CN113256008A - Arrearage risk level determination method, device, equipment and storage medium - Google Patents
Arrearage risk level determination method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113256008A CN113256008A CN202110599733.1A CN202110599733A CN113256008A CN 113256008 A CN113256008 A CN 113256008A CN 202110599733 A CN202110599733 A CN 202110599733A CN 113256008 A CN113256008 A CN 113256008A
- Authority
- CN
- China
- Prior art keywords
- arrearage
- data
- risk level
- risk
- determining
- 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
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000012797 qualification Methods 0.000 claims abstract description 16
- 206010033307 Overweight Diseases 0.000 claims description 26
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000000513 principal component analysis Methods 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 6
- 230000006399 behavior Effects 0.000 description 55
- 230000006870 function Effects 0.000 description 22
- 230000002787 reinforcement Effects 0.000 description 19
- 230000009471 action Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000011084 recovery Methods 0.000 description 6
- 230000005611 electricity Effects 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000003795 chemical substances by application Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000000491 multivariate analysis Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 238000007473 univariate analysis Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a device, equipment and a storage medium for determining defaulting risk level, wherein the method comprises the steps of determining business data of a current user for risk prediction, wherein the business data comprises enterprise qualification data, charge control amount, payment behavior data, defaulting behavior data, overdue behavior data and default behavior data; and determining the arrearage risk level of the current user according to each service data. According to the technical scheme, after the business data of the current user is determined, the arrearage risk level of the current user can be determined according to the business data of the current user. The problem of prior art can't make accurate judgement and timely early warning to user's future arrearage risk is solved.
Description
Technical Field
The embodiment of the invention relates to a risk prediction technology, in particular to a method, a device, equipment and a storage medium for determining arrearage risk level.
Background
The recovery of the electric charge is always the work key point of the electric power enterprise, and plays a very important role in the management and management of the electric power enterprise. For a long time, the electric power enterprises adopt the market rule of first using electricity and then paying, the factors of long electric charge recovery period, lagged charge prompting measures and the like exist, and the electric charge recovery becomes a big problem which troubles the electric power enterprises more and more. In order to solve the problem, the operation pressure is effectively reduced, and various technical means and management measures are taken by power enterprises, for example, an electric charge recovery strategy based on a user grade is established, and cooperation with government departments and banks is enhanced.
In the prior art, analysis is usually carried out from seven dimensions of power utilization credit, power utilization abnormity, operation abnormity, associated risk, loss of credit punishment, policy event and public opinion risk, a risk screening model is constructed, a user arrearage risk portrait is realized, a user arrearage risk is analyzed, a corresponding strategy is adopted, and an arrearage risk screening early warning, prevention and control disposal and post-evaluation mechanism are established.
However, the prediction of the customer arrearages in the prior art is insufficient in the aspects of timeliness, accuracy, usability and the like, and accurate judgment and timely early warning cannot be made on the future arrearage risk of the user.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for determining arrearage risk level, which are used for accurately judging future arrearage risk of a user and giving early warning in time.
In a first aspect, an embodiment of the present invention provides a method for determining an arrearage risk level, including:
determining business data of a current user for risk prediction, wherein the business data comprises enterprise qualification data, charge control amount, payment behavior data, arrearage behavior data, overdue behavior data and default behavior data;
and determining the arrearage risk level of the current user according to each service data.
Further, determining business data of the current user for risk prediction includes:
screening each service index of the current user to determine service data of the current user for risk prediction;
wherein the business indicators include power system data.
Further, screening each service index of the current user includes:
performing principal component analysis on each service index to determine a high-weight index;
and performing variable analysis on the high-weight indexes to reduce the correlation degree of each high-weight index.
Further, determining the arrearage risk level of the current user according to each service data includes:
and inputting each service data into a prediction model, and obtaining an output result as the arrearage risk level of the current user.
Further, inputting each service data into a prediction model, and obtaining an output result as the arrearage risk level of the current user, including:
determining an initial risk level according to each service data;
and determining the optimal initial risk level as the arrearage risk level of the current user.
Further, still include:
and updating the prediction model based on users contained in a risk sample library, wherein the risk sample library comprises real owing users and prediction owing users.
Further, updating the prediction model based on users contained in the risk sample library includes:
determining a user which is coincident in the arrearage risk level of the real arrearage user and the arrearage risk level of the forecast arrearage user as a risk sample user;
model training is carried out on the prediction model based on the risk sample user and the corresponding arrearage risk level of the risk sample user, and a loss function is calculated;
and performing network optimization based on a back propagation algorithm until the loss function is converged to obtain an updated prediction model.
The embodiment of the invention provides a method for determining an arrearage risk level, which comprises the steps of determining business data of a current user for risk prediction, wherein the business data comprises enterprise qualification data, charge control amount, payment behavior data, arrearage behavior data, overdue behavior data and default behavior data; and determining the arrearage risk level of the current user according to each service data. According to the technical scheme, after the business data of the current user is determined, the arrearage risk level of the current user can be determined according to the business data of the current user. The problem of prior art can't make accurate judgement and timely early warning to user's future arrearage risk is solved.
In a second aspect, an embodiment of the present invention further provides an arrearage risk level determining apparatus, including:
the system comprises a business data determining module, a risk prediction module and a risk prediction module, wherein the business data determining module is used for determining business data of a current user for risk prediction, and the business data comprises enterprise qualification data, charge control amount, payment behavior data, owing behavior data, overdue behavior data and default behavior data;
and the arrearage risk level determining module is used for determining the arrearage risk level of the current user according to each service data.
In a third aspect, an embodiment of the present invention further provides a computer device, where the computer device includes:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method of arrearage risk level determination as described in any of the first aspects.
In a fourth aspect, embodiments of the present invention also provide a storage medium containing computer-executable instructions for performing the method for determining a level of arrearage risk as defined in any one of the first aspect when executed by a computer processor.
In a fifth aspect, the present application provides a computer program product comprising computer instructions which, when run on a computer, cause the computer to perform the method for determining a level of risk of arrearages as provided in the first aspect.
It should be noted that all or part of the computer instructions may be stored on the computer readable storage medium. The computer readable storage medium may be packaged with the processor of the arrearage risk level determination device, or may be packaged separately from the processor of the arrearage risk level determination device, which is not limited in this application.
For the descriptions of the second, third, fourth and fifth aspects in this application, reference may be made to the detailed description of the first aspect; in addition, for the beneficial effects described in the second aspect, the third aspect, the fourth aspect and the fifth aspect, reference may be made to the beneficial effect analysis of the first aspect, and details are not repeated here.
In the present application, the name of the above-mentioned arrearage risk level determination means does not constitute a limitation on the devices or functional modules themselves, which may appear under other names in an actual implementation. Insofar as the functions of the respective devices or functional modules are similar to those of the present application, they fall within the scope of the claims of the present application and their equivalents.
These and other aspects of the present application will be more readily apparent from the following description.
Drawings
Fig. 1 is a flowchart of a method for determining an arrearage risk level according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for determining the arrearage risk level according to a second embodiment of the present invention;
fig. 3 is a flowchart of step 230 of a method for determining the arrearage risk level according to a second embodiment of the present invention;
fig. 4 is a flowchart of an implementation of a method for determining an arrearage risk level according to a second embodiment of the present invention;
fig. 5 is a flowchart of another implementation of a method for determining an arrearage risk level according to a second embodiment of the present invention;
fig. 6 is a block diagram of an arrearage risk level determination apparatus according to a third embodiment of the present invention;
fig. 7 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like. In addition, the embodiments and features of the embodiments in the present invention may be combined with each other without conflict.
The arrearage risk prediction method provided by the prior art is insufficient in timeliness, accuracy, usability and the like, lacks an efficient and visual technical support system, forms an arrearage risk label with complex dimensionality, is particularly influenced by epidemic situations and the like, overlaps risk factors, and cannot accurately judge and timely warn the current and future arrearage risk of a user.
Secondly, currently, under the influence of economic environment and partial industry environment, part of users have arrearage risks at the initial stage of enterprise establishment, but the electric power system has insufficient risk assessment in advance, so that phenomena of arrearage electric charge caused by difficult later-stage operation, breakage of fund flow and the like occur, arrearage risk levels are not accurately divided, and a hierarchical management mechanism of the arrearage users cannot be established.
In addition, the existing arrearage risk prevention system is difficult to accurately position future arrearage risk target groups, insufficient in evaluation of new installed users with arrearage risks, insufficient in differentiated application and lack of matched accurate and effective strategies. The user image characterization is imperfect, the pertinence is lacked, the dependence condition of strategy formulation is lacked, and the execution effect of one user or one class of strategies is to be improved.
The embodiment of the invention provides a method for determining the arrearage risk level, which aims to accurately judge the future arrearage risk of a user and give early warning in time, determine the arrearage risk level of a newly installed user and further facilitate the differentiated management of each user. The following example will describe in detail one arrearage risk level determination method provided by the present application.
Example one
Fig. 1 is a flowchart of a method for determining an arrearage risk level according to an embodiment of the present invention, which is applicable to a situation where a future arrearage risk of a user needs to be determined, and the method may be executed by an arrearage risk level determining apparatus, and specifically includes the following steps:
and step 110, determining business data of the current user for risk prediction.
The current user can be an old user or a newly-installed user, and the arrearage risk level of the old user or the newly-installed user can be predicted. The users can be family users, enterprise users and the like. Of course, the user in the embodiment of the invention can be an enterprise user.
The business data comprises enterprise qualification data, fee control amount, payment behavior data, arrearage behavior data, overdue behavior data and default behavior data. The enterprise qualification data may include: enterprise credit rating, industry classification and enterprise industry risk rating, the fee control amount may include: the last balance, the current balance and the user pre-stored balance, and the payment behavior data may include: the frequency of charges, the total number of charges and the number of days between charges, and the arrearage behavior data may include: the arrearage balance and the arrearage times in the preset time period, and the overdue behavior data may include: the number of overdue times in the preset time period and the number of overdue times greater than the preset number of days in the preset time period may include: the method comprises the steps of total default amount, default money starting time, default times in a preset time period, account staying record times in the preset time period and bad account record times in the preset time period. The preset time period may be one year or half a year, and is not specifically limited herein, and may be determined according to specific needs.
Specifically, all power system data of the current user can be extracted from the power system, and then power system data which can be used for risk prediction of the user is screened from the power system data and determined as business data.
In the embodiment of the invention, the current user can be an enterprise user, the business data can comprise enterprise qualification data, fee control amount, payment behavior data, arrearage behavior data, overdue behavior data and default behavior data, if the current user can be a family user, the business data can also comprise fee control amount, payment behavior data, arrearage behavior data, overdue behavior data, default behavior data and the like, of course, if the current user can be other types of users, the business data can also comprise other types of power system data, and the business data can be screened from all power system data of the current user according to specific requirements so as to determine the business data.
And step 120, determining the arrearage risk level of the current user according to each service data.
Where the arrearage risk level may include a low level, a medium level, and a high level.
Specifically, after the business data of the current user is determined, the business data of the current user may be input into the prediction model to perform calculation processing on the business data, so as to obtain the arrearage risk level of the current user.
The prediction model may be a Q-Learning reinforcement Learning model, the service data of the current user may be used as an input of the Q-Learning reinforcement Learning model, and the obtained output result may be an arrearage risk level of the current user.
It should be noted that the Q-Learning reinforcement Learning model does not need to be trained in advance, and in the process of determining the arrearage risk levels of a plurality of users, the Q-Learning reinforcement Learning model can be updated, so that the determination of the arrearage risk levels of the users is more accurate.
The embodiment of the invention provides a method for determining an arrearage risk level, which comprises the steps of determining business data of a current user for risk prediction, wherein the business data comprises enterprise qualification data, charge control amount, payment behavior data, arrearage behavior data, overdue behavior data and default behavior data; and determining the arrearage risk level of the current user according to each service data. According to the technical scheme, after the business data of the current user is determined, the arrearage risk level of the current user can be determined according to the business data of the current user. The problem of prior art can't make accurate judgement and timely early warning to user's future arrearage risk is solved.
Example two
Fig. 2 is a flowchart of a method for determining an arrearage risk level according to a second embodiment of the present invention, which is embodied on the basis of the second embodiment. In this embodiment, the method may further include:
and step 210, determining business data of the current user for risk prediction.
The business data comprises enterprise qualification data, fee control amount, payment behavior data, arrearage behavior data, overdue behavior data and default behavior data.
In one embodiment, step 210 may specifically include:
and screening each service index of the current user to determine the service data of the current user for risk prediction.
Wherein the business indicators include power system data.
Specifically, the service index may include: enterprise qualification data, energy consumption characteristic data, fee control amount, pre-purchase electricity data, payment behavior data, payment mode, arrearage behavior data, overdue behavior data, default behavior data and the like. Wherein the power usage characteristic data may include: the method comprises the steps of judging whether the electricity consumption is large or not, changing data of the electricity consumption, overload data, sudden increase and sudden decrease data and the like, wherein the electricity pre-purchasing data comprise monthly prepayment at the bottom of a month, normal monthly prepayment balance, polar monthly prepayment balance and the like. Of course, in practical applications, the service index may also include other types of power system data according to different types of power consumers.
Specifically, principal component analysis can be performed on each service index of the current user, and important data is reserved, so that the data calculation amount of the Q-Learning reinforcement Learning model is reduced. And performing variable analysis on the important data to reduce redundancy and correlation among the important data to obtain service data, and further facilitating the Q-Learning reinforcement Learning model to analyze and operate the service data so as to determine the defaulting risk level of the current user.
Optionally, the screening of each service index of the current user includes:
performing principal component analysis on each service index to determine a high-weight index; and performing variable analysis on the high-weight indexes to reduce the correlation degree of each high-weight index.
The principal component analysis is a technology for simplifying a data set, a plurality of indexes can be converted into a few comprehensive indexes, and in the embodiment of the invention, the principal component analysis is carried out on each business index. The variable analysis can comprise univariate analysis and multivariate analysis, and in the embodiment of the invention, the variable analysis can be carried out on the high-weight indexes so as to reduce pairwise correlation and multiple collinearity among a plurality of high-weight indexes.
Specifically, a high-weight index can be screened from the service index corresponding to the current user, namely the power system data, based on principal component analysis. Of course, a higher-weight service index may be selected from the service indexes based on the principal component analysis and determined as a high-weight index. And then, performing variable analysis on the high-weight indexes, for example, performing univariate analysis and multivariate analysis on the high-weight indexes in sequence to reduce pairwise correlation and multiple collinearity between the multiple high-weight indexes, and further reducing the scale of the high-weight indexes to form a more global and more optimized service index system.
In the embodiment of the present invention, the number of types of the determined business data of the current user for risk prediction is not specifically limited, and may be set according to actual requirements.
And step 220, determining the arrearage risk level of the current user according to each service data.
In one embodiment, step 220 may specifically include:
and inputting each service data into a prediction model, and obtaining an output result as the arrearage risk level of the current user.
The prediction model can be a Q-Learning reinforcement model constructed based on a Q-Learning reinforcement Learning algorithm.
Because the prediction model lacks a large number of real sample sets in the early stage and cannot be trained by a supervised algorithm model, the Q-Learning reinforcement Learning model constructed based on the Q-Learning reinforcement Learning algorithm is adopted, the state of the arrearage risk level is actively adjusted according to the change of input business data, the arrearage risk level in the optimal state is obtained after continuous trial and action, and then the arrearage risk level of the current user is output.
The Learning algorithm is a value-based algorithm, and the Q-table and Q (s, a) functions are the core of the algorithm. The Q-table is a table storing Q values for directing the actions of agents in the Q-Learning reinforcement Learning model, each column of which represents an action and each row represents a state. The Q (s, a) function is also called an action value function, and is used to calculate an expected reward value after the action a is executed in the s state, and the calculated Q value finally completes the filling of the Q-table cell. For example, the Q (s, a) function may be used to calculate the corresponding arrearage risk level a, the corresponding expected reward value of the Q-Learning reinforcement Learning model after inputting the business data s, and the Q-table cell may be filled with the obtained expected reward value.
Of course, in practical applications, since the Q-Learning algorithm is to implement Learning in an environment by an agent in the Q-Learning reinforcement Learning model, the definition of the environment is first completed before the Q-Learning algorithm is executed, and a specific flow of the Q-Learning algorithm can be started after the definition of the environment is completed.
The specific steps of the Q-Learning algorithm may include: initializing the Q-table, and setting the same initial value (0 in most cases) in all cells; then, an agent in the Q-Learning reinforcement Learning model starts to explore the environment, in the process of continuously trying and receiving feedback, the Q-table can achieve updating of Q (si, aj) values in cells through the Bellman equation in an iteration mode, the best action for each state is found, and finally the optimal strategy is obtained through the Q-table.
In the embodiment of the invention, the Q-Learning algorithm can be used for operating the service data so as to calculate the arrearage risk level corresponding to the service data, and the lines and columns of the Q-table can be respectively determined as the service data and the arrearage risk level corresponding to the service data. In addition, the Q (s, a) function may also calculate expected reward data when calculating the defaulting risk level corresponding to the business data, and store the calculated Q value in the Q-table of the corresponding row and column.
It should be noted that, while the arrearage risk levels of a plurality of users are determined based on the Q-Learning reinforcement Learning model, optimization and updating of the Q-Learning reinforcement Learning model can be realized.
Further, inputting each service data into a prediction model, and obtaining an output result as the arrearage risk level of the current user, which may specifically include:
determining an initial risk level according to each service data; and determining the optimal initial risk level as the arrearage risk level of the current user.
Specifically, the service data is input into the Q-Learning reinforcement Learning model, so that a plurality of initial risk levels can be determined, and then the Q-Learning reinforcement Learning model can find an optimal initial risk level based on the plurality of initial risk levels and determine the optimal initial risk level as the arrearage risk level of the current user.
Wherein the risk sample library includes real owing users and forecast owing users.
The predictive model may be updated after a default risk level determination for a preset number of users based on the predictive model.
Specifically, a risk sample library may be constructed based on historical users who have made arrearage risk level determinations, which may include real arrearage users and forecast arrearage users, and the prediction model includes the possibility of prediction accuracy and prediction inaccuracy after making the arrearage risk level determinations for the users in the risk sample library. Therefore, the predictive model can be updated based on the user whose prediction contained in the risk sample is accurate.
Fig. 3 is a flowchart of step 230 in a method for determining an arrearage risk level according to a second embodiment of the present invention, as shown in fig. 3, in an implementation manner, step 230 may specifically include:
Specifically, after the risk sample user is determined, the risk sample user and the arrearage risk level corresponding to the risk sample user may be determined as a training set, the training set is input to the prediction model as input information, the obtained output information is the training level corresponding to the training set, and the loss function is calculated based on the training level and the arrearage risk level. And network optimization can be carried out on the prediction model based on a back propagation algorithm until the loss function is converged, so that the prediction model can be updated, and an updated prediction model can be obtained.
The method for determining the arrearage risk level provided by the embodiment II of the invention determines the business data of the current user for risk prediction, wherein the business data comprises enterprise qualification data, charge control amount, payment behavior data, arrearage behavior data, overdue behavior data and default behavior data; and determining the arrearage risk level of the current user according to each service data. According to the technical scheme, after the business data of the current user is determined, the arrearage risk level of the current user can be determined according to the business data of the current user. The problem of prior art can't make accurate judgement and timely early warning to user's future arrearage risk is solved.
In addition, the problem of small quantity of marked samples is solved by using a Q-Learning reinforcement Learning model, and the real arrearage user is compared with the forecast arrearage user to form the final risk sample user. Furthermore, a supervised learning algorithm can be adopted to carry out model iteration updating, the prediction precision and efficiency of the prediction model are improved, the full life cycle and closed-loop management of the label scene are formed, and the precision rate and efficiency of risk assessment are improved.
Furthermore, the embodiment of the invention can guide the defaulting risk service of the power industry, more effectively improve the risk identification, problem processing and problem processing of the power charge recovery in advance, and improve the power charge recovery effect of the power industry.
Fig. 4 is a flowchart of an implementation of a method for determining an arrearage risk level according to a second embodiment of the present invention, and an implementation manner of the method is exemplarily shown. As shown in figure 4 of the drawings,
and step 410, acquiring the power system data of the current user, namely the service index of the current user.
And 420, performing principal component analysis on each service index to determine a high-weight index.
And 430, performing variable analysis on the high-weight indexes to reduce the correlation degree of each high-weight index, and further determining the business data of the current user for risk prediction.
Fig. 5 is a flowchart of another implementation of a method for determining an arrearage risk level according to a second embodiment of the present invention. As shown in figure 5 of the drawings,
step 440 may be replaced with:
Step 450 may be replaced with:
and step 4510, determining a user which is coincident with the arrearage risk level of the real arrearage user and the arrearage risk level of the forecast arrearage user as a risk sample user.
And 4520, model training is carried out on the prediction model based on the risk sample user and the corresponding arrearage risk grade, and a loss function is calculated.
And 4530, performing network optimization based on a back propagation algorithm until the loss function converges to obtain an updated prediction model, and continuing to execute step 410.
In the implementation manner of the arrearage risk level determination method provided by the second embodiment of the present invention, the data of the power system of the current user, that is, the service index of the current user, is obtained; performing principal component analysis on each service index to determine a high-weight index; performing variable analysis on the high-weight indexes to reduce the correlation degree of each high-weight index, and further determining the business data of the current user for risk prediction; inputting each service data into a prediction model, and obtaining an output result as the arrearage risk level of the current user; and updating the prediction model based on the users contained in the risk sample library, and continuously acquiring the power system data of the current user. According to the technical scheme, after the business data of the current user is determined, the arrearage risk level of the current user can be determined according to the business data of the current user. The problem of prior art can't make accurate judgement and timely early warning to user's future arrearage risk is solved.
EXAMPLE III
Fig. 6 is a structural diagram of an arrearage risk level determining apparatus according to a third embodiment of the present invention, which may be applied to a situation where a future arrearage risk of a user needs to be determined, so as to improve accuracy of determining the future arrearage risk of the user. The apparatus may be implemented by software and/or hardware and is typically integrated in a computer device.
As shown in fig. 6, the apparatus includes:
the business data determining module 610 is configured to determine business data of a current user for risk prediction, where the business data includes enterprise qualification data, fee control amount, payment behavior data, owing behavior data, overdue behavior data, and default behavior data;
and an arrearage risk level determination module 620, configured to determine an arrearage risk level of the current user according to each service data.
The defaulting risk level determination device provided by this embodiment determines business data of a current user for risk prediction, where the business data includes enterprise qualification data, fee control amount, payment behavior data, defaulting behavior data, overdue behavior data, and default behavior data; and determining the arrearage risk level of the current user according to each service data. According to the technical scheme, after the business data of the current user is determined, the arrearage risk level of the current user can be determined according to the business data of the current user. The problem of prior art can't make accurate judgement and timely early warning to user's future arrearage risk is solved.
On the basis of the foregoing embodiment, the service data determining module 610 is specifically configured to:
screening each service index of the current user to determine service data of the current user for risk prediction;
wherein the business indicators include power system data.
Further, screening each service index of the current user includes:
performing principal component analysis on each service index to determine a high-weight index; and performing variable analysis on the high-weight indexes to reduce the correlation degree of each high-weight index.
On the basis of the foregoing embodiment, the arrearage risk level determination module 620 is specifically configured to:
and inputting each service data into a prediction model, and obtaining an output result as the arrearage risk level of the current user.
In one embodiment, inputting each of the service data into a prediction model, and obtaining an output result as the arrearage risk level of the current user includes:
determining an initial risk level according to each service data; and determining the optimal initial risk level as the arrearage risk level of the current user.
On the basis of the above embodiment, the apparatus further includes:
and the updating module is used for updating the prediction model based on users contained in a risk sample library, wherein the risk sample library comprises real arrearage users and prediction arrearage users.
In one embodiment, the update module is specifically configured to:
determining a generated reward value when each business data of a historical user is input into the prediction model, wherein the historical user is a user who uses the prediction model to determine the defaulting risk level before the current user;
determining a state cost function and an action cost function according to the reward value;
updating the predictive model based on the state cost function and the action cost function.
The arrearage risk level determining device provided by the embodiment of the invention can execute the arrearage risk level determining method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the executing method.
Example four
Fig. 7 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention, as shown in fig. 7, the computer device includes a processor 710 and a memory 720; the number of the processors 710 in the computer device may be one or more, and one processor 710 is taken as an example in fig. 7; the processor 710 and the memory 720 in the computer device may be connected by a bus or other means, as exemplified by the bus connection in fig. 7.
The memory 720 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the arrearage risk level determination method in the embodiment of the present invention (for example, the business data determination module 710 and the arrearage risk level determination module 720 in the arrearage risk level determination device). The processor 710 executes various functional applications of the computer device and data processing by executing software programs, instructions and modules stored in the memory 720, that is, implements the arrearage risk level determination method described above.
The memory 720 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 720 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 720 may further include memory located remotely from the processor 710, which may be connected to a computer device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The computer equipment provided by the embodiment of the invention can execute the arrearage risk level determination method provided by the embodiment, and has corresponding functions and beneficial effects.
EXAMPLE five
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a method for determining a level of arrearage risk, the method including:
determining business data of a current user for risk prediction, wherein the business data comprises enterprise qualification data, charge control amount, payment behavior data, arrearage behavior data, overdue behavior data and default behavior data;
and determining the arrearage risk level of the current user according to each service data.
The computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a RAM, a ROM, an erasable programmable read-only memory (EPROM), a register, a hard disk, an optical fiber, a CD-ROM, an optical storage device, a magnetic storage device, any suitable combination of the foregoing, or any other form of computer readable storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an Application Specific Integrated Circuit (ASIC). In embodiments of the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the operations of the method described above, and may also perform related operations in the method for determining the level of arrearage risk provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the arrearage risk level determining apparatus, the units and modules included in the embodiment are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method for determining an arrearage risk level, comprising:
determining business data of a current user for risk prediction, wherein the business data comprises enterprise qualification data, charge control amount, payment behavior data, arrearage behavior data, overdue behavior data and default behavior data;
and determining the arrearage risk level of the current user according to each service data.
2. The arrearage risk level determination method of claim 1, wherein determining business data of a current user for risk prediction comprises:
screening each service index of the current user to determine service data of the current user for risk prediction;
wherein the business indicators include power system data.
3. The arrearage risk level determination method of claim 2, wherein the screening of the business indicators of the current user comprises:
performing principal component analysis on each service index to determine a high-weight index;
and performing variable analysis on the high-weight indexes to reduce the correlation degree of each high-weight index.
4. The method of claim 1, wherein determining the arrearage risk level of the current subscriber based on the business data comprises:
and inputting each service data into a prediction model, and obtaining an output result as the arrearage risk level of the current user.
5. The arrearage risk level determination method of claim 4, wherein inputting each of the business data into a predictive model, the resulting output being the arrearage risk level of the current user comprises:
determining an initial risk level according to each service data;
and determining the optimal initial risk level as the arrearage risk level of the current user.
6. The arrearage risk level determination method of claim 4, further comprising:
and updating the prediction model based on users contained in a risk sample library, wherein the risk sample library comprises real owing users and prediction owing users.
7. The arrearage risk level determination method of claim 6, wherein the predictive model is updated based on users contained in a risk sample library, wherein the risk sample library includes real arrearage users and predictive arrearage users, comprising:
determining a user which is coincident in the arrearage risk level of the real arrearage user and the arrearage risk level of the forecast arrearage user as a risk sample user;
model training is carried out on the prediction model based on the risk sample user and the corresponding arrearage risk level of the risk sample user, and a loss function is calculated;
and performing network optimization based on a back propagation algorithm until the loss function is converged to obtain an updated prediction model.
8. An arrearage risk level determination apparatus, comprising:
the system comprises a business data determining module, a risk prediction module and a risk prediction module, wherein the business data determining module is used for determining business data of a current user for risk prediction, and the business data comprises enterprise qualification data, charge control amount, payment behavior data, owing behavior data, overdue behavior data and default behavior data;
and the arrearage risk level determining module is used for determining the arrearage risk level of the current user according to each service data.
9. A computer device, the device comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the arrearage risk level determination method as claimed in any one of claims 1-7.
10. A storage medium containing computer executable instructions for performing the arrearage risk level determination method as claimed in any one of claims 1-7 when executed by a computer processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110599733.1A CN113256008A (en) | 2021-05-31 | 2021-05-31 | Arrearage risk level determination method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110599733.1A CN113256008A (en) | 2021-05-31 | 2021-05-31 | Arrearage risk level determination method, device, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113256008A true CN113256008A (en) | 2021-08-13 |
Family
ID=77183831
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110599733.1A Pending CN113256008A (en) | 2021-05-31 | 2021-05-31 | Arrearage risk level determination method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113256008A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113791259A (en) * | 2021-09-02 | 2021-12-14 | 北京京仪北方仪器仪表有限公司 | Fee control system for intelligent electric energy meter |
CN114374618A (en) * | 2021-12-24 | 2022-04-19 | 中国电信股份有限公司 | Training method, user arrearage off-network prediction method and device |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140200953A1 (en) * | 2009-02-11 | 2014-07-17 | Johnathan Mun | Qualitative and quantitative modeling of enterprise risk management and risk registers |
CN106251049A (en) * | 2016-07-25 | 2016-12-21 | 国网浙江省电力公司宁波供电公司 | A kind of electricity charge risk model construction method of big data |
CN106600146A (en) * | 2016-12-15 | 2017-04-26 | 北京中电普华信息技术有限公司 | Electricity fee collection risk evaluation method and apparatus |
CN106920110A (en) * | 2017-02-23 | 2017-07-04 | 国网安徽省电力公司合肥供电公司 | A kind of evaluation method of power customer credit and arrears risk |
US20170357922A1 (en) * | 2016-06-14 | 2017-12-14 | International Business Machines Corporation | Personalized behavior-driven dynamic risk management with constrained service capacity |
CN108256737A (en) * | 2017-12-21 | 2018-07-06 | 广州供电局有限公司 | Method, apparatus, computer equipment and the storage medium of subscriber arrearage risk profile |
CN110210686A (en) * | 2019-06-13 | 2019-09-06 | 郑州轻工业学院 | A kind of electricity charge risk model construction method of electric power big data |
WO2020037942A1 (en) * | 2018-08-20 | 2020-02-27 | 平安科技(深圳)有限公司 | Risk prediction processing method and apparatus, computer device and medium |
CN111340375A (en) * | 2020-02-28 | 2020-06-26 | 创新奇智(上海)科技有限公司 | Electricity charge recycling risk prediction method and device, electronic equipment and storage medium |
CN111639883A (en) * | 2020-06-15 | 2020-09-08 | 江苏电力信息技术有限公司 | Electricity charge recycling risk prediction method based on machine learning |
CN112766665A (en) * | 2021-01-04 | 2021-05-07 | 国网上海市电力公司 | Risk level-based electric charge recycling risk prevention and control method |
-
2021
- 2021-05-31 CN CN202110599733.1A patent/CN113256008A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140200953A1 (en) * | 2009-02-11 | 2014-07-17 | Johnathan Mun | Qualitative and quantitative modeling of enterprise risk management and risk registers |
US20170357922A1 (en) * | 2016-06-14 | 2017-12-14 | International Business Machines Corporation | Personalized behavior-driven dynamic risk management with constrained service capacity |
CN106251049A (en) * | 2016-07-25 | 2016-12-21 | 国网浙江省电力公司宁波供电公司 | A kind of electricity charge risk model construction method of big data |
CN106600146A (en) * | 2016-12-15 | 2017-04-26 | 北京中电普华信息技术有限公司 | Electricity fee collection risk evaluation method and apparatus |
CN106920110A (en) * | 2017-02-23 | 2017-07-04 | 国网安徽省电力公司合肥供电公司 | A kind of evaluation method of power customer credit and arrears risk |
CN108256737A (en) * | 2017-12-21 | 2018-07-06 | 广州供电局有限公司 | Method, apparatus, computer equipment and the storage medium of subscriber arrearage risk profile |
WO2020037942A1 (en) * | 2018-08-20 | 2020-02-27 | 平安科技(深圳)有限公司 | Risk prediction processing method and apparatus, computer device and medium |
CN110210686A (en) * | 2019-06-13 | 2019-09-06 | 郑州轻工业学院 | A kind of electricity charge risk model construction method of electric power big data |
CN111340375A (en) * | 2020-02-28 | 2020-06-26 | 创新奇智(上海)科技有限公司 | Electricity charge recycling risk prediction method and device, electronic equipment and storage medium |
CN111639883A (en) * | 2020-06-15 | 2020-09-08 | 江苏电力信息技术有限公司 | Electricity charge recycling risk prediction method based on machine learning |
CN112766665A (en) * | 2021-01-04 | 2021-05-07 | 国网上海市电力公司 | Risk level-based electric charge recycling risk prevention and control method |
Non-Patent Citations (3)
Title |
---|
刘倩倩: "基于大数据的电力用户欠费风险等级分析", 《自动化应用》, no. 11, pages 88 - 89 * |
赵海宝等: "基于电费大数据客户欠费风险分级管理探索研究", 《电工技术》, no. 12, pages 141 - 143 * |
陈学彬: "中国信用债市场发展研究", 复旦大学出版社, pages: 341 - 342 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113791259A (en) * | 2021-09-02 | 2021-12-14 | 北京京仪北方仪器仪表有限公司 | Fee control system for intelligent electric energy meter |
CN114374618A (en) * | 2021-12-24 | 2022-04-19 | 中国电信股份有限公司 | Training method, user arrearage off-network prediction method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Castro et al. | Measuring and testing for the systemically important financial institutions | |
EP3043447B1 (en) | Distribution transformer heavy loading and overloading mid-term and short-term pre-warning analytics model | |
CN104798043B (en) | A kind of data processing method and computer system | |
KR102009309B1 (en) | Management automation system for financial products and management automation method using the same | |
CN111754116B (en) | Credit evaluation method and device based on label portrait technology | |
Fu | What you should know about simulation and derivatives | |
CN107123982A (en) | A kind of distribution network reliability analysis method of economic benefit based on equipment alteration | |
CN113256008A (en) | Arrearage risk level determination method, device, equipment and storage medium | |
CN110046986A (en) | The overdue customer grouping method and device of loaning bill based on big data | |
CN102496126B (en) | Custody asset transaction data monitoring equipment | |
CN102117469A (en) | System and method for estimating credit risks | |
CN105139079A (en) | Tax revenue prediction method and device based on hybrid model | |
CN107368925A (en) | Stock trend forecasting method and system | |
CN111626543A (en) | Method and device for processing power related data | |
CN112541662B (en) | Prediction method and system for electric charge recycling risk | |
CN111242779B (en) | Financial data characteristic selection and prediction method, device, equipment and storage medium | |
CN112488865A (en) | Financial risk prediction method and device based on financial time nodes and electronic equipment | |
CN110858355A (en) | Project budget balance prediction method and device | |
KR101334891B1 (en) | System for providing financiail risk management service in software as a service | |
CN113421014A (en) | Target enterprise determination method, device, equipment and storage medium | |
CN113742187A (en) | Capacity prediction method, device, equipment and storage medium of application system | |
CN112419025A (en) | User data processing method and device, storage medium and electronic equipment | |
CN117237070A (en) | Evaluation method, device, equipment and medium of resource allocation strategy | |
Beykirch et al. | The Value of Probabilistic Forecasts for Electricity Market Bidding and Scheduling Under Uncertainty | |
CN112598422A (en) | Transaction risk assessment method, system, device and storage medium |
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 |