CN113627692A - Complaint amount prediction method, complaint amount prediction device, complaint amount prediction apparatus, and storage medium - Google Patents
Complaint amount prediction method, complaint amount prediction device, complaint amount prediction apparatus, and storage medium Download PDFInfo
- Publication number
- CN113627692A CN113627692A CN202111093895.4A CN202111093895A CN113627692A CN 113627692 A CN113627692 A CN 113627692A CN 202111093895 A CN202111093895 A CN 202111093895A CN 113627692 A CN113627692 A CN 113627692A
- Authority
- CN
- China
- Prior art keywords
- complaint
- data
- time sequence
- related data
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an artificial intelligence technology, and discloses a complaint amount prediction method, which comprises the following steps: obtaining complaint related data of different dimensions, and carrying out standardization processing on the complaint related data to obtain sample data; constructing the characteristics of the sample data based on preset dimensions to obtain a characteristic data set; training a time sequence prediction model constructed based on a gradient lifting algorithm by using the sample data and the characteristic data set to obtain a trained time sequence prediction model; and predicting the future complaint amount in real time through the trained time sequence prediction model. Furthermore, the invention relates to a blockchain technology, and the complaint-related data can be stored in the nodes of the blockchain. The invention also provides a complaint amount prediction device, an electronic device and a storage medium. The method can solve the problem of low accuracy of the prediction result of the complaint amount.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a complaint amount prediction method and device, electronic equipment and a computer-readable storage medium.
Background
How to better deal with and handle complaints is a difficult point for improving customer satisfaction, and has important significance for business development of enterprises. The complaint quantity is predicted, customers can be pacified in advance, and problems can be improved in time.
The traditional method for predicting the complaint amount is to construct a model for prediction based on historical complaint data, but actually, the complaint amount data is often influenced by other factors in many aspects, and only by relying on an algorithm of historical experience, the accuracy of a prediction result is low, and meanwhile, the early warning hysteresis is possibly caused (the complaint amount is obviously increased and is overlarge when a problem occurs).
Disclosure of Invention
The invention provides a complaint amount prediction method, a complaint amount prediction device and a computer-readable storage medium, and mainly aims to solve the problem of low accuracy of a complaint amount prediction result.
In order to achieve the above object, the present invention provides a complaint amount prediction method, including:
the method comprises the steps of obtaining complaint related data of different dimensions, and conducting standardization processing on the complaint related data based on a resampling method to obtain sample data;
constructing the characteristics of the sample data based on preset dimensions to obtain a characteristic data set;
training a time sequence prediction model constructed based on a gradient lifting algorithm by using the sample data and the feature data set based on a grid search algorithm to obtain a trained time sequence prediction model;
and predicting the obtained related data of the current complaint in real time through the trained time sequence prediction model to obtain the future complaint amount.
Optionally, the normalizing the complaint related data based on the resampling method to obtain sample data includes:
unifying the sampling frequency of the complaint related data into a cycle frequency by a resampling method;
dividing the resampled complaint related data into a plurality of training sets, a plurality of verification sets and a plurality of test sets according to time;
and matching the training set with the corresponding verification set and the test set to obtain sample data.
Optionally, unifying the sampling frequency of the complaint-related data into a cycle frequency by a resampling method includes:
the data with the sampling frequency of daily frequency in the complaint related data is subjected to up-sampling and summation to be data with weekly frequency;
and converting the data with the sampling frequency of the month frequency in the complaint related data into data with the week frequency by a linear interpolation method.
Optionally, the training of the time sequence prediction model constructed based on the gradient lifting algorithm by using the sample data and the feature data set based on the grid search algorithm to obtain the trained time sequence prediction model includes:
respectively constructing a regression decision tree model according to different gradient lifting algorithms with preset numbers to obtain a plurality of basic models;
taking the training set of the sample data and the characteristic data set as input data, and training the plurality of basic models to obtain initial parameters;
adjusting initial parameters of the plurality of basic models based on a grid search algorithm and the verification set of the sample data to obtain a plurality of optimal parameter models;
and calculating an error value of each optimal parameter model by using a preset measurement function and the test set of the sample data, and selecting the optimal parameter model with the lowest error value to obtain a time sequence prediction model.
Optionally, the adjusting initial parameters of the multiple basic models based on the grid search algorithm and the verification set of the sample data to obtain multiple optimal parametric models includes:
obtaining the value range of each parameter in the initial parameters of each basic model;
arranging and combining each parameter in the value range to obtain a candidate parameter, and replacing the initial parameter in the basic model with the candidate parameter to obtain a plurality of parameter models corresponding to each basic model;
calculating the accuracy of the verification set of the sample data in each parameter model;
and selecting the parameter model with the highest accuracy to obtain a plurality of optimal parameter models.
Optionally, the predicting the obtained current complaint related data in real time by the trained time sequence prediction model to obtain a future complaint amount includes:
obtaining historical complaint data, macroscopic index data, holiday data and business index data in a week before the current time to obtain current complaint related data, and constructing the characteristics of the current complaint related data;
and performing regression prediction on the current complaint related data and characteristics by using the trained time sequence prediction model to obtain the predicted complaint total amount in the future month with the week as the latitude, and sending early warning information when the complaint total amount is higher than a preset threshold value.
Optionally, the performing regression prediction on the current complaint related data and features by using the trained time series prediction model includes:
matching the features with nodes of a decision tree in the time sequence prediction model;
calculating the score of each feature based on the current complaint related data and preset parameters in the trained time sequence prediction model;
and adding the scores of each decision tree in the trained time sequence prediction model to obtain a predicted value.
In order to solve the above problem, the present invention also provides a complaint amount prediction apparatus including:
the sample data acquisition module is used for acquiring the complaint related data with different dimensions and carrying out standardization processing on the complaint related data based on a resampling method to obtain sample data;
the characteristic construction module is used for constructing the characteristics of the sample data based on preset dimensions to obtain a characteristic data set;
the model training module is used for training a time sequence prediction model constructed based on a gradient lifting algorithm by using the sample data and the feature data set based on a grid search algorithm to obtain a trained time sequence prediction model;
and the complaint prediction module is used for predicting the obtained current complaint related data in real time through the trained time sequence prediction model to obtain the future complaint amount.
In order to solve the above problem, the present invention also provides an electronic device, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the complaint volume prediction method described above.
In order to solve the above problem, the present invention also provides a computer-readable storage medium having at least one computer program stored therein, the at least one computer program being executed by a processor in an electronic device to implement the complaint amount prediction method described above.
According to the embodiment of the invention, by acquiring the complaint related data with different dimensions and preprocessing the complaint related data to obtain sample data, the data in multiple aspects can be acquired, the range of training data is expanded, and the accuracy of model training is improved; meanwhile, a time sequence prediction model is built based on a gradient lifting algorithm, a plurality of different algorithms are used for building a basic model, and a model with the highest accuracy is selected, so that the accuracy of the model can be effectively improved, and the prediction of the total complaint amount of the next month in the week as the latitude is realized through the time sequence prediction model. Therefore, the complaint amount prediction method, the complaint amount prediction device, the electronic equipment and the computer-readable storage medium can solve the problem of low accuracy of the complaint amount prediction result.
Drawings
FIG. 1 is a flow chart illustrating a complaint quantity prediction method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of model training according to an embodiment of the present invention;
FIG. 3 is a functional block diagram of a complaint quantity prediction apparatus according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device for implementing the complaint amount prediction method according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the application provides a complaint amount prediction method. The main body of execution of the complaint amount prediction method includes, but is not limited to, at least one of electronic devices such as a server and a terminal, which can be configured to execute the method provided by the embodiment of the present application. In other words, the complaint amount prediction method may be executed by software or hardware installed in a terminal device or a server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.
Referring to fig. 1, a flow chart of a complaint amount prediction method according to an embodiment of the invention is shown.
In this embodiment, the complaint amount prediction method includes:
and S1, obtaining the complaint related data with different dimensions, and carrying out standardization processing on the complaint related data based on a resampling method to obtain sample data.
In the embodiment of the invention, the complaint related data refers to data of multiple dimensions which are directly or indirectly related to the complaint quantity, and comprises historical complaint detail data, macroscopic index data, holiday data, business index data and the like.
In detail, the obtaining complaint related data of different dimensions includes:
obtaining historical complaint detail data from a pre-constructed service system to obtain first dimension data;
obtaining second dimension data from macroscopic index data and holiday data acquired from an external public data channel;
acquiring operation index data from the inside of a bank to obtain third dimension data;
and compiling the first dimension data, the second dimension data and the third dimension data to obtain complaint related data.
According to the embodiment of the invention, different types of data are acquired from different dimensions and are used for a subsequent input model, and different data can obtain prediction results, and the difference is only the accuracy degree of the prediction results, so that the problem that complaint quantity prediction cannot be carried out due to the fact that internal data cannot be acquired conveniently can be solved.
To further ensure the security and privacy of the complaint-related data, the complaint-related data can also be stored in a node of a blockchain.
In detail, the standardizing the complaint related data based on a resampling method to obtain sample data includes:
unifying the sampling frequency of the complaint related data into a cycle frequency by a resampling method;
dividing the resampled complaint related data into a plurality of training sets, a plurality of verification sets and a plurality of test sets according to time;
and matching the training set with the corresponding verification set and the test set to obtain sample data.
Further, unifying the sampling frequency of the complaint-related data into a cycle frequency by a resampling method includes:
the data with the sampling frequency of daily frequency in the complaint related data is subjected to up-sampling and summation to be data with weekly frequency;
and converting the data with the sampling frequency of the month frequency in the complaint related data into data with the week frequency by a linear interpolation method.
The complaint related data in the embodiment of the invention comprises data of various latitudes, the sampling frequency is different, if the historical complaint data takes day as the frequency and the macro index data takes month as the frequency, in order to unify the characteristics of the input model, the data needs to be resampled, and the data is processed into a week frequency format.
S2, constructing the characteristics of the sample data based on the preset dimensionality to obtain a characteristic data set.
In detail, the constructing the characteristics of the sample data based on the preset dimensions to obtain a characteristic data set includes:
extracting the year, month characteristic data, lag characteristic data and statistical characteristic data in a window of the current week in the sample data to obtain time sequence characteristics;
calculating the legal holiday days of the current week in the sample data to obtain holiday characteristics;
calculating an increment value of macro index data with a sampling frequency of a cycle frequency in the sample data to obtain macro index features;
calculating an increment value of the operation index data with the sampling frequency of the cycle frequency in the sample data to obtain operation index characteristics;
and collecting the time sequence characteristics, the holiday characteristics, the macroscopic index characteristics and the operation index characteristics to obtain a characteristic data set.
And S3, training a time sequence prediction model constructed based on a gradient lifting algorithm by using the sample data and the feature data set based on a grid search algorithm to obtain the trained time sequence prediction model.
The time sequence prediction model in the embodiment of the invention is a Decision Tree model based on a Gradient Boosting Decision Tree (GBDT).
In detail, referring to fig. 2, the S3 includes:
s31, respectively constructing a regression decision tree model according to different gradient lifting algorithms with preset numbers to obtain a plurality of basic models;
s32, taking the training set of the sample data and the characteristic data set as input data, and training the plurality of basic models to obtain initial parameters;
s33, adjusting the initial parameters of the basic models based on a grid search algorithm and the verification set of the sample data to obtain a plurality of optimal parameter models;
s34, calculating an error value of each optimal parameter model by using a preset measurement function and the test set of the sample data, and selecting the optimal parameter model with the lowest error value to obtain a time sequence prediction model.
The different gradient lifting algorithms include, but are not limited to, LR, SVR, XGboost, LightGBM, and Catboost regression algorithms.
In the embodiment of the present invention, the training set of the sample data and the feature data set are used as input data, and the training of the plurality of basic models to obtain the initial parameters refers to inputting the training set of the sample data and the corresponding feature data set into each basic model respectively to perform regression prediction, performing parameter adjustment by using a back propagation method according to a prediction result, and using a model parameter of each basic model at this time as the initial parameter.
Further, the adjusting initial parameters of the plurality of basic models based on the grid search algorithm and the verification set of the sample data to obtain a plurality of optimal parametric models includes:
obtaining the value range of each parameter in the initial parameters of each basic model;
arranging and combining each parameter in the value range to obtain a candidate parameter, and replacing the initial parameter in the basic model with the candidate parameter to obtain a plurality of parameter models corresponding to each basic model;
calculating the accuracy of the verification set of the sample data in each parameter model;
and selecting the parameter model with the highest accuracy to obtain a plurality of optimal parameter models.
Further, the calculating an error value of each optimal parameter model by using a preset metric function and the test set of the sample data, and selecting the optimal parameter model with the lowest error value to obtain a time sequence prediction model includes:
dividing the test set of the sample data into input data and corresponding actual complaint data according to time;
constructing characteristics of the input data, and inputting the input data and the characteristics into each optimal parameter model respectively for prediction to obtain predicted complaint data;
and calculating an error value between the actual complaint data and the predicted complaint data corresponding to each optimal parameter model by using a preset measurement function, and selecting the optimal parameter model corresponding to the lowest error value as a time sequence prediction model.
Further, in the embodiment of the present invention, the metric function is a MAPE (mean absolute percentage error) function, which is specifically as follows:
where MAPE is the mean absolute percent error, yiIs the actual complaining amount, y'iPredicted complaint volume for the model.
And S4, predicting the obtained related data of the current complaint in real time through the trained time sequence prediction model to obtain the future complaint amount.
In detail, the real-time prediction of the obtained current complaint related data by the trained time sequence prediction model to obtain a future complaint amount includes:
obtaining historical complaint data, macroscopic index data, holiday data and business index data in a week before the current time to obtain current complaint related data, and constructing the characteristics of the current complaint related data;
and performing regression prediction on the current complaint related data and characteristics by using the trained time sequence prediction model to obtain the predicted complaint total amount in the future month with the week as the latitude, and sending early warning information when the complaint total amount is higher than a preset threshold value.
Further, the performing regression prediction on the current complaint related data and features by using the trained time sequence prediction model includes:
matching the features with nodes of a decision tree in the time sequence prediction model;
calculating the score of each feature based on the current complaint related data and preset parameters in the trained time sequence prediction model;
and adding the scores of each decision tree in the trained time sequence prediction model to obtain a predicted value.
The embodiment of the invention can predict the total amount of the complaints of nearly one month in the future with the latitude of week by the time sequence prediction model constructed based on the machine learning algorithm, can realize early identification, early warning and early disposal of the complaint risks, provides decision support for each business department to predict the risks in advance and deploy the operation departments, and effectively ensures the customer satisfaction.
According to the embodiment of the invention, by acquiring the complaint related data with different dimensions and preprocessing the complaint related data to obtain sample data, the data in multiple aspects can be acquired, the range of training data is expanded, and the accuracy of model training is improved; meanwhile, a time sequence prediction model is built based on a gradient lifting algorithm, a plurality of different algorithms are used for building a basic model, and a model with the highest accuracy is selected, so that the accuracy of the model can be effectively improved, and the prediction of the total complaint amount of the next month in the week as the latitude is realized through the time sequence prediction model. Therefore, the complaint amount prediction method, the complaint amount prediction device, the electronic equipment and the computer-readable storage medium can solve the problem of low accuracy of the complaint amount prediction result.
Fig. 3 is a functional block diagram of a complaint amount prediction apparatus according to an embodiment of the present invention.
The complaint amount prediction apparatus 100 according to the present invention can be installed in an electronic device. According to the realized functions, the complaint amount prediction device 100 may include a sample data acquisition module 101, a feature construction module 102, a model training module 103, and a complaint prediction module 104. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the sample data acquisition module 101 is configured to acquire complaint related data of different dimensions, and perform standardization processing on the complaint related data based on a resampling method to obtain sample data;
in the embodiment of the invention, the complaint related data refers to data of multiple dimensions which are directly or indirectly related to the complaint quantity, and comprises historical complaint detail data, macroscopic index data, holiday data, business index data and the like.
In detail, when complaint related data of different dimensions are acquired, the sample data acquisition module 101 specifically executes the following operations:
obtaining historical complaint detail data from a pre-constructed service system to obtain first dimension data;
obtaining second dimension data from macroscopic index data and holiday data acquired from an external public data channel;
acquiring operation index data from the inside of a bank to obtain third dimension data;
and compiling the first dimension data, the second dimension data and the third dimension data to obtain complaint related data.
In detail, when the data related to complaint is standardized based on a resampling method to obtain sample data, the sample data obtaining module 101 specifically executes the following operations:
unifying the sampling frequency of the complaint related data into a cycle frequency by a resampling method;
dividing the resampled complaint related data into a plurality of training sets, a plurality of verification sets and a plurality of test sets according to time;
and matching the training set with the corresponding verification set and the test set to obtain sample data.
Further, unifying the sampling frequency of the complaint-related data into a cycle frequency by a resampling method includes:
the data with the sampling frequency of daily frequency in the complaint related data is subjected to up-sampling and summation to be data with weekly frequency;
and converting the data with the sampling frequency of the month frequency in the complaint related data into data with the week frequency by a linear interpolation method.
The feature construction module 102 is configured to construct features of the sample data based on a preset dimension to obtain a feature data set;
in detail, the feature construction module 102 is specifically configured to:
extracting the year, month characteristic data, lag characteristic data and statistical characteristic data in a window of the current week in the sample data to obtain time sequence characteristics;
calculating the legal holiday days of the current week in the sample data to obtain holiday characteristics;
calculating an increment value of macro index data with a sampling frequency of a cycle frequency in the sample data to obtain macro index features;
calculating an increment value of the operation index data with the sampling frequency of the cycle frequency in the sample data to obtain operation index characteristics;
and collecting the time sequence characteristics, the holiday characteristics, the macroscopic index characteristics and the operation index characteristics to obtain a characteristic data set.
The model training module 103 is configured to train a time sequence prediction model constructed based on a gradient lifting algorithm by using the sample data and the feature data set based on a grid search algorithm to obtain a trained time sequence prediction model;
in detail, the model training module 103 is specifically configured for
Respectively constructing a regression decision tree model according to different gradient lifting algorithms with preset numbers to obtain a plurality of basic models;
taking the training set of the sample data and the characteristic data set as input data, and training the plurality of basic models to obtain initial parameters;
adjusting initial parameters of the plurality of basic models based on a grid search algorithm and the verification set of the sample data to obtain a plurality of optimal parameter models;
and calculating an error value of each optimal parameter model by using a preset measurement function and the test set of the sample data, and selecting the optimal parameter model with the lowest error value to obtain a time sequence prediction model.
The different gradient lifting algorithms include, but are not limited to, LR, SVR, XGboost, LightGBM, and Catboost regression algorithms.
Further, the adjusting initial parameters of the plurality of basic models based on the grid search algorithm and the verification set of the sample data to obtain a plurality of optimal parametric models includes:
obtaining the value range of each parameter in the initial parameters of each basic model;
arranging and combining each parameter in the value range to obtain a candidate parameter, and replacing the initial parameter in the basic model with the candidate parameter to obtain a plurality of parameter models corresponding to each basic model;
calculating the accuracy of the verification set of the sample data in each parameter model;
and selecting the parameter model with the highest accuracy to obtain a plurality of optimal parameter models.
Further, the calculating an error value of each optimal parameter model by using a preset metric function and the test set of the sample data, and selecting the optimal parameter model with the lowest error value to obtain a time sequence prediction model includes:
dividing the test set of the sample data into input data and corresponding actual complaint data according to time;
constructing characteristics of the input data, and inputting the input data and the characteristics into each optimal parameter model respectively for prediction to obtain predicted complaint data;
and calculating an error value between the actual complaint data and the predicted complaint data corresponding to each optimal parameter model by using a preset measurement function, and selecting the optimal parameter model corresponding to the lowest error value as a time sequence prediction model.
Further, in the embodiment of the present invention, the metric function is a MAPE (mean absolute percentage error) function, which is specifically as follows:
where MAPE is the mean absolute percent error, yiIs the actual complaining amount, y'iPredicted complaint volume for the model.
The complaint prediction module 104 is configured to predict the obtained current complaint related data in real time through the trained time sequence prediction model, so as to obtain a future complaint amount.
In detail, the real-time prediction of the obtained current complaint related data by the trained time sequence prediction model to obtain a future complaint amount includes:
obtaining historical complaint data, macroscopic index data, holiday data and business index data in a week before the current time to obtain current complaint related data, and constructing the characteristics of the current complaint related data;
and performing regression prediction on the current complaint related data and characteristics by using the trained time sequence prediction model to obtain the predicted complaint total amount in the future month with the week as the latitude, and sending early warning information when the complaint total amount is higher than a preset threshold value.
Further, the performing regression prediction on the current complaint related data and features by using the trained time sequence prediction model includes:
matching the features with nodes of a decision tree in the time sequence prediction model;
calculating the score of each feature based on the current complaint related data and preset parameters in the trained time sequence prediction model;
and adding the scores of each decision tree in the trained time sequence prediction model to obtain a predicted value.
Fig. 4 is a schematic structural diagram of an electronic device implementing a complaint amount prediction method according to an embodiment of the present invention.
The electronic device 1 may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may further include a computer program, such as a complaint volume prediction program, stored in the memory 11 and executable on the processor 10.
In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same function or different functions, and includes one or more Central Processing Units (CPUs), a microprocessor, a digital Processing chip, a graphics processor, a combination of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the whole electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules (e.g., executing complaint amount prediction programs, etc.) stored in the memory 11 and calling data stored in the memory 11.
The memory 11 includes at least one type of readable storage medium including flash memory, removable hard disks, multimedia cards, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only to store application software installed in the electronic device and various types of data, such as codes of complaint amount prediction programs, but also to temporarily store data that has been output or is to be output.
The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
The communication interface 13 is used for communication between the electronic device and other devices, and includes a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which are typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.
Fig. 4 only shows an electronic device with components, and it will be understood by those skilled in the art that the structure shown in fig. 4 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management and the like are realized through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The complaint quantity prediction program stored in the memory 11 of the electronic device 1 is a combination of a plurality of instructions, and when running in the processor 10, can realize:
the method comprises the steps of obtaining complaint related data of different dimensions, and conducting standardization processing on the complaint related data based on a resampling method to obtain sample data;
constructing the characteristics of the sample data based on preset dimensions to obtain a characteristic data set;
training a time sequence prediction model constructed based on a gradient lifting algorithm by using the sample data and the feature data set based on a grid search algorithm to obtain a trained time sequence prediction model;
and predicting the obtained related data of the current complaint in real time through the trained time sequence prediction model to obtain the future complaint amount.
Specifically, the specific implementation method of the instruction by the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to the drawings, which is not described herein again.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device, may implement:
the method comprises the steps of obtaining complaint related data of different dimensions, and conducting standardization processing on the complaint related data based on a resampling method to obtain sample data;
constructing the characteristics of the sample data based on preset dimensions to obtain a characteristic data set;
training a time sequence prediction model constructed based on a gradient lifting algorithm by using the sample data and the feature data set based on a grid search algorithm to obtain a trained time sequence prediction model;
and predicting the obtained related data of the current complaint in real time through the trained time sequence prediction model to obtain the future complaint amount.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A complaint amount prediction method, characterized in that the method comprises:
the method comprises the steps of obtaining complaint related data of different dimensions, and conducting standardization processing on the complaint related data based on a resampling method to obtain sample data;
constructing the characteristics of the sample data based on preset dimensions to obtain a characteristic data set;
training a time sequence prediction model constructed based on a gradient lifting algorithm by using the sample data and the feature data set based on a grid search algorithm to obtain a trained time sequence prediction model;
and predicting the obtained related data of the current complaint in real time through the trained time sequence prediction model to obtain the future complaint amount.
2. The method of predicting the complaint amount of claim 1, wherein the normalizing the complaint-related data based on the resampling method to obtain sample data comprises:
unifying the sampling frequency of the complaint related data into a cycle frequency by a resampling method;
dividing the resampled complaint related data into a plurality of training sets, a plurality of verification sets and a plurality of test sets according to time;
and matching the training set with the corresponding verification set and the test set to obtain sample data.
3. The complaint quantity prediction method according to claim 2, wherein unifying the sampling frequency of the complaint-related data into a cycle frequency by a resampling method includes:
the data with the sampling frequency of daily frequency in the complaint related data is subjected to up-sampling and summation to be data with weekly frequency;
and converting the data with the sampling frequency of the month frequency in the complaint related data into data with the week frequency by a linear interpolation method.
4. The complaint quantity prediction method of claim 1, wherein the training of the time sequence prediction model constructed based on the gradient lifting algorithm by using the sample data and the feature data set based on the grid search algorithm to obtain the trained time sequence prediction model comprises:
respectively constructing a regression decision tree model according to different gradient lifting algorithms with preset numbers to obtain a plurality of basic models;
taking the training set of the sample data and the characteristic data set as input data, and training the plurality of basic models to obtain initial parameters;
adjusting initial parameters of the plurality of basic models based on a grid search algorithm and the verification set of the sample data to obtain a plurality of optimal parameter models;
and calculating an error value of each optimal parameter model by using a preset measurement function and the test set of the sample data, and selecting the optimal parameter model with the lowest error value to obtain a time sequence prediction model.
5. The complaint volume prediction method of claim 4, wherein the adjusting initial parameters of the plurality of base models based on a grid search algorithm and a validation set of the sample data to obtain a plurality of optimal parametric models comprises:
obtaining the value range of each parameter in the initial parameters of each basic model;
arranging and combining each parameter in the value range to obtain a candidate parameter, and replacing the initial parameter in the basic model with the candidate parameter to obtain a plurality of parameter models corresponding to each basic model;
calculating the accuracy of the verification set of the sample data in each parameter model;
and selecting the parameter model with the highest accuracy to obtain a plurality of optimal parameter models.
6. The complaint quantity prediction method of claim 1, wherein predicting the obtained current complaint-related data in real time by the trained time-series prediction model to obtain a future complaint quantity comprises:
obtaining historical complaint data, macroscopic index data, holiday data and business index data in a week before the current time to obtain current complaint related data, and constructing the characteristics of the current complaint related data;
and performing regression prediction on the current complaint related data and characteristics by using the trained time sequence prediction model to obtain the predicted complaint total amount in the future month with the week as the latitude, and sending early warning information when the complaint total amount is higher than a preset threshold value.
7. The complaint quantity prediction method of claim 6, wherein the performing regression prediction on the current complaint-related data and features using the trained time-series prediction model comprises:
matching the features with nodes of a decision tree in the time sequence prediction model;
calculating the score of each feature based on the current complaint related data and preset parameters in the trained time sequence prediction model;
and adding the scores of each decision tree in the trained time sequence prediction model to obtain a predicted value.
8. A complaint amount prediction apparatus, characterized in that the apparatus comprises:
the sample data acquisition module is used for acquiring the complaint related data with different dimensions and carrying out standardization processing on the complaint related data based on a resampling method to obtain sample data;
the characteristic construction module is used for constructing the characteristics of the sample data based on preset dimensions to obtain a characteristic data set;
the model training module is used for training a time sequence prediction model constructed based on a gradient lifting algorithm by using the sample data and the feature data set based on a grid search algorithm to obtain a trained time sequence prediction model;
and the complaint prediction module is used for predicting the obtained current complaint related data in real time through the trained time sequence prediction model to obtain the future complaint amount.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the complaint volume prediction method of any one of claims 1-7.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the complaint amount prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111093895.4A CN113627692A (en) | 2021-09-17 | 2021-09-17 | Complaint amount prediction method, complaint amount prediction device, complaint amount prediction apparatus, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111093895.4A CN113627692A (en) | 2021-09-17 | 2021-09-17 | Complaint amount prediction method, complaint amount prediction device, complaint amount prediction apparatus, and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113627692A true CN113627692A (en) | 2021-11-09 |
Family
ID=78390370
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111093895.4A Pending CN113627692A (en) | 2021-09-17 | 2021-09-17 | Complaint amount prediction method, complaint amount prediction device, complaint amount prediction apparatus, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113627692A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115271544A (en) * | 2022-09-19 | 2022-11-01 | 中国科学院地理科学与资源研究所 | Method and device for reducing noise complaint rate, electronic equipment and storage medium |
-
2021
- 2021-09-17 CN CN202111093895.4A patent/CN113627692A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115271544A (en) * | 2022-09-19 | 2022-11-01 | 中国科学院地理科学与资源研究所 | Method and device for reducing noise complaint rate, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112541745B (en) | User behavior data analysis method and device, electronic equipment and readable storage medium | |
| CN114663198A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN113342939B (en) | Data quality monitoring method and device and related equipment | |
| CN115002200A (en) | User portrait based message pushing method, device, equipment and storage medium | |
| CN111652279A (en) | Behavior evaluation method and device based on time sequence data and readable storage medium | |
| CN114491047A (en) | Multi-label text classification method and device, electronic equipment and storage medium | |
| CN114997263B (en) | Method, device, equipment and storage medium for analyzing training rate based on machine learning | |
| CN114881616A (en) | Business process execution method and device, electronic equipment and storage medium | |
| CN114612194A (en) | Product recommendation method and device, electronic equipment and storage medium | |
| CN113516417A (en) | Service evaluation method and device based on intelligent modeling, electronic equipment and medium | |
| CN115423535A (en) | Product purchasing method, device, equipment and medium based on market prior big data | |
| CN114399212A (en) | Ecological environment quality evaluation method and device, electronic equipment and storage medium | |
| CN113627692A (en) | Complaint amount prediction method, complaint amount prediction device, complaint amount prediction apparatus, and storage medium | |
| CN113627160A (en) | Text error correction method and device, electronic equipment and storage medium | |
| CN111460293B (en) | Information pushing method and device and computer readable storage medium | |
| CN112651782A (en) | Behavior prediction method, device, equipment and medium based on zoom dot product attention | |
| CN111950707A (en) | Behavior prediction method, apparatus, device and medium based on behavior co-occurrence network | |
| CN111652282A (en) | Big data based user preference analysis method and device and electronic equipment | |
| CN113139129B (en) | Virtual reading trajectory graph generation method and device, electronic equipment and storage medium | |
| CN113706019B (en) | Service capability analysis method, device, equipment and medium based on multidimensional data | |
| CN115081447A (en) | Method, device and equipment for constructing requirement document of software development and storage medium | |
| CN114780688A (en) | Text quality inspection method, device and equipment based on rule matching and storage medium | |
| CN113704407A (en) | Complaint amount analysis method, device, equipment and storage medium based on category analysis | |
| CN113657546A (en) | Information classification method and device, electronic equipment and readable storage medium | |
| CN116991364B (en) | Software development system management method based on big data |
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 |