Market subject evaluation method and system based on risk entropy value model and big data processing

Abstract

The present application relates to a kind of market subject evaluation method and system based on risk entropy model and big data processing, belong to big data analysis and risk assessment technical field.The method includes: obtaining market credit data, market credit data is output market subject benchmark credit data by multi-source data fusion and feature standardization processing, and market subject benchmark credit data is stored in batch using distributed framework;Enterprise risk knowledge graph is constructed based on market subject benchmark credit data, and the risk factor set in enterprise risk knowledge graph is identified by relationship extraction model;Multi-dimensional risk entropy evaluation model is preset, and the risk factor set is output multi-dimensional risk entropy sequence by multi-dimensional risk entropy evaluation model;Subject risk grade score result is obtained based on multi-dimensional risk entropy sequence by subject scoring, and visualization is carried out.Risk entropy model and big data processing based market subject evaluation are realized.

Description

Technical Field

[0001] This invention belongs to the field of big data analysis and risk assessment technology, specifically relating to a market entity assessment method and system based on a risk entropy value model and big data processing. Background Technology

[0002] In recent years, with the rapid development of domestic and international financial markets, the financial industry has gradually evolved into a typical industry highly dependent on information technology. The efficiency, breadth, and quality of information flow have become increasingly prominent in financial activities. Financial risk management and decision-making processes increasingly rely on the comprehensive acquisition and accurate identification of corporate information; the timeliness, authenticity, and completeness of information have become core prerequisites for ensuring the security and efficiency of the financial system. However, in actual market operations, problems such as information distortion, data gaps, and delayed updates frequently occur, directly affecting the risk assessment and decision-making effectiveness of financial assets.

[0003] Existing market entity assessment methods primarily rely on single, structured historical data sources, making it difficult to comprehensively integrate dynamic corporate behavior and changes in the external environment. More importantly, traditional models are inadequate in fusing multi-dimensional risk characteristics and lack adaptive assessment and update mechanisms based on big data processing, failing to reflect the real-time credit evolution of market entities. Therefore, there is an urgent need for a method that can achieve comprehensiveness, objectivity, and dynamism in market entity assessment through deep integration of multi-source heterogeneous data and intelligent identification of unstructured risk factors, thereby accurately identifying risks. Summary of the Invention

[0004] To address the aforementioned problems in existing technologies, this invention provides a market entity assessment method and system based on a risk entropy model and big data processing.

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] A market entity assessment method based on a risk entropy model and big data processing includes:

[0007] S1: Acquire market credit data, process the market credit data through multi-source data fusion and feature standardization to output benchmark credit data of market entities, and use a distributed framework to store the benchmark credit data of market entities in batches;

[0008] S2: Construct an enterprise risk knowledge graph based on the benchmark credit data of the market entities, and identify the risk factor set in the enterprise risk knowledge graph through a relation extraction model;

[0009] S3: Preset a multidimensional risk entropy value assessment model, and output a multidimensional risk entropy value sequence from the risk factor set through the multidimensional risk entropy value assessment model;

[0010] S4: Based on the multidimensional risk entropy value sequence, the subject is scored to obtain the subject risk level score result, and then visualized.

[0011] Preferably, the processing procedure for the market entity benchmark credit data in step S1 includes:

[0012] S101: The market credit data includes structured data and unstructured data;

[0013] S102: Obtain market credit structure data by normalizing the structured data;

[0014] S103: Obtain market credit unstructured data by processing the unstructured data using natural language;

[0015] S104: Label the market credit structure data and the market credit unstructure data using a confidence correction mechanism to form a trusted label set; generate a multi-source market credit set by storing the trusted label set;

[0016] S105: Output benchmark credit data of market entities by unifying the format of the multi-source market credit set.

[0017] Preferably, the natural language processing in step S103 includes word segmentation, named entity recognition, and syntactic analysis.

[0018] Preferably, the confidence correction mechanism in step S104 is processed as follows:

[0019] S104-1: Obtain a confidence score by calculating the confidence levels of the market credit structure data and the market credit unstructure data;

[0020] S104-2: A confidence threshold is preset. If the confidence score is less than the confidence threshold, the data is labeled; if the confidence score is greater than the confidence threshold, the data is stored in the trusted label set.

[0021] Preferably, the process of identifying the risk factor set in step S2 is as follows:

[0022] S201: By identifying entity relationships in the benchmark credit data of the market entities;

[0023] S202: Based on the entity relationships and the enterprise risk knowledge graph, the risk factor set is generated by identifying implicit risk paths through a path reasoning algorithm.

[0024] Preferably, the path reasoning algorithm in step S202 includes the following steps:

[0025] S202-1: Map the entity relationships to the node set and semantic edges in the enterprise risk knowledge graph to generate a basic risk path set;

[0026] S202-2: Obtain the nodes and edges of the basic risk path set, and perform a weighted summation to obtain the path weights;

[0027] S202-3: Preset a risk threshold, and retain paths with path weights greater than the risk threshold to form a candidate risk path set;

[0028] S202-4: Extract associated risk factors based on the candidate risk path set and output the risk factor set.

[0029] Preferably, the modeling process of the multidimensional risk entropy value assessment model in step S3 is as follows:

[0030] S301: Obtain the risk factors in the risk factor set, and calculate the fuzzy membership degree based on the risk factors;

[0031] S302: Calculate the fuzzy entropy value using the fuzzy membership degree;

[0032] S303: Obtain the historical risk factor trigger time, and calculate the time decay risk entropy based on the historical risk factor trigger time and the fuzzy entropy value;

[0033] S304: Output the multidimensional risk entropy value sequence by storing the time decay risk entropy.

[0034] Preferably, the scoring process for the subject rating in step S4 is as follows:

[0035] S401: Obtain the time change rate and trigger intensity, and obtain the multidimensional risk entropy value in the multidimensional risk entropy value sequence;

[0036] S402: Calculate the dynamic scoring weight based on the time change rate, the trigger intensity, and the multidimensional risk entropy value;

[0037] S403: Obtain the final score based on the dynamic scoring weights;

[0038] S404: Map the final score to the grade level to obtain the subject risk level score result.

[0039] Preferably, the mapping process in step S404 is as follows:

[0040] S404-1: Preset mapping rules, first threshold, and second threshold; based on the mapping rules, map the final score to a score range to obtain the risk level.

[0041] The process for determining the mapping is as follows:

[0042] Determine whether the final score is greater than the first threshold; if yes, the risk level is "high risk".

[0043] No, if the final score is greater than the second threshold, the risk level is "medium risk"; if the final score is less than the second threshold, the risk level is "low risk".

[0044] S404-2: Match color codes according to the risk level and dynamically display the subject's scoring results and associated risk paths in the interactive dashboard.

[0045] A market entity assessment system based on a risk entropy model and big data processing includes a data preprocessing module, a relationship extraction module, a risk assessment module, and an entity assessment module, comprising:

[0046] The data preprocessing module is used to acquire market credit data, process the market credit data through multi-source data fusion and feature standardization to output benchmark credit data of market entities, and use a distributed framework to store the benchmark credit data of market entities in batches.

[0047] The relationship extraction module is used to construct an enterprise risk knowledge graph based on the benchmark credit data of the market entities, and to identify the risk factor set in the enterprise risk knowledge graph through the relationship extraction model;

[0048] The risk assessment module is used to preset a multidimensional risk entropy value assessment model and output a multidimensional risk entropy value sequence from the risk factor set through the multidimensional risk entropy value assessment model.

[0049] The subject assessment module is used to score the subject based on the multidimensional risk entropy value sequence to obtain the subject risk level score result, and then visualize it.

[0050] The beneficial effects of this invention are as follows:

[0051] (1) By normalizing structured data and processing unstructured data using natural language, combined with a confidence correction mechanism and a distributed storage framework, efficient integration and standardization of multi-source market credit data were achieved. This significantly improved the efficiency of data processing and ensured the credibility and consistency of the data, providing high-quality input for subsequent risk assessment.

[0052] (2) Based on enterprise risk knowledge graph and path reasoning algorithm, it can identify explicit and implicit risk paths, and dynamically adjust the timeliness and severity weight of risk factors by combining fuzzy membership degree and time decay factor. This mechanism enhances the depth of risk factor mining and improves the comprehensiveness and dynamic adaptability of risk assessment.

[0053] (3) By using a multidimensional risk entropy value assessment model, risk factors are transformed into fuzzy entropy values ​​and time-decaying risk entropy, quantifying the risk impact of different dimensions. Combining the time change rate, trigger intensity, and dynamic scoring weights, the final subject risk level score is generated. This modeling method makes the risk assessment results more scientific and interpretable. Attached Figure Description

[0054] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0055] Figure 1 This is a flowchart illustrating a market entity evaluation method based on a risk entropy model and big data processing according to the present invention. Detailed Implementation

[0056] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided.

[0057] Please see Figure 1 A market entity assessment method based on a risk entropy model and big data processing includes:

[0058] S1: Acquire market credit data, process the market credit data through multi-source data fusion and feature standardization to output benchmark credit data of market entities, and use a distributed framework to store the benchmark credit data of market entities in batches;

[0059] S2: Construct an enterprise risk knowledge graph based on the benchmark credit data of the market entities, and identify the risk factor set in the enterprise risk knowledge graph through a relation extraction model;

[0060] S3: Preset a multidimensional risk entropy value assessment model, and output a multidimensional risk entropy value sequence from the risk factor set through the multidimensional risk entropy value assessment model;

[0061] S4: Based on the multidimensional risk entropy value sequence, the subject is scored to obtain the subject risk level score result, and then visualized.

[0062] Specifically, the market credit data in step S1 includes structured data and unstructured data. The structured data includes financial statements, credit records, and business registration information; the unstructured data includes public opinion texts, announcements, news, and social media content.

[0063] Specifically, the processing of market entity benchmark credit data in step S1 includes:

[0064] S101: The market credit data includes structured data and unstructured data;

[0065] S102: Obtain market credit structure data by normalizing the structured data;

[0066] S103: Obtain market credit unstructured data by processing the unstructured data using natural language;

[0067] S104: Label the market credit structure data and the market credit unstructure data using a confidence correction mechanism to form a trusted label set; generate a multi-source market credit set by storing the trusted label set;

[0068] S105: Output benchmark credit data of market entities by unifying the format of the multi-source market credit set.

[0069] Specifically, the natural language processing in step S103 includes word segmentation, named entity recognition, and syntactic analysis.

[0070] Specifically, the confidence correction mechanism in step S104 is processed as follows:

[0071] S104-1: Obtain a confidence score by calculating the confidence levels of the market credit structure data and the market credit unstructure data;

[0072] S104-2: A confidence threshold is preset. If the confidence score is less than the confidence threshold, the data is labeled; if the confidence score is greater than the confidence threshold, the data is stored in the trusted label set.

[0073] In this embodiment, the confidence score is calculated based on the following indicators: source credibility, content consistency, information integrity, and contextual signals (negative words and speculative words in the text). The confidence score is then obtained by weighted summation of these indicators.

[0074] Specifically, the benchmark credit data of market entities in step S105 is triple data, in the form of <entity ID, feature type, feature value>.

[0075] Specifically, the enterprise risk knowledge graph in step S2 consists of a set of nodes and semantic edges. The set of nodes includes enterprises, events, and personnel; the semantic edges include litigation relationships, penalty relationships, and investment relationships.

[0076] Specifically, the process of identifying the risk factor set in step S2 is as follows:

[0077] S201: By identifying entity relationships in the benchmark credit data of the market entities;

[0078] S202: Based on the entity relationships and the enterprise risk knowledge graph, the risk factor set is generated by identifying implicit risk paths through a path reasoning algorithm.

[0079] Specifically, the entity relationship in step S201 is represented as follows:

[0080] <Subject, risky behavior / event, time / related parties>;

[0081] The attributes included in each factor in the risk factor set in step S202 are:

[0082] r i =<Type, Trigger Time, Severity, Frequency, Associated Subject>

[0083] Where, r i This represents the concentration factor of the risk factors.

[0084] Specifically, the path reasoning algorithm in step S202 includes the following steps:

[0085] S202-1: Map the entity relationships to the node set and semantic edges in the enterprise risk knowledge graph to generate a basic risk path set;

[0086] S202-2: Obtain the nodes and edges of the basic risk path set, and perform a weighted summation to obtain the path weights;

[0087] S202-3: Preset a risk threshold, and retain paths with path weights greater than the risk threshold to form a candidate risk path set;

[0088] S202-4: Extract associated risk factors based on the candidate risk path set and output the risk factor set.

[0089] Specifically, the modeling process of the multidimensional risk entropy value assessment model in step S3 is as follows:

[0090] S301: Obtain the risk factors in the risk factor set, and calculate the fuzzy membership degree based on the risk factors;

[0091] The calculation formula is as follows:

[0092] ,

[0093] Where, μ i Let be the fuzzy membership degree, e represent the logarithmic function calculation, γ be the decay rate, and t be the fuzzy membership degree. now `t` is the current time, `severity(r)` is the event start time, and `t` is the event start time. i ) represents the risk factor r i The severity of the problem is denoted by η, where η is the nonlinear adjustment parameter and k is the smoothing constant.

[0094] S302: Calculate the fuzzy entropy value using the fuzzy membership degree;

[0095] The expression for calculating the fuzzy entropy value is:

[0096] ,

[0097] Among them, H f Let be the fuzzy entropy value, i represent the i-th risk factor, n represent the total number of risk factors, and μ i The fuzzy membership degree is ε, where ε is a very small value.

[0098] S303: Obtain the historical risk factor trigger time, and calculate the time decay risk entropy based on the historical risk factor trigger time and the fuzzy entropy value;

[0099] The expression for calculating the time decay risk entropy is:

[0100] ,

[0101] Among them, H t H represents the time decay risk entropy. f Let λ be the fuzzy entropy value, λ be the time decay coefficient, and ∆t be the interval between the current moment and the time when the event occurred.

[0102] S304: Output the multidimensional risk entropy value sequence by storing the time decay risk entropy.

[0103] Specifically, the scoring process for the subject score in step S4 is as follows:

[0104] S401: Obtain the time change rate and trigger intensity, and obtain the multidimensional risk entropy value in the multidimensional risk entropy value sequence;

[0105] S402: Calculate the dynamic scoring weight based on the time change rate, the trigger intensity, and the multidimensional risk entropy value;

[0106] The calculation expression for the dynamic scoring weight is as follows:

[0107] ,

[0108] Among them, w t For the dynamic scoring weight, H is the attenuation coefficient. t I represents the time decay risk entropy. t The trigger intensity is denoted by ∆t, the rate of change over time is denoted by ε, and ε is a smoothing constant.

[0109] S403: Obtain the final score based on the dynamic scoring weights;

[0110] The mathematical expression for the final score is:

[0111] ,

[0112] Where S represents the final score, t represents the time decay risk entropy at the t-th time, m represents the number of time decay risk entropies, and w t H represents the dynamic scoring weight. t Represents the time decay risk entropy;

[0113] S404: Map the final score to the grade level to obtain the subject risk level score result.

[0114] Specifically, the mapping process in step S404 is as follows:

[0115] S404-1: Preset mapping rules, first threshold, and second threshold; based on the mapping rules, map the final score to a score range to obtain the risk level.

[0116] The process for determining the mapping is as follows:

[0117] Determine whether the final score is greater than the first threshold; if yes, the risk level is "high risk".

[0118] No, if the final score is greater than the second threshold, the risk level is "medium risk"; if the final score is less than the second threshold, the risk level is "low risk".

[0119] S404-2: Match color codes according to the risk level and dynamically display the subject's scoring results and associated risk paths in the interactive dashboard.

[0120] Specifically, the color coding includes: if the risk level is low, the color coding is green; if the risk level is medium, the color coding is orange; and if the risk level is high, the color coding is red.

[0121] In this embodiment, a market entity assessment system based on a risk entropy model and big data processing includes a data preprocessing module, a relationship extraction module, a risk assessment module, and an entity assessment module, comprising:

[0122] The data preprocessing module is used to acquire market credit data, process the market credit data through multi-source data fusion and feature standardization to output benchmark credit data of market entities, and use a distributed framework to store the benchmark credit data of market entities in batches.

[0123] The relationship extraction module is used to construct an enterprise risk knowledge graph based on the benchmark credit data of the market entities, and to identify the risk factor set in the enterprise risk knowledge graph through the relationship extraction model;

[0124] The risk assessment module is used to preset a multidimensional risk entropy value assessment model and output a multidimensional risk entropy value sequence from the risk factor set through the multidimensional risk entropy value assessment model.

[0125] The subject assessment module is used to score the subject based on the multidimensional risk entropy value sequence to obtain the subject risk level score result, and then visualize it.

[0126] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A market entity assessment method based on a risk entropy model and big data processing, characterized in that, Includes the following steps: S1: Acquire market credit data, process the market credit data through multi-source data fusion and feature standardization to output benchmark credit data of market entities, and use a distributed framework to store the benchmark credit data of market entities in batches; S2: Construct an enterprise risk knowledge graph based on the benchmark credit data of the market entities, and identify the risk factor set in the enterprise risk knowledge graph through a relation extraction model. The identification process of the risk factor set is as follows: S201: Identify the entity relationships in the benchmark credit data of the market entities; S202: Based on the entity relationships and the enterprise risk knowledge graph, the risk factor set is generated by identifying implicit risk paths through a path reasoning algorithm; S3: A pre-defined multidimensional risk entropy value assessment model is used to output a multidimensional risk entropy value sequence from the risk factor set. The modeling process of the multidimensional risk entropy value assessment model is as follows: S301: Obtain the risk factors in the risk factor set, and calculate the fuzzy membership degree based on the risk factors; S302: Calculate the fuzzy entropy value using the fuzzy membership degree; S303: Obtain the historical risk factor trigger time, and calculate the time decay risk entropy based on the historical risk factor trigger time and the fuzzy entropy value; S304: Output the multidimensional risk entropy value sequence by storing the time decay risk entropy; S4: Based on the multidimensional risk entropy value sequence, the subject risk level score is obtained and visualized. The subject scoring process is as follows: S401: Obtain the time change rate and trigger intensity, and obtain the multidimensional risk entropy value in the multidimensional risk entropy value sequence; S402: Calculate the dynamic scoring weight based on the time change rate, the trigger intensity, and the multidimensional risk entropy value. The calculation expression for the dynamic scoring weight is as follows: ， in, w t For the dynamic scoring weight, The attenuation coefficient is... H t Represents the time decay risk entropy, I t The trigger strength, ∆t This represents the rate of change over time. ε It is a smoothing constant; S403: Obtain the final score based on the dynamic scoring weights; S404: Map the final score to the grade level to obtain the subject risk level score result.

2. The market entity assessment method based on risk entropy model and big data processing according to claim 1, characterized in that, The processing procedure for market entity benchmark credit data in step S1 includes: S101: The market credit data includes structured data and unstructured data; S102: Obtain market credit structure data by normalizing the structured data; S103: Obtain market credit unstructured data by processing the unstructured data using natural language; S104: Label the market credit structure data and the market credit unstructure data using a confidence correction mechanism to form a trusted label set; generate a multi-source market credit set by storing the trusted label set; S105: Output benchmark credit data of market entities by unifying the format of the multi-source market credit set.

3. The market entity assessment method based on risk entropy model and big data processing according to claim 2, characterized in that, The natural language processing in step S103 includes word segmentation, named entity recognition, and syntactic analysis.

4. The market entity assessment method based on risk entropy model and big data processing according to claim 2, characterized in that, The confidence correction mechanism in step S104 is processed as follows: S104-1: Obtain a confidence score by calculating the confidence levels of the market credit structure data and the market credit unstructure data; S104-2: A pre-set confidence threshold is used. If the confidence score is less than the confidence threshold, the data is labeled. If the confidence score is greater than the confidence threshold, it is stored in the trusted tag set.

5. The market entity assessment method based on risk entropy model and big data processing according to claim 4, characterized in that, The path reasoning algorithm in step S202 includes the following steps: S202-1: Map the entity relationships to the node set and semantic edges in the enterprise risk knowledge graph to generate a basic risk path set; S202-2: Obtain the nodes and edges of the basic risk path set, and perform a weighted summation to obtain the path weights; S202-3: Preset a risk threshold, and retain paths with path weights greater than the risk threshold to form a candidate risk path set; S202-4: Extract associated risk factors based on the candidate risk path set and output the risk factor set.

6. The market entity assessment method based on risk entropy model and big data processing according to claim 1, characterized in that, The mapping process in step S404 is as follows: S404-1: Preset mapping rules, first threshold, and second threshold; based on the mapping rules, map the final score to a score range to obtain the risk level. The process for determining the mapping is as follows: Determine whether the final score is greater than the first threshold; if yes, the risk level is "high risk". No, if the final score is greater than the second threshold, the risk level is "medium risk"; if the final score is less than the second threshold, the risk level is "low risk". S404-2: Match color codes according to the risk level and dynamically display the subject's scoring results and associated risk paths in the interactive dashboard.

7. A market entity assessment system based on a risk entropy model and big data processing, comprising a data preprocessing module, a relationship extraction module, a risk assessment module, and an entity assessment module, characterized in that, include: The data preprocessing module is used to acquire market credit data, process the market credit data through multi-source data fusion and feature standardization to output benchmark credit data of market entities, and use a distributed framework to store the benchmark credit data of market entities in batches. The relationship extraction module is used to construct an enterprise risk knowledge graph based on the benchmark credit data of the market entities, and to identify the risk factor set in the enterprise risk knowledge graph through a relationship extraction model. The identification process of the risk factor set is as follows: S201: Identify the entity relationships in the benchmark credit data of the market entities; S202: Based on the entity relationships and the enterprise risk knowledge graph, the risk factor set is generated by identifying implicit risk paths through a path reasoning algorithm; The risk assessment module is used to preset a multidimensional risk entropy value assessment model, and output a multidimensional risk entropy value sequence from the risk factor set through the multidimensional risk entropy value assessment model. The modeling process of the multidimensional risk entropy value assessment model is as follows: S301: Obtain the risk factors in the risk factor set, and calculate the fuzzy membership degree based on the risk factors; S302: Calculate the fuzzy entropy value using the fuzzy membership degree; S303: Obtain the historical risk factor trigger time, and calculate the time decay risk entropy based on the historical risk factor trigger time and the fuzzy entropy value; S304: Output the multidimensional risk entropy value sequence by storing the time decay risk entropy; The subject assessment module is used to score the subject based on the multidimensional risk entropy value sequence to obtain the subject risk level score result, and then visualize it. The subject scoring process is as follows: S401: Obtain the time change rate and trigger intensity, and obtain the multidimensional risk entropy value in the multidimensional risk entropy value sequence; S402: Calculate the dynamic scoring weight based on the time change rate, the trigger intensity, and the multidimensional risk entropy value. The calculation expression for the dynamic scoring weight is as follows: ， Where wt is the dynamic scoring weight. Ht represents the time decay risk entropy, It is the trigger intensity, ∆t represents the time change rate, and ε is the smoothing constant. S403: Obtain the final score based on the dynamic scoring weights; S404: Map the final score to the grade level to obtain the subject risk level score result.

Images