CN112734154B - Multi-factor public opinion risk assessment method based on fuzzy number similarity - Google Patents

Multi-factor public opinion risk assessment method based on fuzzy number similarity Download PDF

Info

Publication number
CN112734154B
CN112734154B CN202011279436.0A CN202011279436A CN112734154B CN 112734154 B CN112734154 B CN 112734154B CN 202011279436 A CN202011279436 A CN 202011279436A CN 112734154 B CN112734154 B CN 112734154B
Authority
CN
China
Prior art keywords
risk
public opinion
evaluation
factor
influence degree
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011279436.0A
Other languages
Chinese (zh)
Other versions
CN112734154A (en
Inventor
周凡
蒋维娜
刘宁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sun Yat Sen University
Original Assignee
Sun Yat Sen University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Sun Yat Sen University filed Critical Sun Yat Sen University
Priority to CN202011279436.0A priority Critical patent/CN112734154B/en
Publication of CN112734154A publication Critical patent/CN112734154A/en
Application granted granted Critical
Publication of CN112734154B publication Critical patent/CN112734154B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G06F18/24155—Bayesian classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/205—Parsing
    • G06F40/216—Parsing using statistical methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/18—Legal services; Handling legal documents

Abstract

The invention discloses a multi-factor public opinion risk assessment method based on fuzzy number similarity. Firstly, obtaining the influence degree of risk factors by using an extended good-bad solution distance method, and obtaining an index model structure and the arrangement sequence of elements of each layer by using a hierarchical analysis method; secondly, processing the input of different data types to obtain a risk factor fact coefficient evaluation value and fusing the risk factor fact coefficient evaluation value; and finally, mapping the evaluation comprehensive value into a risk grade and fuzzy number conversion system based on the fuzzy number similarity to obtain the public opinion risk grade. The invention can more comprehensively and comprehensively evaluate the current public opinion risk by fusing the risk factors in the workflow in a multi-source way; different statistical strategies are carried out on the negative topics and the positive topics, so that the method is more reasonable than the traditional method, the public opinion tendency can be better reflected, the constructed index model is beneficial to the refinement of risk factors, and meanwhile, the risk index has more objective influence degree evaluation.

Description

Multi-factor public opinion risk assessment method based on fuzzy number similarity
Technical Field
The invention relates to the technical field of risk management and fuzzy mathematics, in particular to a multi-factor public opinion risk assessment method based on fuzzy number similarity.
Background
With the rapid development of the internet, the speed of public opinion formation and propagation is increasing, and public opinion of people aiming at hot events in network media brings great risks and challenges to work. Therefore, the demand for accurate evaluation of public opinion risks in the working process is growing gradually, wherein how to construct the evaluation content of public opinion risks and how to perform quantitative analysis of risk levels are two core problems to be solved. The existing methods such as machine learning, fuzzy matrix and the like are difficult to be effectively applied to actual business due to limited historical data, high risk assessment accuracy requirements and the like.
In this regard, the risk assessment model based on fuzzy number similarity has strong technical advantages in terms of handling risk fuzziness and uncertainty. The method applies the fuzzy set theory to risk assessment and multi-attribute decision, converts qualitative evaluation into mathematical expression in interval number form based on fuzzy number continuous membership function, and performs fuzzy operation, fuzzy aggregation or fuzzy reasoning and other operations on the mathematical expression based on the mathematical expression so as to obtain accurate risk level. Therefore, the risk assessment based on the fuzzy analysis method can effectively solve the conversion problem of qualitative evaluation and quantitative analysis. The method mainly comprises four types of models: an evaluation model based on fuzzy ordering, an evaluation model based on fuzzy number similarity, a fuzzy inference model and a fuzzy matrix model. In the evaluation model based on fuzzy ranking, a ranking reference is first established, and then a risk level is determined according to a ranking result. In an actual working scene, a certain workflow is usually evaluated individually, and the situation that a plurality of evaluation objects are compared is less, so that it is more difficult to establish a ranking model. In the aspect of fuzzy reasoning, researchers usually describe membership functions and If-Then rules by using a risk matrix structure in a fuzzy reasoning system (Fuzzy Inference System, abbreviated as FIS), and evaluate and predict risks based on event information, and the method is a theoretical basis of fuzzy control research, is commonly used in the industrial field, and is not suitable for a scene of converting a document stream into a main operation.
The fuzzy matrix model represents a qualitative analysis method for introducing fuzzy set theory. The model replaces real numbers with fuzzy interval numbers, and human evaluation is reflected more truly, so that matrix granularity is refined. Although the number of risk junctions (risk tie) is reduced to a certain extent, the risk level distinguishing capability is improved, the method still belongs to qualitative evaluation and the construction process is very complicated, and an effective quantitative analysis model is difficult to establish aiming at the business containing multi-factor risks.
The fuzzy number similarity-based assessment model utilizes the similarity of fuzzy risk measures and risk levels to determine the early warning level, the model directly corresponds a single assessment object to the risk level, a plurality of object interdependencies do not exist, when only one workflow exists, the corresponding risk early warning level can be output, and human factors are eliminated to determine the risk level. Therefore, the evaluation requirement of the service scene is met, and the evaluation accuracy is high.
In summary, the evaluation model based on the fuzzy number similarity not only can effectively convert qualitative risk evaluation under a working scene, but also can establish an independent evaluation mechanism aiming at single work. However, the method has the defects in the aspects of special data processing, evaluation accuracy and the like, and becomes a bottleneck for restricting accurate public opinion risk evaluation.
One of the existing technologies is a management system, which mainly serves basic business process specification management and time management, and lacks assessment and management of multi-factor public opinion risks. The current workflow risk prevention and control system is defined in a form of a table, and each risk factor entry is defined as a risk item, a risk grade and a risk responsible person.
One of the disadvantages of the prior art is: (1) The existing mature management system lacks evaluation and management of multifactor working public opinion risks; (2) The existing risk prevention and control system has single risk point factor and does not macroscopically consider multiple risk factors; (3) The risk grade of the existing risk prevention and control system is fixed, objective data is not fully combined in the evaluation process, and the evaluation result is inaccurate.
The second prior art is a multi-dimensional analysis system for internet public opinion, which comprises the following main functions: negative public opinion analysis, hotspot analysis, public opinion outbreak trend analysis, etc. And the negative public opinion analysis is based on positive/negative emotion value analysis on the relevant texts of each mainstream network platform to obtain an evaluation result.
The second disadvantage of the prior art is: (1) In the system, a risk assessment algorithm for multidimensional public opinion analysis is lacked, and the analysis content has multiple dimensions but is independent; (2) Negative public opinion in the system is simple statistics of text emotion values, analysis of focus topics is lacking, and negative emotion analysis accuracy is low.
Disclosure of Invention
The invention aims to overcome the defects of the existing method and provides a multi-factor public opinion risk assessment method based on fuzzy number similarity. The main problems solved by the invention are that (1) in the existing public opinion risk index system, the risk factors are single, and the risk level is fixed; (2) The existing public opinion analysis platform only carries out simple emotion analysis on texts and does not carry out accurate analysis on focus topics; (3) The existing public opinion risk management method cannot overcome the ambiguity and uncertainty of risks, does not comprehensively and dynamically analyze the current public opinion state, and only gives out a fixed evaluation result.
In order to solve the above problems, the present invention provides a multi-factor public opinion risk assessment method based on fuzzy number similarity, which comprises:
extracting public opinion risk factors based on historical work documents and a workflow rule base, constructing a risk factor set, constructing an expert group, expressing the influence degree of the risk factor set by using a phrase set by the expert, and collecting the data to form a risk factor influence degree data set;
constructing a three-layer structure of an initial public opinion risk index model by using an analytic hierarchy process and defining nodes of each layer, wherein the model consists of a target layer, a criterion layer and an index layer, the target layer determines that the main body of evaluation is public opinion risk, the criterion layer defines four standard criteria of decision maker, principal, condition attribute and public opinion state based on fishbone diagram analysis of a historical work document, and the index layer consists of risk factors and corresponding influence degrees;
constructing an evaluation matrix based on the risk factor influence degree data set, and calculating to obtain the influence degree of each risk factor by using an expanded good-bad solution distance method to synthesize a multidimensional evaluation matrix;
based on the influence degree of each risk factor, determining the arrangement order of each layer of elements in the initial public opinion risk index model by using a hierarchical analysis method to obtain a final public opinion risk index model with complete system structure;
collecting and analyzing the related public opinion data of the current processed work, and evaluating the risk factors in the final public opinion risk index model to obtain the fact coefficient of each risk index in the model index layer;
fusing the influence degree of the risk factors in the final public opinion risk index model index layer with the fact coefficient to obtain a public opinion risk comprehensive value based on multi-factor evaluation;
based on the graphic characteristics of the fuzzy numbers, mapping the public opinion risk comprehensive value based on multi-factor evaluation into a risk level and fuzzy number conversion system by calculating the fuzzy number similarity based on the radius of gyration, thereby obtaining the public opinion risk level of the current processed work;
and if the public opinion risk level or the variation trend thereof meets the triggering early warning condition, executing corresponding early warning operation according to a risk plan.
Preferably, the phrase set specifically includes:
the phrase set lt= { "quite low" (absolutely low), "very low" (verylow), "low" (low), "lower" (farly low), "medium" (medium), "higher" (farly high), "very high" (veryhigh), "quite high" (absolutely high) }.
Preferably, the method constructs an evaluation matrix based on the risk factor influence degree dataset, and calculates the influence degree of each risk factor by using an extended good-bad solution distance method to synthesize a multidimensional evaluation matrix, specifically:
constructing an evaluation matrix based on the risk factor influence degree data set;
constructing positive and negative ideal solutions of risk factor evaluation;
calculating the Euclidean distance between each evaluation scheme in the evaluation matrix and the positive ideal solution and the Euclidean distance between each evaluation scheme and the negative ideal solution;
calculating the distance ratio of each evaluation scheme in the evaluation matrix to the positive and negative ideal solutions, and normalizing the distance ratio to obtain the weight of each evaluation scheme;
and carrying out weighted summation on the weight of each evaluation scheme and each evaluation scheme to obtain the influence degree evaluation of each risk factor.
The multi-factor public opinion risk assessment method based on fuzzy number similarity can more comprehensively and comprehensively give out fine-granularity assessment on the current public opinion risk by multi-source fusion of multi-dimensional information such as risk factors in a workflow; different statistical strategies are carried out on the negative topics and the positive topics, the method is more reasonable than the traditional method, the public opinion tendency can be reflected better, the index model constructed by the method is favorable for refining the risk factors in the construction stage, the model expansion in the maintenance stage, and meanwhile, the risk index has more objective influence degree evaluation.
Drawings
FIG. 1 is a general flow chart of a multi-factor public opinion risk assessment method based on fuzzy number similarity according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a language description and fuzzy number conversion system according to an embodiment of the present invention;
FIG. 3 is a diagram of a public opinion risk indicator model according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a fuzzy number and comparative scale conversion system in accordance with an embodiment of the present invention;
FIG. 5 is a graph of a numerical query of a random uniformity index RI in accordance with an embodiment of the present invention;
fig. 6 is a flowchart of the calculation of a negative emotion value of a public opinion text according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Fig. 1 is a multi-factor public opinion risk assessment method based on fuzzy number similarity according to an embodiment of the present invention, as shown in fig. 1, the method includes:
s1, extracting public opinion risk factors based on a historical work document and a workflow rule base, constructing a risk factor set, constructing an expert group, expressing the influence degree of the risk factor set by using a phrase set by the expert, and collecting the data to form a risk factor influence degree data set;
s2, constructing a three-layer structure of an initial public opinion risk index model by using an analytic hierarchy process and defining nodes of each layer, wherein the model consists of a target layer, a criterion layer and an index layer, the target layer determines that an estimated main body is a public opinion risk, the criterion layer defines four standard criteria of a decision maker, a principal, a case attribute and a public opinion state based on fishbone diagram analysis of a historical work document, and the index layer consists of risk factors and corresponding influence degrees;
s3, constructing an evaluation matrix based on the risk factor influence degree data set, and calculating to obtain the influence degree of each risk factor by using an expanded good-bad solution distance method to synthesize a multi-dimensional evaluation matrix;
s4, determining the arrangement sequence of elements of each layer in the initial public opinion risk index model by using a hierarchical analysis method based on the influence degree of each risk factor to obtain a final public opinion risk index model with complete system structure;
s5, collecting and analyzing the current processed work related public opinion data, and evaluating risk factors in the final public opinion risk index model to obtain fact coefficients of each risk index in a model index layer;
s6, fusing the influence degree of the risk factors in the final public opinion risk index model index layer with the fact coefficient to obtain a public opinion risk comprehensive value based on multi-factor evaluation;
s7, mapping the public opinion risk comprehensive value based on multi-factor evaluation into a risk level and fuzzy number conversion system by calculating fuzzy number similarity based on radius gyration based on the graphic characteristics of fuzzy numbers, so as to obtain the current processed working public opinion risk level;
and S8, if the public opinion risk level or the variation trend thereof meets the triggering early warning condition, executing corresponding early warning operation according to a risk plan.
Step S1, wherein the RISK factor set is risk= { r 1 ,r 2 ,…,r n The phrase set lt= { "quite low" (absolutely low), "very low" (verylow), "low" (low), "lower" (farly low), "medium" (medium), "higher" (farly high), "very high" (veryhigh), "quite high" (absolutely high) }.
Step S3, specifically, the following steps are performed:
s3-1, constructing an evaluation matrix based on the risk factor influence degree dataset acquired in the S1 preprocessing stage:
wherein N represents the number of risk factors, M is the number of evaluations in the data set, s mn Giving an evaluation value s for the degree of influence of the mth evaluation on the nth risk factor mn Is a generalized fuzzy number (a) 1 ,a 2 ,a 3 ,a 4 The method comprises the steps of carrying out a first treatment on the surface of the w), the mapping relation of which is shown in fig. 2.
S3-2, constructing positive and negative ideal solutions of risk factor evaluation:
wherein, the liquid crystal display device comprises a liquid crystal display device,and->Respectively defined as:
s3-3, calculating each evaluation scheme S m Euclidean distance from ideal:
calculation of each evaluation scheme s m Euclidean distance from negative ideal solution:
s3-4, calculating the distance ratio of each evaluation scheme to the positive and negative ideal solutions, and normalizing the distance ratio to obtain the weight of the evaluation scheme:
s3-5, for each evaluation scheme weight and each evaluation scheme S m Weighted summation is carried out to obtain the influence degree evaluation of each risk factor
Step S4, the public opinion risk index model comprises a target layer A, a criterion layer B and an index layer C, as shown in FIG. 3, and is specifically as follows:
s4-1, the risk factors are programmed into an index layer C according to the influence degree, and the risk factors are connected with corresponding criteria according to own attributes. In child nodes of B, the metrics are ordered by degree of impact. And (3) assigning initial ordering to the nodes of the layer B, and performing consistency verification of the model.
S4-2, constructing a comparison matrix delta,for the evaluation weight difference between the risk factors i and j, a comparison result delta of the importance of the risk factors i and j is obtained according to FIG. 4 ij Thereby constructing a pair comparison matrix delta, delta ij Is a scalar having the following properties:
s4-3, verifying consistency of the hierarchical single ordering. And calculating the feature vector of the maximum feature root of the matrix delta, and normalizing to obtain the sequencing weight of the same layer of factors on the relative importance of the previous layer. The consistency index CI to be verified is:
where λ is the maximum eigenvalue of matrix C and n is the dimension of matrix C. If ci=0, the ordering has complete consistency; the inconsistency increases as CI increases.
To further quantify the uniformity index, a random uniformity index RI is introduced, and the relationship between RI and the matrix order n is shown in fig. 5. The quantized consistency index CR is defined as:
if CR <0.1, matrix C passes the consistency check.
S4-4, calculating the hierarchical total sequence of all risk factors of the index layer relative to the highest layer. Criterion layer 4 nodes B1, B2, B3, B4 rank weight a for the highest layer 1 ,a 2 ,a 3 ,a 4 The hierarchical order of the BJ by the n risk factors of the index layer is b 1j ,b 2j ,…,b nj . Wherein CI is 1 Corresponds to the contrast matrix constructed with C1, C2 versus B1. The consistency ratio of the total sequence of the layers is as follows:
when CR <0.1, the total rank ordering passes the consistency check.
And S4-5, traversing the sorting and sorting weight calculation of the nodes in the criterion layer until the multi-level public opinion risk index model passes consistency verification, thereby completing the construction of the public opinion risk index model. The weight evaluation given to the risk factors by a comprehensive expert group of the extended superior and inferior solution distance method (TOPSIS) is carried out, so that more objective influence degree weight is obtained. In addition, a more systematic public opinion risk index system is constructed by using an Analytic Hierarchy Process (AHP), so that the updating and maintenance of a risk index model are facilitated.
Step S5, specifically, the following steps are performed:
s5-1, calculating fact coefficients of risk indexes in the risk index model according to all public opinion data updated in real time. Index evaluation data sources are classified into 3 categories: 1) Data provided by other related systems; 2) Risk data actively reported by workflow related personnel; 3) And the public opinion analysis module provides data.
In the final public opinion risk index model constructed in S5-2 and S4, C5 and C7 are actively input by a decision maker, and input data are elements of a phrase set LT.
S5-3, in the final public opinion risk index model constructed in S4, C3 history left-over work is determined by attribute fields, true is mapped to be quite low, and False is mapped to be quite high. C4 critical job type is determined by its attribute field. C9 well known decision makers are provided by decision maker knowledge maps with True mapping "quite low" and False mapping "quite high".
S5-4, in the final public opinion risk index model constructed in S4, C1, C2, C6 and C8 are calculated according to public opinion data collected in real time. Wherein, C2 is the proportion of public opinion covering the white list of the account with high influence, and C6 and C8 are the status values of whether the public opinion covering the high-influence account appears in each big heat search list. C1 is a public opinion negative emotion value based on a focus topic, and a specific processing flow is shown in FIG. 6.
(1) After the text preprocessing and vectorization are completed, topic clustering is carried out based on a K-Means algorithm, a focus topic text is extracted according to word segmentation word frequency information in the text, and an emotion value of the topic text is calculated by using a Bayesian classifier on the basis.
(2) And providing topic texts from the public opinion texts to obtain residual texts, and obtaining emotion values of all topic-related residual texts by using a Bayesian classifier.
(3) Fusing public opinion negative denominations, defined as:
wherein n is i Is the number of negative emotion texts in the topic, otherwise p i Is the number of positive emotion texts in the topic. τ is the threshold of negative emotion text triggering public opinion risk and M is the number of topics relevant to the work. And maps emotion values as 1 to 9 to elements in phrase set LT. Compared with the traditional method, the emotion value analysis method based on the focus topic has higher rationality for judging the public opinion tendency.
Step S6, specifically, the following steps are performed:
s6-1, converting the numerical value of the fact coefficient corresponding to the risk index obtained in the S5, namely the probability of occurrence of the event corresponding to the risk index, into a fuzzy number according to FIG. 2. Make GFNS m ＝(lt m ,GFN m ), lt m Is a language expression phrase, GFN m Is the corresponding generalized fuzzy number. The value v of the risk fact coefficient i The converted blur number is expressed as:
s6-2, fusing a plurality of risk factors according to the influence degree imact and the fact coefficient evaluation to obtain the public opinion risk level of the current workflow, wherein the fusion method comprises the following steps:
wherein N is the number of risk factors, and finally the fuzzy number of the public opinion risk comprehensive evaluation is obtained to represent risk.
Step S7, specifically, the following steps are performed:
based on the graphic characteristics of the fuzzy numbers, mapping the public opinion risk comprehensive evaluation risk obtained in the step S6 into a risk level and fuzzy number conversion system by calculating the fuzzy number similarity based on the radius of gyration, thereby obtaining the public opinion risk level of the current workflow:
the multi-factor public opinion risk assessment method based on fuzzy number similarity provided by the embodiment of the invention can be used for comprehensively and comprehensively giving fine-granularity assessment on the current public opinion risk by multi-source fusion of multi-dimensional information such as risk factors in a workflow; different statistical strategies are carried out on the negative topics and the positive topics, the method is more reasonable than the traditional method, the public opinion tendency can be reflected better, the index model constructed by the method is favorable for refining the risk factors in the construction stage, the model expansion in the maintenance stage, and meanwhile, the risk index has more objective influence degree evaluation.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program to instruct related hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like.
In addition, the multi-factor public opinion risk assessment method based on fuzzy number similarity provided by the embodiment of the invention is described in detail, and specific examples are applied to illustrate the principle and the implementation of the invention, and the description of the above embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.

Claims (3)

1. A multi-factor public opinion risk assessment method based on fuzzy number similarity is characterized by comprising the following steps:
extracting public opinion risk factors based on historical work documents and a workflow rule base, constructing a risk factor set, constructing an expert group, expressing the influence degree of the risk factor set by using a phrase set by the expert, and collecting the data to form a risk factor influence degree data set;
constructing a three-layer structure of an initial public opinion risk index model by using an analytic hierarchy process and defining nodes of each layer, wherein the model consists of a target layer, a criterion layer and an index layer, the target layer determines that an estimated main body is a public opinion risk, the criterion layer defines four standard criteria of a decision maker, a principal, a case attribute and a public opinion state based on fishbone diagram analysis of a historical work document, and the index layer consists of risk factors and corresponding influence degrees;
constructing an evaluation matrix based on the risk factor influence degree data set, and calculating to obtain the influence degree of each risk factor by using an expanded good-bad solution distance method to synthesize a multidimensional evaluation matrix;
based on the influence degree of each risk factor, determining the arrangement order of each layer of elements in the initial public opinion risk index model by using a hierarchical analysis method to obtain a final public opinion risk index model with complete system structure;
collecting and analyzing the related public opinion data of the current processed work, and evaluating the risk factors in the final public opinion risk index model to obtain the fact coefficient of each risk index in the model index layer;
fusing the influence degree of the risk factors in the final public opinion risk index model index layer with the fact coefficient to obtain a public opinion risk comprehensive value based on multi-factor evaluation;
based on the graphic characteristics of the fuzzy numbers, mapping the public opinion risk comprehensive value based on multi-factor evaluation into a risk level and fuzzy number conversion system by calculating the fuzzy number similarity based on the radius of gyration, thereby obtaining the public opinion risk level of the current processed work;
and if the public opinion risk level or the variation trend thereof meets the triggering early warning condition, executing corresponding early warning operation according to a risk plan.
2. The multi-factor public opinion risk assessment method based on fuzzy number similarity of claim 1, wherein the phrase set specifically comprises:
the phrase set lt= { "quite low" (absolutely low), "very low" (verylow), "low" (low), "lower" (farly low), "medium" (medium), "higher" (farly high), "very high" (veryhigh), "quite high" (absolutely high) }.
3. The multi-factor public opinion risk assessment method based on fuzzy number similarity of claim 1, wherein the method is characterized in that an evaluation matrix is constructed based on the risk factor influence degree dataset, and the influence degree of each risk factor is calculated by using an extended good-bad solution distance method to synthesize a multi-dimensional evaluation matrix, specifically:
constructing an evaluation matrix based on the risk factor influence degree data set;
constructing positive and negative ideal solutions of risk factor evaluation;
calculating the Euclidean distance between each evaluation scheme in the evaluation matrix and the positive ideal solution and the Euclidean distance between each evaluation scheme and the negative ideal solution;
calculating the distance ratio of each evaluation scheme in the evaluation matrix to the positive and negative ideal solutions, and normalizing the distance ratio to obtain the weight of each evaluation scheme;
and carrying out weighted summation on the weight of each evaluation scheme and each evaluation scheme to obtain the influence degree evaluation of each risk factor.
CN202011279436.0A 2020-11-16 2020-11-16 Multi-factor public opinion risk assessment method based on fuzzy number similarity Active CN112734154B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011279436.0A CN112734154B (en) 2020-11-16 2020-11-16 Multi-factor public opinion risk assessment method based on fuzzy number similarity

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011279436.0A CN112734154B (en) 2020-11-16 2020-11-16 Multi-factor public opinion risk assessment method based on fuzzy number similarity

Publications (2)

Publication Number Publication Date
CN112734154A CN112734154A (en) 2021-04-30
CN112734154B true CN112734154B (en) 2023-08-01

Family

ID=75597516

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011279436.0A Active CN112734154B (en) 2020-11-16 2020-11-16 Multi-factor public opinion risk assessment method based on fuzzy number similarity

Country Status (1)

Country Link
CN (1) CN112734154B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113570182A (en) * 2021-05-06 2021-10-29 深圳怀新企业投资顾问股份有限公司 Reputation risk management capability assessment method, reputation risk management capability assessment device, reputation risk management equipment and storage medium
CN113360843B (en) * 2021-08-11 2021-11-05 上海建工集团股份有限公司 Multi-factor coupling-based security risk management and control method
CN113779195B (en) * 2021-08-31 2023-12-22 西南电子技术研究所（中国电子科技集团公司第十研究所） Hot event state evaluation method
CN114565408B (en) * 2022-03-01 2023-03-24 北京派瑞威行互联技术有限公司 Bidding prediction method and system for advertisement putting
CN115221416B (en) * 2022-08-18 2023-01-17 上海金仕达软件科技有限公司 Reputation risk positioning analysis method and system

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110738399A (en) * 2019-12-16 2020-01-31 中山大学 judicial judgment flow deviation early warning method based on fuzzy set theory
CN111914087A (en) * 2020-07-30 2020-11-10 广州城市信息研究所有限公司 Public opinion analysis method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110738399A (en) * 2019-12-16 2020-01-31 中山大学 judicial judgment flow deviation early warning method based on fuzzy set theory
CN111914087A (en) * 2020-07-30 2020-11-10 广州城市信息研究所有限公司 Public opinion analysis method

Also Published As

Publication number Publication date
CN112734154A (en) 2021-04-30

Similar Documents

Publication Publication Date Title
CN112734154B (en) Multi-factor public opinion risk assessment method based on fuzzy number similarity
Soui et al. Rule-based credit risk assessment model using multi-objective evolutionary algorithms
Ni et al. Stock trend prediction based on fractal feature selection and support vector machine
CN109657947B (en) Enterprise industry classification-oriented anomaly detection method
Pratt et al. Employee attrition estimation using random forest algorithm
CN107688870B (en) Text stream input-based hierarchical factor visualization analysis method and device for deep neural network
Sánchez et al. Mutual information-based feature selection and partition design in fuzzy rule-based classifiers from vague data
CN112232561A (en) Power load probability prediction method based on constrained parallel LSTM quantile regression
CN116127084A (en) Knowledge graph-based micro-grid scheduling strategy intelligent retrieval system and method
CN105912773A (en) Novel intelligent stamping process design method based on data mining technology
Liu The evaluation of classification models for credit scoring
Nan et al. Heuristic bivariate forecasting model of multi-attribute fuzzy time series based on fuzzy clustering
Gu et al. Fuzzy time series forecasting based on information granule and neural network
Li Forecast and simulation of the public opinion on the public policy based on the markov model
Mao et al. Naive Bayesian algorithm classification model with local attribute weighted based on KNN
CN115293827A (en) Novel model interpretability analysis method for assisting fine operation of enterprise
Li et al. Research on listed companies’ credit ratings, considering classification performance and interpretability
Zhang Research on quantitative investment based on machine learning
CN113987536A (en) Method and device for determining security level of field in data table, electronic equipment and medium
CN114282875A (en) Flow approval certainty rule and semantic self-learning combined judgment method and device
Yuan et al. Analysis of Bank Loan Risk Management Based on BP Neural Network
Jing et al. A multi-dimensional city data embedding model for improving predictive analytics and urban operations
CN114330562B (en) Small sample refinement classification and multi-classification model construction method
Zheng Individualized Recommendation Method of Multimedia Network Teaching Resources Based on Classification Algorithm in a Smart University
CN116552545A (en) Bad driving behavior rating method based on improved extended confidence rule reasoning

Legal Events

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