CN103514566A - Risk control system and method - Google Patents
Risk control system and method Download PDFInfo
- Publication number
- CN103514566A CN103514566A CN201310480300.XA CN201310480300A CN103514566A CN 103514566 A CN103514566 A CN 103514566A CN 201310480300 A CN201310480300 A CN 201310480300A CN 103514566 A CN103514566 A CN 103514566A
- Authority
- CN
- China
- Prior art keywords
- risk
- evaluation
- network
- unit
- index
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides risk control system and method, wherein the system and the method are used for carrying out risk monitoring on transaction data in an electric power transaction platform. The method comprises the steps that (1) an evaluation index system is determined according to properties, characteristics and evaluation purposes of an evaluated object, wherein classification and hierarchy of the evaluation index, specific setting of the evaluation index and the determination of an evaluation standard are comprised; (2) basic data are collected, wherein relevant data of the evaluated object are collected according to the setting of the evaluation index, and the index is pretreated; (3) weight determination is carried out, and weight is given to the index; (4) and comprehensive evaluation is carried out, wherein scoring and grading are carried out on all aspects and the overall credit condition of the evaluated object, so as to reflect the credit risk condition of the evaluated object. The system and the method solve the problems of high cost and poor effect of the risk monitoring method of the existing electric power transaction platform.
Description
Technical field
The present invention relates to the risk control field of electricity transaction platform, relate to particularly a kind of risk control system and method for electricity transaction platform.
Background technology
Electricity transaction platform all the time, adopt some simple infotecies, do not catch up with automatic technology, infotech, the especially development of intellectual technology of computer technology of New Times far away, rudimentary, simple application in intellectual technology, business automation degree is not high, real-time property Bu Qiang， power supply enterprise and user interlock, interaction platform do not form.
Power consumer is the source of profit of enterprise's maximum, is also maximum risk sources.Electric power enterprise GPRS electricity consumption user's credit standing, first will carry out assessing credit risks to electricity consumption user, and assessing credit risks is considered the various features of reflection electricity consumption user credit situation, finally obtains the credit comprehensive evaluation value to electricity consumption user.Existing information risk assessment is all to adopt artificial simple weighted indices, obtains a rough evaluation of estimate, can not very correctly reflect user's credit grade and quality, and the cost of its input is high, and efficiency is low.
Summary of the invention
The object of the present invention is to provide a kind of risk control system of the electricity transaction platform based on neural network, to solve, existing electricity transaction platform risk method for supervising cost is high, the problem of weak effect.
The object of the present invention is to provide a kind of risk control method of the electricity transaction platform based on neural network, to solve, existing electricity transaction platform risk method for supervising cost is high, the problem of weak effect.
In order to achieve the above object, the present invention is by the following technical solutions:
A kind of risk control system of electricity transaction platform, for the transaction data of electricity transaction platform is carried out to risk monitoring and control, described system comprises risk monitoring and control module (10) and electrical network transaction platform (5), risk monitoring and control module (10) is carried out risk monitoring and control to the transaction data in electrical network transaction platform (5) in real time, described risk monitoring and control module (10) is by information acquisition unit (1), training unit (2), storage unit (3) and applying unit (4) form, training unit (2) is comprised of information input unit (21) and computing unit (22), described storage unit (3) is for storing the result of training unit (2), network characterization value extraction unit (31) in storage unit (3) extracts network characterization value, applying unit (4) is connected with storage unit (3), described applying unit (4) comprises risk evaluation model (41) and risk monitoring and control unit (42).
Further, risk monitoring and control unit (42) in described electrical network transaction platform (5) is directly connected with risk monitoring and control module (10), transaction data in risk monitoring and control module (10) is monitored in real time, described training unit (2) builds in the mode of machine learning, by information acquisition unit (1), collect in information input unit (21), pass through again computing unit (22) and calculate users to trust grade, by network characterization value extraction unit (31), the operation result in training unit (2) is extracted, the network characterization value of extracting is deposited in storage unit (3), storage unit (3) comprises database, data in storage unit (3) are as a result of directly applied in risk evaluation model (41), by risk monitoring and control unit (42), feed back to electrical network transaction platform (5) again.
The present invention also proposes a kind of risk control method of the electricity transaction platform based on neural network, for the transaction data of electricity transaction platform is carried out to risk monitoring and control, comprises the following steps:
(1) determine evaluation index system, according to by being commented Properties of Objects, evaluation object to determine evaluation index system, comprise the determining of concrete setting, evaluation criteria of the classification of evaluation index and level, evaluation index;
(2) collect basic data, according to the related data of collecting evaluation object that arranges of evaluation index, index is carried out to pre-service;
(3) weight is determined, to index, gives weight;
(4) comprehensive evaluation, to being commented the each side of object mark and divide rank with overall credit standing, reflects the credit risk situation of evaluation object with this.
Further, described comprehensive evaluation is a kind of power consumer credit rating method based on RBF neural network, and it is as follows that it implements step:
Step 1: the input/output variable of being determined RBF network by evaluation model;
In RBF network, input layer is a kind of Nonlinear Mapping to the basis function output of hidden layer, and what hidden layer adopted is the Gaussian radial basis function in equation (1), and output layer adopts linear activation function;
Step 2: obtain sample data, set up RBF learning sample data;
Step 3: RBF netinit:
Initialization network weight, chooses the number of hidden nodes, 5 of input number of nodes, 1 of output node number; Determine the index system of assessment, be about to the index system of assessment as the input vector of RBF neural network, in credit rating, initialization system consists of the principal element of five investigation power consumer credit standings, be respectively: k1, k2, k3, k4, k5, thus corresponding to five input quantities of RBF neural network.
Step 4: determine network Basis Function Center by fuzzy clustering algorithm;
Step 5: the width parameter σ that determines RBF network;
Step 6: the weights of being adjusted RBF network by gradient descent method:
Described weights adopt subjective enabling legislation to combine with objective weighted model, first according to expertise setting target weight, using this initial value as RBF neural network weight, according to learning sample, constantly adjust neural network weight more subsequently, reach the target that study is optimized;
Step 7: determine the number of hidden nodes by network structure optimized algorithm;
Step 8: network training completes, assessment models builds one's credit:
Step 8: user is graded by Credit Evaluation Model
Credit appraisal combines the weight of index and index, adopts neural computing to go out the comprehensive evaluation value to evaluation object, usings this as the direct basis of weighing evaluation object risk, adopts method of weighting scores to carry out Credit Rank Appraisal to user.
With respect to prior art, the invention has the beneficial effects as follows:
The invention has the beneficial effects as follows: the present invention adopts the mode of RBF network to build users to trust rating model, some potential risks factors can be included in the computation process of model, effectively improve the user quality of the easy platform of electric power.And it is the input as risk rule that the output of users to trust rating model is usingd in the present invention, can greatly improve the quality of electricity transaction platform, and the risk of loss that reduces electricity transaction platform and integrally.
1, the present invention is in the process of monitoring risk data, all the time be the input using the output of users to trust rating model as risk rule, and the different output of users to trust rating model may refer to different risk judgment rules, can greatly improve like this effect of risk monitoring and control.
2, the present invention's users to trust rating model used is the autonomous structure of computing machine, users to trust rating model with respect to tradition with artificial experience training, can avoid occurring in model the factor of subjectivity and one-sidedness, and using the basis of formation of data as model itself, some potential risks factors can be included in the computation process of model, effectively improved the intercepting efficiency of risk data.
Certainly, implement arbitrary product of the present invention and might not need to reach above-described all advantages simultaneously.
Accompanying drawing explanation
Fig. 1 is risk control system and method structural drawing;
Fig. 2 is electric power credit rating process flow diagram;
Fig. 3 is the power consumer credit Rating Model based on RBF neural network; And
Fig. 4 is the implementing procedure figure of the electricity consumption user credit ranking method based on RBF neural network.
Embodiment
Power consumer is the source of profit of enterprise's maximum, is also maximum risk sources.Electric power enterprise GPRS electricity consumption user's credit standing, first will carry out assessing credit risks to electricity consumption user, and assessing credit risks is considered the various features of reflection electricity consumption user credit situation, finally obtains the credit comprehensive evaluation value to electricity consumption user.
Risk control system of the present invention is exactly for the trading activity in electricity transaction is monitored, filter out the credit appraisal data of the electricity consumption user with risk, and returning to electricity transaction platform, the respective handling such as carry out electric power price modification, stop supplying, to avoid the property loss of electric power enterprise.This risk control system can be both a server of setting up separately, can be also the subsystem being integrated in electricity transaction platform.
Main thought of the present invention is to introduce credit Rating Model in risk control system and method, data base as judgement risk, and the input using the result of calculation output of users to trust rating model as risk rule, realize the risk in electricity transaction process is monitored.
Below in conjunction with accompanying drawing, illustrate the present invention:
Referring to Fig. 1, for risk control system of the present invention and method structural drawing, this risk control system and method comprise risk monitoring and control module (10) and electrical network transaction platform (5), risk monitoring and control module (10) is carried out risk monitoring and control to the transaction data in electrical network transaction platform (5) in real time, finds to exist the user data of risk.Wherein risk monitoring and control module (10) is comprised of information acquisition unit (1), training unit (2), storage unit (3) and applying unit (4), training unit (2) is comprised of information input unit (21) and computing unit (22), storage unit (3) is stored the result obtaining of training unit (2), network characterization value extraction unit (31) in storage unit (3) extracts network characterization value, applying unit (4), for the data in storage unit (3) are applied, comprises risk evaluation model (41) and risk monitoring and control unit (42).
In operational process, risk monitoring and control module (10) is monitored in real time to the transaction data in electrical network transaction platform (5), and by credit Rating Model, calculates the risk class of transaction data.Training unit (2) builds in the mode of machine learning, by the collection in information acquisition unit (1), enter in information input unit (21), pass through again computing unit (22), calculate users to trust grade, by network characterization value extraction unit (31), the operation result in training unit (2) is extracted, the network characterization value of extracting is deposited in storage unit (3), storage unit (3) comprises database, data in storage unit (3) are as a result of directly applied in risk evaluation model (41), by risk monitoring and control unit (42), feed back to electrical network transaction platform (5) again, reach the object that customer transaction is monitored in real time.
This risk control system and method will be carried out reliability rating to power consumer from the following aspects and be determined:
1) electric power credit rating flow process:
Flow process and the step of the credit evaluation of the risk control method based on neural network of the present invention are as follows:
(1) determine evaluation index system.Relate to the information that electricity consumption user credit analyzes very extensive, comprise user's financial position, profit situation etc.According to by being commented Properties of Objects, evaluation object to determine evaluation index system, comprise the determining of concrete setting, evaluation criteria of the classification of evaluation index and level, evaluation index.
(2) collect basic data.According to the related data of collecting evaluation object that arranges of evaluation index, and with " index is with dimension principle ", index is carried out to pre-service according to " the index change direction consistency principle ".
(3) weight is determined.Employing science is composed power method, in conjunction with the significance level of each index self, to index, gives weight.
(4) comprehensive evaluation.To being commented the each side of object mark and divide rank with overall credit standing, with this, reflect the credit risk situation of evaluation object.
2) the power consumer credit rating method based on neural network
Radial basis function (Radial basis function, RBF) neural network has fast convergence rate simple in structure to be convenient to realize and the stronger advantages such as robustness, is widely used in the fields such as pattern-recognition approximation of function and automatic control.The common layering of structure of RBF neural network: input layer hidden layer and output layer hidden node consist of radial basis function, the feature of this class function is the distance monotone decreasing of its reaction and Centroid, the distance that is input vector and radial basis function (Gaussian function) center is less, the response of hidden node is larger, lower dimensional space linearly inseparable problem can be mapped to higher dimensional space, making it is linear layer at higher dimensional space linear separability output layer, complete the linear classification to hidden layer spatial model, the linear transformation from Hidden unit space to output region is provided.Refer to the scalar function that certain is radially symmetrical, be normally defined in space any point to the monotonic quantity of the Euclidean distance between a certain center.The most frequently used radial basis function is Gaussian function.The topological structure of RBF neural network as shown in Figure 2, is a kind of three layers of feedforward network, i.e. input layer, hidden layer and output layer.In RBF network, input layer is a kind of Nonlinear Mapping to the basis function output of hidden layer, and what hidden layer adopted is the Gaussian radial basis function in equation (1), and output layer adopts linear activation function.
H wherein
jbe the output of j hidden layer neuron, x is input vector, c
jthe center of hidden neuron, σ
jit is the width parameter at hidden neuron center.
For the credit standing to power consumer preferably, grade, the present invention adopts a kind of power consumer credit rating method based on RBF neural network, the implementation step of the risk control method based on neural network as shown in Figure 3:
Step 1: the input/output variable of being determined RBF network by evaluation model;
In RBF network, input layer is a kind of Nonlinear Mapping to the basis function output of hidden layer, and what hidden layer adopted is the Gaussian radial basis function in equation (1), and output layer adopts linear activation function.
Step 2: obtain sample data, set up RBF learning sample data;
Step 3: RBF netinit:
Initialization network weight, chooses the number of hidden nodes, 5 of input number of nodes, 1 of output node number; Determine the index system of assessment, be about to the index system of assessment as the input vector of RBF neural network, in credit rating, initialization system consists of the principal element of five investigation power consumer credit standings, be respectively: k1, k2, k3, k4, k5, thus corresponding to five input quantities of RBF neural network;
Step 4: determine network Basis Function Center by fuzzy clustering algorithm;
Step 5: the width parameter σ that determines RBF network;
Step 6: the weights of being adjusted RBF network by gradient descent method: after index system is set up, wherein the importance of every index is different, gives different weights to different indexs, just can embody them to the impact in various degree of electricity consumption user credit situation.Definite method of index weights is a lot, is substantially divided into two large classes: subjective enabling legislation and objective weighted model.The subjective method of composing power mainly contains expert adjudicate method, and its principle is to rely on the expert who possesses correlation experience, by virtue of experience subjectively indices is carried out to weight setting; The method of Objective Weight is a kind of method of flexible strategy that directly obtains after certain mathematics manipulation according to the raw information of each index.In the present invention, subjective enabling legislation is combined with objective weighted model, first according to expertise setting target weight, using this initial value as RBF neural network weight, according to learning sample, constantly adjust neural network weight more subsequently, reach the target that study is optimized.
Step 7: determine the number of hidden nodes by network structure optimized algorithm;
Step 8: network training completes, assessment models builds one's credit:
Step 9: user is graded by Credit Evaluation Model.Credit appraisal combines the weight of index and index, adopts neural computing to go out the comprehensive evaluation value to evaluation object, usings this as the direct basis of weighing evaluation object risk, and in the present invention, credit comprehensive evaluation model adopts method of weighting scores.
The present invention adopts the mode of RBF network to build users to trust rating model, some potential risks factors can be included in the computation process of model, effectively improves the user quality of the easy platform of electric power.And it is the input as risk rule that the output of users to trust rating model is usingd in the present invention, can greatly improve the quality of electricity transaction platform, and the risk of loss that reduces electricity transaction platform and integrally.
Although some specific embodiments that exemplified above illustrate and describe the present invention, and do not mean that the present invention is only confined to wherein each kind of details.On the contrary, in being equivalent to the category of claims and scope, can not depart from spirit of the present invention and in various details, make various modifications.
Claims (4)
1. a risk control system, for the transaction data of electricity transaction platform is carried out to risk monitoring and control, comprise risk monitoring and control module (10) and electrical network transaction platform (5), risk monitoring and control module (10) is carried out risk monitoring and control to the transaction data in electrical network transaction platform (5) in real time, it is characterized in that: described risk monitoring and control module (10) is by information acquisition unit (1), training unit (2), storage unit (3) and applying unit (4) form, training unit (2) is comprised of information input unit (21) and computing unit (22), described storage unit (3) is for storing the result of training unit (2), network characterization value extraction unit (31) in storage unit (3) extracts network characterization value, applying unit (4) is connected with storage unit (3), described applying unit (4) comprises risk evaluation model (41) and risk monitoring and control unit (42).
2. risk control system according to claim 1, it is characterized in that, risk monitoring and control unit (42) in described electrical network transaction platform (5) is directly connected with risk monitoring and control module (10), transaction data in risk monitoring and control module (10) is monitored in real time, described training unit (2) builds in the mode of machine learning, by information acquisition unit (1), collect in information input unit (21), pass through again computing unit (22) and calculate users to trust grade, by network characterization value extraction unit (31), the operation result in training unit (2) is extracted, the network characterization value of extracting is deposited in storage unit (3), storage unit (3) comprises database, data in storage unit (3) are as a result of directly applied in risk evaluation model (41), by risk monitoring and control unit (42), feed back to electrical network transaction platform (5) again.
3. the risk control method based on neural network, for the transaction data of electricity transaction platform is carried out to risk monitoring and control, is characterized in that: comprise the following steps:
(1) determine evaluation index system, according to by being commented Properties of Objects, evaluation object to determine evaluation index system, comprise the determining of concrete setting, evaluation criteria of the classification of evaluation index and level, evaluation index;
(2) collect basic data, according to the related data of collecting evaluation object that arranges of evaluation index, index is carried out to pre-service;
(3) weight is determined, to index, gives weight;
(4) comprehensive evaluation, to being commented the each side of object mark and divide rank with overall credit standing, reflects the credit risk situation of evaluation object with this.
4. risk control system according to claim 3 and method, is characterized in that, described comprehensive evaluation is a kind of power consumer credit rating method based on RBF neural network, and it is as follows that it implements step:
Step 1: determine the input/output variable of RBF network by evaluation model: in RBF network, input layer is a kind of Nonlinear Mapping to the basis function output of hidden layer, what hidden layer adopted is the Gaussian radial basis function in equation (1), and output layer adopts linear activation function:
H wherein
jbe the output of j hidden layer neuron, x is input vector, c
jthe center of hidden neuron, σ
jit is the width parameter at hidden neuron center;
Step 2: obtain sample data, set up RBF learning sample data;
Step 3: RBF netinit: initialization network weight, choose the number of hidden nodes, 5 of input number of nodes, 1 of output node number; Determine the index system of assessment, be about to the index system of assessment as the input vector of RBF neural network, in credit rating, initialization system consists of the principal element of five investigation power consumer credit standings, be respectively: k1, k2, k3, k4, k5, thus corresponding to five input quantities of RBF neural network;
Step 4: determine network Basis Function Center by fuzzy clustering algorithm;
Step 5: the width parameter σ that determines RBF network;
Step 6: the weights of being adjusted RBF network by gradient descent method: described weights adopt subjective enabling legislation to combine with objective weighted model, first according to expertise setting target weight, using this initial value as RBF neural network weight, according to learning sample, constantly adjust neural network weight more subsequently, reach the target that study is optimized;
Step 7: determine the number of hidden nodes by network structure optimized algorithm;
Step 8: network training completes, assessment models builds one's credit:
Step 9: user is graded by Credit Evaluation Model: credit appraisal combines the weight of index and index, adopt neural computing to go out the comprehensive evaluation value to evaluation object, using this as the direct basis of weighing evaluation object risk, adopt method of weighting scores to carry out Credit Rank Appraisal to user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310480300.XA CN103514566A (en) | 2013-10-15 | 2013-10-15 | Risk control system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310480300.XA CN103514566A (en) | 2013-10-15 | 2013-10-15 | Risk control system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103514566A true CN103514566A (en) | 2014-01-15 |
Family
ID=49897247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310480300.XA Pending CN103514566A (en) | 2013-10-15 | 2013-10-15 | Risk control system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103514566A (en) |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104835103A (en) * | 2015-05-11 | 2015-08-12 | 大连理工大学 | Mobile network health evaluation method based on neural network and fuzzy comprehensive evaluation |
| CN105139293A (en) * | 2015-09-21 | 2015-12-09 | 南京工程学院 | Large power grid emergency control system experiment verification and assessment index system and method |
| CN105989291A (en) * | 2015-02-06 | 2016-10-05 | 卓望数码技术（深圳）有限公司 | Security risk assessment method and system for mobile application |
| CN106204246A (en) * | 2016-08-18 | 2016-12-07 | 易联众信息技术股份有限公司 | A kind of BP neutral net credit estimation method based on PCA |
| WO2016206557A1 (en) * | 2015-06-24 | 2016-12-29 | 阿里巴巴集团控股有限公司 | Risk identification method and apparatus |
| CN106600131A (en) * | 2016-12-07 | 2017-04-26 | 国网河北省电力公司 | Power grid investment analysis model evaluation method |
| CN106934701A (en) * | 2015-12-28 | 2017-07-07 | 航天信息股份有限公司 | A kind of enterprise tax risk value calculating method |
| CN106934413A (en) * | 2015-12-31 | 2017-07-07 | 阿里巴巴集团控股有限公司 | Model training method, apparatus and system and sample set optimization method, device |
| CN107067157A (en) * | 2017-03-01 | 2017-08-18 | 北京奇艺世纪科技有限公司 | Business risk appraisal procedure, device and air control system |
| CN107133865A (en) * | 2016-02-29 | 2017-09-05 | 阿里巴巴集团控股有限公司 | A kind of acquisition of credit score, the output intent and its device of characteristic vector value |
| WO2017157165A1 (en) * | 2016-03-15 | 2017-09-21 | 腾讯科技（深圳）有限公司 | Credit-score model training method, and credit-score calculation method, device, and server |
| CN107240014A (en) * | 2017-04-28 | 2017-10-10 | 天合泽泰（厦门）征信服务有限公司 | A kind of credit rating method based on enterprise's reference business |
| CN107273974A (en) * | 2017-05-22 | 2017-10-20 | 浙江鹏信信息科技股份有限公司 | A kind of safe emergency disposal appraisement system construction method and system |
| CN107316134A (en) * | 2017-06-16 | 2017-11-03 | 深圳乐信软件技术有限公司 | A kind of risk control method, device, server and storage medium |
| CN107330572A (en) * | 2016-04-28 | 2017-11-07 | 阿里巴巴集团控股有限公司 | Air control method, apparatus and system |
| CN107705050A (en) * | 2017-11-15 | 2018-02-16 | 中国农业银行股份有限公司 | A kind of construction method and constructing system of customer information disclosure risk assessment system |
| CN108053094A (en) * | 2017-11-15 | 2018-05-18 | 九次方大数据信息集团有限公司 | A kind of weight grade evaluation method and system |
| CN108062629A (en) * | 2017-12-26 | 2018-05-22 | 平安科技（深圳）有限公司 | Processing method, terminal device and the medium of transaction event |
| CN108564376A (en) * | 2018-04-20 | 2018-09-21 | 阿里巴巴集团控股有限公司 | Risk control method, device, server and readable storage medium storing program for executing |
| CN109472453A (en) * | 2018-10-12 | 2019-03-15 | 山大地纬软件股份有限公司 | Power consumer credit assessment method based on global optimum's fuzzy kernel clustering model |
| CN109636257A (en) * | 2019-01-31 | 2019-04-16 | 长安大学 | A kind of net about risk evaluating method of vehicle before travel |
| CN109740914A (en) * | 2018-12-28 | 2019-05-10 | 武汉金融资产交易所有限公司 | A kind of method, storage medium, equipment and system that financial business is assessed, recommended |
| CN109948932A (en) * | 2019-03-20 | 2019-06-28 | 杭州虹晟信息科技有限公司 | Risk monitoring and control analysis system based on big data |
| CN109978300A (en) * | 2017-12-28 | 2019-07-05 | 北京顺智信科技有限公司 | Customer risk withstands forces quantization method and system, Asset Allocation method and system |
| CN110060047A (en) * | 2019-03-28 | 2019-07-26 | 阿里巴巴集团控股有限公司 | Credit risk method of discrimination and its device based on transaction |
| CN110348705A (en) * | 2019-06-25 | 2019-10-18 | 阿里巴巴集团控股有限公司 | Method and apparatus for risk control |
| CN110414834A (en) * | 2019-07-26 | 2019-11-05 | 上海全成通信技术有限公司 | User credit dynamic monitoring and controlling method and system based on big data and feedback mechanism |
| CN110490448A (en) * | 2019-08-14 | 2019-11-22 | 深圳精确数字科技集团有限公司 | 721 big data air control models are borrowed by trade company based on scene |
| CN110751400A (en) * | 2019-10-22 | 2020-02-04 | 宜人恒业科技发展（北京）有限公司 | Risk assessment method and device |
| CN110826935A (en) * | 2019-11-22 | 2020-02-21 | 国网陕西省电力公司电力科学研究院 | Machine learning-based medium and long term electric power market risk assessment method |
| CN111144778A (en) * | 2019-12-30 | 2020-05-12 | 智慧神州(北京)科技有限公司 | Management and evaluation method and system based on data account |
| CN111383115A (en) * | 2020-03-16 | 2020-07-07 | 中科天玑数据科技股份有限公司 | Transaction place abnormal behavior monitoring and analyzing method and system |
| CN111723367A (en) * | 2020-06-12 | 2020-09-29 | 国家电网有限公司 | Power monitoring system service scene disposal risk evaluation method and system |
| CN111861174B (en) * | 2020-07-09 | 2021-04-13 | 北京睿知图远科技有限公司 | Credit assessment method for user portrait |
| CN113256422A (en) * | 2021-06-09 | 2021-08-13 | 深圳华锐金融技术股份有限公司 | Method and device for identifying bin account, computer equipment and storage medium |
| CN113780887A (en) * | 2021-09-28 | 2021-12-10 | 深圳供电局有限公司 | Risk quantitative evaluation system for power communication network |
| CN113793007A (en) * | 2021-09-06 | 2021-12-14 | 深圳市数聚湾区大数据研究院 | Data transaction authority control method, device and equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030115133A1 (en) * | 2001-12-13 | 2003-06-19 | Dun & Bradstreet, Inc. | Higher risk score for identifying potential illegality in business-to-business relationships |
| CN101493913A (en) * | 2008-01-23 | 2009-07-29 | 阿里巴巴集团控股有限公司 | Method and system for assessing user credit in internet |
| CN102436622A (en) * | 2011-12-28 | 2012-05-02 | 浙江汇信科技有限公司 | Method for evaluating network market operator credit status |
| CN103123712A (en) * | 2011-11-17 | 2013-05-29 | 阿里巴巴集团控股有限公司 | Method and system for monitoring network behavior data |
-
2013
- 2013-10-15 CN CN201310480300.XA patent/CN103514566A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030115133A1 (en) * | 2001-12-13 | 2003-06-19 | Dun & Bradstreet, Inc. | Higher risk score for identifying potential illegality in business-to-business relationships |
| CN101493913A (en) * | 2008-01-23 | 2009-07-29 | 阿里巴巴集团控股有限公司 | Method and system for assessing user credit in internet |
| CN103123712A (en) * | 2011-11-17 | 2013-05-29 | 阿里巴巴集团控股有限公司 | Method and system for monitoring network behavior data |
| CN102436622A (en) * | 2011-12-28 | 2012-05-02 | 浙江汇信科技有限公司 | Method for evaluating network market operator credit status |
Non-Patent Citations (1)
| Title |
|---|
| 郑明文: "径向基神经网络训练算法及其性能研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 3, 15 March 2010 (2010-03-15) * |
Cited By (51)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105989291A (en) * | 2015-02-06 | 2016-10-05 | 卓望数码技术（深圳）有限公司 | Security risk assessment method and system for mobile application |
| CN105989291B (en) * | 2015-02-06 | 2019-03-29 | 卓望数码技术（深圳）有限公司 | A kind of safety risk estimating method and system of mobile application |
| CN104835103B (en) * | 2015-05-11 | 2018-04-27 | 大连理工大学 | Mobile network's health assessment method based on neutral net and fuzzy overall evaluation |
| CN104835103A (en) * | 2015-05-11 | 2015-08-12 | 大连理工大学 | Mobile network health evaluation method based on neural network and fuzzy comprehensive evaluation |
| WO2016206557A1 (en) * | 2015-06-24 | 2016-12-29 | 阿里巴巴集团控股有限公司 | Risk identification method and apparatus |
| CN105139293A (en) * | 2015-09-21 | 2015-12-09 | 南京工程学院 | Large power grid emergency control system experiment verification and assessment index system and method |
| CN106934701B (en) * | 2015-12-28 | 2021-04-23 | 航天信息股份有限公司 | Enterprise tax risk value calculation method |
| CN106934701A (en) * | 2015-12-28 | 2017-07-07 | 航天信息股份有限公司 | A kind of enterprise tax risk value calculating method |
| CN106934413A (en) * | 2015-12-31 | 2017-07-07 | 阿里巴巴集团控股有限公司 | Model training method, apparatus and system and sample set optimization method, device |
| CN106934413B (en) * | 2015-12-31 | 2020-10-13 | 阿里巴巴集团控股有限公司 | Model training method, device and system and sample set optimization method and device |
| CN107133865B (en) * | 2016-02-29 | 2021-06-01 | 阿里巴巴集团控股有限公司 | Credit score obtaining and feature vector value output method and device |
| CN107133865A (en) * | 2016-02-29 | 2017-09-05 | 阿里巴巴集团控股有限公司 | A kind of acquisition of credit score, the output intent and its device of characteristic vector value |
| WO2017157165A1 (en) * | 2016-03-15 | 2017-09-21 | 腾讯科技（深圳）有限公司 | Credit-score model training method, and credit-score calculation method, device, and server |
| US11915311B2 (en) | 2016-03-15 | 2024-02-27 | Tencent Technology (Shenzhen) Company Limited | User score model training and calculation |
| CN107330572B (en) * | 2016-04-28 | 2020-06-02 | 阿里巴巴集团控股有限公司 | Wind control method, device and system |
| CN107330572A (en) * | 2016-04-28 | 2017-11-07 | 阿里巴巴集团控股有限公司 | Air control method, apparatus and system |
| CN106204246A (en) * | 2016-08-18 | 2016-12-07 | 易联众信息技术股份有限公司 | A kind of BP neutral net credit estimation method based on PCA |
| CN106600131A (en) * | 2016-12-07 | 2017-04-26 | 国网河北省电力公司 | Power grid investment analysis model evaluation method |
| CN107067157A (en) * | 2017-03-01 | 2017-08-18 | 北京奇艺世纪科技有限公司 | Business risk appraisal procedure, device and air control system |
| CN107240014A (en) * | 2017-04-28 | 2017-10-10 | 天合泽泰（厦门）征信服务有限公司 | A kind of credit rating method based on enterprise's reference business |
| CN107273974A (en) * | 2017-05-22 | 2017-10-20 | 浙江鹏信信息科技股份有限公司 | A kind of safe emergency disposal appraisement system construction method and system |
| CN107316134A (en) * | 2017-06-16 | 2017-11-03 | 深圳乐信软件技术有限公司 | A kind of risk control method, device, server and storage medium |
| CN107705050B (en) * | 2017-11-15 | 2020-07-03 | 中国农业银行股份有限公司 | Construction method and construction system of customer information leakage risk assessment system |
| CN108053094A (en) * | 2017-11-15 | 2018-05-18 | 九次方大数据信息集团有限公司 | A kind of weight grade evaluation method and system |
| CN107705050A (en) * | 2017-11-15 | 2018-02-16 | 中国农业银行股份有限公司 | A kind of construction method and constructing system of customer information disclosure risk assessment system |
| CN108062629A (en) * | 2017-12-26 | 2018-05-22 | 平安科技（深圳）有限公司 | Processing method, terminal device and the medium of transaction event |
| CN108062629B (en) * | 2017-12-26 | 2021-07-09 | 平安科技（深圳）有限公司 | Transaction event processing method, terminal device and medium |
| CN109978300B (en) * | 2017-12-28 | 2023-05-23 | 百融至信(北京)科技有限公司 | Customer risk tolerance quantification method and system, and asset configuration method and system |
| CN109978300A (en) * | 2017-12-28 | 2019-07-05 | 北京顺智信科技有限公司 | Customer risk withstands forces quantization method and system, Asset Allocation method and system |
| CN108564376A (en) * | 2018-04-20 | 2018-09-21 | 阿里巴巴集团控股有限公司 | Risk control method, device, server and readable storage medium storing program for executing |
| CN109472453A (en) * | 2018-10-12 | 2019-03-15 | 山大地纬软件股份有限公司 | Power consumer credit assessment method based on global optimum's fuzzy kernel clustering model |
| CN109740914A (en) * | 2018-12-28 | 2019-05-10 | 武汉金融资产交易所有限公司 | A kind of method, storage medium, equipment and system that financial business is assessed, recommended |
| CN109636257A (en) * | 2019-01-31 | 2019-04-16 | 长安大学 | A kind of net about risk evaluating method of vehicle before travel |
| CN109948932A (en) * | 2019-03-20 | 2019-06-28 | 杭州虹晟信息科技有限公司 | Risk monitoring and control analysis system based on big data |
| CN110060047A (en) * | 2019-03-28 | 2019-07-26 | 阿里巴巴集团控股有限公司 | Credit risk method of discrimination and its device based on transaction |
| CN110348705A (en) * | 2019-06-25 | 2019-10-18 | 阿里巴巴集团控股有限公司 | Method and apparatus for risk control |
| CN110414834A (en) * | 2019-07-26 | 2019-11-05 | 上海全成通信技术有限公司 | User credit dynamic monitoring and controlling method and system based on big data and feedback mechanism |
| CN110490448A (en) * | 2019-08-14 | 2019-11-22 | 深圳精确数字科技集团有限公司 | 721 big data air control models are borrowed by trade company based on scene |
| CN110751400A (en) * | 2019-10-22 | 2020-02-04 | 宜人恒业科技发展（北京）有限公司 | Risk assessment method and device |
| CN110751400B (en) * | 2019-10-22 | 2022-08-02 | 宜人恒业科技发展（北京）有限公司 | Risk assessment method and device |
| CN110826935B (en) * | 2019-11-22 | 2022-03-08 | 国网陕西省电力公司电力科学研究院 | Machine learning-based medium and long term electric power market risk assessment method |
| CN110826935A (en) * | 2019-11-22 | 2020-02-21 | 国网陕西省电力公司电力科学研究院 | Machine learning-based medium and long term electric power market risk assessment method |
| CN111144778A (en) * | 2019-12-30 | 2020-05-12 | 智慧神州(北京)科技有限公司 | Management and evaluation method and system based on data account |
| CN111383115A (en) * | 2020-03-16 | 2020-07-07 | 中科天玑数据科技股份有限公司 | Transaction place abnormal behavior monitoring and analyzing method and system |
| CN111723367A (en) * | 2020-06-12 | 2020-09-29 | 国家电网有限公司 | Power monitoring system service scene disposal risk evaluation method and system |
| CN111723367B (en) * | 2020-06-12 | 2023-06-23 | 国家电网有限公司 | Method and system for evaluating service scene treatment risk of power monitoring system |
| CN111861174B (en) * | 2020-07-09 | 2021-04-13 | 北京睿知图远科技有限公司 | Credit assessment method for user portrait |
| CN113256422A (en) * | 2021-06-09 | 2021-08-13 | 深圳华锐金融技术股份有限公司 | Method and device for identifying bin account, computer equipment and storage medium |
| CN113793007A (en) * | 2021-09-06 | 2021-12-14 | 深圳市数聚湾区大数据研究院 | Data transaction authority control method, device and equipment |
| CN113793007B (en) * | 2021-09-06 | 2024-02-27 | 深圳市数聚湾区大数据研究院 | Data transaction authority control method, device and equipment |
| CN113780887A (en) * | 2021-09-28 | 2021-12-10 | 深圳供电局有限公司 | Risk quantitative evaluation system for power communication network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103514566A (en) | Risk control system and method | |
| Wu et al. | Evolving RBF neural networks for rainfall prediction using hybrid particle swarm optimization and genetic algorithm | |
| CN104798043B (en) | A kind of data processing method and computer system | |
| CN101782976B (en) | Automatic selection method for machine learning in cloud computing environment | |
| Rejc et al. | Short-term transmission-loss forecast for the slovenian transmission power system based on a fuzzy-logic decision approach | |
| Xiao et al. | Self-evolving trading strategy integrating internet of things and big data | |
| CN110221225A (en) | Spacecraft lithium ion battery cycle life prediction method | |
| Corney et al. | Putting the crowd to work in a knowledge-based factory | |
| CN106022614A (en) | Data mining method of neural network based on nearest neighbor clustering | |
| Musango et al. | Technology sustainability assessment of biodiesel development in South Africa: A system dynamics approach | |
| CN103729687A (en) | Electricity price forecasting method based on wavelet transform and neural network | |
| Liu et al. | An overview of decision tree applied to power systems | |
| CN110147389A (en) | Account number treating method and apparatus, storage medium and electronic device | |
| CN110175689A (en) | A kind of method of probabilistic forecasting, the method and device of model training | |
| Minli et al. | Research on the application of artificial neural networks in tender offer for construction projects | |
| Lin et al. | Revenue prediction for integrated renewable energy and energy storage system using machine learning techniques | |
| Salam et al. | Energy consumption prediction model with deep inception residual network inspiration and LSTM | |
| Azadeh et al. | An integrated artificial neural network fuzzy C-means-normalization algorithm for performance assessment of decision-making units: The cases of auto industry and power plant | |
| Ray et al. | Short-term load forecasting using genetic algorithm | |
| CN109711707A (en) | A kind of Ship Power Equipment synthetical condition assessment method | |
| Mohammad et al. | Short term load forecasting using deep neural networks | |
| CN107256461A (en) | A kind of electrically-charging equipment builds address evaluation method and system | |
| CN106874676A (en) | A kind of electric power meter state evaluating method | |
| CN107273361A (en) | The word computational methods and its device closed based on the general type-2 fuzzy sets of broad sense | |
| CN116776209A (en) | Method, system, equipment and medium for identifying operation state of gateway metering device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140115 |
|
| RJ01 | Rejection of invention patent application after publication |