the underlying indicators of the enterprise to be assessed through the individual risk degree comprises the following steps:
removing the bottom layer indexes with the individual risk values of zero in all the bottom layer indexes;
the remaining underlying indicators are defined as risk indicators.
7. The enterprise operation risk assessment method according to claim 4, wherein the risk coefficient satisfies the following formula:
wherein D is q Individual risk for the qth risk indicator，α q The risk factor, α, representing the qth risk indicator q0 An initial weight representing the qth risk indicator, D representing the individual risk, [ D ]] max Represents the maximum value of the individual risks, [ alpha ] 0 ] max Representing the maximum value of the initial weight.
8. The enterprise operation risk assessment method according to claim 3, wherein the risk assessment subsystem of the enterprise to be assessed is established by combining the risk indexes with the corresponding risk coefficients, and comprises the following steps:
removing bottom layer indexes without corresponding risk indexes in the enterprise risk assessment system;
assigning the risk coefficients to corresponding risk indicators;
and carrying out gradient layering on the risk indexes according to the risk coefficients to obtain an enterprise risk assessment subsystem.
9. The enterprise business risk assessment method according to claim 8, wherein the assessment of the risk level of the enterprise to be assessed through the visualized risk assessment subsystem of the enterprise to be assessed comprises the following steps:
according to the quantity of the risk indexes in the visualized enterprise risk assessment subsystem to be assessed, the risk coefficient range and the risk index gradient layering result, an enterprise risk level assessment model is constructed, the enterprise risk level is assessed by utilizing the enterprise risk level, and the enterprise risk level assessment model meets the following formula:
wherein, E 0 Indicating that the risk level of the enterprise to be evaluated is normal, E 1 Indicating that the risk level of the enterprise to be assessed is slight, E 2 Indicating that the risk level of the enterprise to be evaluated is medium, E 3 Indicating that the risk level of the enterprise to be assessed is higher, E 4 Indicating that the risk level of the enterprise to be evaluated is high，α min Representing the minimum risk factor value, alpha max Value representing the maximum Risk coefficient, Q 0 Representing the value of the risk factor alpha e (alpha) min ，0.9α min +0.1α max ]Risk index corresponding to hour, num [ Q ] 0 ]Represents Q 0 The number of (b) represents Q 0 Compensation coefficient of quantity, Q 1 Value representing the risk factor alpha e (0.9 alpha) min +0.1α max ，0.8α min +0.2α max ]Risk index corresponding to hour, num [ Q ] 1 ]Represents Q 1 Gamma represents Q 1 Compensation coefficient of the amount of, Q 2 Value representing the risk factor alpha e (0.8 alpha) min +0.2α max ，0.5α min +0.5α max ]Risk index corresponding to hour, hum [ Q ] 2 ]Represents Q 2 Delta denotes Q 2 Compensation coefficient of the amount of, Q 3 Value representing the value of the risk factor alpha ∈ (0.5 alpha) min +0.5α max ，0.75α min +0.25α max ]Risk index corresponding to hour, num [ Q ] 3 ]Represents Q 3 The quantity of (e) represents Q 3 Compensation coefficient of the amount of, Q 4 Value representing the risk factor alpha e (0.75 alpha) min +0.25α max ，α max ]Risk index corresponding to hour, num [ Q ] 4 ]Represents Q 4 The number of (b), ζ represents Q 4 The amount of compensation factor.
10. An enterprise operation risk assessment system, comprising a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are connected with each other, wherein the memory is used for storing a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the enterprise operation risk assessment method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211501503.8A CN115796585A (en) | 2022-11-28 | 2022-11-28 | Enterprise operation risk assessment method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211501503.8A CN115796585A (en) | 2022-11-28 | 2022-11-28 | Enterprise operation risk assessment method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115796585A true CN115796585A (en) | 2023-03-14 |
Family
ID=85442211
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211501503.8A Withdrawn CN115796585A (en) | 2022-11-28 | 2022-11-28 | Enterprise operation risk assessment method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115796585A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117010697A (en) * | 2023-09-25 | 2023-11-07 | 山东财经大学 | Visual enterprise risk assessment method based on artificial intelligence |
-
2022
- 2022-11-28 CN CN202211501503.8A patent/CN115796585A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117010697A (en) * | 2023-09-25 | 2023-11-07 | 山东财经大学 | Visual enterprise risk assessment method based on artificial intelligence |
| CN117010697B (en) * | 2023-09-25 | 2023-12-19 | 山东财经大学 | Visual enterprise risk assessment method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20040186753A1 (en) | System and method for catastrophic risk assessment | |
| US20110196719A1 (en) | System for enhancing business performance | |
| CN108280541A (en) | Customer service strategies formulating method, device based on random forest and decision tree | |
| US20080172348A1 (en) | Statistical Determination of Multi-Dimensional Targets | |
| KR20030020864A (en) | Methods and apparatus for rapid deployment of a valuation system | |
| KR20020063615A (en) | Methods and systems for quantifying cash flow recovery and risk | |
| KR20020075389A (en) | Cross correlation tool for automated portfolio descriptive statistics | |
| CN113537807B (en) | Intelligent wind control method and equipment for enterprises | |
| CN112700324A (en) | User loan default prediction method based on combination of Catboost and restricted Boltzmann machine | |
| KR100713546B1 (en) | Method of technology evaluation | |
| CN112085388A (en) | Land value evaluation method, apparatus, terminal and readable storage medium | |
| CN115796585A (en) | Enterprise operation risk assessment method and system | |
| CN117217634B (en) | Enterprise cooperation community discovery method based on complex network | |
| CN110298759A (en) | A kind of fund diagnostic method, device and computer readable storage medium | |
| CN114154866A (en) | Marketing enterprise financial risk early warning method and system | |
| CN113361959A (en) | Method and device for calculating maturity of centralized operation of banking business | |
| CN108140051A (en) | Data based on whole world retrieval generate the connection to global networks system of global commerce grading in real time | |
| CN113283806A (en) | Enterprise information evaluation method and device, computer equipment and storage medium | |
| CN113627977A (en) | House value prediction method based on heteromorphic graph | |
| CN112767126A (en) | Collateral grading method and device based on big data | |
| CN117114812A (en) | Financial product recommendation method and device for enterprises | |
| CN117252688A (en) | Financial risk assessment method, system, terminal equipment and storage medium | |
| US20090187412A1 (en) | Correlation/relationship and forecasting generator | |
| CN107093018A (en) | Communication engineering project information method for visualizing and device based on health model | |
| CN112348220A (en) | Credit risk assessment prediction method and system based on enterprise behavior pattern |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230314 |
|
| WW01 | Invention patent application withdrawn after publication |