CN116911773A - Service data prediction system, method, electronic equipment and storage medium - Google Patents
Service data prediction system, method, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116911773A CN116911773A CN202310762499.9A CN202310762499A CN116911773A CN 116911773 A CN116911773 A CN 116911773A CN 202310762499 A CN202310762499 A CN 202310762499A CN 116911773 A CN116911773 A CN 116911773A
- Authority
- CN
- China
- Prior art keywords
- prediction
- value
- service data
- residual
- sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000009499 grossing Methods 0.000 claims abstract description 148
- 238000013528 artificial neural network Methods 0.000 claims abstract description 29
- 238000013112 stability test Methods 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims description 37
- 210000002569 neuron Anatomy 0.000 claims description 31
- 238000011478 gradient descent method Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000001744 unit root test Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 abstract description 8
- 230000006870 function Effects 0.000 description 19
- 238000010586 diagram Methods 0.000 description 15
- 238000004590 computer program Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000012360 testing method Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000006467 substitution reaction Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000010485 coping Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a service data prediction system, a service data prediction method, electronic equipment and a storage medium, wherein a historical service data sequence is firstly obtained, and the historical service data sequence is subjected to stability test so as to determine a smooth initial value; based on the smooth initial value and the historical service data sequence, performing second-order exponential smoothing prediction through residual iteration to obtain a fitting service data predicted value and a residual sequence; analyzing the residual sequence by using a residual prediction model to obtain a residual prediction result; and obtaining target service data prediction according to the fitting service data prediction value and the residual prediction result. According to the embodiment of the invention, after the business data is predicted through the exponential smoothing, the residual error of the prediction result of the exponential smoothing method is corrected through the neural network, and the fitting capacity of nonlinear data and the result precision of the business data prediction are improved by combining the characteristic advantages of the exponential smoothing method and the neural network, so that the method and the device can be widely applied to the technical field of data processing.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a service data prediction system, a service data prediction method, an electronic device, and a storage medium.
Background
In the actual project and the business process, the decision factors of business data (such as various data generated by the operation of management systems such as projects, power grids, commodities or projects) are very diversified, so that the fluctuation of the data is repeated, the existing management system of the business data is only predicted based on the rough change trend of the data, and the trend characteristics of the data with obvious fluctuation cannot be extracted to effectively predict, so that the prediction effect of the management system of the business data is poor. The prior art has the problems of insufficient robustness and precision caused by incomplete coping with various bursty, nonlinear or fluctuating situations in the business situation.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems in the related art to some extent. Therefore, the invention provides a service data prediction system, a service data prediction method, electronic equipment and a storage medium, which can improve the accuracy of service data prediction.
In one aspect, an embodiment of the present invention provides a service data prediction system, including:
The stability test module is used for acquiring a historical service data sequence, carrying out stability test on the historical service data sequence and further determining a smooth initial value; the historical service data sequence comprises service data of a plurality of periods;
the exponential smoothing prediction module is used for carrying out second-order exponential smoothing prediction through residual iteration based on the smoothing initial value and the historical service data sequence to obtain a fitting service data predicted value and a residual sequence;
the residual prediction module is used for analyzing the residual sequence by utilizing a residual prediction model to obtain a residual prediction result;
the residual prediction model is obtained by training a gradient descent method based on a neural network, and the neural network comprises an input layer, a hidden layer and an output layer;
and the result prediction module is used for obtaining target service data prediction according to the fitting service data prediction value and the residual error prediction result.
Optionally, the stationarity checking module includes:
the significant value acquisition unit is used for carrying out stability test on the historical service data sequence through unit root test to obtain a significant value of the unit root test;
the first initial value acquisition module is used for acquiring the service data in the first period in the historical service data sequence as a service data initial value when the significance value is smaller than or equal to a first preset threshold value;
And the second initial value acquisition module is used for acquiring the average value of the service data in each period in the historical service data sequence as a service data initial value when the significance value is larger than the first preset threshold value.
Optionally, the exponential smoothing prediction module comprises:
a first acquisition unit configured to acquire an initial smoothing coefficient as a target smoothing coefficient;
an exponential smoothing value determining unit, configured to determine an exponential smoothing value of each period in combination with the target smoothing coefficient, based on the smoothing initial value and the service data of each period; the exponent-smoothed value includes a primary exponent-smoothed value and a secondary exponent-smoothed value;
a first business prediction unit, configured to determine a first business data prediction value of each period based on the exponential smoothing value of each period;
a smoothing coefficient determining unit, configured to determine a residual value of each period based on the first service data prediction value of each period; determining a final smoothing coefficient based on the residual error values of each period;
and the second business prediction unit is used for taking the final smoothing coefficient as a target smoothing coefficient, returning to the exponential smoothing value determination unit, further determining a fitting business data prediction value according to the obtained first business data prediction value, and determining a residual sequence based on the residual value of each period.
Optionally, the first traffic prediction unit includes:
a first prediction subunit configured to determine a first prediction parameter based on the primary exponential smoothing value and the secondary exponential smoothing value;
a second prediction subunit, configured to determine a second prediction parameter based on the primary exponential smoothing value and the secondary exponential smoothing value, in combination with the initial smoothing coefficient;
and the third prediction subunit is used for determining a first service data predicted value of each period according to the first prediction parameter and the second prediction parameter and combining the prediction period number.
Optionally, the smoothing coefficient determining unit includes:
and the residual iteration subunit is used for obtaining a final smoothing coefficient through iteration of residual square sums based on the residual values of each period.
Optionally, the system further comprises:
the training sample determining module is used for determining a residual training sample according to the residual sequence;
the model training module is used for training the neural network by the gradient descent method through the residual error training sample, adjusting the weights of the input layer and the hidden layer based on the calculation error obtained by each round of training until the calculation error is smaller than a second preset threshold value, and obtaining a residual error prediction model.
Optionally, the residual prediction module includes:
the output information unit is used for combining the weight value from each neuron of the input layer to each neuron of the hidden layer and the first parameter threshold value of each neuron of the hidden layer according to the residual error sequence to obtain output information from the input layer to the hidden layer; wherein the input layer and the hidden layer each comprise a plurality of neurons;
the input information unit is used for combining the weight of each neuron of the hidden layer according to the output information to obtain the input information from the hidden layer to the output layer;
and the residual prediction unit is used for combining a second parameter threshold according to the input information to obtain a residual prediction result.
On the other hand, the embodiment of the invention provides a service data prediction method, which is applied to the previous system and comprises the following steps:
acquiring a historical service data sequence, and performing stability test on the historical service data sequence to further determine a smooth initial value; the historical service data sequence comprises service data of a plurality of periods;
based on the smooth initial value and the historical service data sequence, performing second-order exponential smoothing prediction through residual iteration to obtain a fitting service data predicted value and a residual sequence;
Analyzing the residual sequence by using a residual prediction model to obtain a residual prediction result;
the residual prediction model is obtained by training a gradient descent method based on a neural network, and the neural network comprises an input layer, a hidden layer and an output layer;
and obtaining target service data prediction according to the fitting service data prediction value and the residual prediction result.
Optionally, performing a stationarity check on the historical service data sequence and determining an initial value of the service data, including:
carrying out stationarity test on the historical business data sequence through unit root test to obtain a significance value of the unit root test;
when the significance value is smaller than or equal to a first preset threshold value, acquiring first-period service data in a historical service data sequence as a service data initial value;
when the significance value is larger than a first preset threshold value, acquiring an average value of service data in each period in the historical service data sequence as a service data initial value.
Optionally, performing second-order exponential smoothing prediction through residual iteration based on the smoothed initial value and the historical service data sequence to obtain a fitting service data predicted value and a residual sequence, including:
acquiring an initial smoothing coefficient as a target smoothing coefficient;
Based on the smooth initial value and the business data of each period, determining an exponential smooth value of each period by combining the target smooth coefficient; the exponent smoothing values include a primary exponent smoothing value and a secondary exponent smoothing value;
determining a first business data predicted value of each period based on the exponential smoothing value of each period;
determining a residual value of each period based on the first service data predicted value of each period; determining a final smoothing coefficient based on the residual value of each period;
and taking the final smoothing coefficient as a target smoothing coefficient, returning to an exponential smoothing value determining unit, further determining a fitting service data predicted value according to the obtained first service data predicted value, and determining a residual sequence based on the residual value of each period.
Optionally, determining the first traffic data prediction value for each period based on the exponentially smoothed value for each period includes:
determining a first prediction parameter based on the primary and secondary exponential smoothing values;
determining a second prediction parameter based on the primary exponential smoothing value and the secondary exponential smoothing value in combination with the initial smoothing coefficient;
and determining a first business data predicted value of each period based on the first predicted parameter and the second predicted parameter and combining the predicted period number.
Optionally, determining the final smoothing coefficient based on the residual values of each period includes:
Based on the residual values of each period, the final smoothing coefficient is obtained through iteration of residual square sum.
Optionally, the method further comprises:
determining a residual training sample according to the residual sequence;
the model training module is used for training the neural network by a gradient descent method through residual training samples, adjusting weights of the input layer and the hidden layer based on calculation errors obtained by each round of training until the calculation errors are smaller than a second preset threshold value, and obtaining a residual prediction model.
Optionally, analyzing the residual sequence with a residual prediction model to obtain a residual prediction result, including:
according to the residual sequence, combining the weight value from each neuron of the input layer to each neuron of the hidden layer and the first parameter threshold value of each neuron of the hidden layer to obtain output information from the input layer to the hidden layer; wherein the input layer and the hidden layer each include a plurality of neurons;
according to the output information, combining weights of all neurons of the hidden layer to obtain input information from the hidden layer to the output layer;
and according to the input information, combining the second parameter threshold value to obtain a residual prediction result.
In another aspect, an embodiment of the present invention provides an electronic device, including: a processor and a memory; the memory is used for storing programs; the processor executes the program to realize the service data prediction method.
In another aspect, an embodiment of the present invention provides a computer storage medium in which a program executable by a processor is stored, the program executable by the processor being configured to implement the service data prediction method described above when executed by the processor.
Firstly, acquiring a historical service data sequence through a stability test module, and carrying out stability test on the historical service data sequence to further determine a smooth initial value; the historical service data sequence comprises service data of a plurality of periods; performing second-order exponential smoothing prediction by an exponential smoothing prediction module based on the smoothing initial value and the historical service data sequence through residual iteration to obtain a fitting service data predicted value and a residual sequence; further, a residual prediction module analyzes the residual sequence by utilizing a residual prediction model to obtain a residual prediction result; the residual prediction model is obtained by training a gradient descent method based on a neural network, and the neural network comprises an input layer, a hidden layer and an output layer; and finally, obtaining target service data prediction according to the fitting service data prediction value and the residual error prediction result by a result prediction module. According to the embodiment of the invention, after the business data is predicted through the exponential smoothing, the residual error of the prediction result of the exponential smoothing method is corrected through the neural network, and the fitting capacity of the nonlinear data and the result accuracy of the business data prediction are improved by combining the characteristic advantages of the exponential smoothing method and the neural network. The method can effectively solve the problems of insufficient robustness and precision caused by incomplete coping of various burst, nonlinear or fluctuation conditions in the service conditions of the existing management system.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate and do not limit the invention.
FIG. 1 is a schematic diagram of an implementation environment for performing business data prediction according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a service data prediction system according to an embodiment of the present invention;
fig. 3 is a flow chart of a service data prediction method according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a method for determining a smooth initial value according to an embodiment of the present invention;
FIG. 5 is a schematic flow chart of a second order exponential smoothing prediction according to an embodiment of the present invention;
FIG. 6 is a schematic flow chart of obtaining a residual prediction result according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of the overall flow of service data prediction and early warning provided by the embodiment of the invention;
fig. 8 is a schematic diagram of an example of error proportion distribution of service data prediction according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;
fig. 10 is a block diagram of a computer system suitable for implementing an electronic device according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
It should be noted that although functional block diagrams are depicted as block diagrams, and logical sequences are shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the block diagrams in the system. The terms first/S100, second/S200, and the like in the description and in the claims and in the above-described figures, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
It can be understood that the service data prediction system provided by the embodiment of the invention can be equipped/applied to any computer device with data processing and computing capabilities to realize the functional logic of each module, and the computer device can be various terminals or servers. When the computer device in the embodiment is a server, the server is an independent physical server, or is a server cluster or a distributed system formed by a plurality of physical servers, or is a cloud server for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network ), basic cloud computing services such as big data and artificial intelligence platforms, and the like. Alternatively, the terminal is a smart phone, a tablet computer, a notebook computer, a desktop computer, or the like, but is not limited thereto.
FIG. 1 is a schematic view of an embodiment of the invention. Referring to fig. 1, the implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be connected through a network in a wireless or wired mode to complete data transmission and exchange.
The server 101 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs (Content Delivery Network, content delivery networks), basic cloud computing services such as big data and artificial intelligent platforms, and the like.
In addition, server 101 may also be a node server in a blockchain network. The blockchain 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.
The terminal 102 may be, but is not limited to, a smart phone, tablet, notebook, desktop, smart box, smart watch, etc. The terminal 102 and the server 101 may be directly or indirectly connected through wired or wireless communication, which is not limited in this embodiment of the present application.
Exemplary based on the implementation environment shown in fig. 1, the embodiment of the present application provides a service data prediction system, which lacks an intelligent system with a service data prediction function in the prior art, so the present application proposes a service data prediction system to overcome related technical obstacles (problems of insufficient robustness and precision caused by incomplete response to various burstiness, nonlinearity or fluctuation situations in service situations), and the service data prediction system is described below by taking the service data prediction system as an example in the server 101, and it can be understood that the service data prediction system may also be provided in the terminal 102.
As shown in fig. 2, an embodiment of the present invention provides a service data prediction system 200, including:
the stationarity checking module 210 is configured to obtain a historical service data sequence, perform stationarity checking on the historical service data sequence, and further determine a smooth initial value; the historical service data sequence comprises service data of a plurality of periods;
it should be noted that, in some embodiments, the stability checking module may include: the significant value acquisition unit is used for carrying out stability test on the historical service data sequence through unit root test to obtain a significant value of the unit root test; the first initial value acquisition module is used for acquiring the service data in the first period in the historical service data sequence as a service data initial value when the significance value is smaller than or equal to a first preset threshold value; and the second initial value acquisition module is used for acquiring the average value of the service data in each period in the historical service data sequence as a service data initial value when the significance value is larger than the first preset threshold value.
The exponential smoothing prediction module 220 is configured to perform second-order exponential smoothing prediction through residual iteration based on the smoothed initial value and the historical service data sequence, so as to obtain a fitting service data predicted value and a residual sequence;
It should be noted that, in some embodiments, the exponential smoothing prediction module may include: a first acquisition unit configured to acquire an initial smoothing coefficient as a target smoothing coefficient; an exponential smoothing value determining unit, configured to determine an exponential smoothing value of each period in combination with the target smoothing coefficient, based on the smoothing initial value and the service data of each period; the exponent-smoothed value includes a primary exponent-smoothed value and a secondary exponent-smoothed value; a first business prediction unit, configured to determine a first business data prediction value of each period based on the exponential smoothing value of each period; a smoothing coefficient determining unit, configured to determine a residual value of each period based on the first service data prediction value of each period; determining a final smoothing coefficient based on the residual error values of each period; and the second business prediction unit is used for taking the final smoothing coefficient as a target smoothing coefficient, returning to the exponential smoothing value determination unit, further determining a fitting business data prediction value according to the obtained first business data prediction value, and determining a residual sequence based on the residual value of each period.
In some embodiments, the first traffic prediction unit may include: a first prediction subunit configured to determine a first prediction parameter based on the primary exponential smoothing value and the secondary exponential smoothing value; a second prediction subunit, configured to determine a second prediction parameter based on the primary exponential smoothing value and the secondary exponential smoothing value, in combination with the initial smoothing coefficient; and the third prediction subunit is used for determining a first service data predicted value of each period according to the first prediction parameter and the second prediction parameter and combining the prediction period number.
In some embodiments, the smoothing coefficient determining unit may include: and the residual iteration subunit is used for obtaining a final smoothing coefficient through iteration of residual square sums based on the residual values of each period.
The residual prediction module 230 is configured to analyze the residual sequence by using a residual prediction model to obtain a residual prediction result; the residual prediction model is obtained by training a gradient descent method based on a neural network, and the neural network comprises an input layer, a hidden layer and an output layer;
it should be noted that, in some embodiments, the residual prediction module may include: the output information unit is used for combining the weight value from each neuron of the input layer to each neuron of the hidden layer and the first parameter threshold value of each neuron of the hidden layer according to the residual error sequence to obtain output information from the input layer to the hidden layer; wherein the input layer and the hidden layer each comprise a plurality of neurons; the input information unit is used for combining the weight of each neuron of the hidden layer according to the output information to obtain the input information from the hidden layer to the output layer; and the residual prediction unit is used for combining a second parameter threshold according to the input information to obtain a residual prediction result.
The result prediction module 240 is configured to obtain a target service data prediction according to the fitted service data prediction value and the residual prediction result.
It should be noted that, in some embodiments, the system may further include the following modules:
the training sample determining module is used for determining residual training samples according to the residual sequences; the model training module is used for training the neural network by a gradient descent method through residual training samples, adjusting weights of the input layer and the hidden layer based on calculation errors obtained by each round of training until the calculation errors are smaller than a second preset threshold value, and obtaining a residual prediction model.
The data logic processing principle of the system according to the embodiment of the present invention is described below by taking the flow logic of the method implemented by each module of the system and each unit included in the module as an example.
Referring to fig. 3, fig. 3 is a flowchart of a service data prediction method applied to a server according to an embodiment of the present invention, and an execution subject of the service data prediction method may be any one of the aforementioned (equipped with a system according to an embodiment of the present invention). Referring to fig. 3, the system execution flow includes the steps of:
S100, acquiring a historical service data sequence, and performing stability test on the historical service data sequence to further determine a smooth initial value;
it should be noted that the historical service data sequence includes service data of a plurality of periods; in some embodiments, as shown in fig. 4, performing a stationarity check on the historical service data sequence to determine a smoothed initial value may include: s101, performing stationarity test on a historical business data sequence through unit root test to obtain a significance value of the unit root test; s102, when the significance value is smaller than or equal to a first preset threshold value, acquiring first-period service data in a historical service data sequence as a service data initial value; and S103, when the significance value is larger than a first preset threshold value, acquiring an average value of the service data in each period in the historical service data sequence as a service data initial value.
In some embodiments, the historical service data sequence is subjected to unit root test for stability, if the historical service data sequence is stable, the first-period data is used as an initial value, and if the historical service data sequence is not stable, an average value of n data is used as the initial value, so that the influence of the initial value on the smooth value is reduced. For example, ADF unit root stationarity test is performed on the time series, and if P (significance value) is less than or equal to 0.5, it is indicated that the test is stationary, historical first-period data is used as an initial value, and if not, historical n-period average is used as an initial value.
Taking the example of a unit root test as non-stationary:
the initial values are:
in the method, in the process of the invention,represents a smoothed initial value, n represents the number of periods of service data included in the historical service data sequence, X n Indicating the nth phase of the harvest data.
The derivation formula is:
in the method, in the process of the invention,a primary exponential smoothing value representing the t-th period, alpha representing the smoothing coefficient, X t Indicating the data received at time t.
When t=1:
it should be noted that, in some embodiments, after the historical service data sequence is acquired, the method further includes a step of preprocessing data of the historical service data sequence, where the step may include: and processing the input historical service data blank value and abnormal value. For the null values, a near 5-phase data mean fill is used. Outliers were detected using the triple standard deviation method, and for the identified outliers, a near 5-phase data mean substitution was used.
S200, performing second-order exponential smoothing prediction through residual iteration based on a smoothing initial value and a historical service data sequence to obtain a fitting service data predicted value and a residual sequence;
it should be noted that, in some embodiments, as shown in fig. 5, step S200 may include: s201, acquiring an initial smoothing coefficient as a target smoothing coefficient; s202, determining an exponential smoothing value of each period by combining a target smoothing coefficient based on a smoothing initial value and service data of each period; the exponent smoothing values include a primary exponent smoothing value and a secondary exponent smoothing value; s203, determining a first business data predicted value of each period based on the exponential smoothing value of each period; s204, determining residual values of each period based on the first service data predicted value of each period; determining a final smoothing coefficient based on the residual value of each period; s205, taking the final smoothing coefficient as a target smoothing coefficient, returning to an exponential smoothing value determining unit, further determining a fitting service data predicted value according to the obtained first service data predicted value, and determining a residual sequence based on residual values of each period.
In some embodiments, determining the first traffic data prediction value of each period based on the exponential smoothing value of each period may include: determining a first prediction parameter based on the primary and secondary exponential smoothing values; determining a second prediction parameter based on the primary exponential smoothing value and the secondary exponential smoothing value in combination with the initial smoothing coefficient; and determining a first business data predicted value of each period based on the first predicted parameter and the second predicted parameter and combining the predicted period number.
In some embodiments, determining the final smoothing coefficients based on the residual values for each period may include: based on the residual values of each period, the final smoothing coefficient is obtained through iteration of residual square sum.
In some embodiments, the first and second exponential smoothing values of the historical traffic data sequence may be calculated. Wherein the first exponential smoothing value of the t-th phaseThe method comprises the following steps:
secondary exponential smoothing value at t-phaseThe method comprises the following steps:
wherein X is t For the actual business data value (such as cost, revenue, etc.) of the t period, the source of the t periodThe time sequence number of the initial data, not defined by the algorithm, is t and X in Table 1 below t α is a smoothing coefficient.
TABLE 1
And then a secondary exponential smoothing prediction model is established, wherein the linear equation of the prediction model is as follows:
Y t+T ＝a t +b t T,T＝1,2,3...
Wherein Y is t+T For the traffic data predictive value of the t+T period, T represents the number of periods shifted from the T period to the back (i.e., predictive period), a t Representing a first traffic data predictor, b t Representing a second traffic data predictor.
The prediction model is used for prediction, if alpha is too large, the more the recent service data value occupies the future predicted value, the more sensitive the predicted result is to the recent historical service value, namely, the random fluctuation situation of the service time sequence is excessively tracked, and the fundamental change is ignored. Too small a will result in a too smooth prediction.
Setting the sum of squares of residual errors as follows:
ε(i)＝Y t -X t
epsilon (i) represents a residual value, alpha is determined by a residual square sum minimum method, namely, an initial interval is set to be (0, 1), and iteration is sequentially carried out until the residual square sum E (alpha) is the minimum result. And determining a final smoothing coefficient, and then sleeving the final smoothing coefficient to the related calculation step to obtain a fitting service data predicted value based on the final smoothing coefficient and predicted by second-order exponential smoothing, and determining a residual sequence by the difference value between the service data predicted value of each period and the corresponding actual service in the historical service data sequence.
S300, analyzing a residual sequence by using a residual prediction model to obtain a residual prediction result;
The residual prediction model is obtained by training a gradient descent method based on a neural network, and the neural network comprises an input layer, a hidden layer and an output layer;
in some embodiments, the method may further include: determining a residual training sample according to the residual sequence; the model training module is used for training the neural network by a gradient descent method through residual training samples, adjusting weights of the input layer and the hidden layer based on calculation errors obtained by each round of training until the calculation errors are smaller than a second preset threshold value, and obtaining a residual prediction model.
In some embodiments, as shown in fig. 6, step S300 may include: s301, according to the residual sequence, combining the weight value from each neuron of the input layer to each neuron of the hidden layer and the first parameter threshold value of each neuron of the hidden layer to obtain output information from the input layer to the hidden layer; wherein the input layer and the hidden layer each include a plurality of neurons; s302, according to the output information, combining weights of all neurons of the hidden layer to obtain input information from the hidden layer to the output layer; s303, according to the input information, combining the second parameter threshold value to obtain a residual prediction result.
In some embodiments, after obtaining the service result of the second-order exponential smoothing prediction, the method further superimposes the predicted result of the BP neural network on the residual error, where the implementation steps may be:
1. The residual sequence between the business result and the true value of the second-order exponential smoothing prediction is epsilon () And takes it as input to the neural network model. Wherein ε is () The method comprises the following steps:
let the input layer have m neurons, the hidden layer has n neurons, the output information of input layer to hidden layer is:
wherein f (x) is an S-type transfer function, and the input residual data is mapped into a (0, 1) range, omega ij Representing weights of each neuron of the input layer to each neuron of the hidden layer, theta j For the threshold value (i.e. the first parameter threshold value, subscript j indicates the index of the hidden layer corresponding to the neuron) and pass the hidden layer data to the output layer, its hidden layer to the input net of the output layer p Prediction output of output layer residualThe (i.e. residual prediction result) is:
wherein w is j And (5) representing the weight value of each neuron of the hidden layer, wherein θ is a second parameter threshold. The first parameter threshold and the second parameter threshold can be adjusted according to the actual requirement of the residual prediction model.
p=1, 2, 3..the calculated error E for p residual training samples is:
and a gradient descent method is adopted to enable the calculation error to reach the minimum value, and the optimal value of model training is achieved by continuously adjusting the weights of the input layer and the hidden layer.
S400, obtaining target service data prediction according to the fitting service data prediction value and the residual error prediction result;
In some specific embodiments, the corrected prediction result may be obtained by overlapping the second-order exponential-smoothed service data prediction result and the residual result predicted by the BP neural networkAnd the final predicted business data of the mixed model is obtained.
The model fully considers the influence of partial linearity and nonlinearity of the time sequence on the service data prediction result, and is also a reasonable improvement of the traditional mixed model. The mean square error of the true value and the predicted value of the service is further reduced, so that the predicted result is more accurate.
It should be further noted that, in some embodiments, the predicted service data may be pre-monitored based on a preset pre-alarm threshold.
By taking the application of the invention in a income prediction scene as an example, important index income can be divided into summarized income, market-breaking income, client income, fusion income, important business income, government enterprise income, charging income and other aspects for prediction, and compared with the early warning threshold value of each derivative index determined according to business experience and standard, the income abnormality early warning index can be positioned in detail.
In order to fully explain the technical principles of the service data prediction according to the embodiments of the present invention, the following describes the service data prediction according to the present invention in detail with reference to some specific embodiments. It is to be understood that the following is illustrative of the principles of the present invention and is not in limitation thereof.
As shown in fig. 7, in some embodiments, the service data prediction may be implemented by:
1. acquiring input historical data (historical service data sequences) of each class, and preprocessing data (filling missing data and the like);
2. checking whether the business data sequence is stable; if yes, adopting first-period data as an initial value, otherwise, adopting a historical n-period average value as the initial value;
3. establishing a second-order exponential smoothing model;
4. determining a model attenuation factor alpha (i.e. a smoothing coefficient) according to a residual square sum minimum method;
5. outputting a service data predicted value, namely a residual sequence;
6. establishing a BP neural network model for the residual sequence;
7. determining weights of an input layer and a hidden layer by adopting a gradient descent method, and outputting residual errors;
8. superposing the residual predictive value and the business data value of the exponential smoothing prediction to obtain a final value;
9. comparing the final predicted value with an early warning threshold value, and judging whether the final predicted value falls in an early warning interval or not; if yes, early warning is carried out, otherwise, early warning is not carried out.
To sum up, in order to solve the related problems in the prior art, the method for predicting service data based on the second-order exponential smoothing neural network in the embodiment of the invention firstly performs unit root stationarity test on historical service data, and then uses first-period data as an initial value if the historical service data is stationary, and otherwise uses a historical n-period data average value as an initial value. And establishing a second-order exponential smoothing model, determining an attenuation factor alpha through a residual square sum minimum method, outputting a service data predicted value and a predicted residual, taking the residual as an input value to establish a BP neural network model, determining weights of an input layer and a hidden layer by adopting a gradient descent method, outputting the predicted residual, and superposing the residual predicted value and the service data value of exponential smoothing prediction to obtain a final value. And comparing the service data values with the early warning threshold values to judge whether the service data values with different indexes need early warning. Specifically, most of the current technologies generally take a fixed value for the second-order exponential smoothing attenuation factor, but the invention reduces the prediction deviation by iteratively taking an optimal value; in addition, the invention carries out neural network prediction again aiming at the residual error of the second-order exponential smoothing prediction result, thereby reducing the loss of information; according to the invention, the business data is split into different aspects, and the grid is used as the grip, so that the business data transaction range can be further reduced. The invention adopts a method of combining secondary smoothing and a neural network, can reduce the influence of information loss caused by adopting second-order exponential smoothing prediction, and as shown in fig. 8, the error proportion distribution of the invention for predicting the daily degree business data in a month can be seen that the prediction value error is gradually reduced. Compared with the prior art, the invention has the following beneficial effects:
1. When the second-order exponential smoothing initial value is determined, the first-period data are adopted if the second-order exponential smoothing initial value is stable, and the average value of the historical n data is adopted as the initial value if the second-order exponential smoothing initial value is not stable, so that the influence of the initial value on a prediction result is reduced.
2. When the attenuation factor alpha of the second-order exponential smoothing model is determined, the method is used for determining by adopting a residual square sum minimum method, and deviation generated by prediction by adopting a fixed value is reduced.
And 3, when the BP neural network predicts the residual error, determining the weights of the input layer and the hidden layer by adopting a gradient descent method, so that the calculation error in the process of predicting the residual error is minimized.
The content of the method embodiment of the invention is applicable to the system embodiment, the flow steps specifically realized by the method embodiment are the same as the functional flows executed by the modules of the system embodiment, and the achieved beneficial effects are the same as those achieved by the system.
On the other hand, as shown in fig. 9, an embodiment of the present invention further provides an electronic device 900, which includes at least one processor 910, and at least one memory 920 for storing at least one program; take a processor 910 and a memory 920 as examples.
The processor 910 and the memory 920 may be connected by a bus or other means.
Memory 920 acts as a non-transitory computer readable storage medium that may be used to store non-transitory software programs as well as non-transitory computer executable programs. In addition, memory 920 may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some implementations, the memory 920 may optionally include memory located remotely from the processor, which may be connected to the device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The above described embodiments of the electronic device are merely illustrative, wherein the units described as separate components may or may not be physically separate, i.e. may be located in one place, or may be distributed over 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 this embodiment.
In particular, FIG. 10 schematically shows a block diagram of a computer system for implementing an electronic device of an embodiment of the invention.
It should be noted that, the computer system 1000 of the electronic device shown in fig. 10 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present invention.
As shown in fig. 10, the computer system 1000 includes a central processing unit 1001 (Central Processing Unit, CPU) which can execute various appropriate actions and processes according to a program stored in a Read-Only Memory 1002 (ROM) or a program loaded from a storage section 1008 into a random access Memory 1003 (Random Access Memory, RAM). In the random access memory 1003, various programs and data necessary for the system operation are also stored. The cpu 1001, the rom 1002, and the ram 1003 are connected to each other via a bus 1004. An Input/Output interface 1005 (i.e., an I/O interface) is also connected to bus 1004.
The following components are connected to the input/output interface 1005: an input section 1006 including a keyboard, a mouse, and the like; an output portion 1007 including a Cathode Ray Tube (CRT), a liquid crystal display (Liquid Crystal Display, LCD), and a speaker; a storage portion 1008 including a hard disk or the like; and a communication section 1009 including a network interface card such as a local area network card, a modem, or the like. The communication section 1009 performs communication processing via a network such as the internet. The drive 1010 is also connected to the input/output interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like, is installed as needed in the drive 1010, so that a computer program read out therefrom is installed as needed in the storage section 1008.
In particular, the processes described in the various method flowcharts may be implemented as computer software programs according to embodiments of the invention. For example, embodiments of the present invention include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 1009, and/or installed from the removable medium 1011. The computer programs, when executed by the central processor 1001, perform the various functions defined in the system of the present invention.
It should be noted that, the computer readable medium shown in the embodiments of the present invention may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-Only Memory (ROM), an erasable programmable read-Only Memory (Erasable Programmable Read Only Memory, EPROM), flash Memory, an optical fiber, a portable compact disc read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
The content of the method embodiment of the invention is suitable for the system embodiment, the specific function of the system embodiment is the same as that of the method embodiment, and the achieved beneficial effects are the same as those of the method.
Another aspect of the embodiments of the present invention also provides a computer-readable storage medium storing a program that is executed by a processor to implement a method as before.
The content of the method embodiment of the invention is applicable to the computer readable storage medium embodiment, the functions of the computer readable storage medium embodiment are the same as those of the method embodiment, and the achieved beneficial effects are the same as those of the method.
Embodiments of the present invention also disclose a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions may be read from a computer-readable storage medium by a processor of a computer device, and executed by the processor, to cause the computer device to perform the foregoing method.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
It should be noted that although in the above detailed description several modules of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functions of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the invention. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present invention may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, a touch terminal, or a network device, etc.) to perform the method according to the embodiments of the present invention.
In some alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flowcharts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed, and in which sub-operations described as part of a larger operation are performed independently.
Furthermore, while the invention is described in the context of functional modules, it should be appreciated that, unless otherwise indicated, one or more of the functions and/or features may be integrated in a single physical device and/or software module or may be implemented in separate physical devices or software modules. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary to an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be apparent to those skilled in the art from consideration of their attributes, functions and internal relationships. Accordingly, one of ordinary skill in the art can implement the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative and are not intended to be limiting upon the scope of the invention, which is to be defined in the appended claims and their full scope of equivalents.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution apparatus, device, or apparatus, such as a computer-based apparatus, processor-containing apparatus, or other apparatus that can fetch the instructions from the instruction execution apparatus, device, or apparatus and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution apparatus, device, or apparatus.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium may even be paper or other suitable medium upon which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution device. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiment of the present invention has been described in detail, the present invention is not limited to the embodiments, and those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention, and the equivalent modifications or substitutions are intended to be included in the scope of the present invention as defined in the appended claims.
Claims (10)
1. A traffic data prediction system, comprising:
the stability test module is used for acquiring a historical service data sequence, carrying out stability test on the historical service data sequence and further determining a smooth initial value; the historical service data sequence comprises service data of a plurality of periods;
the exponential smoothing prediction module is used for carrying out second-order exponential smoothing prediction through residual iteration based on the smoothing initial value and the historical service data sequence to obtain a fitting service data predicted value and a residual sequence;
The residual prediction module is used for analyzing the residual sequence by utilizing a residual prediction model to obtain a residual prediction result;
the residual prediction model is obtained by training a gradient descent method based on a neural network, and the neural network comprises an input layer, a hidden layer and an output layer;
and the result prediction module is used for obtaining a target service data prediction result according to the fitting service data prediction value and the residual error prediction result.
2. The business data prediction system according to claim 1, wherein the stationarity check module comprises:
the significant value acquisition unit is used for carrying out stability test on the historical service data sequence through unit root test to obtain a significant value of the unit root test;
the first initial value acquisition module is used for acquiring the service data in the first period in the historical service data sequence as a service data initial value when the significance value is smaller than or equal to a first preset threshold value;
and the second initial value acquisition module is used for acquiring the average value of the service data in each period in the historical service data sequence as a service data initial value when the significance value is larger than the first preset threshold value.
3. The traffic data prediction system according to claim 1, wherein the exponential smoothing prediction module comprises:
a first acquisition unit configured to acquire an initial smoothing coefficient as a target smoothing coefficient;
an exponential smoothing value determining unit, configured to determine an exponential smoothing value of each period in combination with the target smoothing coefficient, based on the smoothing initial value and the service data of each period; the exponent-smoothed value includes a primary exponent-smoothed value and a secondary exponent-smoothed value;
a first business prediction unit, configured to determine a first business data prediction value of each period based on the exponential smoothing value of each period;
a smoothing coefficient determining unit, configured to determine a residual value of each period based on the first service data prediction value of each period; determining a final smoothing coefficient based on the residual error values of each period;
and the second business prediction unit is used for taking the final smoothing coefficient as a target smoothing coefficient, returning to the exponential smoothing value determination unit, further determining a fitting business data prediction value according to the obtained first business data prediction value, and determining a residual sequence based on the residual value of each period.
4. The traffic data prediction system according to claim 3, wherein the first traffic prediction unit comprises:
A first prediction subunit configured to determine a first prediction parameter based on the primary exponential smoothing value and the secondary exponential smoothing value;
a second prediction subunit, configured to determine a second prediction parameter based on the primary exponential smoothing value and the secondary exponential smoothing value, in combination with the initial smoothing coefficient;
and the third prediction subunit is used for determining a first service data predicted value of each period according to the first prediction parameter and the second prediction parameter and combining the prediction period number.
5. The traffic data prediction system according to claim 3, wherein the smoothing coefficient determination unit includes:
and the residual iteration subunit is used for obtaining a final smoothing coefficient through iteration of residual square sums based on the residual values of each period.
6. The traffic data prediction system according to claim 1, wherein the system further comprises:
the training sample determining module is used for determining a residual training sample according to the residual sequence;
the model training module is used for training the neural network by the gradient descent method through the residual error training sample, adjusting the weights of the input layer and the hidden layer based on the calculation error obtained by each round of training until the calculation error is smaller than a second preset threshold value, and obtaining a residual error prediction model.
7. The traffic data prediction system according to claim 1, wherein the residual prediction module comprises:
the output information unit is used for combining the weight value from each neuron of the input layer to each neuron of the hidden layer and the first parameter threshold value of each neuron of the hidden layer according to the residual error sequence to obtain output information from the input layer to the hidden layer; wherein the input layer and the hidden layer each comprise a plurality of neurons;
the input information unit is used for combining the weight of each neuron of the hidden layer according to the output information to obtain the input information from the hidden layer to the output layer;
and the residual prediction unit is used for combining a second parameter threshold according to the input information to obtain a residual prediction result.
8. A service data prediction method applied to the prediction system according to any one of claims 1 to 7, comprising:
acquiring a historical service data sequence, and performing stability test on the historical service data sequence to further determine a smooth initial value; the historical service data sequence comprises service data of a plurality of periods;
performing second-order exponential smoothing prediction through residual iteration based on the smoothing initial value and the historical service data sequence to obtain a fitting service data predicted value and a residual sequence;
Analyzing the residual sequence by using a residual prediction model to obtain a residual prediction result;
the residual prediction model is obtained by training a gradient descent method based on a neural network, and the neural network comprises an input layer, a hidden layer and an output layer;
and obtaining target service data prediction according to the fitting service data prediction value and the residual error prediction result.
9. An electronic device comprising a processor and a memory;
the memory is used for storing programs;
the processor executing the program implements the method of claim 8.
10. A computer storage medium in which a processor-executable program is stored, characterized in that the processor-executable program is for realizing the method of claim 8 when being executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310762499.9A CN116911773A (en) | 2023-06-26 | 2023-06-26 | Service data prediction system, method, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310762499.9A CN116911773A (en) | 2023-06-26 | 2023-06-26 | Service data prediction system, method, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116911773A true CN116911773A (en) | 2023-10-20 |
Family
ID=88361939
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310762499.9A Pending CN116911773A (en) | 2023-06-26 | 2023-06-26 | Service data prediction system, method, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116911773A (en) |
-
2023
- 2023-06-26 CN CN202310762499.9A patent/CN116911773A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110766184A (en) | Order quantity prediction method and device | |
| CN110866625A (en) | Promotion index information generation method and device | |
| CN116684330A (en) | Traffic prediction method, device, equipment and storage medium based on artificial intelligence | |
| CN114049072B (en) | Index determination method and device, electronic equipment and computer readable medium | |
| CN115599650A (en) | Health degree evaluation method and device of IT system, electronic equipment and storage medium | |
| CN114418189A (en) | Water quality grade prediction method, system, terminal device and storage medium | |
| CN108509179B (en) | Method for detecting human face and device for generating model | |
| CN114118570A (en) | Service data prediction method and device, electronic equipment and storage medium | |
| CN116756522B (en) | Probability forecasting method and device, storage medium and electronic equipment | |
| CN113159453A (en) | Resource data prediction method, device, equipment and storage medium | |
| CN113052063A (en) | Confidence threshold selection method, device, equipment and storage medium | |
| CN117132315A (en) | Active user prediction method, device, equipment and storage medium | |
| CN116362894A (en) | Multi-objective learning method, multi-objective learning device, electronic equipment and computer readable storage medium | |
| CN116911773A (en) | Service data prediction system, method, electronic equipment and storage medium | |
| CN116128135A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN113902230A (en) | Electric quantity deviation control method, system, storage medium and electronic equipment | |
| CN112989203B (en) | Material throwing method, device, equipment and medium | |
| CN116166957A (en) | LSTM-based data processing method, LSTM-based data processing device, computer equipment and medium | |
| CN111709786B (en) | Method, apparatus, device and medium for generating user retention time | |
| CN116402321B (en) | Method and device for determining demand of article, electronic equipment and storage medium | |
| CN116501993B (en) | House source data recommendation method and device | |
| CN111709785B (en) | Method, apparatus, device and medium for determining user retention time | |
| CN115567406A (en) | Method, device and system for managing network nodes | |
| CN114707666A (en) | Model training method, and method and device for pushing article data | |
| CN118245341A (en) | Service model switching method, device, electronic equipment and computer readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |