Management system based on enterprise risk control

Abstract

The invention relates to the field of enterprise risk control management, in particular to a management system based on enterprise risk control, which comprises a data acquisition module for periodically acquiring public opinion texts and click rate information from each network platform according to keywords, a data storage module for storing the public opinion texts and negative public opinion feature words, and a data processing module for processing the public opinion texts and the negative public opinion feature words. The data preprocessing module is used for preprocessing the acquired public opinion text, the data processing module is used for carrying out semantic division on the preprocessed public opinion text, and the data processing module is used for judging whether the preprocessed public opinion text conforms to a preset standard of a negative public opinion text or not, judging a risk level and a corresponding processing strategy of an enterprise, and sending the enterprise risk level to the data processing module. The risk control analysis module is used for verifying the risk control state of the enterprise or sending out risk control event early warning when it is judged that the risk control state of the enterprise exists, and the display module is used for displaying the analysis result of the risk control analysis module, intelligent early warning of enterprise risk control is achieved, and the enterprise risk control management level is improved.

Description

Technical Field

[0001] The present invention relates to the field of enterprise risk control management, and in particular to a management system based on enterprise risk control. Background Art

[0002] Enterprise risk control refers to a series of management activities that protect enterprise assets and ensure stable business operations by identifying, evaluating, monitoring and responding to potential risks. It not only involves multiple fields such as finance, market, and operations, but also runs through the entire process of enterprise strategic planning, daily operations and decision-making. With the development of network science and technology, public opinion has brought opportunities and challenges to corporate brand building. How to effectively and accurately manage public opinion for enterprise risk control has become a concern for enterprises.

[0003] Chinese patent publication number: CN111950860B, discloses a monitoring method and device for enterprise public opinion risk index, respectively obtaining the first target public opinion data of the target enterprise in the first specified time period and the second target public opinion data in the second specified time period; respectively calculating the first target public opinion index of the first target public opinion data in the first specified time period and the second target public opinion index corresponding to the second target public opinion data in the second specified time period according to the first processing rule, and calculating the target index safety fluctuation range corresponding to the first target public opinion index according to the second processing rule; judging whether the second target public opinion data corresponding to the target enterprise in the second specified time period has abnormal fluctuations; if so, judging that the public opinion data risk index of the target enterprise is too high. It can be seen that the technical solution cannot intelligently judge the negative public opinion text according to the collected public opinion text, and lacks accurate and efficient judgment of the risk level of the enterprise and the corresponding processing strategy. Summary of the invention

[0004] To this end, the present invention provides a management system based on enterprise risk control to overcome the lack of effective monitoring and processing means for online public opinion information in the prior art, which results in the enterprise being unable to determine the enterprise public opinion risk control status and thus unable to make accurate strategies to eliminate negative impacts, thereby affecting the business operations.

[0005] To achieve the above objectives, the present invention provides a management system based on enterprise risk control, comprising:

[0006] A data collection module, which is used to periodically obtain public opinion texts and the number of clicks on public opinion texts within a preset period on news portals, social media, and search engines based on enterprise name keywords and risk control event keywords;

[0007] A data storage module, which is connected to the data acquisition module, includes a first storage unit for storing the public opinion text acquired by the data acquisition module and a second storage unit for storing a plurality of negative public opinion feature words, wherein a corresponding preset negative sentiment coefficient is set for each negative public opinion feature word;

[0008] A data preprocessing module, which is used together with the data storage module to preprocess the acquired public opinion text, wherein the preprocessing includes deduplication and arrangement of the public opinion text;

[0009] A data processing module, which is connected to the data preprocessing module and is used to divide the preprocessed public opinion text according to semantics;

[0010] A risk control analysis module, which is respectively connected to the data acquisition module, the data storage module, the data preprocessing module and the data processing module, and is used to determine whether the preprocessed public opinion text meets the preset standard of negative public opinion text according to the single public opinion evaluation value, and to determine the risk level and corresponding processing strategy of the enterprise according to the event risk control evaluation value, and, when it is determined that the risk control status of the enterprise is at risk, verify the risk control status of the enterprise based on the public opinion extended evaluation value or issue a warning that the risk control event is high risk;

[0011] A display module is connected to the risk control analysis module and is used to display the analysis results of the risk control analysis module.

[0012] Furthermore, the risk control analysis module determines whether the pre-processed public opinion text meets the preset standard of negative public opinion text according to the single public opinion evaluation value, wherein:

[0013] If the single public opinion evaluation value is less than the first preset public opinion evaluation threshold, the risk control analysis module determines that the pre-processed public opinion text does not meet the preset standard of negative public opinion text and deletes the public opinion text from the first storage unit;

[0014] If the single public opinion evaluation value is greater than or equal to the first preset public opinion evaluation threshold and less than the second preset public opinion evaluation threshold; the risk control analysis module determines that the pre-processed public opinion text does not meet the preset standard of negative public opinion text and reduces the average character length of the text division and then re-determines the negative public opinion feature words in the public opinion text;

[0015] If the single public opinion evaluation value is greater than or equal to the second preset public opinion evaluation threshold, the risk control analysis module determines that the preprocessed public opinion text meets the preset standard of negative public opinion text and determines the event risk control evaluation value based on the negative public opinion text determined within the preset time period.

[0016] Furthermore, the single public opinion evaluation value is determined based on all negative public opinion feature words determined in the single public opinion text after preprocessing and the preset negative sentiment coefficient corresponding to the negative public opinion feature words.

[0017] Furthermore, the risk control analysis module is provided with several reduction methods for reducing the average character length of the text divisions, and each reduction method has a different reduction range for the average character length of the text divisions.

[0018] Furthermore, the risk control analysis module determines the risk level of the enterprise according to the event risk control evaluation value, wherein:

[0019] If the event risk control evaluation value is less than the first preset event risk control evaluation value, the risk control analysis module determines that the risk level of the enterprise is level 1;

[0020] If the event risk control evaluation value is greater than or equal to the first preset event risk control evaluation value and less than the second preset event risk control evaluation value, the risk control analysis module determines that the risk level of the enterprise is level 2;

[0021] If the event risk control evaluation value is greater than or equal to the second preset event risk control evaluation value, the risk control analysis module determines that the risk level of the enterprise is level 3.

[0022] Furthermore, the event risk control evaluation value is calculated by the following formula:

[0023]

[0024] In the formula, P represents the event risk control evaluation value, α represents the news portal risk control evaluation coefficient, β represents the social media risk control evaluation coefficient, γ represents the search engine risk control evaluation coefficient, Lj represents the single public opinion evaluation value of the jth public opinion text belonging to the news portal, wherein j=1,2...m, m represents the total number of pre-processed public opinion texts obtained from the news portal, LO1 represents the first preset risk control threshold, Lc represents the single public opinion evaluation value of the cth public opinion text belonging to the social media public opinion text, wherein c=1,2...o, o represents the total number of pre-processed public opinion texts obtained from social media, LO2 represents the second preset risk control threshold, Lk represents the single public opinion evaluation value of the kth search engine public opinion text, wherein k=1,2...q, q represents the total number of pre-processed public opinion texts obtained from the search engine, and LO3 represents the third preset risk control threshold.

[0025] Furthermore, the risk control analysis module determines a corresponding processing strategy based on the risk level of the enterprise, wherein:

[0026] If the risk level of the enterprise is level 1, the risk control analysis module determines that the enterprise risk control status is risk-free and continues monitoring according to the current monitoring cycle;

[0027] If the risk level of the enterprise is level 2, the risk control analysis module determines that the risk control status of the enterprise is low risk, and the risk control analysis module verifies the risk control status of the enterprise based on the public opinion extended evaluation value;

[0028] If the risk level of the enterprise is level 3, the risk control analysis module determines that the enterprise risk control status is high risk, and the risk control analysis module issues a warning to the display module that the risk control event is high risk.

[0029] Furthermore, the risk control analysis module verifies the risk control status of the enterprise based on the public opinion extended evaluation value, wherein:

[0030] If the public opinion expansion evaluation value is less than the preset public opinion expansion evaluation value, the risk control analysis module determines that the risk control status of the enterprise is low risk, and corrects the collection cycle of the data collection module according to the difference between the preset public opinion expansion evaluation value and the public opinion expansion evaluation value;

[0031] If the public opinion expansion evaluation value is greater than or equal to the preset public opinion expansion evaluation value, the risk control analysis module determines that the risk control status of the enterprise is high risk and issues a warning to the display module that the risk control event is high risk.

[0032] Furthermore, the public opinion expansion evaluation value is determined by the total number of public opinion texts and the number of clicks on the public opinion texts collected by the data collection module within a preset time period.

[0033] Furthermore, the risk control analysis module determines that the determination criteria for the enterprise risk level do not meet the criteria in response to the deduplication rate of the public opinion text obtained within a preset time period being greater than or equal to a preset deduplication rate threshold, and corrects the determination criteria for the enterprise risk level based on the difference between the deduplication rate and the preset deduplication rate threshold, wherein the determination criteria for the enterprise risk level include the first preset event risk control evaluation value and the second preset event risk control evaluation value.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] Furthermore, the present invention collects public opinion texts and clicks from multiple channels based on keywords, performs semantic division on the pre-processed public opinion texts and filters out negative public opinion texts according to preset standards for negative public opinion texts, determines the risk level of the enterprise based on the event risk control evaluation value of the negative public opinion texts, verifies the risk control status of the enterprise based on the public opinion extended evaluation value, corrects the determination standard of the enterprise risk level through the deduplication rate, and the display module displays the early warning intuitively, providing the enterprise with an efficient and visual means of monitoring network public opinion information, ensuring that the enterprise can effectively monitor, accurately make decisions, and efficiently handle negative public opinions.

[0036] Furthermore, the risk control analysis module determines whether the pre-processed public opinion text meets the preset standard of negative public opinion text according to the evaluation value of the single public opinion text, and sets the evaluation value and the preset standard to quantitatively process and analyze the public opinion text.

[0037] Furthermore, when the text does not meet the negative public opinion standard, by reducing the average character length of the text segmentation, the negative feature words can be re-identified to increase the accuracy of the analysis.

[0038] Furthermore, the setting of the negative sentiment coefficient improves the calculation accuracy of the single public opinion evaluation value, thereby improving the accuracy of identifying negative public opinion texts.

[0039] Furthermore, the risk control analysis module determines the enterprise's risk level based on the event risk control evaluation value and adopts corresponding treatment strategies accordingly. By setting specific preset values ​​and quantifying the influence of negative public opinion texts, the enterprise risk can be clearly divided into three levels, and different treatment strategies can be adopted according to different levels to improve the processing efficiency of risk monitoring.

[0040] Furthermore, the risk control module quantifies the diffusion capacity of low-risk public opinion texts, verifies the risk control status of the enterprise according to the public opinion expansion evaluation value, can adjust the collection cycle of the data collection module, optimize the text collection efficiency, improve the data collection relevance, and issue early warnings for high-risk events, reminding enterprises to take measures to eliminate negative impacts.

[0041] Furthermore, the risk control analysis module determines whether the enterprise risk level determination criteria are met based on whether the deduplication rate is greater than or equal to a preset deduplication rate threshold, thereby improving the accuracy of enterprise risk level assessment and enhancing enterprise decision-making efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a schematic diagram of the structure of a management system based on enterprise risk control according to an embodiment of the present invention;

[0043] Figure 2 A flowchart of an embodiment of the present invention for determining whether a pre-processed public opinion text meets a preset standard for a negative public opinion text;

[0044] Figure 3 This is a flow chart of a corresponding processing strategy determined based on the risk level of an enterprise according to an embodiment of the present invention;

[0045] Figure 4 The present invention is a flowchart of verifying the risk control status of an enterprise according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0047] It should be pointed out that the data in this embodiment are obtained by comprehensive analysis and evaluation of the historical data of the system of the present invention in the three months before this operation and the corresponding historical operation results. It can be understood by those skilled in the art that the system of the present invention can determine the above parameters for a single item by selecting the value with the highest proportion as the preset standard parameter according to the data distribution, using weighted summation to use the obtained value as the preset standard parameter, substituting each historical data into a specific formula and using the value obtained by the formula as the preset standard parameter or other selection methods, as long as the system of the present invention can clearly define different specific situations in the single determination process through the obtained values.

[0048] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0049] See also Figure 1 , Figure 2 , Figure 3 as well as Figure 4 As shown, they are respectively a schematic diagram of the management system structure based on enterprise risk control according to an embodiment of the present invention; a flowchart of an embodiment of the present invention for determining whether a pre-processed public opinion text meets the preset standard of a negative public opinion text; a flowchart of an embodiment of the present invention for determining a corresponding processing strategy based on the risk level of the enterprise; and a flowchart of an embodiment of the present invention for verifying the risk control status of an enterprise.

[0050] The management system based on enterprise risk control in the embodiment of the present invention includes:

[0051] The data collection module is used to periodically obtain the public opinion text and the number of clicks on the public opinion text within a preset period of 4 hours on news portals, social media and search engines based on the enterprise name keywords and risk control event keywords;

[0052] A data storage module, which is connected to the data acquisition module, includes a first storage unit for storing the public opinion text acquired by the data acquisition module and a second storage unit for storing a plurality of negative public opinion feature words, wherein a corresponding preset negative sentiment coefficient is set for each negative public opinion feature word;

[0053] A data preprocessing module, which is used together with the data storage module to preprocess the acquired public opinion text, wherein the preprocessing includes deduplication and arrangement of the public opinion text;

[0054] A data processing module, which is connected to the data preprocessing module and is used to divide the preprocessed public opinion text according to semantics;

[0055] A risk control analysis module, which is respectively connected to the data acquisition module, the data storage module, the data preprocessing module and the data processing module, and is used to determine whether the preprocessed public opinion text meets the preset standard of negative public opinion text according to the single public opinion evaluation value, and to determine the risk level and corresponding processing strategy of the enterprise according to the event risk control evaluation value, and, when it is determined that the risk control status of the enterprise is at risk, verify the risk control status of the enterprise based on the public opinion extended evaluation value or issue a warning that the risk control event is high risk;

[0056] A display module is connected to the risk control analysis module and is used to display the analysis results of the risk control analysis module.

[0057] Specifically, the risk control analysis module, such as the CPU, is not specifically limited and only needs to output the corresponding judgment result based on the input parameters.

[0058] Specifically, negative public opinion feature words can be screened from historical reports and stored in the first storage unit, and their corresponding preset negative emotion coefficients can be manually set according to the emotion level of the negative public opinion feature words. Negative public opinion feature words can also be selected from existing emotion dictionaries, and their corresponding preset negative emotion coefficients can be determined according to the intensity values ​​given in existing emotion dictionaries such as SentiWordNet. For example, negative public opinion feature words such as "disappointment", "negative impact", and "outrageous", among which the preset negative emotion coefficient of "disappointment" is 0.25, the preset negative emotion coefficient of "negative impact" is 0.32, and the preset negative emotion coefficient of "outrageous" is 0.84.

[0059] It should be pointed out that the data in this embodiment are all the results obtained by the system of the present invention through preliminary operation verification before this operation. The preset values ​​and preset thresholds can be adjusted according to the specific usage conditions, as long as the method of the present invention can clearly define different specific situations in the single determination process through the obtained values. The preset values ​​and preset thresholds set in this embodiment are all obtained based on preliminary experiments.

[0060] Specifically, the risk control analysis module determines whether the pre-processed public opinion text meets the preset standard of negative public opinion text according to the single public opinion evaluation value, wherein:

[0061] If the single public opinion evaluation value is less than the first preset public opinion evaluation threshold, the risk control analysis module determines that the pre-processed public opinion text does not meet the preset standard of negative public opinion text and deletes the public opinion text from the first storage unit;

[0062] If the single public opinion evaluation value is greater than or equal to the first preset public opinion evaluation threshold and less than the second preset public opinion evaluation threshold; the risk control analysis module determines that the pre-processed public opinion text does not meet the preset standard of negative public opinion text and reduces the average character length of the text division and then re-determines the negative public opinion feature words in the public opinion text;

[0063] If the single public opinion evaluation value is greater than or equal to the second preset public opinion evaluation threshold, the risk control analysis module determines that the pre-processed public opinion text meets the preset standard of negative public opinion text and determines the event risk control evaluation value based on the negative public opinion text determined within the preset time period;

[0064] Among them, the first preset public opinion evaluation threshold is set to 2.21, and the second preset public opinion evaluation threshold is set to 12.47.

[0065] Specifically, the single public opinion evaluation value is determined based on all negative public opinion feature words determined in the single public opinion text after preprocessing and the preset negative sentiment coefficient corresponding to the negative public opinion feature words. The single public opinion evaluation value is calculated by the following formula:

[0066]

[0067] In the formula, L represents the evaluation value of a single public opinion article, i=1,2...u, where i represents a single negative public opinion feature word in the public opinion text, f(i) represents the preset negative sentiment coefficient corresponding to the i-th negative public opinion feature word, and u represents the total number of negative public opinion feature words determined in the public opinion text.

[0068] Specifically, the risk control analysis module is provided with several reduction methods for reducing the average character length of text segmentation, wherein:

[0069] If the public opinion evaluation difference is less than the first preset public opinion evaluation difference, the risk control analysis module uses the first preset character length adjustment coefficient 0.8 to reduce the average character length of the text segmentation, and if the average character length after the reduction is not an integer, it is rounded down;

[0070] If the public opinion evaluation difference is greater than or equal to the first preset public opinion evaluation difference and less than the second preset public opinion evaluation difference, the risk control analysis module uses the second preset character length adjustment coefficient of 0.9 to reduce the average character length of the text segmentation, and if the average character length after the reduction is not an integer, it is rounded down;

[0071] If the public opinion evaluation difference is greater than or equal to the second preset public opinion evaluation difference, the risk control analysis module uses the third preset character length adjustment coefficient of 0.95 to reduce the average character length of the text segmentation. If the average character length after the reduction is not an integer, it is rounded down.

[0072] The public opinion evaluation difference is the difference between the single public opinion evaluation value and the first preset public opinion evaluation threshold;

[0073] The first preset public opinion evaluation difference is set to 3.31, and the second preset public opinion evaluation difference is set to 7.55.

[0074] Specifically, the risk control analysis module determines the risk level of the enterprise according to the event risk control evaluation value, wherein:

[0075] If the event risk control evaluation value is less than the first preset event risk control evaluation value of 1.43, the risk control analysis module determines that the risk level of the enterprise is level 1;

[0076] If the event risk control evaluation value is greater than or equal to the first preset event risk control evaluation value 1.43 and less than the second preset event risk control evaluation value 13.23, the risk control analysis module determines that the risk level of the enterprise is level 2;

[0077] If the event risk control evaluation value is greater than or equal to the second preset event risk control evaluation value 13.23, the risk control analysis module determines that the risk level of the enterprise is level 3.

[0078] Specifically, the event risk control evaluation value is calculated by the following formula:

[0079]

[0080] In the formula, P represents the event risk control evaluation value, α represents the news portal risk control evaluation coefficient, α=0.71, β represents the social media risk control evaluation coefficient, β=0.52, γ represents the search engine risk control evaluation coefficient, γ=0.23, Lj represents the single public opinion evaluation value of the jth public opinion text belonging to the news portal website, where j=1,2…m, m represents the total number of pre-processed public opinion texts obtained from the news portal website, LO1 represents the first preset risk control threshold, LO1=5.74, Lc represents the single public opinion evaluation value of the cth public opinion text belonging to social media, where c=1,2...o, o represents the total number of pre-processed public opinion texts obtained from social media, LO2 represents the second preset risk control threshold, LO2=10.37, Lk represents the single public opinion evaluation value of the kth public opinion text belonging to the search engine public opinion text, where k=1,2...q, q represents the total number of pre-processed public opinion texts obtained from the search engine, LO3 represents the third preset risk control threshold, LO3=6.29.

[0081] Specifically, the risk control analysis module determines the corresponding processing strategy based on the risk level of the enterprise, wherein:

[0082] If the risk level of the enterprise is level 1, the risk control analysis module determines that the enterprise risk control status is risk-free and continues monitoring according to the current monitoring cycle;

[0083] If the risk level of the enterprise is level 2, the risk control analysis module determines that the risk control status of the enterprise is low risk, and the risk control analysis module verifies the risk control status of the enterprise based on the public opinion extended evaluation value;

[0084] If the risk level of the enterprise is level 3, the risk control analysis module determines that the enterprise risk control status is high risk, and the risk control analysis module issues a warning to the display module that the risk control event is high risk.

[0085] Specifically, the risk control analysis module verifies the risk control status of the enterprise based on the public opinion extended evaluation value, wherein:

[0086] If the public opinion expansion evaluation value is less than the preset public opinion expansion evaluation value, the risk control analysis module determines that the risk control status of the enterprise is low risk, and corrects the collection cycle of the data collection module according to the difference between the preset public opinion expansion evaluation value and the public opinion expansion evaluation value;

[0087] If the public opinion expansion evaluation value is greater than or equal to the preset public opinion expansion evaluation value, the risk control analysis module determines that the risk control status of the enterprise is high risk and issues a warning to the display module that the risk control event is high risk.

[0088] The default public opinion expansion evaluation value is set to 0.647.

[0089] Specifically, the correction amplitude of the collection period of the data collection module is negatively correlated with the correction difference, wherein the correction difference is the difference between the preset public opinion expansion evaluation value and the public opinion expansion evaluation value. It can be understood that the larger the correction difference, the smaller the correction amplitude of the collection period of the data collection module. At the same time, it can be understood that the correction of the collection period means the shortening of the collection period.

[0090] Specifically, the public opinion expansion evaluation value is calculated by the following formula:

[0091]

[0092] In the formula, A represents the public opinion expansion evaluation value, λ represents the public opinion text volume weight coefficient, λ=0.45, μ represents the click volume weight coefficient, μ=0.64, N represents the total number of public opinion texts collected by the data collection module within the preset time period, N0 represents the preset text volume threshold, and N0 is set to 2000, H represents the click volume of the public opinion text collected within the preset time period, H0 represents the preset click volume threshold, and H0 is set to 5000.

[0093] Specifically, the risk control analysis module determines whether the enterprise risk level determination standard meets the standard based on the deduplication rate of the public opinion text obtained within a preset period of time, wherein:

[0094] If the deduplication rate is less than the preset deduplication rate threshold, the risk control analysis module determines that the enterprise risk level meets the criteria;

[0095] If the deduplication rate is greater than or equal to the preset deduplication rate threshold, the risk control analysis module determines that the enterprise risk level determination standard does not meet the standard, and modifies the enterprise risk level determination standard according to the difference between the deduplication rate and the preset deduplication rate threshold.

[0096] The enterprise risk level determination criteria include the first preset event risk control evaluation value and the second preset event risk control evaluation value;

[0097] The deduplication rate is the percentage of the number of public opinion texts deduplicated by the data preprocessing module to the total number of public opinion texts collected by the data collection module.

[0098] Specifically, the correction range of the enterprise risk level determination standard is positively correlated with the difference between the deduplication rate and the preset deduplication rate threshold, wherein it can be understood that the correction of the enterprise risk level determination standard is a reduction in the first preset event risk control evaluation value and the second preset event risk control evaluation value.

[0099] Specifically, the preset deduplication rate threshold is 35%.

[0100] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0101] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A management system based on enterprise risk control, characterized in that: include: A data collection module, which is used to periodically obtain public opinion texts and the number of clicks on public opinion texts within a preset period on news portals, social media, and search engines based on enterprise name keywords and risk control event keywords; A data storage module, which is connected to the data acquisition module, includes a first storage unit for storing the public opinion text acquired by the data acquisition module and a second storage unit for storing a plurality of negative public opinion feature words, wherein a corresponding preset negative sentiment coefficient is set for each negative public opinion feature word; A data preprocessing module, which is used together with the data storage module to preprocess the acquired public opinion text, wherein the preprocessing includes deduplication and arrangement of the public opinion text; A data processing module, which is connected to the data preprocessing module and is used to divide the preprocessed public opinion text according to semantics; A risk control analysis module, which is respectively connected to the data acquisition module, the data storage module, the data preprocessing module and the data processing module, and is used to determine whether the preprocessed public opinion text meets the preset standard of negative public opinion text according to the single public opinion evaluation value, and to determine the risk level and corresponding processing strategy of the enterprise according to the event risk control evaluation value, and, when it is determined that the risk control status of the enterprise is at risk, verify the risk control status of the enterprise based on the public opinion extended evaluation value or issue a warning that the risk control event is high risk; A display module is connected to the risk control analysis module and is used to display the analysis results of the risk control analysis module.

2. The enterprise risk control-based management system according to claim 1 is characterized in that: The risk control analysis module determines whether the pre-processed public opinion text meets the preset standard of negative public opinion text according to the single public opinion evaluation value, wherein: If the single public opinion evaluation value is less than the first preset public opinion evaluation threshold, the risk control analysis module determines that the pre-processed public opinion text does not meet the preset standard of negative public opinion text and deletes the public opinion text from the first storage unit; If the single public opinion evaluation value is greater than or equal to the first preset public opinion evaluation threshold and less than the second preset public opinion evaluation threshold, the risk control analysis module determines that the pre-processed public opinion text does not meet the preset standard of negative public opinion text and reduces the average character length of the text division and then re-determines the negative public opinion feature words in the public opinion text; If the single public opinion evaluation value is greater than or equal to the second preset public opinion evaluation threshold, the risk control analysis module determines that the preprocessed public opinion text meets the preset standard of negative public opinion text and determines the event risk control evaluation value based on the negative public opinion text determined within the preset time period.

3. The enterprise risk control-based management system according to claim 2 is characterized in that: The single public opinion evaluation value is determined based on all negative public opinion feature words determined in the single public opinion text after preprocessing and the preset negative sentiment coefficients corresponding to the negative public opinion feature words.

4. The enterprise risk control-based management system according to claim 3 is characterized in that: The risk control analysis module is provided with several reduction methods for reducing the average character length of the text divisions, and each reduction method has a different reduction range for the average character length of the text divisions.

5. The management system based on enterprise risk control according to claim 4 is characterized in that: The risk control analysis module determines the risk level of the enterprise according to the event risk control evaluation value, wherein: If the event risk control evaluation value is less than the first preset event risk control evaluation value, the risk control analysis module determines that the risk level of the enterprise is level 1; If the event risk control evaluation value is greater than or equal to the first preset event risk control evaluation value and less than the second preset event risk control evaluation value, the risk control analysis module determines that the risk level of the enterprise is level 2; If the event risk control evaluation value is greater than or equal to the second preset event risk control evaluation value, the risk control analysis module determines that the risk level of the enterprise is level 3.

6. The management system based on enterprise risk control according to claim 5 is characterized in that: The event risk control evaluation value is calculated by the following formula: In the formula, P represents the event risk control evaluation value, α represents the news portal risk control evaluation coefficient, β represents the social media risk control evaluation coefficient, γ represents the search engine risk control evaluation coefficient, Lj represents the single public opinion evaluation value of the jth public opinion text belonging to the news portal, wherein j=1,2...m, m represents the total number of pre-processed public opinion texts obtained from the news portal, LO1 represents the first preset risk control threshold, Lc represents the single public opinion evaluation value of the cth public opinion text belonging to the social media public opinion text, wherein c=1,2...o, o represents the total number of pre-processed public opinion texts obtained from social media, LO2 represents the second preset risk control threshold, Lk represents the single public opinion evaluation value of the kth search engine public opinion text, wherein k=1,2...q, q represents the total number of pre-processed public opinion texts obtained from the search engine, and LO3 represents the third preset risk control threshold.

7. The enterprise risk control-based management system according to claim 6 is characterized in that: The risk control analysis module determines the corresponding processing strategy based on the risk level of the enterprise, wherein: If the risk level of the enterprise is level 1, the risk control analysis module determines that the enterprise risk control status is risk-free and continues monitoring according to the current monitoring cycle; If the risk level of the enterprise is level 2, the risk control analysis module determines that the risk control status of the enterprise is low risk, and the risk control analysis module verifies the risk control status of the enterprise based on the public opinion extended evaluation value; If the risk level of the enterprise is level 3, the risk control analysis module determines that the enterprise risk control status is high risk, and the risk control analysis module issues a warning to the display module that the risk control event is high risk.

8. The management system based on enterprise risk control according to claim 7 is characterized in that: The risk control analysis module verifies the risk control status of the enterprise based on the public opinion extended evaluation value, wherein: If the public opinion expansion evaluation value is less than the preset public opinion expansion evaluation value, the risk control analysis module determines that the risk control status of the enterprise is low risk, and corrects the collection cycle of the data collection module according to the difference between the preset public opinion expansion evaluation value and the public opinion expansion evaluation value; If the public opinion expansion evaluation value is greater than or equal to the preset public opinion expansion evaluation value, the risk control analysis module determines that the risk control status of the enterprise is high risk and issues a warning to the display module that the risk control event is high risk.

9. The enterprise risk control-based management system according to claim 8, characterized in that: The public opinion expansion evaluation value is determined by the total number of public opinion texts and the number of clicks on the public opinion texts collected by the data collection module within a preset time period.

10. The enterprise risk control-based management system according to claim 9, characterized in that: In response to the deduplication rate of the public opinion text obtained within a preset time period being greater than or equal to a preset deduplication rate threshold, the risk control analysis module determines that the determination criteria of the enterprise risk level are not met, and corrects the determination criteria of the enterprise risk level according to the difference between the deduplication rate and the preset deduplication rate threshold, wherein the determination criteria of the enterprise risk level include the first preset event risk control evaluation value and the second preset event risk control evaluation value.

Images