Artificial intelligence risk assessment system
By setting up a data processing system at the front end of the AI risk assessment system, the problems of insufficient data quality and integrity were solved, and the systematic processing and labeling of data were realized, thereby improving the accuracy and reliability of the assessment results.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NANJING SU XIAOKE INFORMATION TECH CO LTD
- Filing Date
- 2023-12-19
- Publication Date
- 2026-04-28
AI Technical Summary
In existing technologies, the lack of unified standards in the data collection and processing of artificial intelligence risk assessment systems leads to insufficient data quality and integrity, affecting the accuracy and reliability of assessment results. In particular, it makes it impossible to effectively assess special data in a big data environment.
A data processing system is set up at the front end of the evaluation system, including a data collection and processing module, a data preprocessing module, a data processing module, and a data storage module. Through steps such as data cleaning, format conversion, standardization, quality inspection, anomaly detection, and distribution analysis, the integrity and consistency of the data are ensured, and the accuracy of annotation is improved through data annotation units and comparison modules.
By implementing a systematic data processing workflow, the quality and completeness of the data are improved, thereby enhancing the accuracy and reliability of the AI-based risk assessment system and ensuring the credibility of the assessment results.
Smart Images
Figure CN121936883A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of assessment system technology, specifically an artificial intelligence risk assessment system. Background Technology
[0002] An AI risk assessment system is a system that uses artificial intelligence technology to identify, analyze, and assess potential security threats to information systems. Its purpose is to improve the security and stability of information systems, reduce the probability of risk events, and provide a basis for enterprises to formulate scientific security strategies. The AI risk assessment system assesses the risk level of information systems by automatically scanning and identifying security vulnerabilities and threats in networks, systems, and applications, and by analyzing historical data and attack patterns. The system can provide real-time monitoring and early warning functions to promptly detect and respond to potential security threats, thereby protecting the enterprise's information security.
[0003] However, data collection is required before an AI-powered assessment system can be implemented. The collected data is often extensive and complex, leading to insufficient data quality and completeness, which affects the accuracy and reliability of the assessment results. Specifically, this is due to the following reasons: During data collection and processing, the lack of unified standards and specifications affects data quality and completeness, manifesting as potentially inaccurate data sources, inconsistent data formats, and insufficient data cleaning and processing. Furthermore, the large volume of data makes it difficult for AI-powered assessment systems to perform enhanced assessments on specific data. Both of these factors can result in insufficient data quality and completeness, thus affecting the accuracy and reliability of the assessment results. Therefore, an AI-powered risk assessment system is needed to address the aforementioned problems. Summary of the Invention
[0004] In view of the above situation and to overcome the shortcomings of the prior art, the present invention provides an artificial intelligence risk assessment system, which effectively solves the problems mentioned in the background art.
[0005] To achieve the above objectives, the present invention provides the following technical solution: an artificial intelligence risk assessment system, comprising a data processing system and an assessment system, wherein the data processing system and the assessment system are linearly connected, and the assessment system and the data processing system cooperate with each other;
[0006] The data processing system includes a data collection and processing module, a data preprocessing module, a data processing module, and a data storage module. The data collection and processing module is linearly connected to the data preprocessing module, the data preprocessing module is linearly connected to the data processing module, and the data processing module is linearly connected to the data storage module. The data storage module stores the data processed by the data processing module.
[0007] Furthermore, the data preprocessing module includes a data cleaning unit, a data transformation unit, and a data standardization unit. The data cleaning unit is used to clean the data collected by the data collection and processing module, remove duplicate data, fill in missing values, and transform the data format. The data transformation unit is used to convert the cleaned data into a format suitable for machine learning algorithms, such as converting categorical data into one-hot encoding. The data standardization unit is used to standardize the cleaned data, scaling the data to a specific range or performing normalization.
[0008] Furthermore, the data processing module includes a data quality inspection unit, a data anomaly detection unit, and a data distribution unit. The data quality inspection unit performs quality checks on the input data, checking its integrity, accuracy, and consistency. The data anomaly detection unit detects outliers in the data, including extreme values and outliers, to assess the data quality. The data distribution analysis performs distribution analysis on the data, calculating the mean, variance, skewness, and kurtosis to assess the stability and reliability of the data.
[0009] Furthermore, the evaluation system is linearly connected to the data processing module and the data storage module by a data annotation unit and a comparison module, respectively.
[0010] Furthermore, the comparison module is used to extract the data completed by the evaluation system and compare it with the corresponding data extracted by the data storage module to determine whether the evaluation has errors. At the same time, the data is compared with the data entered in real time during the evaluation process of the evaluation system, thereby improving the accuracy of the risk assessment by the artificial intelligence system.
[0011] Furthermore, the data annotation unit annotates the data that needs to be annotated, evaluates the quality of the annotation, and collaborates with the comparison module to check the consistency of annotations among personnel who have previously annotated similar data, so as to ensure the accuracy of the annotation.
[0012] Compared with the prior art, the beneficial effects of the present invention are:
[0013] This invention, by setting up a data processing system at the front end of the evaluation system, includes a data preprocessing module that cleans the data collected by the data collection and processing module during the data collection and processing process, converts the cleaned data into a format suitable for machine learning algorithms, and finally standardizes the cleaned data by scaling it to a specific range or normalizing it. The data processing module performs quality checks on the input data, checking its completeness, accuracy, consistency, and outliers to assess data quality, and conducts distribution analysis to assess its stability and reliability. This results in more comprehensive data quality and completeness for the evaluation system, preventing the evaluation results from being affected and improving the accuracy and reliability of the evaluation system.
[0014] Secondly, the data annotation unit annotates the data that needs to be annotated, and annotates the processed data, thereby assessing the key points of the risk assessment terminal and further improving the accuracy and reliability of the artificial intelligence risk assessment system. Attached Figure Description
[0015] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:
[0016] Figure 1 This is a system flowchart of the present invention. Detailed Implementation
[0017] This invention provides, for example Figure 1 The artificial intelligence risk assessment system shown includes a data processing system and an assessment system, which are linearly connected and cooperate with each other.
[0018] The data processing system includes a data collection and processing module, a data preprocessing module, a data processing module, and a data storage module. The data collection and processing module is linearly connected to the data preprocessing module, the data preprocessing module is linearly connected to the data processing module, and the data processing module is linearly connected to the data storage module. The data storage module stores the data processed by the data processing module in a database or file system. The data collection and processing module is responsible for collecting data from various sources.
[0019] Meanwhile, the data preprocessing module includes a data cleaning unit, a data transformation unit, and a data standardization unit. The data cleaning unit is used to clean the data collected by the data collection and processing module, remove duplicate data, fill in missing values, and transform the data format. The data transformation unit is used to convert the cleaned data into a format suitable for machine learning algorithms, such as converting categorical data into one-hot encoding. The data standardization unit is used to standardize the cleaned data, scaling the data to a specific range or performing normalization.
[0020] In addition, the data processing module includes a data quality inspection unit, a data anomaly detection unit, and a data distribution unit. The data quality inspection unit performs quality checks on the input data, checking its completeness, accuracy, and consistency. The data anomaly detection unit detects outliers in the data, including extreme values and outliers, to assess the data quality. The data distribution analysis unit performs distribution analysis on the data, calculating the mean, variance, skewness, and kurtosis to assess the stability and reliability of the data.
[0021] Furthermore, the evaluation system is linearly connected to the data processing module and the data storage module by a data annotation unit and a comparison module, respectively.
[0022] Furthermore, the comparison module is used to extract the data completed by the evaluation system and compare it with the corresponding data extracted by the data storage module to determine whether the evaluation has errors. At the same time, the data is compared with the data entered in real time during the evaluation process of the evaluation system, thereby improving the accuracy of the risk assessment by the artificial intelligence system.
[0023] It should also be noted that the data annotation unit annotates the data that needs to be annotated, such as images and text, and evaluates the quality of the annotation, calculates the accuracy and recall of the annotation, and collaborates with the comparison module to check the consistency of annotations among personnel for similar data in the past, so as to ensure the accuracy of the annotation.
[0024] The working principle of this invention is as follows: First, the data to be evaluated is collected through the data collection and processing module, including data from various sources. The data preprocessing module preprocesses the data, including a data quality check unit that checks the quality of the input data, a data anomaly detection unit that detects outliers in the data, including extreme values and outliers, and a data distribution analysis unit that performs distribution analysis on the data, calculating the mean, variance, skewness, and kurtosis. Then, the preprocessed data is processed by the data processing module. The data quality check unit checks the quality of the input data, the data anomaly detection unit detects outliers in the data, including extreme values and outliers, and the data distribution analysis unit performs distribution analysis on the data, calculating the mean, variance, skewness, and kurtosis. Finally, before evaluation, the processed data is labeled by the data labeling and evaluation unit. Finally, the evaluation system performs a risk assessment on the processed data.
[0025] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.
[0026] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.
Claims
1. An artificial intelligence risk assessment system, characterized in that: The system includes a data processing system and an evaluation system, which are linearly connected and cooperate with each other. The data processing system includes a data collection and processing module, a data preprocessing module, a data processing module, and a data storage module. The data collection and processing module is linearly connected to the data preprocessing module, the data preprocessing module is linearly connected to the data processing module, and the data processing module is linearly connected to the data storage module. The data storage module stores the data processed by the data processing module.
2. The artificial intelligence risk assessment system according to claim 1, characterized in that: The data preprocessing module includes a data cleaning unit, a data transformation unit, and a data standardization unit. The data cleaning unit is used to clean the data collected by the data collection and processing module, remove duplicate data, fill in missing values, and transform the data format. The data transformation unit is used to convert the cleaned data into a format suitable for machine learning algorithms, such as converting categorical data into one-hot encoding. The data standardization unit is used to standardize the cleaned data, scaling the data to a specific range or performing normalization.
3. The artificial intelligence risk assessment system according to claim 1, characterized in that: The data processing module includes a data quality inspection unit, a data anomaly detection unit, and a data distribution unit. The data quality inspection unit performs quality checks on the input data, checking its completeness, accuracy, and consistency. The data anomaly detection unit detects outliers in the data, including extreme values and outliers, to assess the data quality. The data distribution analysis unit performs distribution analysis on the data, calculating the mean, variance, skewness, and kurtosis to assess the stability and reliability of the data.
4. The artificial intelligence risk assessment system according to claim 1, characterized in that: The evaluation system is linearly connected to the data processing module and the data storage module by a data annotation unit and a comparison module, respectively.
5. The artificial intelligence risk assessment system according to claim 4, characterized in that: The comparison module is used to extract the data completed by the evaluation system and compare it with the corresponding data extracted by the data storage module to determine whether there are any errors in the evaluation. At the same time, the data is compared with the data entered in real time during the evaluation process of the evaluation system, thereby improving the accuracy of the risk assessment by the artificial intelligence system.
6. The artificial intelligence risk assessment system according to claim 4, characterized in that: The data annotation unit annotates the data that needs to be annotated, evaluates the quality of the annotation, and collaborates with the comparison module to check the consistency of annotations among personnel for similar data in the past, so as to ensure the accuracy of the annotation.