CN114154714A

CN114154714A - Time series data prediction method, time series data prediction device, computer equipment and medium

Info

Publication number: CN114154714A
Application number: CN202111452298.6A
Authority: CN
Inventors: 马国良
Original assignee: Xinzhi I Lai Network Technology Co ltd
Current assignee: Xinzhi I Lai Network Technology Co ltd
Priority date: 2021-12-01
Filing date: 2021-12-01
Publication date: 2022-03-08

Abstract

The disclosure relates to the technical field of energy data processing, and provides a time sequence data prediction method, a time sequence data prediction device, computer equipment and a time sequence data prediction medium. The method comprises the following steps: acquiring a reference data set and at least one supplementary test set; processing the metadata in the reference data set and the supplementary test set based on a preset data set decomposition mode to obtain a reference trend subset, a reference period subset, a supplementary trend subset and a supplementary period subset; generating a target trend model; generating a target periodic model; and generating target prediction data based on a preset calculation strategy, a reference trend subset, a reference period subset, a target trend model and a target period model. Through the steps, the prediction precision of the data can be greatly improved.

Description

Time series data prediction method, time series data prediction device, computer equipment and medium

Technical Field

The present disclosure relates to the field of energy data processing technologies, and in particular, to a time series data prediction method, apparatus, computer device, and medium.

Background

With the rapid development of data processing technology, the energy field generates more and more data processing requirements. In some cases, due to the limitation of current data or the sensitivity of data, the data which can be obtained is very little, and the problem of data heterogeneity of different sources is large, so that the accuracy of data prediction is low.

Disclosure of Invention

In view of this, embodiments of the present disclosure provide a time series data prediction method, an apparatus, a computer device, and a medium, so as to solve the problem in the prior art that the accuracy of data prediction is low because the obtained data is very few and the problem of data heterogeneity of different sources is large.

In a first aspect of the embodiments of the present disclosure, a time series data prediction method is provided, including: acquiring a reference data set and at least one supplementary test set; processing the metadata in the reference data set and the supplementary test set based on a preset data set decomposition mode to obtain a reference trend subset, a reference period subset, a supplementary trend subset and a supplementary period subset; training the initial trend model through the reference trend subset and the supplementary trend subset to generate a target trend model; training the initial period model through the reference period subset and the supplementary period subset to generate a target period model; and generating target prediction data based on a preset calculation strategy, a reference trend subset, a reference period subset, a target trend model and a target period model.

In a second aspect of the embodiments of the present disclosure, there is provided a time series data prediction apparatus, including: an acquisition module configured to acquire a reference data set and at least one supplemental test set; the analysis module is configured to process the metadata in the reference data set and the supplementary test set based on a preset data set analysis mode to obtain a reference trend subset, a reference period subset, a supplementary trend subset and a supplementary period subset; the trend training module is configured to train the initial trend model through the reference trend subset and the supplementary trend subset to generate a target trend model; the period training module is configured to train the initial period model through the reference period subset and the supplementary period subset to generate a target period model; the generating module is configured to generate target prediction data based on a preset computing strategy, the reference trend subset, the reference period subset, the target trend model and the target period model.

In a third aspect of the embodiments of the present disclosure, a computer device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above method when executing the computer program.

In a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, which stores a computer program, which when executed by a processor, implements the steps of the above-mentioned method.

Compared with the prior art, the embodiment of the disclosure has the advantages that at least: the embodiment of the present disclosure obtains a reference data set and at least one supplemental test set; processing the metadata in the reference data set and the supplementary test set based on a preset data set decomposition mode to obtain a reference trend subset, a reference period subset, a supplementary trend subset and a supplementary period subset; training the initial trend model through the reference trend subset and the supplementary trend subset to generate a target trend model; training the initial period model through the reference period subset and the supplementary period subset to generate a target period model; target prediction data are generated based on a preset calculation strategy, a reference trend subset, a reference period subset, a target trend model and a target period model, and the prediction precision of the data can be greatly improved.

Drawings

To more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings needed for the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without inventive efforts.

FIG. 1 is an architectural diagram of a joint learning of an embodiment of the present disclosure;

FIG. 2 is a flow chart of a method for predicting time series data according to an embodiment of the disclosure;

FIG. 3 is a flowchart of an embodiment of a method for predicting timing data according to the present disclosure;

FIG. 4 is a block diagram of a time series data prediction apparatus provided by an embodiment of the present disclosure;

fig. 5 is a schematic diagram of a computer device provided by an embodiment of the present disclosure.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the disclosed embodiments. However, it will be apparent to one skilled in the art that the present disclosure may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present disclosure with unnecessary detail.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Joint learning refers to comprehensively utilizing multiple AI (Artificial Intelligence) technologies on the premise of ensuring data security and user privacy, jointly mining data values by combining multiple parties, and promoting new intelligent business states and modes based on joint modeling. The joint learning has at least the following characteristics:

(1) and the participating nodes control the weak centralized joint training mode of own data, so that the data privacy security in the co-creation intelligent process is ensured.

(2) Under different application scenes, a plurality of model aggregation optimization strategies are established by utilizing screening and/or combined AI algorithm and privacy protection calculation so as to obtain a high-level and high-quality model.

(3) On the premise of ensuring data security and user privacy, the method for improving the efficiency of the joint learning engine is obtained based on a plurality of model aggregation optimization strategies, wherein the efficiency method can improve the overall efficiency of the joint learning engine by solving the problems of information interaction, intelligent perception, abnormal processing mechanisms and the like under the conditions of parallel computing architectures and large-scale cross-domain networks.

(4) The requirements of the users of multiple parties in each scene are acquired, the real contribution degree of each joint participant is determined and reasonably evaluated through a mutual trust mechanism, and distribution stimulation is carried out.

Based on the mode, the AI technical ecology based on the joint learning can be established, the industrial data value is fully exerted, and the falling of scenes in the vertical field is promoted.

The present disclosure will be described in detail below with reference to the accompanying drawings.

Fig. 1 is an architecture diagram of joint learning according to an embodiment of the present disclosure. As shown in fig. 1, the architecture of joint learning may include a server (central node) 101, as well as a participant 102, a participant 103, and a participant 104.

In the joint learning process, a basic model may be built by the server 101, and the server 101 sends the model to the

participants

102, 103, and 104 with which communication connections are established. The basic model may also be uploaded to the server 101 after any participant has established the model, and the server 101 sends the model to other participants with whom communication connection is established. The participating party 102, the participating party 103 and the participating party 104 construct models according to the downloaded basic structures and model parameters, perform model training by using local data to obtain updated model parameters, and upload the updated model parameters to the server 101 in an encrypted manner. Server 101 aggregates the model parameters sent by

participants

102, 103, and 104 to obtain global model parameters, and passes the global model parameters back to

participants

102, 103, and 104. And the

participants

102, 103 and 104 iterate the respective models according to the received global model parameters until the models finally converge, thereby realizing the training of the models. In the joint learning process, data uploaded by the

participants

102, 103 and 104 are model parameters, local data are not uploaded to the server 101, and all the participants can share the final model parameters, so that common modeling can be realized on the basis of ensuring data privacy. It should be noted that the number of the participants is not limited to three as described above, but may be set according to needs, which is not limited by the embodiment of the present disclosure.

Fig. 2 is a flowchart of a time series data prediction method according to an embodiment of the disclosure. The time series data prediction method of fig. 2 may be performed by the terminal device or the server 2 of fig. 1. As shown in fig. 2, the time series data prediction method includes:

s201, acquiring a reference data set and at least one supplementary test set.

The reference data set and the supplemental test set comprise a data set composed of a plurality of metadata, wherein the metadata refers to a data structure composed of one or more types of characteristic data, and the characteristic data can be basic numerical units, such as an "average temperature: 35.4 "," daily gas amount: 55.65 ", etc.

S202, processing the metadata in the reference data set and the at least one supplementary test set based on a preset data set decomposition mode to obtain a reference trend subset, a reference period subset, at least one supplementary trend subset and at least one supplementary period subset.

The data set decomposition mode may be a mode of decomposing the data set into a plurality of sub data sets having the same structure as the data set, where the same structure may mean that the number, the category, and other aspects of the feature data of the metadata in two or more data sets are the same, the trend subset refers to a data subset decomposed based on the trend change, and the cycle subset refers to a data subset decomposed based on the cycle change. Trend changes refer to a trend or state that continuously changes over a period of time. For example, when a predicted value has a trend that changes upward or downward over time over a period of time, it is considered to have a trend.

S203, training the initial trend model through the reference trend subset and the at least one supplementary trend subset to generate a target trend model.

The initial trend model refers to an existing or self-set mathematical expression related to trend change, and parameters of the mathematical expression can be constants, arrays, vectors and the like. Training the initial trend model may refer to a process of determining model parameters through a series of steps or methods based on the acquired data of the reference trend subset and the supplementary trend subset, and finally obtaining a target trend model satisfying requirements.

S204, training the initial period model through the reference period subset and the at least one supplementary period subset to generate a target period model.

The initial periodic model may refer to a preset model with parameters of the model at initial default values. The model is trained based on the data of the reference and supplemental period subsets, and its parameters can be optimized to obtain a trained target period model.

And S205, generating target prediction data based on a preset calculation strategy, a reference trend subset, a reference period subset, a target trend model and a target period model.

The embodiment of the present disclosure obtains a reference data set and at least one supplemental test set; processing the metadata in the reference data set and the at least one supplementary test set based on a preset data set decomposition mode to obtain a reference trend subset, a reference period subset, at least one supplementary trend subset and at least one supplementary period subset; training the initial trend model through the reference trend subset and at least one supplementary trend subset to generate a target trend model; training the initial period model through the reference period subset and at least one supplementary period subset to generate a target period model; target prediction data are generated based on a preset calculation strategy, a reference trend subset, a reference period subset, a target trend model and a target period model, and the prediction precision of the data can be greatly improved.

In some embodiments, obtaining a reference data set and at least one supplemental test set comprises: obtaining an original data set, wherein the original data set comprises at least one metadata; processing at least one metadata in the original data set based on a basic data processing strategy to generate at least one basic processed metadata to obtain a reference data set; acquiring at least one original supplementary set; and processing each original supplementary set in the at least one original supplementary set based on a supplementary processing strategy to generate at least one supplementary processed original supplementary set, so as to obtain at least one supplementary test set.

The raw data set may refer to a data structure composed of the acquired raw metadata. Raw metadata may refer to a data structure composed of the data in the raw format that is acquired. The timestamp data may refer to data representing time in the metadata, and a format of the timestamp data may be set according to needs, which is not particularly limited herein. An underlying data processing policy may refer to a step or method of manipulating data in a raw format so that the data may be used to process a model. A supplemental processing policy may refer to a step or method of processing data in at least one supplemental test set in a certain manner.

In some embodiments, the underlying data processing policy comprises: performing exception processing on the acquired at least one piece of metadata to acquire the metadata after exception processing, wherein the number of the metadata can be one or more; smoothing the metadata subjected to the exception processing to obtain the metadata subjected to the smoothing processing so as to construct a smooth data set; and processing the smooth data set based on the splitting processing strategy to obtain processed metadata.

Specifically, the abnormal data may refer to one or some data in the metadata that does not meet a preset requirement, and the abnormal processing may include checking data consistency or processing invalid values and missing values, and deleting or replacing the abnormal data in the metadata. Invalid values may refer to null values, values that do not meet data type requirements, or other outliers, and missing values may refer to values in an existing data set for which the value of one or some attributes is incomplete.

Smoothing may refer to reducing the magnitude of change in metadata, and smoothing may make the trend of data more noticeable. As an example, the smoothing process may use the following mathematical formula:

F(t+n)/2＝(F(t+1)+F(t+1)+F(t+1)+...+F(t+n))/n

where t denotes a data number, and F (t + n) denotes data of the t + n-th number, where t and n are integers.

The splitting processing policy represents a step or method of additionally splitting out one or more feature data based on the time stamp data. As an example, one time stamp data may be "09/04/2017", which may be additionally split into any one of the following data: "week: 6 "," day of the year: 245 "," year week: 35 "," year information: 2017 "or" monthly information: 09". Through splitting the timestamp into other time characteristic data, data dimensionality can be increased, and a result obtained by training is more accurate.

In some embodiments, processing the smoothed data set based on the split processing policy to obtain processed metadata comprises: obtaining at least one split index; generating an intermediate timestamp dataset based on the split index and timestamp data for each metadata in the smoothed dataset; and updating each timestamp data in the smoothed data set to each metadata in the smoothed data set to obtain the processed metadata.

In some embodiments, generating the intermediate timestamp dataset based on the split index and the timestamp data for each metadata in the smoothed dataset comprises: acquiring one index which is not marked as split in the splitting indexes to obtain an intermediate index; processing the timestamp data of each metadata in the smooth data set based on the intermediate index to generate intermediate timestamp data to obtain an intermediate timestamp data set; marking the intermediate index as split; and repeating the steps until each split index is marked as split, so as to obtain an intermediate timestamp data set.

In some embodiments, the supplemental processing strategy comprises: obtaining an original supplementary set, wherein the original supplementary set comprises at least one metadata; acquiring a conversion coefficient corresponding to the original supplement set; generating at least one transformed metadata based on the at least one metadata in the original supplemental set and the transformation coefficients; and processing the at least one converted metadata based on the basic data processing strategy to generate at least one basic processed metadata, so as to obtain the supplemented original supplement set.

The conversion coefficient may refer to a coefficient that performs conversion processing on metadata in the supplementary data. Because the data of the supplementary set is different from the reference data set, a certain conversion coefficient can be set, and the proportion of training the model by the data of the supplementary set is reduced. The conversion coefficient can be specified by human experience or calculated in a certain mode. As an example, the statistical target is daily gas consumption, the reference data set includes 100 pieces of daily gas consumption data, and the 100 pieces of daily gas consumption data are summed to obtain a reference data sum. One supplementary data set contains 200 data, and the 200 data are summed to obtain a supplementary data sum. The coefficient may be the supplementary data sum/(base data sum + supplementary data sum). It should be noted that the above calculation method is only one use method, and other use methods may also be set according to needs, and are not limited specifically herein.

In some embodiments, the predetermined data set decomposition method is an STL additive data set decomposition method.

STL (temporal sequence decomposition method using robust local weighted regression as smoothing method) is an implementation method based on local weighted regression. Wherein, Loess (localized weighted scattered regression, LOWESS or LOESS) is a common method for smoothing a two-dimensional scatter diagram, and combines the simplicity of the traditional linear regression and the flexibility of the nonlinear regression. The STL additive dataset factorization approach may refer to the division of a dataset into three data subsets: a trend subset, a period subset, and a residual subset. The trend subset and the period subset are referred to the above description, and are not described herein again. The residual subset may refer to a subset of data decomposed based on a residual phenomenon. Residual phenomena may refer to the effects on a time series due to numerous incidental factors. And adding the metadata corresponding to each of the trend subset, the period subset and the residual error subset to obtain the data before splitting. It is noted that since the contribution of the residuals is very small, typically not more than 1%, subsets of the residuals are typically ignored. As an example, the initial data is 100, and after the STL additive data and the decomposition method are processed, the trend value is 60 and the period value is 40 (the residual value is ignored), and then the trend value and the period value are added, so that the initial data 100 before splitting can be obtained.

In some embodiments, computing the policy comprises: importing the reference trend subset into a target trend model to obtain trend target data; importing the reference period subset into a target period model to obtain period target data; and obtaining target prediction data based on the trend target data and the period target data. The trend target data may refer to a predicted trend value, and the cycle target data may refer to a predicted cycle value. And if the data set decomposition mode is an STL additive data set decomposition mode, adding the trend value and the target value to obtain target prediction data.

Fig. 3 is a flowchart of a method for predicting daily gas consumption of company a in 2021, provided by an embodiment of the present disclosure. The daily gas consumption prediction method of company a of fig. 3 in 2021 may be performed by the server of fig. 1. As shown in fig. 3, the daily gas consumption prediction method includes:

s301, acquiring an original daily gas volume data set of company A in 2020, wherein the original daily gas volume comprises at least one metadata.

S302, processing at least one metadata in the original daily gas consumption data set based on a basic data processing strategy to generate at least one basic processed metadata, and obtaining a reference daily gas consumption data set.

S303, acquiring a supplementary daily gas volume data set of company B in 2020.

S304, obtaining a conversion coefficient corresponding to the supplementary daily air volume data set and the original daily air volume data set.

S305, generating at least one converted metadata based on each metadata and conversion coefficient in the supplementary daily gas amount data set to obtain a target daily gas amount supplementary data set.

And S306, respectively processing the metadata in the reference daily gas consumption data set and the metadata in the target daily gas consumption supplementary data set based on the STL additive data set decomposition mode to obtain a reference trend subset, a reference period subset, a supplementary trend subset and a supplementary period subset.

And S307, training the initial trend model through the reference trend subset and the supplementary trend subset to generate a target trend model.

And S308, training the initial period model through the reference period subset and the supplementary period subset to generate a target period model.

And S309, importing the reference trend subset into the target trend model to obtain trend target data of the company A.

S310, importing the reference period subset into a target period model to obtain period target data of the company A.

S311, the trend target data and the period target data are summed to obtain the predicted data of company a in 2021.

All the above optional technical solutions may be combined arbitrarily to form optional embodiments of the present application, and are not described herein again.

The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods. For details not disclosed in the embodiments of the apparatus of the present disclosure, refer to the embodiments of the method of the present disclosure.

Fig. 4 is a schematic diagram of a time series data prediction apparatus according to an embodiment of the disclosure. As shown in fig. 4, the time series data prediction apparatus includes:

an acquisition module 401 configured to acquire a reference data set and at least one supplemental test set.

A decomposition module 402 configured to process the metadata in the reference data set and the at least one supplementary test set based on a preset data set decomposition manner, so as to obtain a reference trend subset, a reference cycle subset, at least one supplementary trend subset, and at least one supplementary cycle subset.

And a trend training module 403 configured to train the initial trend model through the reference trend subset and the at least one supplementary trend subset to generate a target trend model.

A period training module 404 configured to train the initial period model through the reference period subset and the at least one supplemental period subset to generate a target period model.

A generating module 405 configured to generate target prediction data based on a preset calculation strategy, the reference trend subset, the reference cycle subset, the target trend model, and the target cycle model.

According to the technical scheme provided by the embodiment of the disclosure, a reference data set and at least one supplementary test set are obtained; processing the metadata in the reference data set and the at least one supplementary test set based on a preset data set decomposition mode to obtain a reference trend subset, a reference period subset, at least one supplementary trend subset and at least one supplementary period subset; training the initial trend model through the reference trend subset and at least one supplementary trend subset to generate a target trend model; training the initial period model through the reference period subset and at least one supplementary period subset to generate a target period model; target prediction data are generated based on a preset calculation strategy, a reference trend subset, a reference period subset, a target trend model and a target period model, and the prediction precision of the data can be greatly improved.

In some embodiments, the acquisition module 401 of the time series data prediction apparatus is further configured to: obtaining an original data set, wherein the original data set comprises at least one metadata; processing at least one metadata in the original data set based on a basic data processing strategy to generate at least one basic processed metadata to obtain a reference data set; acquiring at least one original supplementary set; and processing each original supplementary set in the at least one original supplementary set based on a supplementary processing strategy to generate at least one supplementary processed original supplementary set, so as to obtain at least one supplementary test set.

In some embodiments, the underlying data processing policy comprises: obtaining timestamp data of each metadata in at least one metadata to obtain at least one timestamp data; performing exception handling on the acquired at least one metadata to obtain at least one metadata after exception handling; smoothing the at least one metadata subjected to the exception processing to obtain at least one metadata subjected to smoothing processing to obtain a smoothed data set; and processing the smooth data set based on the splitting processing strategy to obtain at least one piece of basic processed metadata.

In some embodiments, processing the smoothed data set based on the split processing policy to obtain at least one underlying processed metadata comprises: obtaining at least one split index; generating at least one intermediate timestamp dataset based on the at least one split index and timestamp data for each metadata in the smoothed dataset; and updating each timestamp data in the smoothed data set to each metadata in the smoothed data set to obtain at least one piece of metadata processed based on the metadata.

In some embodiments, the supplemental processing strategy comprises: obtaining an original supplementary set, wherein the original supplementary set comprises at least one metadata; acquiring a conversion coefficient corresponding to the original supplement set; generating at least one converted metadata based on the at least one metadata in the original complementary set and the conversion coefficient; and processing the at least one converted metadata based on the basic data processing strategy to generate at least one basic processed metadata to obtain an original supplement set after supplement processing.

In some embodiments, computing the policy comprises: importing the reference trend subset into a target trend model to obtain trend target data; importing the reference period subset into a target period model to obtain period target data; and obtaining target prediction data based on the trend target data and the period target data.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.

Fig. 5 is a schematic diagram of a computer device 500 provided by an embodiment of the present disclosure. As shown in fig. 5, the computer apparatus 500 of this embodiment includes: a processor 501, a memory 502 and a computer program 503 stored in the memory 502 and operable on the processor 501. The steps in the various method embodiments described above are implemented when the processor 501 executes the computer program 503. Alternatively, the processor 501 implements the functions of the respective modules/units in the above-described respective apparatus embodiments when executing the computer program 503.

Illustratively, the computer program 503 may be partitioned into one or more modules/units, which are stored in the memory 502 and executed by the processor 501 to accomplish the present disclosure. One or more modules/units may be a series of computer program instruction segments capable of performing certain functions, which are used to describe the execution of computer program 503 in computer device 500.

The computer device 500 may be a desktop computer, a notebook computer, a palm computer, a cloud server, or other computer devices. Computer device 500 may include, but is not limited to, a processor 501 and a memory 502. Those skilled in the art will appreciate that fig. 5 is only an example of a computer device 500 and is not intended to limit the computer device 500 and that the computer device 500 may include more or less components than shown, or some of the components may be combined, or different components, e.g., the computer device may also include input output devices, network access devices, buses, etc.

The Processor 501 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The storage 502 may be an internal storage unit of the computer device 500, such as a hard disk or a memory of the computer device 500. The memory 502 may also be an external storage device of the computer device 500, such as a plug-in hard disk provided on the computer device 500, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. Further, memory 502 may also include both internal and external storage devices for computer device 500. The memory 502 is used for storing computer programs and other programs and data required by the computer device. The memory 502 may also be used to temporarily store data that has been output or is to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules, so as to perform all or part of the functions described above. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

In the embodiments provided in the present disclosure, it should be understood that the disclosed apparatus/computer device and method may be implemented in other ways. For example, the above-described apparatus/computer device embodiments are merely illustrative, and for example, a division of modules or units, a division of logical functions only, an additional division may be made in actual implementation, multiple units or components may be combined or integrated with another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, the present disclosure may implement all or part of the flow of the method in the above embodiments, and may also be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of the above methods and embodiments. The computer program may comprise computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain suitable additions or additions that may be required in accordance with legislative and patent practices within the jurisdiction, for example, in some jurisdictions, computer readable media may not include electrical carrier signals or telecommunications signals in accordance with legislative and patent practices.

The above examples are only intended to illustrate the technical solutions of the present disclosure, not to limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present disclosure, and are intended to be included within the scope of the present disclosure.

Claims

1. A method for predicting time series data, comprising:

acquiring a reference data set and at least one supplementary test set;

processing the metadata in the reference data set and the supplementary test set based on a preset data set decomposition mode to obtain a reference trend subset, a reference period subset, a supplementary trend subset and a supplementary period subset;

training an initial trend model through the reference trend subset and the supplementary trend subset to generate a target trend model;

training an initial period model through the reference period subset and the supplementary period subset to generate a target period model;

and generating target prediction data based on a preset calculation strategy, the reference trend subset, the reference period subset, the target trend model and the target period model.

2. The method of claim 1, wherein the obtaining a reference data set and at least one supplemental test set comprises:

obtaining an original data set, wherein the original data set comprises at least one metadata;

processing at least one metadata in the original data set based on a basic data processing strategy to generate at least one basic processed metadata to obtain the reference data set;

acquiring at least one original supplementary set;

and processing each original supplementary set in the original supplementary sets based on a supplementary processing strategy to generate at least one supplementary processed original supplementary set to obtain the supplementary test set.

3. The method of claim 2, wherein the underlying data processing policy comprises:

performing exception processing on the acquired at least one metadata to acquire the metadata after exception processing;

smoothing the metadata subjected to the exception processing to obtain the metadata subjected to the smoothing processing so as to construct a smooth data set;

and processing the smooth data set based on a splitting processing strategy to obtain processed metadata.

4. The method of claim 3, wherein the processing the smoothed data set based on the split processing policy to obtain basic processed metadata comprises:

obtaining at least one split index;

generating an intermediate timestamp dataset based on the split index and timestamp data for each metadata in the smoothed dataset;

and updating each timestamp data in the smooth data set to each metadata in the smooth data set to obtain the metadata processed by the basis.

5. The method of claim 2, wherein the supplemental processing strategy comprises:

obtaining an original supplementary set, wherein the original supplementary set comprises at least one metadata;

acquiring a conversion coefficient corresponding to the original supplement set;

generating at least one transformed metadata based on the at least one metadata in the original supplemental set and the transformation coefficients;

and processing the converted metadata based on the basic data processing strategy to generate basic processed metadata so as to construct an original supplement set after supplement processing.

6. The method of claim 1, wherein the predetermined dataset decomposition is an STL additive dataset decomposition.

7. The method of any of claims 1 to 6, wherein the computational strategy comprises:

importing the reference trend subset into the target trend model to obtain trend target data;

importing the reference period subset into the target period model to obtain period target data;

and obtaining target prediction data based on the trend target data and the period target data.

8. A time series data prediction apparatus, comprising:

an acquisition module configured to acquire a reference data set and at least one supplemental test set;

the analysis module is configured to process the metadata in the reference data set and the at least one supplementary test set based on a preset data set analysis mode to obtain a reference trend subset, a reference period subset, at least one supplementary trend subset and at least one supplementary period subset;

a trend training module configured to train an initial trend model through the reference trend subset and the at least one supplementary trend subset to generate a target trend model;

a period training module configured to train an initial period model through the reference period subset and the at least one supplementary period subset to generate a target period model;

a generating module configured to generate target prediction data based on a preset calculation strategy, the reference trend subset, the reference cycle subset, the target trend model, and the target cycle model.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.