CN112330475A - AI risk identification system - Google Patents
AI risk identification system Download PDFInfo
- Publication number
- CN112330475A CN112330475A CN202011346288.XA CN202011346288A CN112330475A CN 112330475 A CN112330475 A CN 112330475A CN 202011346288 A CN202011346288 A CN 202011346288A CN 112330475 A CN112330475 A CN 112330475A
- Authority
- CN
- China
- Prior art keywords
- unit
- target
- risk
- behavior
- characteristic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000006399 behavior Effects 0.000 claims abstract description 56
- 238000012986 modification Methods 0.000 claims abstract description 39
- 230000004048 modification Effects 0.000 claims abstract description 38
- 238000004458 analytical method Methods 0.000 claims abstract description 33
- 238000004364 calculation method Methods 0.000 claims abstract description 28
- 238000010801 machine learning Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 11
- 238000012502 risk assessment Methods 0.000 claims abstract description 6
- 238000011156 evaluation Methods 0.000 claims description 50
- 238000013473 artificial intelligence Methods 0.000 abstract description 12
- 238000007405 data analysis Methods 0.000 abstract description 8
- 238000005516 engineering process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Technology Law (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of artificial intelligence big data analysis, and particularly relates to an AI risk identification system which comprises a rule modification perfecting module, a feature identification entry storage module and a result analysis matching module, wherein the rule modification perfecting module is used for perfecting machine learning training rules according to calculation analysis and improving analysis and calculation capabilities, the feature identification entry storage module is used for identifying behavior features of a target and entering and storing the behavior features of the target into a learning experience database, and the result analysis matching module is used for matching corresponding risk degrees for the target after analyzing the identified behavior feature data of the target. The artificial intelligence risk assessment system is perfected by improving the machine learning capability and perfecting the machine learning training rules, so that the artificial intelligence realizes accurate risk assessment in a big data analysis and statistics mode.
Description
Technical Field
The invention belongs to the technical field of artificial intelligence big data analysis, and particularly relates to an AI risk identification system.
Background
With the coming of the internet era, the changes of life styles and social and economic styles of people accumulate huge data, big data is proposed, namely massive data sets, the data cannot be stored and analyzed by common tools within a certain time range, and the big data has the characteristics of huge data volume, multiple data types and high data value. The big data technology can be said to be an improvement and progress of the data analysis technology. The development of network technology and the gradual accumulation of network information have caused the traditional data processing mode to fail to meet the requirement of data analysis, so that a new processing mode is required to analyze a large amount of data, and a big data technology is provided.
The artificial intelligence is a product of rapid development of information technology, and replaces some traditional operations in the aspect of labor force by technical means, so that the labor force is released, and the life of people is more convenient. The artificial intelligence is based on high-end technologies such as big data, sensors and the like, so that human behaviors are simulated and learned, and further, some things which cannot be done by manpower are solved. The artificial intelligence relies on the analysis result of big data to mass data, so that the artificial intelligence is conducted to sensors at each part through a processing center, and anthropomorphic and humanoid operations are performed.
The traditional insurance risk assessment means realized in a manual mode is not suitable for risk assessment in the current big data environment due to low efficiency and large manpower investment. Therefore, a large amount of insurance risk related data are collected and used for artificial intelligence data analysis, and a data model constructed by big data is used for risk control and risk prompt.
Disclosure of Invention
The present invention is directed to an AI risk identification system to solve the problems set forth above.
In order to achieve the purpose, the invention provides the following technical scheme:
an AI risk identification system comprises a rule modification perfecting module, a feature identification entry storage module and a result analysis matching module, wherein the rule modification perfecting module is used for perfecting machine learning training rules and improving analysis and calculation capabilities according to calculation and analysis, the feature identification entry storage module is used for identifying behavior features of targets and entering and storing the behavior features of the targets into a learning experience database, and the result analysis matching module is used for matching corresponding risk degrees for the targets after analyzing identified target behavior feature data.
Preferably, the rule modification perfection module comprises an integrity evaluation unit and a modification perfection unit, wherein the integrity evaluation unit is used for evaluating the perfection of the computer learning ability, and the modification perfection unit is used for perfecting the machine learning training rule.
Preferably, the calculation formula of the integrity evaluation unit for evaluating the learning ability of the calculation machine is as follows:
where ρ is a completeness evaluation parameter, yiIs a standard evaluation value of the i-th evaluation unit, yi' is an actual evaluation value of the i-th evaluation unit.
Preferably, the workflow of the modifying and perfecting unit is as follows:
step S1: setting a threshold value of the integrity evaluation parameter rho, and searching for influencing factors by a modification perfecting unit according to a calculation formula for evaluating and calculating the machine learning capacity when the integrity evaluation parameter rho is lower than the threshold value;
step S2: in the comparison formula (y)i′-yi) Size of (d), taking out the formula (y)i′-yi) Calculating three influence factors with the maximum result;
step S3: and adjusting the selected three influence factors, calculating the numerical value of the integrity evaluation parameter rho after the adjustment is completed, and when the numerical value of the integrity evaluation parameter rho is higher than the threshold value, reserving the modification for effective modification, and when the integrity evaluation parameter rho is still lower than the threshold value, continuously selecting the three influence factors for modification until the integrity evaluation parameter rho is higher than the threshold value.
Preferably, the feature recognition and entry storage module comprises a feature recognition unit and a feature storage and entry unit, the feature recognition unit is used for detecting behavior operation features of the target, and the feature storage and entry unit is used for entering known behavior features of the target and entering newly-added behavior features detected by the feature recognition unit.
Preferably, the calculation formula of the feature recognition unit for recognizing the behavior feature of the detected target is as follows:
wherein, P0Setting a threshold value Q for the proportion of N events to the total events M when P is0And when the N events are greater than or equal to the threshold value Q, the N events are collected as the behavior characteristics of the target.
Preferably, the characteristic storage and entry unit is provided with a target behavior characteristic database, the target behavior operation characteristics detected by the characteristic identification unit are compared with data in the database before entry into the database, and are entered into the database after comparison to confirm unrepeated updated data and stored in a data file database corresponding to the target.
Preferably, the result analysis matching module includes a result analysis unit and a matching output unit, the result analysis unit analyzes and calculates the risk index of the target by calling the behavior feature data of the target in the database, and the matching output unit calculates and outputs the risk index of the target and the high risk behavior feature.
Preferably, the calculation formula for calculating the risk parameter of the predicted behavior feature in the result analysis unit is as follows:
wherein, the event A is that the risk index meets the requirement, and the event B is that the risk index meets the requirementiFor characteristic behavior event groups, P (B)i) Is BiProbability of occurrence, P (B)i) Is used to represent BiRisk threshold of P (B)i| A) is B in case of satisfying A eventiCalculating the probability of occurrence of an event in a characteristic behavior event group by calculating the predicted P (B)iAnd comparing the | A) with the risks corresponding to the behavior characteristics to obtain a risk index.
Preferably, the matching output unit outputs P (B)iI A) and P (B)i) Comparing, outputting the risk evaluation result, and outputting P (B) by the matching output unitiI A) and P (B)i) Three groups with the largest difference.
Compared with the prior art, the invention has the beneficial effects that: according to the invention, the target risk is evaluated by carrying out data analysis through artificial intelligence, and then the artificial intelligence risk evaluation system is perfected by improving the machine learning capability and perfecting the machine learning training rules, so that the artificial intelligence realizes accurate risk evaluation in a big data analysis and statistics mode.
Drawings
FIG. 1 is a schematic view of the overall structure of the present invention;
FIG. 2 is a schematic structural diagram of a rule modification perfection module according to the present invention;
FIG. 3 is a schematic structural diagram of a feature recognition entry storage module according to the present invention;
FIG. 4 is a schematic diagram of a result analysis matching module according to the present invention;
fig. 5 is a flow chart of the operation of the modification perfection unit in the present invention.
In the figure: the system comprises a 1 rule modification perfection module, a 2 feature recognition recording storage module, a 3 result analysis matching module, a 101 integrity evaluation unit, a 102 modification perfection unit, a 201 feature recognition unit, a 202 feature storage recording unit, a 301 result analysis unit and a 302 matching output unit.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-5, the present invention provides a technical solution:
an AI risk identification system comprises a rule modification perfecting module 1, a feature recognition input storage module 2 and a result analysis matching module 3, wherein the rule modification perfecting module 1 is used for perfecting machine learning training rules and improving analysis and calculation capabilities according to calculation and analysis, the feature recognition input storage module 2 is used for recognizing row features of targets and inputting and storing target behavior features into a learning experience database, and the result analysis matching module 3 is used for matching corresponding risk degrees for the targets after analyzing recognized target behavior feature data. The rule modification perfection module 1 comprises an integrity evaluation unit 101 and a modification perfection unit 102, wherein the integrity evaluation unit 101 is used for evaluating the perfection of the computer learning ability, and the modification perfection unit 102 is used for perfecting the machine learning training rules.
The calculation formula used by the integrity evaluation unit 101 to evaluate the learning ability of the calculation machine is:
where ρ is a completeness evaluation parameter, yiIs a standard evaluation value of the i-th evaluation unit, yi' is an actual evaluation value of the i-th evaluation unit.
The workflow of the modification perfection unit 102 is as follows:
step S1: setting a threshold value of the integrity evaluation parameter rho, and when the integrity evaluation parameter rho is lower than the threshold value, the modification and improvement unit 102 searches for influencing factors according to a calculation formula for evaluating and calculating the machine learning capacity;
step S2: in the comparison formula (y)i′-yi) Size of (d), taking out the formula (y)i′-yi) Calculating three influence factors with the maximum result;
step S3: and adjusting the selected three influence factors, calculating the numerical value of the integrity evaluation parameter rho after the adjustment is completed, and when the numerical value of the integrity evaluation parameter rho is higher than the threshold value, reserving the modification for effective modification, and when the integrity evaluation parameter rho is still lower than the threshold value, continuously selecting the three influence factors for modification until the integrity evaluation parameter rho is higher than the threshold value.
The feature recognition and entry storage module 2 includes a feature recognition unit 201 and a feature storage and entry unit 202, the feature recognition unit 201 is configured to detect a behavior operation feature of the target, and the feature storage and entry unit 202 is configured to enter a known behavior feature of the target and a newly added behavior feature detected by the entry feature recognition unit 201.
The calculation formula of the feature recognition unit 201 for recognizing the behavior feature of the detected target is as follows:
wherein, P0Setting a threshold value Q for the proportion of N events to the total events M when P is0And when the N events are greater than or equal to the threshold value Q, the N events are collected as the behavior characteristics of the target.
The characteristic storage and entry unit 202 is provided with a target behavior characteristic database, the target behavior operation characteristics detected by the characteristic identification unit 201 are compared with data in the database before entry into the database, and are entered into the database after comparison confirms that the data are unrepeated and updated, and are stored in a data file database corresponding to the target.
The result analyzing and matching module 3 comprises a result analyzing unit 301 and a matching output unit 302, wherein the result analyzing unit 301 analyzes and calculates the risk index of the target by calling the behavior feature data of the target in the database, and the matching output unit 302 calculates and outputs the risk index of the target and the high-risk behavior feature. The calculation formula for calculating the risk parameter of the predicted behavior feature in the result analysis unit 301 is:
wherein, the event A is that the risk index meets the requirement, and the event B is that the risk index meets the requirementiFor characteristic behavior event groups being event groups having an effect on the risk index, PBiIs BiProbability of occurrence, PBiIs used to represent BiRisk threshold of, PBiI A is B in the case of satisfying A eventiCalculating predicted PB by probability of occurrence of event in characteristic behavior event groupiAnd comparing the risk corresponding to the behavior characteristics with the | A to obtain a risk index. Match output unit 302 outputs PBi| A and PBiCompares the data to output a risk assessment result, and the matching output unit 302 outputs PBi| A and PBiThree groups with the largest difference.
The specific working process of the invention is as follows: when in use, the rule modification perfecting module 1 is used for perfecting a machine learning training rule and improving analysis and calculation capacity according to calculation and analysis, the threshold value of the integrity evaluation parameter rho is set, then the modification perfecting unit 102 searches and selects three influence factors with the highest weight values according to a calculation formula for evaluating the learning capacity of the computer, then the three influence factors with the highest weight values are modified, calculation, evaluation and re-modification are carried out again after modification until the integrity evaluation parameter rho is higher than the threshold value, then after the training rule is perfected, the behavior characteristics of a target are identified through the characteristic identification and entry storage module 2 and are entered and stored into a learning experience database, the warehoused target behavior characteristic data are used for evaluating the risk index of the calculation target, the result analysis matching module 3 calculates the risk probability corresponding to the behavior characteristics when the risk index meets the requirement through prediction and analysis, and comparing the corresponding risk probability with a risk threshold set by the behavior characteristics, and finally outputting a risk evaluation result and three behavior characteristics with the maximum influence result.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. An AI risk identification system, which comprises a rule modification perfection module (1), a characteristic identification entry storage module (2) and a result analysis matching module (3), and is characterized in that: the rule modification and improvement module (1) is used for improving machine learning training rules and improving analysis and calculation capacity according to calculation and analysis, the characteristic recognition and entry storage module (2) is used for recognizing behavior characteristics of a target and entering and storing the behavior characteristics of the target into a learning experience database, and the result analysis and matching module (3) is used for matching corresponding risk degrees for the target after analyzing recognized target behavior characteristic data.
2. The AI risk identification system of claim 1, wherein: the rule modification perfection module (1) comprises an integrity evaluation unit (101) and a modification perfection unit (102), wherein the integrity evaluation unit (101) is used for evaluating the perfection of the computer learning capacity, and the modification perfection unit (102) is used for perfecting the machine learning training rules.
3. The AI risk identification system of claim 2, wherein: the calculation formula of the integrity evaluation unit (101) for evaluating the learning ability of the calculation machine is as follows:
where ρ is a completeness evaluation parameter, yiIs a standard evaluation value of the i-th evaluation unit, yi' is an actual evaluation value of the i-th evaluation unit.
4. The AI risk identification system of claim 2, wherein: the work flow of the modification perfection unit (102) is as follows:
step S1: setting a threshold value of the integrity evaluation parameter rho, and when the integrity evaluation parameter rho is lower than the threshold value, modifying and perfecting the unit (102) to search for influencing factors according to a calculation formula for evaluating and calculating the machine learning capacity;
step S2: in the comparison formula (y)i′-yi) Size of (d), taking out the formula (y)i′-yi) ComputingThree influencing factors with the largest result;
step S3: and adjusting the selected three influence factors, calculating the numerical value of the integrity evaluation parameter rho after the adjustment is completed, and when the numerical value of the integrity evaluation parameter rho is higher than the threshold value, reserving the modification for effective modification, and when the integrity evaluation parameter rho is still lower than the threshold value, continuously selecting the three influence factors for modification until the integrity evaluation parameter rho is higher than the threshold value.
5. The AI risk identification system of claim 1, wherein: the characteristic identification recording storage module (2) comprises a characteristic identification unit (201) and a characteristic storage recording unit (202), wherein the characteristic identification unit (201) is used for detecting behavior operation characteristics of a target, and the characteristic storage recording unit (202) is used for recording known behavior characteristics of the target and recording newly-added behavior characteristics detected by the characteristic identification unit (201).
6. The AI risk identification system of claim 5, wherein: the calculation formula of the feature recognition unit (201) for recognizing the behavior features of the detected target is as follows:
wherein, P0Setting a threshold value Q for the proportion of N events to the total events M when P is0And when the N events are greater than or equal to the threshold value Q, the N events are collected as the behavior characteristics of the target.
7. The AI risk identification system of claim 5, wherein: the characteristic storage and entry unit (202) is provided with a target behavior characteristic database, the target behavior operation characteristics detected by the characteristic identification unit (201) are compared with data in the database before entry into the database, and after comparison, the data are entered into the database after the comparison confirms that the data are unrepeated and updated, and the data are stored in a data file database corresponding to the target.
8. The AI risk identification system of claim 1, wherein: the result analysis matching module (3) comprises a result analysis unit (301) and a matching output unit (302), wherein the result analysis unit (301) analyzes and calculates the risk index of the target by calling the behavior characteristic data of the target in the database, and the matching output unit (302) calculates and outputs the risk index of the target and the high-risk behavior characteristic.
9. The AI risk identification system of claim 8, wherein: the calculation formula for calculating the risk parameter of the predicted behavior characteristic in the result analysis unit (301) is as follows:
wherein, the event A is that the risk index meets the requirement, and the event B is that the risk index meets the requirementiFor characteristic behavior event groups, P (B)i) Is BiProbability of occurrence, P (B)i) Is used to represent BiRisk threshold of P (B)i| A) is B in case of satisfying A eventiCalculating the probability of occurrence of an event in a characteristic behavior event group by calculating the predicted P (B)iAnd comparing the | A) with the risks corresponding to the behavior characteristics to obtain a risk index.
10. The AI risk identification system of claim 8, wherein: the matching output unit (302) outputs P (B)iI A) and P (B)i) Comparing, outputting the risk assessment result, and outputting P (B) by the matching output unit (302)iI A) and P (B)i) Three groups with the largest difference.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011346288.XA CN112330475A (en) | 2020-11-26 | 2020-11-26 | AI risk identification system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011346288.XA CN112330475A (en) | 2020-11-26 | 2020-11-26 | AI risk identification system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112330475A true CN112330475A (en) | 2021-02-05 |
Family
ID=74308821
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011346288.XA Pending CN112330475A (en) | 2020-11-26 | 2020-11-26 | AI risk identification system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112330475A (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102521710A (en) * | 2011-12-22 | 2012-06-27 | 上海建科工程咨询有限公司 | Building construction quality safety online risk assessment system |
CN105046389A (en) * | 2015-02-13 | 2015-11-11 | 国家电网公司 | Intelligent risk assessment method for electric power security risk assessment, and system thereof |
US20160104163A1 (en) * | 2014-10-14 | 2016-04-14 | Jpmorgan Chase Bank, N.A. | ldentifying Potentially Risky Transactions |
CN106503910A (en) * | 2016-10-27 | 2017-03-15 | 扬州大学 | A kind of dynamic man-machine interaction security risk assessment System and method for |
CN106910078A (en) * | 2015-12-22 | 2017-06-30 | 阿里巴巴集团控股有限公司 | Risk identification method and device |
CN108492050A (en) * | 2018-04-04 | 2018-09-04 | 冯世程 | A kind of P2P network loan platforms operations risks assessment system |
CN110610293A (en) * | 2019-08-13 | 2019-12-24 | 中国人民解放军国防科技大学 | Marine environment risk assessment method based on improved Bayesian network |
CN111652496A (en) * | 2020-05-28 | 2020-09-11 | 中国能源建设集团广东省电力设计研究院有限公司 | Operation risk assessment method and device based on network security situation awareness system |
-
2020
- 2020-11-26 CN CN202011346288.XA patent/CN112330475A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102521710A (en) * | 2011-12-22 | 2012-06-27 | 上海建科工程咨询有限公司 | Building construction quality safety online risk assessment system |
US20160104163A1 (en) * | 2014-10-14 | 2016-04-14 | Jpmorgan Chase Bank, N.A. | ldentifying Potentially Risky Transactions |
CN105046389A (en) * | 2015-02-13 | 2015-11-11 | 国家电网公司 | Intelligent risk assessment method for electric power security risk assessment, and system thereof |
CN106910078A (en) * | 2015-12-22 | 2017-06-30 | 阿里巴巴集团控股有限公司 | Risk identification method and device |
CN106503910A (en) * | 2016-10-27 | 2017-03-15 | 扬州大学 | A kind of dynamic man-machine interaction security risk assessment System and method for |
CN108492050A (en) * | 2018-04-04 | 2018-09-04 | 冯世程 | A kind of P2P network loan platforms operations risks assessment system |
CN110610293A (en) * | 2019-08-13 | 2019-12-24 | 中国人民解放军国防科技大学 | Marine environment risk assessment method based on improved Bayesian network |
CN111652496A (en) * | 2020-05-28 | 2020-09-11 | 中国能源建设集团广东省电力设计研究院有限公司 | Operation risk assessment method and device based on network security situation awareness system |
Non-Patent Citations (1)
Title |
---|
汪荣贵: "《机器学习简明教程》", 机械工业出版社, pages: 8 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111614491B (en) | Power monitoring system oriented safety situation assessment index selection method and system | |
CN111598179B (en) | Power monitoring system user abnormal behavior analysis method, storage medium and equipment | |
CN110636066B (en) | Network security threat situation assessment method based on unsupervised generative reasoning | |
CN111126820A (en) | Electricity stealing prevention method and system | |
CN113449919B (en) | Power consumption prediction method and system based on feature and trend perception | |
CN112363896A (en) | Log anomaly detection system | |
CN111539845A (en) | Enterprise environment-friendly management and control response studying and judging method based on power consumption mode membership grade | |
CN117251700B (en) | Artificial intelligence-based environmental monitoring sensor data analysis method and system | |
CN117290462B (en) | Intelligent decision system and method for large data model | |
CN115719283A (en) | Intelligent accounting management system | |
CN101187872A (en) | Program kind distinguishing method based on behavior, device and program control method and device | |
CN112215254A (en) | Transformer substation fault diagnosis method and diagnosis device based on improved case reasoning | |
CN116633601A (en) | Detection method based on network traffic situation awareness | |
CN114548494A (en) | Visual cost data prediction intelligent analysis system | |
CN112491891B (en) | Network attack detection method based on hybrid deep learning in Internet of things environment | |
CN116365519B (en) | Power load prediction method, system, storage medium and equipment | |
CN117763316A (en) | High-dimensional data dimension reduction method and dimension reduction system based on machine learning | |
CN111984514A (en) | Prophet-bLSTM-DTW-based log anomaly detection method | |
Chernyshev et al. | Integration of building information modeling and artificial intelligence systems to create a digital twin of the construction site | |
CN116545679A (en) | Industrial situation security basic framework and network attack behavior feature analysis method | |
CN112330475A (en) | AI risk identification system | |
CN117009509A (en) | Data security classification method, apparatus, device, storage medium and program product | |
Huang et al. | Comparison of carbon emission forecasting in Guangdong province based on multiple machine learning models | |
CN113722230B (en) | Integrated evaluation method and device for vulnerability mining capability of fuzzy test tool | |
CN111221704B (en) | Method and system for determining running state of office management application system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information |
Address after: 401120 No.3, 2nd floor, area C, Jingxin center, No.2 Xihu Branch Road, Liangjiang New District, Yubei District, Chongqing Applicant after: Chongqing quhi rent Technology Co.,Ltd. Address before: 401120 16-8, building 3, Longzhu garden, 145 Xinnan Road, Longxi street, Yubei District, Chongqing Applicant before: Chongqing quhi rent Technology Co.,Ltd. |
|
CB02 | Change of applicant information |