CN111985713B - Data index waveform prediction method and device - Google Patents

Data index waveform prediction method and device Download PDF

Info

Publication number
CN111985713B
CN111985713B CN202010836482.XA CN202010836482A CN111985713B CN 111985713 B CN111985713 B CN 111985713B CN 202010836482 A CN202010836482 A CN 202010836482A CN 111985713 B CN111985713 B CN 111985713B
Authority
CN
China
Prior art keywords
index
predicted
data
time period
determining
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010836482.XA
Other languages
Chinese (zh)
Other versions
CN111985713A (en
Inventor
李瑞男
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Bank of China Ltd
Original Assignee
Bank of China Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Bank of China Ltd filed Critical Bank of China Ltd
Priority to CN202010836482.XA priority Critical patent/CN111985713B/en
Publication of CN111985713A publication Critical patent/CN111985713A/en
Application granted granted Critical
Publication of CN111985713B publication Critical patent/CN111985713B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G06F18/24155—Bayesian classification
    • 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
    • G06N3/044—Recurrent networks, e.g. Hopfield 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
    • G06N3/045—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
    • G06N3/08—Learning methods
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Business, Economics & Management (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Human Resources & Organizations (AREA)
  • Game Theory and Decision Science (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Probability & Statistics with Applications (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Development Economics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a data index waveform prediction method and a device, wherein the method comprises the following steps: according to historical index data of the index to be predicted, determining first index data of the index to be predicted in a time period to be predicted; determining index data of each associated index in a time period to be predicted according to historical index data of each associated index, wherein the associated index is a data index with an associated relation with the index to be predicted; determining second index data of the to-be-predicted index in the to-be-predicted time period according to the index data of each associated index in the to-be-predicted time period; and determining a waveform prediction result of the index to be predicted in the time period to be predicted according to the first index data and the second index data of the index to be predicted in the time period to be predicted. The method and the device combine the historical index data of the index to be predicted and the associated index to predict the index to be predicted, so that the waveform prediction result of the data index can be more accurate.

Description

Data index waveform prediction method and device
Technical Field
The present invention relates to the field of data processing, and in particular, to a method and apparatus for predicting a waveform of a data indicator.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
In the field of operation and maintenance, it is often involved in making predictions about waveforms generated by various services and operation and maintenance data. In the existing operation and maintenance data prediction method, only the historical trend of the to-be-predicted index data is analyzed, and in fact, in the operation and maintenance field, the state of certain index data is often internally related to the state of other index data. Therefore, how to provide a scheme for predicting the index to be predicted by combining the association relationship between the index to be predicted and the related index is still an urgent need.
Disclosure of Invention
The embodiment of the invention provides a data index waveform prediction method, which is used for solving the technical problems that the prediction result is inaccurate only by considering the historical waveform trend of a data index to be predicted in the existing data index prediction method, and comprises the following steps: according to historical index data of the index to be predicted, determining first index data of the index to be predicted in a time period to be predicted; determining index data of each associated index in a time period to be predicted according to historical index data of each associated index, wherein the associated index is a data index with an associated relation with the index to be predicted; determining second index data of the to-be-predicted index in the to-be-predicted time period according to the index data of each associated index in the to-be-predicted time period; and determining a waveform prediction result of the index to be predicted in the time period to be predicted according to the first index data and the second index data of the index to be predicted in the time period to be predicted.
The embodiment of the invention also provides a data index waveform prediction device, which is used for solving the technical problem that the prediction result is inaccurate only by considering the historical waveform trend of the data index to be predicted in the existing data index prediction method, and comprises the following steps: the index prediction module is used for determining first index data of the index to be predicted in the time period to be predicted according to the historical index data of the index to be predicted; the associated index prediction module is used for determining index data of each associated index in a time period to be predicted according to historical index data of each associated index, wherein the associated index is a data index with an associated relation with the index to be predicted; the index data processing module is used for determining second index data of the index to be predicted in the time period to be predicted according to the index data of each associated index in the time period to be predicted; the waveform prediction module is used for determining a waveform prediction result of the to-be-predicted index in the to-be-predicted time period according to the first index data and the second index data of the to-be-predicted index in the to-be-predicted time period.
The embodiment of the invention also provides computer equipment which is used for solving the technical problems that the prediction result is inaccurate only by considering the historical waveform trend of the data index to be predicted in the existing data index prediction method.
The embodiment of the invention also provides a computer readable storage medium for solving the technical problem that the prediction result is inaccurate only by considering the historical waveform trend of the data index to be predicted in the existing data index prediction method, and the computer readable storage medium stores a computer program for executing the data index waveform prediction method.
In the embodiment of the invention, after the first index data of the to-be-predicted index in the to-be-predicted time period is determined according to the historical index data of each associated index having an association relationship with the to-be-predicted index, the index data of each associated index in the to-be-predicted time period is determined, the second index data of the to-be-predicted index in the to-be-predicted time period is further determined according to the index data of each associated index in the to-be-predicted time period, and finally the waveform prediction result of the to-be-predicted index in the to-be-predicted time period is determined according to the first index data and the second index data of the to-be-predicted index.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
FIG. 1 is a flowchart of a method for predicting a waveform of a data indicator according to an embodiment of the present invention;
FIG. 2 is a flowchart of an alternative method for determining an association indicator according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a data indicator waveform prediction apparatus according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of an alternative apparatus for predicting waveforms of data indicators according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a computer device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
In the embodiment of the present invention, a method for predicting a waveform of a data index is provided, and fig. 1 is a flowchart of a method for predicting a waveform of a data index, as shown in fig. 1, where the method may include the following steps:
s101, determining first index data of the index to be predicted in a time period to be predicted according to historical index data of the index to be predicted.
It should be noted that, in the embodiment of the present invention, the index to be predicted may be any data index to be predicted, and may be a service data index or a service data index.
For data in a single operation and maintenance field, the trend of the data is generally periodic, different businesses and periods are different, and the data is periodic in one day, and periodic in one week or one month or even one year.
For the periodic data index, according to index data of the index to be predicted in a plurality of historical periods, index prediction values of the index to be predicted in one or more future periods can be determined. Because the data in different historical periods has different importance degrees on the data of the predicted result and different importance degrees on the data of different historical moments, in general, the farther the data is from the current moment, the smaller the historical reference meaning is, and the smaller the influence on the trend and the value of the waveform at the current next moment is.
Thus, in one embodiment, when the index to be predicted is a periodic data index, the period to be predicted may include: one or more cycles to be predicted for the index to be predicted; the above S101 may be implemented by the following steps: acquiring weight values corresponding to each history period and weight values corresponding to each preset moment in each history period; and carrying out weighted average calculation on index data of the index to be predicted in each history period according to the weight value corresponding to each history period and the weight value corresponding to each preset moment in each history period to obtain first index data of the index to be predicted in the time period to be predicted. By the embodiment, the historical data in different periods and at different moments are given appropriate weight values to participate in the prediction of the future data values, and more accurate prediction results can be obtained.
In particular implementations, embodiments of the present invention introduce a time decay function f 1 And f 2 By f 1 The weight of the influence of the data which is far away along with time on the data at the current next moment in a period T is represented as f 1 (t 1 ) Wherein, -T 1 ≤t 1 Less than or equal to 0; by f 2 The weight for representing the influence of the integral historical data in different periods on the current next time data is f 2 (t 2 ) Wherein t is 2 Is a non-positive integer, t 2 =0 denotes the current period, t 2 = -1 represents the last cycle). t is t 2 Can select |T according to actual conditions 2 I values, e.g. consider only the last three cycles of data, then t 2 The values can be respectively 0, -1 and-2.
The index value DataNextVal of the data index to be predicted at the next moment is calculated by the following formula:
wherein,,
f 1 (t)＝e α·t (t < = 0, α is a constant factor);
f 2 (t)＝1/(t+1) β (t < = 0 and is an integer, β is a constant factor);
data (t) =data, (t < =0, the function being used to derive a wave value at a time in the past);
wherein, data is a function of history Data, data (0) represents current Data, and Data (t) represents Data from the current time t.
In the embodiment of the invention, different periods are given different weights, different moments in each period are given different weights, and finally, the weighted historical data of each period are overlapped to obtain the prediction data PreData of the current next moment.
It should be noted that in the embodiment of the present invention, f 1 And f 2 The formula of (2) can be replaced, and the formula with the best effect can be selected according to the specific application situation.
S102, determining index data of each associated index in a time period to be predicted according to historical index data of each associated index, wherein the associated index is a data index with an associated relation with the index to be predicted.
It should be noted that, in an actual application scenario, a change of one data index often has a certain correlation with other data indexes, so that prediction of an index to be predicted can be facilitated by analyzing index data of some correlated indexes.
It should be noted that, the data index having the association relationship with the index to be predicted may be a periodic data index, or may be an aperiodic data index, or may be a discrete data index, and the above S102 may be implemented in any one or more of the following manners:
mode one: if the associated index is a periodic data index, determining index data of the associated index in a time period to be predicted according to index data of the associated index in a plurality of history periods;
mode two: if the associated index is an aperiodic data index, determining index data of the associated index in a time period to be predicted based on a long-short-term memory network model;
mode three: and if the associated index is a discrete data index, determining index data of the associated index in a time period to be predicted based on a naive Bayesian classification model.
S103, determining second index data of the to-be-predicted index in the to-be-predicted time period according to the index data of each associated index in the to-be-predicted time period.
In specific implementation, the second index data of the index to be predicted in the time period to be predicted can be determined according to the index data of each associated index in the time period to be predicted based on a pre-trained AdaBoost algorithm regression model.
S104, determining a waveform prediction result of the index to be predicted in the period to be predicted according to the first index data and the second index data of the index to be predicted in the period to be predicted.
As can be seen from the foregoing, in the method for predicting a waveform of a data index provided in the embodiment of the present invention, after determining, according to historical index data of an index to be predicted, first index data of the index to be predicted in a time period to be predicted, according to historical index data of each associated index having an association relationship with the index to be predicted, determining index data of each associated index in the time period to be predicted, further determining, according to index data of each associated index in the time period to be predicted, second index data of the index to be predicted in the time period to be predicted, and finally determining a waveform prediction result of the index to be predicted in the time period to be predicted according to the first index data and the second index data of the index to be predicted in the time period to be predicted.
By the waveform prediction method of the data index, which is provided by the embodiment of the invention, the to-be-predicted index is predicted by combining the historical index data of the to-be-predicted index and the associated index, so that the waveform prediction result of the data index can be more accurate.
In one embodiment, as shown in fig. 2, the method for predicting waveforms of data indexes provided in the embodiment of the present invention may determine each associated index having an association relationship with an index to be predicted by:
s201, acquiring a pre-configured association index mapping table, wherein the association index mapping table comprises association relations among all data indexes;
s202, determining an associated index set of an index to be predicted according to an associated index mapping table, wherein the associated index set comprises: one or more associated indexes having an associated relation with the index to be predicted.
Table 1 shows a related index mapping table, assuming that X is used to represent the waveform of the index to be measured, Y is used to represent the set of operation and maintenance indexes related to the index to be measured, yi represents the ith index in the set; and respectively carrying out data prediction on each index in the Y. If the related index set has a periodic waveform, a non-periodic waveform and discrete data indexes, predicting the periodic waveform by the method with the first part; if the waveform is a non-periodic waveform, predicting through LTSM; in the case of discrete index data, prediction is performed through a naive Bayesian trained multi-classification model. Finally, the predicted value Ypre of Y is obtained.
When determining the index data (i.e., the second index data) of the index to be predicted in the period to be predicted according to the index data of each associated index in the period to be predicted, it may be assumed that the value of X at time t is Xt and the value of Y is Yt (Yt is a set). For the historical data of X and Y, xt and Yt corresponding to a plurality of time points are taken to form a training set; using an AdaBoost regression model, taking Yt as a model input, taking Xt as a model output, and training the model to obtain a model M-ada based on Y prediction X; after training the model M-ada, inputting a predicted value Ypre of the associated index into the model M-ada to obtain an index value Xpre of the index to be predicted; and finally, averaging the PreData and the Xpre to obtain a predicted value of the data index to be predicted, namely X-fin= (PreData+Xpre)/2.
In specific implementation, the data index waveform prediction method provided in the embodiment of the invention can be realized by the following steps:
the first step: and calling an N6 module, wherein the N6 calls an N0 module, and the relation of all the modules in the N0 is as follows:
(1) and calling M1, determining whether the index to be detected is a periodic data index, and if so, determining the period T1.
(2) And calling M2, determining a time decay function f1 to be used, and determining a constant factor therein.
(3) And calling M3, determining a time decay function f2 to be used, and determining a constant factor therein.
(4) Call M4, M4 call M5 (M5 bottom call M7) read history data, while call M2 get f 1 Calling M3 to obtain f 2 And assisting M4 to complete online prediction (the formula used for online prediction is the formula for solving DataNextVal). Outputting the predicted value of the data wave at the next moment. If there is no need to predict the data wave value for a future period of time, exit, otherwise enter (5).
(5) A length F of time that a future segment of the data wave needs to be predicted is determined. And (4) iteratively calling M4 (simulating historical data of the predicted data of each round of M4), so as to iteratively obtain predicted data waves of a period of time F in the future, and outputting a predicted result.
And a second step of: and calling an N3 module to determine an associated index set of the index to be detected.
And a third step of: and calling N4, N4 and N0, N1 and N2 according to the association index set to respectively obtain the predicted value of each association index.
Fourth step: the AdaBoost model of N5 is invoked (the model needs to be trained in advance based on AdaBoost).
Fifth step: and calling N7, receiving the prediction results output by the N5 and the N6, and outputting a final prediction result after integration.
Wherein M1 is a period determining module; m2 is f 1 A time decay function module; m3 is f 2 A time decay function module; m4 is an online prediction function module; m5 is a historical data reading module; m6 is a future segment of data wave value prediction module; m7 is a database module; n0 is a periodic continuous data prediction module; n1 is a non-periodic continuous data prediction module (LSTM); n2 is a discrete data prediction module (naive bayes); n3 is an associated index mapping table reading module; n4 is an associated index prediction module; n5 is based on the associated index predictionThe index module to be predicted; n6 is a module for predicting the index to be predicted based on the history data of the index to be predicted; and N7 is a result integration module.
The functions of the respective modules are described below:
(1) Module N0:
m1 receives historical data and business knowledge and outputs a data wave period T1. And transmitted to M4. Outputs f1 and f 2 Constant factors of (2) are respectively transmitted to M2 and M3;
m2 reception t 1 Characterizing the position of one history data in one period, and outputting the weight f of the history data corresponding to the position 1 (t 1 ). Transmitting to M4;
m3 reception t 2 Characterizing that one historical data is far from the current data, and outputting the weight f of the whole historical data belonging to the period by T2 periods 2 (t 2 ) Transmitting to M4;
m5 receives time t of a certain moment in the past, calls M7, outputs historical Data of a Data wave at the moment, and transmits the historical Data to M4;
m4 inputs the data wave period T1 and the number T2 of history periods needing backtracking, calls M5, M2 and M3, and outputs the predicted value of the data wave at the next moment. If M4 is called by M6, the result is transmitted to M6, otherwise, the terminal is directly output;
m6, inputting a parameter F which needs to be predicted for a period of time in the future, and iteratively calling M4 to obtain a continuous value of a data wave with the length of F in the period of time in the future;
and M7, wherein the input is t, the time length from a certain time to the current time is represented, the data wave value from the current time to the current time in history is output, and the result is transmitted to M5.
Modules N1, N2: in the initialization phase: receiving an associated index mapping table of N3, and respectively training a prediction model for all the related indexes; in the service phase: and receiving each associated index of the indexes to be detected, calling a related model, and outputting a prediction result of each associated index.
Module N3: acquiring an associated index mapping table pre-configured by operation and maintenance personnel;
module N4: and receiving each associated index of the indexes to be detected, and calling the corresponding models of N1 and N2 to predict. The return values of N1 and N2 are taken as output results.
Module N5: in the initialization phase: receiving an associated index mapping table of N3, and respectively training a corresponding AdaBoost model for each row in the table according to the relation of two columns of data in the table; in the service phase: and receiving the output of N4, calling a correlation model, and outputting a predicted value of the index to be detected.
Module N6: and calling N0 to obtain a predicted value.
Module N7: and receiving the output of N5 and N6, and outputting a final result after integration.
Based on the same inventive concept, the embodiment of the invention also provides a data index waveform prediction device, as described in the following embodiment. Because the principle of the device for solving the problem is similar to that of the data index waveform prediction method, the implementation of the device can refer to the implementation of the data index waveform prediction method, and the repetition is omitted.
Fig. 3 is a schematic diagram of a data indicator waveform prediction apparatus according to an embodiment of the present invention, where, as shown in fig. 3, the apparatus may include: an index prediction module 31, an associated index prediction module 32, an index data processing module 33, and a waveform prediction module 34.
The index prediction module 31 is configured to determine, according to historical index data of an index to be predicted, first index data of the index to be predicted in a time period to be predicted; the associated index prediction module 32 is configured to determine index data of each associated index in a time period to be predicted according to historical index data of each associated index, where the associated index is a data index having an associated relationship with the index to be predicted; an index data processing module 33, configured to determine second index data of the index to be predicted in the period to be predicted according to the index data of each associated index in the period to be predicted; the waveform prediction module 34 is configured to determine a waveform prediction result of the to-be-predicted index in the to-be-predicted time period according to the first index data and the second index data of the to-be-predicted index in the to-be-predicted time period.
As can be seen from the above, in the waveform prediction device of the data index provided in the embodiment of the present invention, the index prediction module 31 determines the first index data of the index to be predicted in the period of time to be predicted according to the history index data of the index to be predicted; determining, by the associated index prediction module 32, index data of each associated index in a time period to be predicted according to historical index data of each associated index having an associated relation with the index to be predicted; determining, by the index data processing module 33, second index data of the index to be predicted in the period to be predicted according to the index data of each associated index in the period to be predicted; the waveform prediction module 34 determines a waveform prediction result of the to-be-predicted index in the to-be-predicted time period according to the first index data and the second index data of the to-be-predicted index in the to-be-predicted time period.
By means of the waveform prediction device of the data index, the to-be-predicted index is predicted by combining the historical index data of the to-be-predicted index and the associated index, and the waveform prediction result of the data index can be more accurate.
In an embodiment, in the data index waveform prediction apparatus provided in the embodiment of the present invention, the index to be predicted may be a periodic data index, and the period to be predicted may include: one or more cycles to be predicted for the index to be predicted; as shown in fig. 4, the index prediction module 31 may include: the weight configuration module 311 is configured to obtain a weight value corresponding to each history period and a weight value corresponding to each preset time in each history period; the index calculation module 312 is configured to perform weighted average calculation on index data of the index to be predicted in each history period according to the weight value corresponding to each history period and the weight value corresponding to each preset time in each history period, so as to obtain first index data of the index to be predicted in the time period to be predicted.
In one embodiment, as shown in fig. 4, the association index prediction module 32 includes: the first associated index prediction module 321 is configured to determine, if the associated index is a periodic data index, index data of the associated index in a period to be predicted according to index data of the associated index in a plurality of history periods; the second associated index prediction module 322 is configured to determine index data of the associated index in a period to be predicted based on the long-short-term memory network model if the associated index is an aperiodic data index; a third associated index prediction module 323, configured to determine index data of the associated index in the period to be predicted based on the naive bayes classification model.
In one embodiment, as shown in fig. 4, the data indicator waveform prediction apparatus provided in the embodiment of the present invention may further include: an associated index mapping table obtaining module 35, configured to obtain a pre-configured associated index mapping table, where the associated index mapping table includes an associated relationship between each data index; the association index determining module 36 is configured to determine an association index set of the index to be predicted according to the association index mapping table, where the association index set includes: one or more associated indexes having an associated relation with the index to be predicted.
Alternatively, the above-mentioned index data processing module 33 may be further configured to determine, based on a pre-trained regression model of AdaBoost algorithm, second index data of the index to be predicted in the period to be predicted according to the index data of each associated index in the period to be predicted.
Based on the same inventive concept, the embodiment of the invention further provides a computer device for solving the technical problem that the prediction result is inaccurate only by considering the historical waveform trend of the data index to be predicted in the existing data index prediction method, and fig. 5 is a schematic diagram of the computer device in the embodiment of the invention, as shown in fig. 5, the computer device 50 includes a memory 501, a processor 502 and a computer program stored on the memory 501 and capable of running on the processor 502, and the processor 502 implements the data index waveform prediction method when executing the computer program.
Based on the same inventive concept, the embodiment of the invention also provides a computer readable storage medium for solving the technical problem that the prediction result is inaccurate only by considering the historical waveform trend of the data index to be predicted in the existing data index prediction method, and the computer readable storage medium stores a computer program for executing the data index waveform prediction method.
In summary, the embodiment of the invention provides a data index waveform prediction method, a device, a computer device and a computer readable storage medium, which are compared with the technical scheme in the prior art that only the historical waveform trend of the data index to be predicted is considered to predict the waveform of the data index to be predicted, the embodiment of the invention combines the historical index data of the index to be predicted and the associated index to predict the data index to be predicted, so that the waveform prediction result of the data index is more accurate.
It should be noted that, in the prior art, the waveform trend of the data index is predicted by using the neural network model, for the data wave with periodic trend, the interpretability of the neural network model is poor, no clear logic exists, and once the model is trained, the model is used for prediction, so that the flexibility is lacking; if the reference range of the historical data needs to be enlarged, the model needs to be retrained, but the training of deep learning is relatively slow, so that the response capability of quickly changing the configuration is lacked, in addition, the operation of the neural network model is complex, the requirement on hardware is too high, and the terminal equipment cannot be deployed. The data index waveform prediction scheme provided by the embodiment of the invention relies on real observation and analysis of the objective world for period determination, fully utilizes priori knowledge of business logic for confirmation, and has strong interpretability; if the reference range of the historical data needs to be enlarged, only the time decay function f needs to be modified 2 The value range of the independent variable can be realized quickly, and the hardware requirement is low because only mathematical operation is involved; the prediction of the index to be detected is assisted by the information of the associated index, so that the prediction result is more accurate.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention 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, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.

Claims (8)

1. A method for predicting a waveform of a data indicator, comprising:
according to historical index data of an index to be predicted, determining first index data of the index to be predicted in a time period to be predicted;
determining index data of each associated index in the time period to be predicted according to historical index data of each associated index, wherein the associated index is a data index with an associated relation with the index to be predicted;
determining second index data of the index to be predicted in the time period to be predicted according to the index data of each associated index in the time period to be predicted;
determining a waveform prediction result of the to-be-predicted index in the to-be-predicted time period according to the first index data and the second index data of the to-be-predicted index in the to-be-predicted time period;
the to-be-predicted index is a periodic data index, and the to-be-predicted time period includes: one or more periods to be predicted of the indicators to be predicted; according to historical index data of an index to be predicted, determining first index data of the index to be predicted in a time period to be predicted comprises the following steps:
acquiring weight values corresponding to each history period and weight values corresponding to each preset moment in each history period;
according to the weight value corresponding to each history period and the weight value corresponding to each preset moment in each history period, carrying out weighted average calculation on the index data of the index to be predicted in each history period to obtain first index data of the index to be predicted in the time period to be predicted;
according to the historical index data of each associated index, determining the index data of each associated index in the to-be-predicted time period comprises the following steps:
if the associated index is a periodic data index, determining index data of the associated index in the period to be predicted according to index data of the associated index in a plurality of history periods;
if the associated index is an aperiodic data index, determining index data of the associated index in the to-be-predicted time period based on a long-short-period memory network model;
and if the associated index is a discrete data index, determining index data of the associated index in the to-be-predicted time period based on a naive Bayesian classification model.
2. The method of claim 1, wherein the method further comprises:
acquiring a pre-configured association index mapping table, wherein the association index mapping table comprises association relations among all data indexes;
determining an associated index set of the index to be predicted according to the associated index mapping table, wherein the associated index set comprises: and the one or more associated indexes have an associated relation with the index to be predicted.
3. The method of claim 1, wherein determining second index data for the time period to be predicted for each associated index based on the index data for the time period to be predicted for each associated index, comprises:
and determining second index data of the index to be predicted in the time period to be predicted according to the index data of each associated index in the time period to be predicted based on a pre-trained AdaBoost algorithm regression model.
4. A data index waveform prediction apparatus, comprising:
the index prediction module is used for determining first index data of the index to be predicted in a time period to be predicted according to historical index data of the index to be predicted;
the associated index prediction module is used for determining index data of each associated index in the time period to be predicted according to historical index data of each associated index, wherein the associated index is a data index with an associated relation with the index to be predicted;
the index data processing module is used for determining second index data of the index to be predicted in the time period to be predicted according to the index data of each associated index in the time period to be predicted;
the waveform prediction module is used for determining a waveform prediction result of the to-be-predicted index in the to-be-predicted time period according to the first index data and the second index data of the to-be-predicted index in the to-be-predicted time period;
the to-be-predicted index is a periodic data index, and the to-be-predicted time period includes: one or more periods to be predicted of the indicators to be predicted; the index prediction module comprises:
the weight configuration module is used for acquiring weight values corresponding to each history period and weight values corresponding to each preset moment in each history period;
the index calculation module is used for carrying out weighted average calculation on the index data of the index to be predicted in each history period according to the weight value corresponding to each history period and the weight value corresponding to each preset moment in each history period to obtain first index data of the index to be predicted in the time period to be predicted;
the associated index prediction module comprises:
the first associated index prediction module is used for determining index data of the associated index in the to-be-predicted time period according to index data of the associated index in a plurality of history periods if the associated index is a periodic data index;
the second associated index prediction module is used for determining index data of the associated index in the to-be-predicted time period based on the long-short-period memory network model if the associated index is an aperiodic data index;
and the third associated index prediction module is used for determining index data of the associated index in the time period to be predicted based on a naive Bayesian classification model.
5. The apparatus of claim 4, wherein the apparatus further comprises:
the system comprises an associated index mapping table acquisition module, a data processing module and a data processing module, wherein the associated index mapping table acquisition module is used for acquiring a pre-configured associated index mapping table, and the associated index mapping table comprises the associated relation among all data indexes;
the association index determining module is used for determining an association index set of the index to be predicted according to the association index mapping table, wherein the association index set comprises: and the one or more associated indexes have an associated relation with the index to be predicted.
6. The apparatus of claim 4, wherein the metric data processing module is further configured to determine second metric data for the metric to be predicted for the period of time to be predicted based on a pre-trained AdaBoost algorithm regression model from metric data for each associated metric for the period of time to be predicted.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the data index waveform prediction method of any one of claims 1 to 3 when the computer program is executed by the processor.
8. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, implements the data index waveform prediction method of any one of claims 1 to 3.
CN202010836482.XA 2020-08-19 2020-08-19 Data index waveform prediction method and device Active CN111985713B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010836482.XA CN111985713B (en) 2020-08-19 2020-08-19 Data index waveform prediction method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010836482.XA CN111985713B (en) 2020-08-19 2020-08-19 Data index waveform prediction method and device

Publications (2)

Publication Number Publication Date
CN111985713A CN111985713A (en) 2020-11-24
CN111985713B true CN111985713B (en) 2023-08-18

Family

ID=73435424

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010836482.XA Active CN111985713B (en) 2020-08-19 2020-08-19 Data index waveform prediction method and device

Country Status (1)

Country Link
CN (1) CN111985713B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103617564A (en) * 2013-12-04 2014-03-05 国家电网公司 Whole-network load prediction method based on local load predicted value comprehensive evaluation
CN106156875A (en) * 2015-04-10 2016-11-23 株式会社日立制作所 For the method and apparatus that prediction object is predicted
CN106549772A (en) * 2015-09-16 2017-03-29 华为技术有限公司 Resource prediction method, system and capacity management device
WO2019056499A1 (en) * 2017-09-20 2019-03-28 平安科技（深圳）有限公司 Prediction model training method, data monitoring method, apparatuses, device and medium
CN109872003A (en) * 2019-03-06 2019-06-11 中国科学院软件研究所 Obj State prediction technique, system, computer equipment and storage medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103617564A (en) * 2013-12-04 2014-03-05 国家电网公司 Whole-network load prediction method based on local load predicted value comprehensive evaluation
CN106156875A (en) * 2015-04-10 2016-11-23 株式会社日立制作所 For the method and apparatus that prediction object is predicted
CN106549772A (en) * 2015-09-16 2017-03-29 华为技术有限公司 Resource prediction method, system and capacity management device
WO2019056499A1 (en) * 2017-09-20 2019-03-28 平安科技（深圳）有限公司 Prediction model training method, data monitoring method, apparatuses, device and medium
CN109872003A (en) * 2019-03-06 2019-06-11 中国科学院软件研究所 Obj State prediction technique, system, computer equipment and storage medium

Also Published As

Publication number Publication date
CN111985713A (en) 2020-11-24

Similar Documents

Publication Publication Date Title
US11216741B2 (en) Analysis apparatus, analysis method, and non-transitory computer readable medium
US20130024173A1 (en) Computer-Implemented Systems and Methods for Testing Large Scale Automatic Forecast Combinations
US9934470B2 (en) Production equipment including machine learning system and assembly and test unit
KR20200075071A (en) Apparatus and Method for Generating Sampling Model for Uncertainty Prediction, Apparatus for Predicting Uncertainty
CN109472412A (en) A kind of prediction technique and device of event
EP3239905A1 (en) Methods and apparatus for use in predicting non-stationary time-series data
CN112381320A (en) Community personnel flow prediction method, system, storage medium and equipment
Bhardwaj et al. Health insurance amount prediction
CN114417733A (en) Method and device for constructing power consumption prediction model, electronic equipment and storage medium
CN111563236B (en) Short-term wind speed prediction method and device
Yanto et al. Implementation multiple linear regresion in neural network predict gold price
Minitaeva Analysis of the multi-criteria decision-making problem under conditions of heterogeneous interval uncertainty
CN111985713B (en) Data index waveform prediction method and device
CN113988264A (en) Method and device for obtaining graph neural network for executing flow prediction service
CN110909884A (en) Method, apparatus, product and medium for updating parameter model
CN105894138A (en) Optimum weighted composite prediction method for shipment amount of manufacturing industry
US20230267363A1 (en) Machine learning with periodic data
Chen et al. A novel interval estimation framework for wind power forecasting using multi-objective gradient descent optimization
CN114612231A (en) Stock quantitative trading method and device, terminal device and readable storage medium
RU2622858C1 (en) Evaluation method of information on the system functioning effectiveness and device on its basis for control tasks solving, monitoring and diagnostics
Crone et al. Feature selection of autoregressive neural network inputs for trend time series forecasting
Wong et al. Information processing constraints in travel behaviour modelling: A generative learning approach
Sarıcıoğlu et al. Analyzing One-Step and Multi-Step Forecasting to Mitigate the Bullwhip Effect and Improve Supply Chain Performance
CN117234954B (en) Intelligent online testing method and system based on machine learning algorithm
Kemp Gamma test analysis tools for non-linear time series

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
GR01 Patent grant
GR01 Patent grant