CN112598443A - Online channel business data processing method and system based on deep learning - Google Patents
Online channel business data processing method and system based on deep learning Download PDFInfo
- Publication number
- CN112598443A CN112598443A CN202011565296.3A CN202011565296A CN112598443A CN 112598443 A CN112598443 A CN 112598443A CN 202011565296 A CN202011565296 A CN 202011565296A CN 112598443 A CN112598443 A CN 112598443A
- Authority
- CN
- China
- Prior art keywords
- data
- deep learning
- channel
- business
- online channel
- 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
- 238000013135 deep learning Methods 0.000 title claims abstract description 37
- 238000003672 processing method Methods 0.000 title claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 230000007787 long-term memory Effects 0.000 claims abstract description 10
- 238000003062 neural network model Methods 0.000 claims abstract description 10
- 230000006403 short-term memory Effects 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 23
- 230000015654 memory Effects 0.000 claims description 11
- 230000005611 electricity Effects 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 8
- 230000004927 fusion Effects 0.000 claims description 7
- 230000006399 behavior Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 5
- 238000005192 partition Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 241000282813 Aepyceros melampus Species 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 2
- 238000013500 data storage Methods 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 claims description 2
- 238000007689 inspection Methods 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 16
- 238000007418 data mining Methods 0.000 abstract description 4
- 230000008447 perception Effects 0.000 abstract 1
- 238000004422 calculation algorithm Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000013079 data visualisation Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013439 planning Methods 0.000 description 2
- 241000220317 Rosa Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06F16/904—Browsing; Visualisation therefor
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- 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
-
- 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
- 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)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Accounting & Taxation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Finance (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a deep learning-based online channel business data processing method and system, which are used for acquiring operation data and power consumption customer data of each online channel; preprocessing the acquired data to obtain data with a uniform format; inputting the preprocessed data into a preset long-term and short-term memory neural network model to obtain various service handling trend data and risk point data of the online channel; fusing historical data, service handling trend data and risk point data to obtain multidimensional data based on dates, units and channels, and conducting service guidance according to the obtained multidimensional data; the method adopts deep learning and expands a multivariate data mining analysis model, improves the data prediction precision, realizes the prediction of various service handling trends and possible risk points of the predicted online channels, drives the marketing lean management in a digital mode, and improves the perception, analysis and control capability of the marketing operation condition.
Description
Technical Field
The disclosure relates to the technical field of data processing, in particular to a method and a system for processing online channel business data based on deep learning.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
At present, aiming at each pair of external service online channels of a power company, channel operation data analysis, deep fusion mobile operation application, business hall intellectualization, data mining and sharing are strengthened, an online and offline integrated service mode is created, a channel service mode and a user portrait are mined and analyzed, medium and short-term online channel service behavior trend prediction is researched, an operation strategy is made in a targeted mode, various online national network APP and other channel operation activities are supported comprehensively, various service values are promoted to be created together, and service channel application is deepened comprehensively.
The problems of the power company in the aspect of channel operation analysis at present mainly include:
(1) the method has the advantages that the existing company has scattered online channels, crossed channel businesses, unshared public services, independent and longitudinal development of unit businesses, no fusion in the transverse direction, scattered business data resources, complex cross-professional data integration relation and non-uniform data of each channel. Analysis and operation of each channel lack powerful technical support, business development trend prediction of the channel and basis and mechanism of service resource scheduling and distribution.
(2) In the process of deeply promoting the 'internet +' power supply service, the cooperation mechanism of province, city and county integrated systems and the cooperation mechanism of online and offline services are not sound enough, and the service fusion transition from offline to online needs to be accelerated. The advantages of the power grid, the technology and the information platform of the company are combined, internal and external resources are further integrated, cross-domain and multi-dimensional value-added services are provided for users, and the market influence of the company in each channel is improved.
(3) The method has the advantages that a large amount of stored data is obtained, the data value utilization is not high, a large amount of business data are accumulated since each online channel is online, the real-time business handling amount is huge, the data sources and the recording modes of each channel are different, a large amount of data are irrelevant information, the value density and the authenticity of the channel operation data are greatly influenced, the accuracy of analysis of each channel operation data is greatly influenced by the difference, and the data value utilization is low at present.
Disclosure of Invention
In order to solve the defects of the prior art, the disclosure provides an online channel business data processing method and system based on deep learning, aiming at realizing the operation monitoring and operation management of online and offline channels, constructing a channel service panoramic view, providing data support for the operation management and control of the channels, namely combining variable information of the channels, dates, units and the like, carrying out business analysis and trend prediction by deep learning according to a large amount of real-time data, historical data, structured data and unstructured data by collecting account information and user behavior data of each channel and each unit, predicting and quantifying various business handling trends and possible risk points of the online channels, improving the prediction precision, showing the data change trend of each time period, providing data support for the operation activity planning and risk management and control of the channels, and the co-creation of various service values is promoted.
In order to achieve the purpose, the following technical scheme is adopted in the disclosure:
the first aspect of the disclosure provides an online channel business data processing method based on deep learning.
A deep learning-based online channel business data processing method comprises the following steps:
acquiring operation data and electricity consumption customer data of each channel on line;
preprocessing the acquired data to obtain data with a uniform format;
inputting the preprocessed data into a preset long-term and short-term memory neural network model to obtain various service handling trend data and risk point data of the online channel;
and fusing the historical data, the business handling trend data and the risk point data to obtain multidimensional data based on dates, units and channels, and conducting business guidance according to the obtained multidimensional data.
The second aspect of the disclosure provides an online channel business data processing system based on deep learning.
An online channel business data processing system based on deep learning, comprising:
a data acquisition module configured to: acquiring operation data and electricity consumption customer data of each channel on line;
a data pre-processing module configured to: preprocessing the acquired data to obtain data with a uniform format;
a data prediction module configured to: inputting the preprocessed data into a preset long-term and short-term memory neural network model to obtain various service handling trend data and risk point data of the online channel;
a data fusion module configured to: and fusing the historical data, the business handling trend data and the risk point data to obtain multidimensional data based on dates, units and channels, and conducting business guidance according to the obtained multidimensional data.
A third aspect of the present disclosure provides a computer-readable storage medium, on which a program is stored, which when executed by a processor, implements the steps in the deep learning-based online channel business data processing method according to the first aspect of the present disclosure.
A fourth aspect of the present disclosure provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor, where the processor executes the program to implement the steps in the method for processing online channel business data based on deep learning according to the first aspect of the present disclosure.
Compared with the prior art, the beneficial effect of this disclosure is:
1. according to the online channel business data processing method based on deep learning, deep learning is adopted, the multivariate data mining analysis model is expanded, the data prediction precision is improved, the prediction of various business handling trends and possible risk points of online channels is realized, the marketing lean management is driven in a digital mode, and the sensing, analysis and control capacity of marketing operation conditions is improved.
2. According to the content disclosed by the disclosure, through the online channel business data processing method based on deep learning, the analysis of channel operation data is strengthened, the mobile operation application, the business hall intellectualization, the data mining and sharing are deeply integrated, the operation activities of each channel are comprehensively supported, the co-creation of various business values is promoted, and the service channel application is comprehensively deepened.
3. According to the content, the method for processing the online channel business data based on deep learning accelerates the fusion and transformation of services from offline to online, integrates internal and external resources, provides cross-domain and multi-dimensional value-added services for users, and improves the market share and influence of the own channel of the power company.
Advantages of additional aspects of the disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the disclosure.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and are not to limit the disclosure.
Fig. 1 is a schematic flow chart of an online channel business data processing method based on deep learning according to embodiment 1 of the present disclosure.
Detailed Description
The present disclosure is further described with reference to the following drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
Example 1:
as shown in fig. 1, an embodiment 1 of the present disclosure provides an online channel business data processing method based on deep learning, including the following steps:
acquiring operation data and electricity consumption customer data of each channel on line;
preprocessing the acquired data to obtain data with a uniform format;
inputting the preprocessed data into a preset long-term and short-term memory neural network model to obtain various service handling trend data and risk point data of the online channel;
and fusing the historical data, the business handling trend data and the risk point data to obtain multidimensional data based on dates, units and channels, and conducting business guidance according to the obtained multidimensional data.
Specifically, the method comprises the following steps:
s1: business diagnosis and demand investigation
Related business data of business pain points and typical channel application scenes of the power company are combed, and then business requirements are analyzed.
Service pain point: each channel is provided with a website or APP software, so that the management is troublesome; the data counted by each channel is inconsistent, and the data counted by which channel is not known as the standard; too many products corresponding to the channels are troublesome to popularize; it cannot be seen that the services corresponding to each channel are different, and the conditions of the services cannot be comprehensively known.
Service data: the system comprises operation data, business data, activity data, power utilization customer archive information and the like of channels such as a network of China, a palm power SD, a 95598 intelligent website and the like, wherein the types of the channels comprise structured data and unstructured data.
Service requirements are as follows: by combining variable information of channels, dates, units and the like, by collecting account information and user behavior data of each channel and each unit, according to business analysis and prediction of a large amount of real-time data and historical data, the operation development rule of the channels is mastered, the data change trend of each time period is accurately displayed, and data support is provided for operation activity planning and risk control of the channels by combining the operation rule and the time change trend of each channel.
S2: data access
Based on a cloud platform and a Hadoop big data platform, a data middle platform framework is constructed, and components such as kudu, hdfs, hive, impala, spark, flink, kafka, rds, drds, dts and gbase are applied to realize storage and classification of accessed historical data, real-time data, structured data and unstructured data.
The method comprises the steps of deploying various data access modes such as a real-time message queue, an ETL (extract transform load), a Webservie, an ESB (enterprise service bus), an OGG (open customer service) and the like according to the difference of the type, real-time performance and data volume of external system data, and accessing structured data such as user information, orders, operation classes, integral activities and the like of an Internet and a national network, unstructured data of a user operation behavior log, user operation behavior data of a palm power SD, payment data of a treasure, WeChat and the like, business orders, processes and electricity consumption customer data of a marketing system and unstructured data of a business hall video into OSS (operating system) of a data center platform and a cloud platform respectively.
And formulating corresponding data storage and data processing schemes according to different data sources and data access modes. The method comprises the steps of accessing operation data of a network of the Internet and the country, storing the operation data in Gbase, performing data processing in the Gbase, creating a Mysql partition table to store the data, performing data processing according to service logic to form an index result table, judging whether a result is accurate, setting a daily automatic operation workflow including a historical data workflow and a data transmission workflow if the result is accurately transmitted to RDS by a key, and analyzing the service again to perform data processing if the result is not accurate.
The palm electric power SD operation data and the payment transaction service data are accessed by a marketing check platform IDM, an index result table is formed by using an IMPALA calculation method according to service logic, whether the result data are accurate or not is judged, if the result data are accurate, the calculation result is stored in a HIVE library and is sent to an RSD by using DataX, a daily workflow is set to partition the HIVE according to time, index types and frequency, later maintenance is facilitated, and if the result data are not accurate, the service is analyzed again to perform data processing.
S3: data management and cleaning: and carrying out data cleaning and data conversion on operation data and power consumption customer data collected from the Internet, the national network, the palm power SD, the 95598 intelligent website, the Payment treasure, the WeChat and other channels to form a data set which has typical characteristics and can be analyzed.
S4: selecting a data training sample, training a data set: selecting a characteristic data training sample set according to the training characteristics of the long-term and short-term memory neural network, defining the key data category and the label of the structured data, extracting the bottom characteristic and the label of the unstructured data, loading the data into a python visualization tool for preliminary analysis, and preliminarily selecting 200000 samples;
determining an RNN structure and a network structure, and preliminarily determining: RNN is divided into 2 types, the length of each type is 24, the length of each type is 30, and the number of network layers is 3; dividing the processed samples into a training set, a verification set and a test set, wherein the proportion of the processed samples in the total samples is as follows: 60%, 10% and 30%;
determining indexes of a single evaluation algorithm, mainly focusing on precision (precision) and recall (call), considering both indexes (F1 or area under ROC curve), and combining the indexes with a model loss rate;
the training set and test set data are normalized/normalized: the method is characterized by unifying dimensions, facilitating calculation of gradients, accelerating convergence and the like, mainly acquiring the maximum value, the minimum value, the average value, the variance and the standard deviation of data, printing and outputting, normalizing by using max-min or z-scores, and selecting an optimal processing mode in the subsequent training process.
S5: training a neural network algorithm model to obtain an optimal algorithm model and parameters: according to the scheme, a TensorFlow deep learning technology framework and a Python language are selected to carry out specific training work.
Selecting and constructing a long-short term memory neural network (LSTM) regression prediction model; setting initial parameters, wherein the main parameters are as follows: the number of the neurons is 40, the number of network layers is 3 (a hidden layer is 1), the time step is 24, the dimension of an input layer is 6, an output layer is 1, and the initial learning rate is 0.01; defining a loss function; the number of initial training times is 10000; dropout is set to 0.5; and selecting an adaptive gradient descent algorithm for training.
And (3) formally training the algorithm model by using the training sample set and the verification sample set, observing the model loss rate, precision ratio and recall ratio training indexes at any time, discarding when the training index (precision ratio) is less than 99 percent, and obtaining the weight of the primary full-connection layer and the algorithm model with verification when the training index (precision ratio) reaches more than 99 percent. And identifying results by using the model, and performing weighted summation to obtain a predicted value. The predicted value and the test set are checked and compared (mainly by curve superposition comparison), parameters and network structure adjustment and repeated training processes are carried out, the optimization adjustment and debugging for more than 1000 times are carried out, a relatively optimal algorithm model is selected, and the prediction accuracy rate reaches more than 99.5%.
Aiming at the over-fitting problem in the training process, a regularization and discarding method, a dropout method, a BN layer and other means and methods are adopted; aiming at the under-fitting problem, a method for increasing the depth (layer number) of the network and the number of the neurons is mainly adopted; increasing the data volume of the training set; and synchronously substituting the predicted value into the restored service data, and simulating and verifying scenes such as access, payment, service handling, activities and the like of each channel to obtain the optimal algorithm and parameter which is closest to the actual service.
S6: model application and data visualization analysis: the model is applied to channel business prediction analysis, the processing trend of various businesses of the online channel and possible risk points are predicted and quantified, and the prediction precision is improved. Based on historical data and prediction trends, a data visualization display mode is formulated, multidimensional data analysis and prediction work such as regional analysis, time analysis, channel analysis and the like is carried out according to dimensions such as dates, units and channels, and operation control and risk prevention and control of service channels are achieved.
In S6, the data visualization display mode mainly comprises display modes such as a bar chart, a ring chart, a radar chart, a rose chart, a pie chart and a line chart, and the complex patterns and the multi-level data information are displayed by utilizing the mixed display mode.
Example 2:
the embodiment 2 of the present disclosure provides an online channel business data processing system based on deep learning, including:
a data acquisition module configured to: acquiring operation data and electricity consumption customer data of each channel on line;
a data pre-processing module configured to: preprocessing the acquired data to obtain data with a uniform format;
a data prediction module configured to: inputting the preprocessed data into a preset long-term and short-term memory neural network model to obtain various service handling trend data and risk point data of the online channel;
a data fusion module configured to: and fusing the historical data, the business handling trend data and the risk point data to obtain multidimensional data based on dates, units and channels, and conducting business guidance according to the obtained multidimensional data.
The working method of the system is the same as the method for processing the online channel service data based on deep learning provided in embodiment 1, and details are not repeated here.
Example 3:
the embodiment 3 of the present disclosure provides a computer-readable storage medium, on which a program is stored, where the program, when executed by a processor, implements the steps in the method for processing the service data of the online channel based on deep learning according to the embodiment 1 of the present disclosure, where the steps are:
acquiring operation data and electricity consumption customer data of each channel on line;
preprocessing the acquired data to obtain data with a uniform format;
inputting the preprocessed data into a preset long-term and short-term memory neural network model to obtain various service handling trend data and risk point data of the online channel;
and fusing the historical data, the business handling trend data and the risk point data to obtain multidimensional data based on dates, units and channels, and conducting business guidance according to the obtained multidimensional data.
The detailed steps are the same as those of the method for processing the online channel business data based on deep learning provided in embodiment 1, and are not described herein again.
Example 4:
an embodiment 4 of the present disclosure provides an electronic device, including a memory, a processor, and a program stored in the memory and capable of running on the processor, where the processor executes the program to implement the steps in the method for processing online channel business data based on deep learning according to the first aspect of the present disclosure, where the steps are:
acquiring operation data and electricity consumption customer data of each channel on line;
preprocessing the acquired data to obtain data with a uniform format;
inputting the preprocessed data into a preset long-term and short-term memory neural network model to obtain various service handling trend data and risk point data of the online channel;
and fusing the historical data, the business handling trend data and the risk point data to obtain multidimensional data based on dates, units and channels, and conducting business guidance according to the obtained multidimensional data.
The detailed steps are the same as those of the method for processing the online channel business data based on deep learning provided in embodiment 1, and are not described herein again.
As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Claims (10)
1. A method for processing online channel business data based on deep learning is characterized in that: the method comprises the following steps:
acquiring operation data and electricity consumption customer data of each channel on line;
preprocessing the acquired data to obtain data with a uniform format;
inputting the preprocessed data into a preset long-term and short-term memory neural network model to obtain various service handling trend data and risk point data of the online channel;
and fusing the historical data, the business handling trend data and the risk point data to obtain multidimensional data based on dates, units and channels, and conducting business guidance according to the obtained multidimensional data.
2. The deep learning-based online channel business data processing method of claim 1, wherein:
the operation data and the electricity utilization customer data of each channel at least comprise: the operation data, the business data, the activity data and the electric customer file information data of the Internet, the palm power SD and 95598 intelligent websites.
3. The deep learning-based online channel business data processing method of claim 1, wherein:
and acquiring popularization, registration, binding and active account information and user behavior data of each channel and each date of each unit by combining the channel, date and unit variable information.
4. The deep learning-based online channel business data processing method of claim 1, wherein:
training of the long-short term memory neural network model, comprising:
selecting a characteristic data training sample set, defining the key data category and label of the structured data, extracting the bottom characteristic and label of the unstructured data, and selecting sample data with preset quantity;
determining an RNN structure and a network structure, dividing the processed samples into a training set, a verification set and a test set, and performing proportional allocation on the data sets;
and (3) carrying out model training and verification by using the distributed data set and adopting a TensorFlow deep learning technical framework and a Python language.
5. The deep learning-based online channel business data processing method of claim 1, wherein:
according to the difference of the type, real-time performance and data volume of external system data, a plurality of data access modes are deployed and respectively accessed into the OSS of the data center platform and the cloud platform, and data storage and data processing are carried out according to the difference of data sources and data access modes.
6. The deep learning-based online channel business data processing method of claim 1, wherein:
storing the accessed operation data of the network in Gbase, performing the data processing in Gbase, and storing the data by creating a Mysql partition table;
processing data according to the service logic to form an index result table, judging whether the result is accurate, and if so, sending the result to the RDS by using a key;
and setting daily automatic operation workflows comprising historical data workflows and data transmission workflows, and if the workflows are inaccurate, analyzing the services again to perform data processing.
7. The deep learning-based online channel business data processing method of claim 1, wherein:
the palm electric SD operation data and the payment transaction service data are accessed by a marketing inspection platform IDM, and an index result table is formed by using an IMPALA calculation method according to service logic;
and judging whether the result data is accurate, if so, storing the calculation result into an HIVE library and simultaneously sending the calculation result into the RSD by using the DataX, setting a daily workflow to partition the HIVE according to time, index types and frequency so as to facilitate later maintenance, and if not, analyzing the service again to perform data processing.
8. An online channel business data processing system based on deep learning is characterized in that: the method comprises the following steps:
a data acquisition module configured to: acquiring operation data and electricity consumption customer data of each channel on line;
a data pre-processing module configured to: preprocessing the acquired data to obtain data with a uniform format;
a data prediction module configured to: inputting the preprocessed data into a preset long-term and short-term memory neural network model to obtain various service handling trend data and risk point data of the online channel;
a data fusion module configured to: and fusing the historical data, the business handling trend data and the risk point data to obtain multidimensional data based on dates, units and channels, and conducting business guidance according to the obtained multidimensional data.
9. A computer-readable storage medium on which a program is stored, the program implementing the steps in the deep learning based online channel traffic data processing method according to any one of claims 1 to 7 when executed by a processor.
10. An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor implements the steps of the deep learning based on-line channel business data processing method according to any one of claims 1 to 7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011565296.3A CN112598443A (en) | 2020-12-25 | 2020-12-25 | Online channel business data processing method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011565296.3A CN112598443A (en) | 2020-12-25 | 2020-12-25 | Online channel business data processing method and system based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112598443A true CN112598443A (en) | 2021-04-02 |
Family
ID=75202443
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011565296.3A Pending CN112598443A (en) | 2020-12-25 | 2020-12-25 | Online channel business data processing method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112598443A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570205A (en) * | 2021-07-07 | 2021-10-29 | 北京淇瑀信息科技有限公司 | API risk equipment identification method and device based on single classification and electronic equipment |
| CN114491168A (en) * | 2022-01-27 | 2022-05-13 | 中国电力科学研究院有限公司 | Method and system for regulating and controlling cloud sample data sharing, computer equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105335816A (en) * | 2015-10-13 | 2016-02-17 | 国网安徽省电力公司铜陵供电公司 | Electric power communication operation trend and business risk analyzing method based on deep learning |
| CN109685240A (en) * | 2018-10-24 | 2019-04-26 | 国网浙江省电力有限公司 | A kind of prediction of 95598 traffic work orders and unusual fluctuation method for early warning based on LSTM deep learning |
| CN110489459A (en) * | 2019-08-07 | 2019-11-22 | 国网安徽省电力有限公司 | A kind of enterprise-level industry number fused data analysis system based on big data platform |
| CN110674100A (en) * | 2019-09-28 | 2020-01-10 | 上海浦东发展银行股份有限公司信用卡中心 | User demand prediction method and framework based on full-channel operation data |
| CN111709566A (en) * | 2020-06-09 | 2020-09-25 | 信雅达系统工程股份有限公司 | Bank branch business prediction and scheduling method |
| CN112015952A (en) * | 2019-06-03 | 2020-12-01 | 食亨(上海)科技服务有限公司 | Data processing system and method |
-
2020
- 2020-12-25 CN CN202011565296.3A patent/CN112598443A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105335816A (en) * | 2015-10-13 | 2016-02-17 | 国网安徽省电力公司铜陵供电公司 | Electric power communication operation trend and business risk analyzing method based on deep learning |
| CN109685240A (en) * | 2018-10-24 | 2019-04-26 | 国网浙江省电力有限公司 | A kind of prediction of 95598 traffic work orders and unusual fluctuation method for early warning based on LSTM deep learning |
| CN112015952A (en) * | 2019-06-03 | 2020-12-01 | 食亨(上海)科技服务有限公司 | Data processing system and method |
| CN110489459A (en) * | 2019-08-07 | 2019-11-22 | 国网安徽省电力有限公司 | A kind of enterprise-level industry number fused data analysis system based on big data platform |
| CN110674100A (en) * | 2019-09-28 | 2020-01-10 | 上海浦东发展银行股份有限公司信用卡中心 | User demand prediction method and framework based on full-channel operation data |
| CN111709566A (en) * | 2020-06-09 | 2020-09-25 | 信雅达系统工程股份有限公司 | Bank branch business prediction and scheduling method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570205A (en) * | 2021-07-07 | 2021-10-29 | 北京淇瑀信息科技有限公司 | API risk equipment identification method and device based on single classification and electronic equipment |
| CN114491168A (en) * | 2022-01-27 | 2022-05-13 | 中国电力科学研究院有限公司 | Method and system for regulating and controlling cloud sample data sharing, computer equipment and storage medium |
| CN114491168B (en) * | 2022-01-27 | 2022-12-13 | 中国电力科学研究院有限公司 | Method and system for regulating and controlling cloud sample data sharing, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bi et al. | Temporal prediction of multiapplication consolidated workloads in distributed clouds | |
| CN106951984B (en) | Dynamic analysis and prediction method and device for system health degree | |
| Hompes et al. | Discovering causal factors explaining business process performance variation | |
| CN106886481A (en) | A kind of system health degree static analysis Forecasting Methodology and device | |
| CN112100219B (en) | Report generation method, device, equipment and medium based on database query processing | |
| US10671926B2 (en) | Method and system for generating predictive models for scoring and prioritizing opportunities | |
| CN111582341B (en) | User abnormal operation prediction method and device | |
| US20170124459A1 (en) | Method and system for generating predictive models for scoring and prioritizing leads | |
| CN112598443A (en) | Online channel business data processing method and system based on deep learning | |
| WO2017071369A1 (en) | Method and device for predicting user unsubscription | |
| JP2023504103A (en) | MODEL UPDATE SYSTEM, MODEL UPDATE METHOD AND RELATED DEVICE | |
| CN111242430A (en) | Power equipment supplier evaluation method and device | |
| CN112508723A (en) | Financial risk prediction method and device based on automatic preferential modeling and electronic equipment | |
| CN108804601A (en) | Power grid operation monitors the active analysis method of big data and device | |
| CN113450158A (en) | Bank activity information pushing method and device | |
| CN110910241B (en) | Cash flow evaluation method, apparatus, server device and storage medium | |
| CN117408561A (en) | Residential engineering construction supervision method and device and electronic equipment | |
| CN117196630A (en) | Transaction risk prediction method, device, terminal equipment and storage medium | |
| CN116827950A (en) | Cloud resource processing method, device, equipment and storage medium | |
| CN111352820A (en) | Method, equipment and device for predicting and monitoring running state of high-performance application | |
| Ibragimov | AN IMITATION MODEL OF THE DEVELOPMENT OF PUBLIC UTILITIES | |
| CN115827232A (en) | Method, device, system and equipment for determining configuration for service model | |
| Wang et al. | A simulation study of workforce management for a two-stage multi-skill customer service center | |
| CN114429297A (en) | Method and device for monitoring risk of project, computer equipment and storage medium | |
| CN113869973A (en) | Product recommendation method, product recommendation system, and computer-readable 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210402 |
|
| RJ01 | Rejection of invention patent application after publication |