CN117056591A - Intelligent electric power payment channel recommendation method and system based on dynamic prediction - Google Patents
Intelligent electric power payment channel recommendation method and system based on dynamic prediction Download PDFInfo
- Publication number
- CN117056591A CN117056591A CN202310907936.1A CN202310907936A CN117056591A CN 117056591 A CN117056591 A CN 117056591A CN 202310907936 A CN202310907936 A CN 202310907936A CN 117056591 A CN117056591 A CN 117056591A
- Authority
- CN
- China
- Prior art keywords
- payment
- euclidean distance
- electric power
- membership
- deviation
- 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 48
- 230000006399 behavior Effects 0.000 claims description 67
- 206010033799 Paralysis Diseases 0.000 claims description 59
- 239000011159 matrix material Substances 0.000 claims description 30
- 230000002068 genetic effect Effects 0.000 claims description 22
- 238000012163 sequencing technique Methods 0.000 claims description 15
- 238000013135 deep learning Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000000295 complement effect Effects 0.000 claims 2
- 229910044991 metal oxide Inorganic materials 0.000 claims 2
- 150000004706 metal oxides Chemical class 0.000 claims 2
- 239000004065 semiconductor Substances 0.000 claims 2
- 238000011156 evaluation Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2337—Non-hierarchical techniques using fuzzy logic, i.e. fuzzy clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Automation & Control Theory (AREA)
- Software Systems (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an intelligent recommendation method and an intelligent recommendation system for an electric power payment channel based on dynamic prediction, which belong to the technical field of payment channel recommendation. According to the invention, the clustering algorithm is introduced to cluster the behavior information of the user payment, so that the real-time flow membership of each payment channel is determined, and the real-time payment behavior of the user can be rapidly evaluated; on the other hand, the method and the device for predicting the flow of the payment channel by using the clustering deviation prediction model are used for calculating the deviation index of the membership of the flow of the real-time payment channel, and can further perform fuzzy clustering evaluation on the flow information of the payment channel and judge whether deviation occurs in the clustering process, so that the prediction accuracy of the flow information of the payment channel is improved.
Description
Technical Field
The invention relates to the field of payment channel recommendation, in particular to an intelligent electric power payment channel recommendation method and system based on dynamic prediction.
Background
Along with the development of economy, the power consumption of the whole society is rapidly increased, the number of power consumption clients is greatly increased, the demand for power consumption service shows a diversified trend, and the diversified requirements are also provided for the power payment mode. In order to meet the increasing demands of customers, power supply enterprises must continuously improve payment modes, expand payment channels, actively popularize novel payment modes, and guide power customers to pay by adopting the novel payment channels, so that a comprehensive and diversified power payment channel is formed. At present, users are in busy periods of some payment, because the number of people paid by the users is numerous, crowding phenomenon is generated in some payment channels, the payment channels are blocked, so that the user experience is poor, and how to recommend a high-quality payment channel according to real-time payment flow data is a key for improving the user experience.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides an intelligent recommendation method and system for an electric power payment channel based on dynamic prediction.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the invention provides an intelligent recommendation method of an electric power payment channel based on dynamic prediction, which comprises the following steps:
Acquiring payment behavior data information of a user in a target area, determining an electric power payment channel in the target area according to the payment behavior data information of the user, and acquiring real-time operation data information of the electric power payment channel in the target area;
introducing an FCM fuzzy clustering algorithm, and clustering real-time operation data information of the electric power payment channels in the target area through the FCM fuzzy clustering algorithm to obtain the payment flow membership of each electric power payment channel in the current time scale;
constructing a clustering deviation prediction model, and calculating a deviation index of the membership degree of the payment flow of each electric power payment channel in the current time scale through the clustering deviation prediction model to acquire deviation index information;
updating the membership degree of the payment flow according to the deviation index information, generating a new membership degree of the payment flow, and intelligently recommending the payment channel based on the new membership degree of the payment flow.
Further, in a preferred embodiment of the present invention, payment behavior data information of a user in a target area is obtained, and a power payment channel in the target area is determined according to the payment behavior data information of the user, which specifically includes:
acquiring payment behavior data information of a user in a target area, and tracing payment channels on the payment behavior data information of the user in the target area to generate payment behavior quantity information of each payment channel within a preset time;
Setting related payment behavior data threshold data information, and comparing the payment behavior quantity information of each payment channel within preset time with the related payment behavior data threshold data information to obtain deviation rate;
judging whether the deviation rate is larger than a preset deviation rate threshold value, and if the deviation rate is larger than the preset deviation rate threshold value, taking a payment channel corresponding to the deviation rate larger than the preset deviation rate threshold value as a power payment channel in the target area;
if the deviation rate is not greater than the preset deviation rate threshold, eliminating the payment channels corresponding to the deviation rate not greater than the preset deviation rate threshold, and simultaneously updating the electric power payment channels in the target area in real time.
Further, in a preferred embodiment of the present invention, an FCM fuzzy clustering algorithm is introduced, and real-time operation data information of the electric power payment channels in the target area is clustered by the FCM fuzzy clustering algorithm, so as to obtain a membership degree of the payment flow of each electric power payment channel in the current time scale, and the method specifically includes the following steps:
constructing a sample data set according to real-time operation data information of the electric power payment channel in the target area, introducing an FCM fuzzy clustering algorithm, initializing the number of clustering centers, and calculating the Euclidean distance from each sample data in the sample data set to the clustering centers;
The Euclidean distance between each sample data and each cluster center is obtained, the Euclidean distance between each sample data and each cluster center is ordered, an Euclidean distance ordering result is obtained, each sample data is classified according to the minimum Euclidean distance in the Euclidean distance ordering result, and each sample data classification result is obtained;
acquiring Euclidean distance of each sample data in each sample data classification result, setting an average Euclidean distance threshold, counting the Euclidean distance of each sample data in each sample data classification result, acquiring a total Euclidean distance value, and calculating the average Euclidean distance of the sample data according to the total Euclidean distance value;
introducing a genetic algorithm, setting a genetic algebra through the genetic algorithm when the average Euclidean distance of the sample data is lower than the average Euclidean distance threshold, carrying out iterative operation on the number of the clustering centers until the average Euclidean distance of the sample data is lower than the average Euclidean distance threshold, updating the number of the clustering centers, and finally carrying out data classification to obtain the membership degree of the payment flow of each electric power payment channel in the current time scale.
Further, in a preferred embodiment of the present invention, a cluster deviation prediction model is constructed, and deviation index calculation is performed on the membership of the payment flow of each electric power payment channel in the current time scale through the cluster deviation prediction model, so as to obtain deviation index information, and the method specifically includes the following steps:
Acquiring the Euclidean distance from each sample data to a clustering center according to the membership degree of the payment flow of each electric power payment channel in the current time scale, and constructing a clustering deviation prediction model;
and calculating deviation index information based on a cluster deviation prediction model and Euclidean distance from each sample data to a cluster center, wherein the cluster deviation prediction model meets the following relational expression:
；
wherein p is the deviation index; n isThe number of sample data; i represents the sequence number of the ith sample data; m is the number of clustering centers; j represents the serial number of the jth cluster center;representing real-time sample data->Is a Euclidean distance of (2); />Representing the ith sample data in the last time scale; />Representing the jth cluster center in the last time scale; a is the number of Euclidean distances in the previous time scale; k is the sequence number of the kth euclidean distance in the last time scale. Further, in a preferred embodiment of the present invention, the membership degree of the payment flow is updated according to the deviation index information to generate a new membership degree of the payment flow, which specifically includes the following steps:
setting deviation index threshold information, judging whether the deviation index information is larger than the deviation index threshold information, and outputting the current payment flow membership degree if the deviation index information is not larger than the deviation index threshold information;
If the deviation index information is larger than the deviation index threshold information, resetting the number of the clustering centers, and performing iterative computation on the number of the clustering centers through a genetic algorithm to generate new clustering centers;
and redistributing the current sample data according to the clustering center, generating new payment flow membership, and outputting the new payment flow membership.
Further, in a preferred embodiment of the present invention, intelligent recommendation is performed on a payment channel based on a new payment flow membership, which specifically includes:
acquiring payment flow membership of each payment channel based on the new payment flow membership, and acquiring historical payment paralysis probability information corresponding to the payment flow membership of each payment channel through big data;
constructing a feature matrix according to historical payment paralysis probability information corresponding to the membership of the payment flow of each payment channel, simultaneously, introducing a feature sequencing CMFS (continuous matrix motion) sequencing algorithm to calculate redundant features in the feature matrix, and removing the redundant features to generate a corrected feature matrix;
constructing a payment paralysis probability prediction model based on the deep learning network, inputting the corrected feature matrix into the payment paralysis probability prediction model for coding learning, and storing model parameters and outputting the payment paralysis probability prediction model after the payment paralysis probability prediction model meets the preset requirements;
And predicting paralysis probability values corresponding to the membership of the payment flow of each current payment channel through a payment paralysis probability prediction model, setting priority orders according to the paralysis probability values corresponding to the membership of the payment flow of each current payment channel, and performing intelligent recommendation based on the priority orders.
The invention provides an intelligent power payment channel recommending system based on dynamic prediction, which comprises a memory and a processor, wherein the memory comprises an intelligent power payment channel recommending method program based on dynamic prediction, and when the intelligent power payment channel recommending method program based on dynamic prediction is executed by the processor, the following steps are realized:
acquiring payment behavior data information of a user in a target area, determining an electric power payment channel in the target area according to the payment behavior data information of the user, and acquiring real-time operation data information of the electric power payment channel in the target area;
introducing an FCM fuzzy clustering algorithm, and clustering real-time operation data information of the electric power payment channels in the target area through the FCM fuzzy clustering algorithm to obtain the payment flow membership of each electric power payment channel in the current time scale;
constructing a clustering deviation prediction model, and calculating a deviation index of the membership degree of the payment flow of each electric power payment channel in the current time scale through the clustering deviation prediction model to acquire deviation index information;
Updating the membership degree of the payment flow according to the deviation index information, generating a new membership degree of the payment flow, and intelligently recommending the payment channel based on the new membership degree of the payment flow.
In the system, payment behavior data information of a user in a target area is acquired, and an electric power payment channel in the target area is determined according to the payment behavior data information of the user, and the system specifically comprises the following steps:
acquiring payment behavior data information of a user in a target area, and tracing payment channels on the payment behavior data information of the user in the target area to generate payment behavior quantity information of each payment channel within a preset time;
setting related payment behavior data threshold data information, and comparing the payment behavior quantity information of each payment channel within preset time with the related payment behavior data threshold data information to obtain deviation rate;
judging whether the deviation rate is larger than a preset deviation rate threshold value, and if the deviation rate is larger than the preset deviation rate threshold value, taking a payment channel corresponding to the deviation rate larger than the preset deviation rate threshold value as a power payment channel in the target area;
if the deviation rate is not greater than the preset deviation rate threshold, eliminating the payment channels corresponding to the deviation rate not greater than the preset deviation rate threshold, and simultaneously updating the electric power payment channels in the target area in real time.
In the system, an FCM fuzzy clustering algorithm is introduced, and the real-time operation data information of the electric power payment channels in the target area is clustered through the FCM fuzzy clustering algorithm to acquire the membership degree of the payment flow of each electric power payment channel in the current time scale, and the method specifically comprises the following steps:
constructing a sample data set according to real-time operation data information of the electric power payment channel in the target area, introducing an FCM fuzzy clustering algorithm, initializing the number of clustering centers, and calculating the Euclidean distance from each sample data in the sample data set to the clustering centers;
the Euclidean distance between each sample data and each cluster center is obtained, the Euclidean distance between each sample data and each cluster center is ordered, an Euclidean distance ordering result is obtained, each sample data is classified according to the minimum Euclidean distance in the Euclidean distance ordering result, and each sample data classification result is obtained;
acquiring Euclidean distance of each sample data in each sample data classification result, setting an average Euclidean distance threshold, counting the Euclidean distance of each sample data in each sample data classification result, acquiring a total Euclidean distance value, and calculating the average Euclidean distance of the sample data according to the total Euclidean distance value;
Introducing a genetic algorithm, setting a genetic algebra through the genetic algorithm when the average Euclidean distance of the sample data is lower than the average Euclidean distance threshold, carrying out iterative operation on the number of the clustering centers until the average Euclidean distance of the sample data is lower than the average Euclidean distance threshold, updating the number of the clustering centers, and finally carrying out data classification to obtain the membership degree of the payment flow of each electric power payment channel in the current time scale.
In the system, intelligent recommendation is carried out on the payment channel based on the new payment flow membership, and the system specifically comprises the following steps:
acquiring payment flow membership of each payment channel based on the new payment flow membership, and acquiring historical payment paralysis probability information corresponding to the payment flow membership of each payment channel through big data;
constructing a feature matrix according to historical payment paralysis probability information corresponding to the membership of the payment flow of each payment channel, simultaneously, introducing a feature sequencing CMFS (continuous matrix motion) sequencing algorithm to calculate redundant features in the feature matrix, and removing the redundant features to generate a corrected feature matrix;
constructing a payment paralysis probability prediction model based on the deep learning network, inputting the corrected feature matrix into the payment paralysis probability prediction model for coding learning, and storing model parameters and outputting the payment paralysis probability prediction model after the payment paralysis probability prediction model meets the preset requirements;
And predicting paralysis probability values corresponding to the membership of the payment flow of each current payment channel through a payment paralysis probability prediction model, setting priority orders according to the paralysis probability values corresponding to the membership of the payment flow of each current payment channel, and performing intelligent recommendation based on the priority orders.
The invention solves the defects existing in the background technology, and has the following beneficial effects:
according to the invention, the real-time operation data information of the electric power payment channels in the target area is acquired by acquiring the payment behavior data information of the user in the target area, the electric power payment channels in the target area are determined according to the payment behavior data information of the user, the FCM fuzzy clustering algorithm is introduced, the real-time operation data information of the electric power payment channels in the target area is clustered through the FCM fuzzy clustering algorithm, the payment flow membership of each electric power payment channel in the current time scale is acquired, a clustering deviation prediction model is constructed, the deviation index calculation is carried out on the payment flow membership of each electric power payment channel in the current time scale through the clustering deviation prediction model, the deviation index information is acquired, the payment flow membership is updated finally according to the deviation index information, a new payment flow membership is generated, and intelligent recommendation is carried out on the payment channels based on the new payment flow membership. According to the invention, the clustering algorithm is introduced to cluster the behavior information of the user payment, so that the real-time flow membership of each payment channel is determined, and the real-time payment behavior of the user can be rapidly evaluated; on the other hand, the method and the device for predicting the flow of the payment channel by using the clustering deviation prediction model are used for calculating the deviation index of the membership of the flow of the real-time payment channel, and can further perform fuzzy clustering evaluation on the flow information of the payment channel and judge whether deviation occurs in the clustering process, so that the prediction accuracy of the flow information of the payment channel is improved.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows an overall method flow chart of an intelligent recommendation method for an electric power payment channel based on dynamic prediction;
FIG. 2 shows a first method flow diagram of an intelligent recommendation method for a power payment channel based on dynamic prediction;
FIG. 3 shows a second method flow diagram of a dynamic prediction-based intelligent recommendation method for electric power payment channels;
FIG. 4 shows a system block diagram of an intelligent recommendation system for electric power payment channels based on dynamic prediction.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
As shown in fig. 1, the first aspect of the present invention provides an intelligent recommendation method for a power payment channel based on dynamic prediction, which comprises the following steps:
s102, acquiring payment behavior data information of a user in a target area, determining an electric power payment channel in the target area according to the payment behavior data information of the user, and acquiring real-time operation data information of the electric power payment channel in the target area;
as shown in fig. 2, in the step S102, it is to be noted that specifically including:
s202, acquiring payment behavior data information of a user in a target area, and tracing payment channels on the payment behavior data information of the user in the target area to generate payment behavior quantity information of each payment channel within a preset time;
s204, setting related payment behavior data threshold data information, and comparing the payment behavior quantity information of each payment channel within preset time with the related payment behavior data threshold data information to obtain deviation rate;
S206, judging whether the deviation rate is larger than a preset deviation rate threshold value, and if the deviation rate is larger than the preset deviation rate threshold value, taking a payment channel corresponding to the deviation rate larger than the preset deviation rate threshold value as a power payment channel in the target area;
and S208, if the deviation rate is not greater than the preset deviation rate threshold, eliminating the payment channels corresponding to the deviation rate which is not greater than the preset deviation rate threshold, and simultaneously updating the electric power payment channels in the target area in real time.
The payment behavior quantity information is the information of the number of people in each payment channel, the information of the click rate of the web page in the payment channel, and the like in unit time. By the method, the paralyzed or unused payment channels can be removed, so that the identification of the electric power payment channels in the target area is more reasonable.
S104, introducing an FCM fuzzy clustering algorithm, and clustering real-time operation data information of the electric power payment channels in the target area through the FCM fuzzy clustering algorithm to acquire the membership degree of the payment flow of each electric power payment channel in the current time scale;
in step S104, the method specifically includes:
constructing a sample data set according to real-time operation data information of the electric power payment channel in the target area, introducing an FCM fuzzy clustering algorithm, initializing the number of clustering centers, and calculating the Euclidean distance from each sample data in the sample data set to the clustering centers;
The Euclidean distance between each sample data and each cluster center is obtained, the Euclidean distance between each sample data and each cluster center is ordered, an Euclidean distance ordering result is obtained, each sample data is classified according to the minimum Euclidean distance in the Euclidean distance ordering result, and each sample data classification result is obtained;
acquiring Euclidean distance of each sample data in each sample data classification result, setting an average Euclidean distance threshold, counting the Euclidean distance of each sample data in each sample data classification result, acquiring a total Euclidean distance value, and calculating the average Euclidean distance of the sample data according to the total Euclidean distance value;
introducing a genetic algorithm, setting a genetic algebra through the genetic algorithm when the average Euclidean distance of the sample data is lower than the average Euclidean distance threshold, carrying out iterative operation on the number of the clustering centers until the average Euclidean distance of the sample data is lower than the average Euclidean distance threshold, updating the number of the clustering centers, and finally carrying out data classification to obtain the membership degree of the payment flow of each electric power payment channel in the current time scale.
The method is characterized in that the number of the clustering centers is calculated iteratively by introducing a genetic algorithm, so that the accuracy of classifying the real-time operation data information of the electric power payment channel in the target area can be improved. The real-time operation data information of the electric power payment channels in the target area comprises real-time number information of each payment channel in unit time, real-time webpage click rate information of the payment channels and the like.
S106, constructing a clustering deviation prediction model, and calculating a deviation index of the membership degree of the payment flow of each electric power payment channel in the current time scale through the clustering deviation prediction model to acquire deviation index information;
in step S106, the method specifically includes:
acquiring the Euclidean distance from each sample data to a clustering center according to the membership degree of the payment flow of each electric power payment channel in the current time scale, and constructing a clustering deviation prediction model;
and calculating deviation index information based on a cluster deviation prediction model and Euclidean distance from each sample data to a cluster center, wherein the cluster deviation prediction model meets the following relational expression:
；
wherein p is the deviation index; n is the number of sample data; i represents the sequence number of the ith sample data; m is the number of clustering centers; j represents the serial number of the jth cluster center;representing real-time sample data->Is a Euclidean distance of (2); />Representing the ith sample data in the last time scale; />Representing the jth cluster center in the last time scale; a is the number of Euclidean distances in the previous time scale; k is the sequence number of the kth euclidean distance in the last time scale.
It should be noted that, each cluster set obtained through the clustering algorithm is a degree of membership of a payment behavior of a user, for example, 60 people are paid in a unit time, the value represents a smooth payment channel, for example, 1000 people are paid in a unit time, the value represents a busy payment channel, the implementation is merely exemplary and not limiting the setting principle, and a person skilled in the art can set according to actual requirements.
Over time, the behavior of the user may change to some extent, and the corresponding cluster center point may also change, where the deviation index indicates the difference between each data in the data set and the cluster center, and the larger the deviation index, the worse the classification effect of the sample data is represented. The clustering effect can be evaluated by the method, so that the clustering effect can be timely adjusted according to the deviation index.
S108, updating the membership degree of the payment flow according to the deviation index information, generating a new membership degree of the payment flow, and intelligently recommending the payment channel based on the new membership degree of the payment flow.
Further, in a preferred embodiment of the present invention, the membership degree of the payment flow is updated according to the deviation index information to generate a new membership degree of the payment flow, which specifically includes the following steps:
setting deviation index threshold information, judging whether the deviation index information is larger than the deviation index threshold information, and outputting the current payment flow membership degree if the deviation index information is not larger than the deviation index threshold information;
if the deviation index information is larger than the deviation index threshold information, resetting the number of the clustering centers, and performing iterative computation on the number of the clustering centers through a genetic algorithm to generate new clustering centers;
And redistributing the current sample data according to the clustering center, generating new payment flow membership, and outputting the new payment flow membership.
By the method, the payment flow clustering effect of the current time scale can be further improved, so that the classification accuracy of the payment flow data is improved, and more accurate payment channel flow data is provided for a user to refer to.
As shown in fig. 3, in a further preferred embodiment of the present invention, intelligent recommendation is performed on a payment channel based on a new payment flow membership, which specifically includes:
s302, acquiring payment flow membership of each payment channel based on the new payment flow membership, and acquiring historical payment paralysis probability information corresponding to the payment flow membership of each payment channel through big data;
s304, constructing a feature matrix according to historical payment paralysis probability information corresponding to the membership of the payment flow of each payment channel, simultaneously, introducing a feature sequencing CMFS (continuous matrix motion) sequencing algorithm to calculate redundant features in the feature matrix, and removing the redundant features to generate a corrected feature matrix;
s306, constructing a payment paralysis probability prediction model based on the deep learning network, inputting the corrected feature matrix into the payment paralysis probability prediction model for coding learning, and storing model parameters and outputting the payment paralysis probability prediction model after the payment paralysis probability prediction model meets the preset requirements;
S308, predicting paralysis probability values corresponding to the membership of the payment flow of each current payment channel through a payment paralysis probability prediction model, setting priority orders according to the paralysis probability values corresponding to the membership of the payment flow of each current payment channel, and performing intelligent recommendation based on the priority orders.
The method is characterized in that redundant features in the feature matrix are calculated by introducing a feature sequencing CMFS sequencing algorithm, and the redundant features are removed to generate a corrected feature matrix, so that on one hand, the calculated amount of the model is reduced, and on the other hand, the prediction precision of the payment paralysis probability prediction model is improved. According to the method, the paralysis probability value corresponding to the membership degree of the payment flow of each payment channel can be calculated, so that a more suitable payment channel can be provided for a user when payment time with busy payment is paid.
The invention can cluster the behavior information of user payment by introducing a clustering algorithm, thereby determining the real-time flow membership of each payment channel and rapidly evaluating the real-time payment behavior of the user; on the other hand, the method and the device for predicting the flow of the payment channel by using the clustering deviation prediction model are used for calculating the deviation index of the membership of the flow of the real-time payment channel, and can further perform fuzzy clustering evaluation on the flow information of the payment channel and judge whether deviation occurs in the clustering process, so that the prediction accuracy of the flow information of the payment channel is improved.
In addition, the method can further comprise the following steps:
acquiring the payment flow limit bearing capacity of each payment channel, acquiring the payment flow data information of each payment channel in real time, and judging whether the payment flow data information of each payment channel exceeds the payment flow limit bearing capacity;
if the payment flow data information of the payment channel exceeds the payment flow limit bearing capacity, acquiring the payment channel information that the payment flow data information of the payment channel does not exceed the payment flow limit bearing capacity;
according to the payment flow data information of the payment channels, which does not exceed the payment flow limit bearing capacity, carrying out drainage distribution on the payment flow data information of each payment channel, and generating a drainage distribution result;
and sending related prompt information to related payment channels according to the drainage distribution result, and displaying according to a preset mode.
By means of the method, the payment flow data information of each payment channel can be drained according to the payment flow limit bearing capacity of each payment channel, normal operation of each payment channel is guaranteed, management of the optimized payment channel is achieved, and payment experience of a user is improved. The payment flow limit bearing capacity is a critical flow value when a payment channel is paralyzed, and the data can be obtained from the payment flow data when the historical paralysis is caused.
In addition, the method can further comprise the following steps:
constructing a time stamp, combining the time stamp and the drainage distribution result to construct a drainage distribution result based on a time sequence, and recording the historical payment success rate of the drainage distribution result based on the time sequence;
constructing a database, inputting the historical payment success rate of the drainage distribution result based on the time sequence into the database for storage, and acquiring the historical payment success rate of the current drainage distribution result through the database;
constructing a historical payment success rate ranking table, inputting the historical payment success rate of the current drainage allocation result into the historical payment success rate ranking table for ranking, and obtaining a historical payment success rate ranking result;
generating a payment channel priority according to the historical payment success rate sequencing result, generating a corresponding payment channel recommendation result based on the payment channel priority, and displaying the corresponding payment channel recommendation result according to a preset mode.
By the method, the payment success rate of each drainage distribution result can be recorded, so that the priority of the payment channel is generated according to the historical payment success rate sorting result, the corresponding recommendation result of the payment channel is generated based on the priority of the payment channel, and the recommendation rationality of the payment channel is improved.
As shown in fig. 4, the second aspect of the present invention provides an intelligent power payment channel recommendation system 4 based on dynamic prediction, the system includes a memory 41 and a processor 62, the memory 41 includes an intelligent power payment channel recommendation method program based on dynamic prediction, and when the intelligent power payment channel recommendation method program based on dynamic prediction is executed by the processor 62, the following steps are implemented:
acquiring payment behavior data information of a user in a target area, determining an electric power payment channel in the target area according to the payment behavior data information of the user, and acquiring real-time operation data information of the electric power payment channel in the target area;
introducing an FCM fuzzy clustering algorithm, and clustering real-time operation data information of the electric power payment channels in the target area through the FCM fuzzy clustering algorithm to obtain the payment flow membership of each electric power payment channel in the current time scale;
constructing a clustering deviation prediction model, and calculating a deviation index of the membership degree of the payment flow of each electric power payment channel in the current time scale through the clustering deviation prediction model to acquire deviation index information;
updating the membership degree of the payment flow according to the deviation index information, generating a new membership degree of the payment flow, and intelligently recommending the payment channel based on the new membership degree of the payment flow.
In the system, payment behavior data information of a user in a target area is acquired, and an electric power payment channel in the target area is determined according to the payment behavior data information of the user, and the system specifically comprises the following steps:
acquiring payment behavior data information of a user in a target area, and tracing payment channels on the payment behavior data information of the user in the target area to generate payment behavior quantity information of each payment channel within a preset time;
setting related payment behavior data threshold data information, and comparing the payment behavior quantity information of each payment channel within preset time with the related payment behavior data threshold data information to obtain deviation rate;
judging whether the deviation rate is larger than a preset deviation rate threshold value, and if the deviation rate is larger than the preset deviation rate threshold value, taking a payment channel corresponding to the deviation rate larger than the preset deviation rate threshold value as a power payment channel in the target area;
if the deviation rate is not greater than the preset deviation rate threshold, eliminating the payment channels corresponding to the deviation rate not greater than the preset deviation rate threshold, and simultaneously updating the electric power payment channels in the target area in real time.
In the system, an FCM fuzzy clustering algorithm is introduced, and the real-time operation data information of the electric power payment channels in the target area is clustered through the FCM fuzzy clustering algorithm to acquire the membership degree of the payment flow of each electric power payment channel in the current time scale, and the method specifically comprises the following steps:
Constructing a sample data set according to real-time operation data information of the electric power payment channel in the target area, introducing an FCM fuzzy clustering algorithm, initializing the number of clustering centers, and calculating the Euclidean distance from each sample data in the sample data set to the clustering centers;
the Euclidean distance between each sample data and each cluster center is obtained, the Euclidean distance between each sample data and each cluster center is ordered, an Euclidean distance ordering result is obtained, each sample data is classified according to the minimum Euclidean distance in the Euclidean distance ordering result, and each sample data classification result is obtained;
acquiring Euclidean distance of each sample data in each sample data classification result, setting an average Euclidean distance threshold, counting the Euclidean distance of each sample data in each sample data classification result, acquiring a total Euclidean distance value, and calculating the average Euclidean distance of the sample data according to the total Euclidean distance value;
introducing a genetic algorithm, setting a genetic algebra through the genetic algorithm when the average Euclidean distance of the sample data is lower than the average Euclidean distance threshold, carrying out iterative operation on the number of the clustering centers until the average Euclidean distance of the sample data is lower than the average Euclidean distance threshold, updating the number of the clustering centers, and finally carrying out data classification to obtain the membership degree of the payment flow of each electric power payment channel in the current time scale.
In the system, intelligent recommendation is carried out on the payment channel based on the new payment flow membership, and the system specifically comprises the following steps:
acquiring payment flow membership of each payment channel based on the new payment flow membership, and acquiring historical payment paralysis probability information corresponding to the payment flow membership of each payment channel through big data;
constructing a feature matrix according to historical payment paralysis probability information corresponding to the membership of the payment flow of each payment channel, simultaneously, introducing a feature sequencing CMFS (continuous matrix motion) sequencing algorithm to calculate redundant features in the feature matrix, and removing the redundant features to generate a corrected feature matrix;
constructing a payment paralysis probability prediction model based on the deep learning network, inputting the corrected feature matrix into the payment paralysis probability prediction model for coding learning, and storing model parameters and outputting the payment paralysis probability prediction model after the payment paralysis probability prediction model meets the preset requirements;
and predicting paralysis probability values corresponding to the membership of the payment flow of each current payment channel through a payment paralysis probability prediction model, setting priority orders according to the paralysis probability values corresponding to the membership of the payment flow of each current payment channel, and performing intelligent recommendation based on the priority orders.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. The intelligent recommendation method for the electric power payment channel based on dynamic prediction is characterized by comprising the following steps of:
acquiring payment behavior data information of a user in a target area, determining an electric power payment channel in the target area according to the payment behavior data information of the user, and acquiring real-time operation data information of the electric power payment channel in the target area;
introducing an FCM fuzzy clustering algorithm, and clustering real-time operation data information of the electric power payment channels in the target area through the FCM fuzzy clustering algorithm to obtain the membership of the payment flow of each electric power payment channel in the current time scale;
constructing a clustering deviation prediction model, and calculating deviation indexes of the membership of the payment flow of each electric power payment channel in the current time scale through the clustering deviation prediction model to obtain deviation index information;
Updating the payment flow membership according to the deviation index information, generating a new payment flow membership, and intelligently recommending the payment channel based on the new payment flow membership.
2. The intelligent recommendation method for the electric power payment channel based on dynamic prediction according to claim 1, wherein the method for intelligent recommendation for the electric power payment channel based on dynamic prediction is characterized by obtaining payment behavior data information of a user in a target area and determining the electric power payment channel in the target area according to the payment behavior data information of the user, and specifically comprises the following steps:
acquiring payment behavior data information of a user in a target area, and tracing payment channels of the payment behavior data information of the user in the target area to generate payment behavior quantity information of each payment channel within a preset time;
setting related payment behavior data threshold data information, and comparing the payment behavior quantity information of each payment channel within preset time with the related payment behavior data threshold data information to obtain deviation rate;
judging whether the deviation rate is larger than a preset deviation rate threshold value, and if the deviation rate is larger than the preset deviation rate threshold value, taking a payment channel corresponding to the deviation rate larger than the preset deviation rate threshold value as a power payment channel in a target area;
If the deviation rate is not greater than the preset deviation rate threshold, eliminating the payment channels corresponding to the deviation rate which is not greater than the preset deviation rate threshold, and updating the electric power payment channels in the target area in real time.
3. The intelligent recommendation method of the electric power payment channel based on dynamic prediction according to claim 1, wherein an FCM fuzzy clustering algorithm is introduced, real-time operation data information of the electric power payment channels in the target area is clustered through the FCM fuzzy clustering algorithm, and the membership degree of the payment flow of each electric power payment channel in the current time scale is obtained, and the method specifically comprises the following steps:
constructing a sample data set according to real-time operation data information of the electric power payment channel in the target area, introducing an FCM fuzzy clustering algorithm, initializing the number of clustering centers, and calculating the Euclidean distance from each sample data in the sample data set to the clustering centers;
the Euclidean distance between each sample data and each cluster center is obtained, the Euclidean distance between each sample data and each cluster center is ordered, an Euclidean distance ordering result is obtained, each sample data is classified according to the minimum Euclidean distance in the Euclidean distance ordering result, and each sample data classification result is obtained;
Acquiring Euclidean distance of each sample data in each sample data classification result, setting an average Euclidean distance threshold, counting the Euclidean distance of each sample data in each sample data classification result, acquiring a total Euclidean distance value, and calculating the average Euclidean distance of the sample data according to the total Euclidean distance value;
introducing a genetic algorithm, setting a genetic algebra through the genetic algorithm when the average Euclidean distance of the sample data is lower than the average Euclidean distance threshold, carrying out iterative operation on the number of clustering centers until the average Euclidean distance of the sample data is lower than the average Euclidean distance threshold, updating the number of the clustering centers, and finally carrying out data classification to obtain the membership degree of the payment flow of each electric power payment channel in the current time scale.
4. The intelligent recommendation method of the electric power payment channels based on dynamic prediction according to claim 1, wherein a cluster deviation prediction model is constructed, deviation index calculation is performed on the membership of the payment flow of each electric power payment channel in the current time scale through the cluster deviation prediction model, and deviation index information is obtained, and the method specifically comprises the following steps:
Acquiring Euclidean distance from each sample data to a clustering center according to the membership degree of the payment flow of each electric power payment channel in the current time scale, and constructing a clustering deviation prediction model;
calculating deviation index information based on a cluster deviation prediction model and the Euclidean distance between each sample data and a cluster center, wherein the cluster deviation prediction model meets the following relational expression:
；
wherein,pis a deviation index; n is the number of sample data; i represents the sequence number of the ith sample data; m is the number of clustering centers; j represents the serial number of the jth cluster center;representing real-time sample data->A Euclidean distance; />Representing the ith sample data in the last time scale; />Representing the jth cluster center in the last time scale; a is the number of Euclidean distances in the previous time scale; k is the sequence number of the kth euclidean distance in the last time scale.
5. The intelligent recommendation method of the electric power payment channel based on dynamic prediction according to claim 1, wherein the update of the payment flow membership according to the deviation index information generates a new payment flow membership, and specifically comprises the following steps:
Setting deviation index threshold information, judging whether the deviation index information is larger than the deviation index threshold information, and outputting the current payment flow membership degree if the deviation index information is not larger than the deviation index threshold information;
if the deviation index information is larger than the deviation index threshold information, resetting the number of the clustering centers, and performing iterative computation on the number of the clustering centers through a genetic algorithm to generate new clustering centers;
and redistributing the current sample data according to the clustering center, generating a new payment flow membership degree, and outputting the new payment flow membership degree.
6. The intelligent recommendation method for the electric power payment channel based on dynamic prediction according to claim 1, wherein intelligent recommendation is performed on the payment channel based on the new payment flow membership, and specifically comprises the following steps:
acquiring the payment flow membership of each payment channel based on the new payment flow membership, and acquiring historical payment paralysis probability information corresponding to the payment flow membership of each payment channel through big data;
constructing a feature matrix according to historical payment paralysis probability information corresponding to the membership of the payment flow of each payment channel, simultaneously, introducing a feature sequencing CMFS (complementary metal oxide semiconductor) sequencing algorithm to calculate redundant features in the feature matrix, and removing the redundant features to generate a corrected feature matrix;
Constructing a payment paralysis probability prediction model based on an deep learning network, inputting the corrected feature matrix into the payment paralysis probability prediction model for coding learning, and storing model parameters and outputting the payment paralysis probability prediction model after the payment paralysis probability prediction model meets the preset requirement;
and predicting paralysis probability values corresponding to the membership of the payment flow of each current payment channel through the payment paralysis probability prediction model, setting priority orders according to the paralysis probability values corresponding to the membership of the payment flow of each current payment channel, and performing intelligent recommendation based on the priority orders.
7. The intelligent power payment channel recommending system based on dynamic prediction is characterized by comprising a memory and a processor, wherein the memory comprises an intelligent power payment channel recommending method program based on dynamic prediction, and when the intelligent power payment channel recommending method program based on dynamic prediction is executed by the processor, the following steps are realized:
acquiring payment behavior data information of a user in a target area, determining an electric power payment channel in the target area according to the payment behavior data information of the user, and acquiring real-time operation data information of the electric power payment channel in the target area;
Introducing an FCM fuzzy clustering algorithm, and clustering real-time operation data information of the electric power payment channels in the target area through the FCM fuzzy clustering algorithm to obtain the membership of the payment flow of each electric power payment channel in the current time scale;
constructing a clustering deviation prediction model, and calculating deviation indexes of the membership of the payment flow of each electric power payment channel in the current time scale through the clustering deviation prediction model to obtain deviation index information;
updating the payment flow membership according to the deviation index information, generating a new payment flow membership, and intelligently recommending the payment channel based on the new payment flow membership.
8. The intelligent recommendation system for electric power payment channels based on dynamic prediction according to claim 7, wherein the system for intelligent recommendation for electric power payment channels based on dynamic prediction is characterized by obtaining payment behavior data information of users in a target area and determining electric power payment channels in the target area according to the payment behavior data information of the users, and specifically comprises:
acquiring payment behavior data information of a user in a target area, and tracing payment channels of the payment behavior data information of the user in the target area to generate payment behavior quantity information of each payment channel within a preset time;
Setting related payment behavior data threshold data information, and comparing the payment behavior quantity information of each payment channel within preset time with the related payment behavior data threshold data information to obtain deviation rate;
judging whether the deviation rate is larger than a preset deviation rate threshold value, and if the deviation rate is larger than the preset deviation rate threshold value, taking a payment channel corresponding to the deviation rate larger than the preset deviation rate threshold value as a power payment channel in a target area;
if the deviation rate is not greater than the preset deviation rate threshold, eliminating the payment channels corresponding to the deviation rate which is not greater than the preset deviation rate threshold, and updating the electric power payment channels in the target area in real time.
9. The intelligent recommendation system of power payment channels based on dynamic prediction according to claim 7, wherein an FCM fuzzy clustering algorithm is introduced, and real-time operation data information of the power payment channels in the target area is clustered through the FCM fuzzy clustering algorithm, so as to obtain the membership degree of the payment flow of each power payment channel in the current time scale, and the intelligent recommendation system specifically comprises the following steps:
constructing a sample data set according to real-time operation data information of the electric power payment channel in the target area, introducing an FCM fuzzy clustering algorithm, initializing the number of clustering centers, and calculating the Euclidean distance from each sample data in the sample data set to the clustering centers;
The Euclidean distance between each sample data and each cluster center is obtained, the Euclidean distance between each sample data and each cluster center is ordered, an Euclidean distance ordering result is obtained, each sample data is classified according to the minimum Euclidean distance in the Euclidean distance ordering result, and each sample data classification result is obtained;
acquiring Euclidean distance of each sample data in each sample data classification result, setting an average Euclidean distance threshold, counting the Euclidean distance of each sample data in each sample data classification result, acquiring a total Euclidean distance value, and calculating the average Euclidean distance of the sample data according to the total Euclidean distance value;
introducing a genetic algorithm, setting a genetic algebra through the genetic algorithm when the average Euclidean distance of the sample data is lower than the average Euclidean distance threshold, carrying out iterative operation on the number of clustering centers until the average Euclidean distance of the sample data is lower than the average Euclidean distance threshold, updating the number of the clustering centers, and finally carrying out data classification to obtain the membership degree of the payment flow of each electric power payment channel in the current time scale.
10. The intelligent recommendation system for electric power payment channels based on dynamic prediction according to claim 7, wherein intelligent recommendation is performed on the payment channels based on the new payment flow membership, and specifically comprises:
acquiring the payment flow membership of each payment channel based on the new payment flow membership, and acquiring historical payment paralysis probability information corresponding to the payment flow membership of each payment channel through big data;
constructing a feature matrix according to historical payment paralysis probability information corresponding to the membership of the payment flow of each payment channel, simultaneously, introducing a feature sequencing CMFS (complementary metal oxide semiconductor) sequencing algorithm to calculate redundant features in the feature matrix, and removing the redundant features to generate a corrected feature matrix;
constructing a payment paralysis probability prediction model based on an deep learning network, inputting the corrected feature matrix into the payment paralysis probability prediction model for coding learning, and storing model parameters and outputting the payment paralysis probability prediction model after the payment paralysis probability prediction model meets the preset requirement;
and predicting paralysis probability values corresponding to the membership of the payment flow of each current payment channel through the payment paralysis probability prediction model, setting priority orders according to the paralysis probability values corresponding to the membership of the payment flow of each current payment channel, and performing intelligent recommendation based on the priority orders.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310907936.1A CN117056591A (en) | 2023-07-24 | 2023-07-24 | Intelligent electric power payment channel recommendation method and system based on dynamic prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310907936.1A CN117056591A (en) | 2023-07-24 | 2023-07-24 | Intelligent electric power payment channel recommendation method and system based on dynamic prediction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117056591A true CN117056591A (en) | 2023-11-14 |
Family
ID=88656365
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310907936.1A Pending CN117056591A (en) | 2023-07-24 | 2023-07-24 | Intelligent electric power payment channel recommendation method and system based on dynamic prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117056591A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117808024A (en) * | 2024-02-29 | 2024-04-02 | 深圳市捷通科技有限公司 | Reader-writer equipment management method and system based on self-adaptive regulation and control |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105260815A (en) * | 2015-09-18 | 2016-01-20 | 国网辽宁省电力有限公司鞍山供电公司 | Electric power system payment channel evaluating method based on large data |
| CN106650763A (en) * | 2016-07-05 | 2017-05-10 | 国网内蒙古东部电力有限公司电力科学研究院 | Calculating method of index selection, weight optimization and channel planning of electric power payment channel analysis |
| CN107423859A (en) * | 2017-08-07 | 2017-12-01 | 国家电网公司客户服务中心 | A kind of built-up pattern modeling method and system |
| CN109523246A (en) * | 2018-10-25 | 2019-03-26 | 云南电网有限责任公司昆明供电局 | Subscriber payment channel method and device for planning |
| CN111062757A (en) * | 2019-12-17 | 2020-04-24 | 山大地纬软件股份有限公司 | Information recommendation method and system based on multi-path optimization matching |
| CN111221868A (en) * | 2018-11-26 | 2020-06-02 | 国网上海市电力公司 | Data mining and analyzing method applied to channel preference of power customer |
| US20200356964A1 (en) * | 2019-05-06 | 2020-11-12 | Alibaba Group Holding Limited | Payment channel recommendation |
| CN114022205A (en) * | 2021-11-05 | 2022-02-08 | 国网江苏省电力有限公司营销服务中心 | Power consumer payment channel preference matching method and system based on improved clustering method |
| CN115221404A (en) * | 2022-07-15 | 2022-10-21 | 辽宁工程技术大学 | Recommendation method for optimizing fuzzy clustering by using moth fire-fighting algorithm |
| CN115496338A (en) * | 2022-09-02 | 2022-12-20 | 国家电网有限公司客户服务中心 | Electric power payment channel drainage method, system and medium based on big data technology |
-
2023
- 2023-07-24 CN CN202310907936.1A patent/CN117056591A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105260815A (en) * | 2015-09-18 | 2016-01-20 | 国网辽宁省电力有限公司鞍山供电公司 | Electric power system payment channel evaluating method based on large data |
| CN106650763A (en) * | 2016-07-05 | 2017-05-10 | 国网内蒙古东部电力有限公司电力科学研究院 | Calculating method of index selection, weight optimization and channel planning of electric power payment channel analysis |
| CN107423859A (en) * | 2017-08-07 | 2017-12-01 | 国家电网公司客户服务中心 | A kind of built-up pattern modeling method and system |
| CN109523246A (en) * | 2018-10-25 | 2019-03-26 | 云南电网有限责任公司昆明供电局 | Subscriber payment channel method and device for planning |
| CN111221868A (en) * | 2018-11-26 | 2020-06-02 | 国网上海市电力公司 | Data mining and analyzing method applied to channel preference of power customer |
| US20200356964A1 (en) * | 2019-05-06 | 2020-11-12 | Alibaba Group Holding Limited | Payment channel recommendation |
| CN111062757A (en) * | 2019-12-17 | 2020-04-24 | 山大地纬软件股份有限公司 | Information recommendation method and system based on multi-path optimization matching |
| CN114022205A (en) * | 2021-11-05 | 2022-02-08 | 国网江苏省电力有限公司营销服务中心 | Power consumer payment channel preference matching method and system based on improved clustering method |
| CN115221404A (en) * | 2022-07-15 | 2022-10-21 | 辽宁工程技术大学 | Recommendation method for optimizing fuzzy clustering by using moth fire-fighting algorithm |
| CN115496338A (en) * | 2022-09-02 | 2022-12-20 | 国家电网有限公司客户服务中心 | Electric power payment channel drainage method, system and medium based on big data technology |
Non-Patent Citations (3)
| Title |
|---|
| 金媛媛: "渠道引流推荐研究", 电子技术与软件工程, no. 1, 15 January 2020 (2020-01-15) * |
| 陆伟伟;刘解放;霍尧;于晨;王士同;: "基于模糊聚类的用电客户交费渠道偏好研究", 计算机工程与应用, no. 19, 1 October 2016 (2016-10-01) * |
| 黄金凤;雷筱珍;: "基于蚁群模糊聚类的协同过滤推荐算法", 湖南工程学院学报(自然科学版), no. 04, 25 December 2011 (2011-12-25) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117808024A (en) * | 2024-02-29 | 2024-04-02 | 深圳市捷通科技有限公司 | Reader-writer equipment management method and system based on self-adaptive regulation and control |
| CN117808024B (en) * | 2024-02-29 | 2024-05-07 | 深圳市捷通科技有限公司 | Reader-writer equipment management method and system based on self-adaptive regulation and control |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110119948B (en) | Power consumer credit evaluation method and system based on time-varying weight dynamic combination | |
| CN109389321B (en) | Item list classification method and device | |
| CN117494072B (en) | Method and system for monitoring operation state of battery-changing cabinet based on data fusion | |
| CN117056591A (en) | Intelligent electric power payment channel recommendation method and system based on dynamic prediction | |
| CN111191814A (en) | Electricity price prediction method, system and computer readable storage medium | |
| CN116340586B (en) | Cloud platform-based automobile fault management method, system and storage medium | |
| CN110858219A (en) | Logistics object information processing method and device and computer system | |
| CN108399553A (en) | It is a kind of to consider geographical and circuit subordinate relation user characteristics label setting method | |
| CN114004654A (en) | Internet card user portrait construction method and system based on big data analysis | |
| CN114170002A (en) | Method and device for predicting access frequency | |
| CN106997371B (en) | Method for constructing single-user intelligent map | |
| CN117575858B (en) | Management method, system and storage medium of intelligent course arrangement system | |
| CN115982646B (en) | Management method and system for multisource test data based on cloud platform | |
| CN115860548B (en) | SaaS one-stop platform management method, system and medium based on big data | |
| CN113420165B (en) | Training of classification model and classification method and device of multimedia data | |
| CN115936184A (en) | Load prediction matching method suitable for multi-user types | |
| CN113298120B (en) | Fusion model-based user risk prediction method, system and computer equipment | |
| CN115330201A (en) | Power grid digital project pareto optimization method and system | |
| CN114581098A (en) | Passenger group classification method and device, computer equipment and storage medium | |
| CN113821717A (en) | Information processing method, information processing apparatus, storage medium, and electronic device | |
| CN117540101B (en) | Online bookend management method and system based on artificial intelligence | |
| CN112308340A (en) | Power data processing method and device | |
| CN110059219A (en) | A kind of video preference prediction technique, device, equipment and readable storage medium storing program for executing | |
| CN116468271B (en) | Enterprise risk analysis method, system and medium based on big data | |
| CN116681266B (en) | Production scheduling method and system of mirror surface electric discharge machine |
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 |