WO2023020257A1 - Data prediction method and apparatus, and storage medium - Google Patents

Abstract

The present application provides a data prediction method and apparatus, and a storage medium. The method comprises: acquiring hierarchical time series data, the hierarchical time series data being multiple data sets corresponding to various hierarchical time series, and the sum of data of sub-hierarchical levels of each hierarchical level being equal to data of a corresponding parent hierarchical level; and predicting the hierarchical time series data by using a preset data prediction model, and determining a prediction result within a preset time period after multiple historical time periods, the preset data prediction model being obtained by jointly performing training on the basis of prediction errors of multiple training data sets within a historical preset time period in the hierarchical time series data and errors between the hierarchical levels.

Description

Data prediction method, device and storage medium

Cross References to Related Applications

This application is based on a Chinese patent application with application number 202110943383.6 and a filing date of August 17, 2021, and claims the priority of this Chinese patent application. The entire content of this Chinese patent application is hereby incorporated by reference into this application.

technical field

The embodiments of the present application relate to the technical field of prediction models, and relate to a data prediction method, device, and storage medium.

Background technique

Time series forecasting has a wide range of applications, such as financial market forecasting, logistics volume forecasting, and so on. In the process of realizing automation and intelligence in many fields, time series forecasting plays a very important role. Therefore, forecasting technical capabilities will ultimately have an important impact on item transaction volume, inventory costs, etc. At the same time, the logistics volume of large logistics warehouses can reach up to one million, and large-scale time series pose new challenges to modern time series forecasting technology.

In related technologies, time series forecasting uses single-level data to make forecasts, and then obtains forecast results of other levels by splitting or aggregating. Although it is simple and convenient to use, it also leads to relatively low forecasting accuracy , the main disadvantages are: firstly, the existing forecasting methods essentially only use the forecasting results of a single level, and do not use the information contained in the forecasting data of other levels, resulting in the loss of accuracy; secondly, the forecasting results are aggregated upward or decomposed downward It also introduces additional prediction error. In addition, since the results obtained by using different single levels are different, it not only depends on manual experience in the selection of levels, but also leads to loss of accuracy.

Contents of the invention

A data prediction method, device, and storage medium provided in the embodiments of the present application.

The technical scheme of the present application is realized like this:

The embodiment of the present application provides a data prediction method, including:

Obtain hierarchical time series data; hierarchical time series data are multiple sets of data corresponding to time series of each level, wherein the sum of the data of the sub-levels of each level in each level is equal to the data of the corresponding parent level;

Use the preset data forecasting model to predict the hierarchical time series data, and determine the forecast results in the preset time period after multiple historical time periods; among them,

The preset data prediction model is based on the hierarchical time series data, the prediction errors of multiple sets of training data in the historical preset time period, and the errors between each level are jointly trained.

In the above scheme, using the preset data forecasting model to predict the hierarchical time series data, before determining the forecast results in the preset time period after multiple historical time periods, after obtaining the hierarchical time series data, the method also includes :

Standardize multiple sets of data of hierarchical time series data, and divide the standardized multiple sets of data into training set and test set according to the preset historical time period; the training set includes: multiple sets of training data; the test set includes: Multiple sets of test data;

Use the loss function of the initial prediction model to calculate the prediction error of the training set and the error between each level, and iteratively adjust the model parameters of the initial prediction model according to the prediction error and the error between each level until the training conditions are met. Obtaining the first prediction data set corresponding to the test set; the first prediction data set includes: multiple prediction data in the iterative process of each level of each historical time period corresponding to the test set;

A preset data prediction model is determined by comparing multiple sets of test data with the first prediction data set.

In the above scheme, use the loss function of the initial prediction model to calculate the prediction error of the training set and the error between each level, and iteratively adjust the model parameters of the initial prediction model according to the prediction error and the error between each level until it meets the training requirements. When the condition is stopped, the first prediction data set corresponding to the test set is obtained, including:

Inputting multiple sets of training data into the initial forecasting model to obtain a second forecasting data set; the second forecasting data set includes: forecasting data of various levels in multiple historical time periods;

Based on the second prediction data set and multiple sets of training data, the prediction error and the error between each level are calculated in combination with a loss function;

performing a gradient solution to the loss function by using the prediction error and the errors between the various levels to obtain model parameters in the iterative process, thereby obtaining an updated prediction model;

Using the updated prediction model, continue to train multiple sets of training data until the training conditions are met, and then obtain the final prediction model, thereby obtaining multiple prediction models in the iterative process;

In each of the corresponding second prediction data sets obtained by using multiple prediction models, the prediction data of each level of each historical time period corresponding to the test set is extracted, and then the first prediction data set in the iterative process is obtained.

In the above scheme, based on the second prediction data set and multiple sets of training data, the prediction error and the error between each level are calculated in combination with the loss function, including:

Based on the first prediction data in the second prediction data set and multiple sets of training data, the prediction error is calculated; the first prediction data is the prediction data of each level in multiple first time periods in the second prediction data set; multiple The first time period is a time period before a preset historical time period among the plurality of historical time periods;

Based on the second prediction data in the second prediction data set, calculate the error between each level; the second prediction data is the prediction data of each level in a plurality of second time periods in the second prediction data set; a plurality of second time periods The time period after the preset historical time period for multiple historical time periods.

In the above scheme, the prediction error is calculated based on the first prediction data in the second prediction data set and multiple sets of training data, including:

Calculate the sum of the squares of the difference between the first prediction data in the same first time period and the training data of the corresponding level, and then obtain the first sum of each level in the same first time period, and combine the multiple first time periods corresponding to The first sums are added to obtain the prediction error.

In the above solution, based on the second prediction data in the second prediction data set, the calculation of the error between each level includes:

Calculate the sum of the squares of the difference between the forecast data of each parent level in the second forecast data of each layer in the second forecast data in the same second time period, and the forecast data sum of the corresponding sub-levels, and combine multiple squares of multiple second time periods and sum to get the second sum;

Multiple second sums are multiplied by the harmonic error penalty hyperparameter to get the error between layers.

In the above scheme, multiple sets of test data are compared with the first prediction data set to determine a preset data prediction model, including:

Comparing the multiple sets of test data with the multiple forecast data in the first forecast data set respectively, and determining the multiple comparison errors corresponding to the multiple forecast data;

Determining a target comparison error within a preset error range among multiple comparison errors;

Determine the target iteration times corresponding to the target times forecast data corresponding to the target comparison error;

A preset data prediction model corresponding to the target iteration is determined among multiple prediction models.

In the above solution, multiple sets of training data include: multiple sets of first processed data; multiple sets of test data include: multiple sets of second processed data;

Standardize multiple sets of data of hierarchical time series data, and divide the standardized multiple sets of data into training sets and test sets according to preset historical time periods, including:

updating the outliers in each stratum with the average data for each stratum;

Using the average data corresponding to the level with blank data, fill the blank data corresponding to each level in multiple sets of data, and then obtain multiple sets of processed data corresponding to the time series of each level;

A preset historical time period is determined in a plurality of historical time periods, and multiple groups of first processed data corresponding to a plurality of first time periods before the preset historical time period are combined into the training set, and the preset historical time period is Multiple groups of second processed data corresponding to multiple second time periods after the first time period are combined into the test set.

In the above scheme, the method also includes:

Obtain multiple sets of logistics volume data corresponding to multiple historical time periods;

A preset data forecasting model is used to process multiple sets of logistics cargo volume data to obtain predicted logistics cargo volume data for a preset time period after multiple historical time periods.

The embodiment of the present application also provides a data prediction device, including:

The data acquisition module is configured to obtain hierarchical time series data; the hierarchical time series data are multiple sets of data corresponding to the time series of each level, wherein the sum of the data of the sub-levels of each level in each level is equal to the data of the corresponding parent level data;

The prediction module is configured to use a preset data prediction model to predict hierarchical time series data, and determine the prediction results within a preset time period after multiple historical time periods; wherein,

The preset data prediction model is obtained by joint training based on the prediction errors of multiple sets of training data in the historical preset time period in the hierarchical time series data, and the errors between each level.

The embodiment of the present application also provides a data prediction device, including a memory and a processor, the memory stores a computer program that can run on the processor, and the processor implements the steps in the above method when executing the program.

The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above method are implemented.

Description of drawings

FIG. 1 is an optional schematic flow chart of the data prediction method provided by the embodiment of the present application;

FIG. 2 is a schematic diagram of an optional effect of the data prediction method provided by the embodiment of the present application;

FIG. 3 is a schematic diagram of an optional effect of the data prediction method provided by the embodiment of the present application;

FIG. 4 is an optional schematic flow chart of the data prediction method provided in the embodiment of the present application;

FIG. 5 is an optional schematic flow chart of the data prediction method provided by the embodiment of the present application;

FIG. 6 is an optional schematic flow chart of the data prediction method provided by the embodiment of the present application;

FIG. 7 is an optional schematic flow chart of the data prediction method provided by the embodiment of the present application;

FIG. 8 is an optional schematic flow chart of the data prediction method provided by the embodiment of the present application;

FIG. 9 is an optional schematic flow chart of the data prediction method provided by the embodiment of the present application;

FIG. 10 is a schematic structural diagram of a logistics volume forecasting device provided in an embodiment of the present application;

FIG. 11 is an optional schematic flow chart of the data prediction method provided by the embodiment of the present application;

FIG. 12 is a first structural schematic diagram of a data prediction device provided by an embodiment of the present application;

FIG. 13 is a second structural schematic diagram of the data prediction device provided by the embodiment of the present application;

FIG. 14 is a schematic diagram of a hardware entity of a data prediction device provided by an embodiment of the present application.

Detailed ways

In order to make the purpose, technical solution and advantages of the application more clear, the technical solution of the application will be further elaborated below in conjunction with the accompanying drawings and embodiments. The described embodiments should not be considered as limiting the application. All other embodiments obtained under the premise of no creative work belong to the scope of protection of this application.

In the following description, references to "some embodiments" describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or a different subset of all possible embodiments, and Can be combined with each other without conflict.

If there is a similar description of "first/second" in the application documents, add the following explanation. In the following description, the terms "first\second\third" are only used to distinguish similar objects and do not mean Regarding the specific ordering of objects, it can be understood that "first\second\third" can be interchanged with specific order or sequence if allowed, so that the embodiment of the application described here can be used in addition to the performed in an order other than that shown or described.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application, and are not intended to limit the present application.

In related technologies, for example, a national fast-moving consumer goods manufacturer needs to predict the future sales of a certain product in the whole country and provinces at the same time in order to formulate inventory layout and stocking plan. The forecasting scheme is to make a single time-series forecast for the sales time series of each province and the whole country, then the forecast results of these different levels often do not automatically meet the consistency, that is, the sales forecast of the whole country is not equal to the sum of the sales forecast of each province. "Inconsistent" prediction results cannot be used in the collaborative decision-making process at all levels.

At present, the main forecasting methods include: "Top-Down", "Bottom-Up", "Middle-Out" and "Optimal Blending". As the name implies, "top-down" refers to forecasting the highest-level time series first, and then splitting the forecast results to lower levels according to a fixed ratio. "Bottom-up" refers to first predicting the most granular time series, and then The prediction results are aggregated upwards. The "break in the middle" approach combines bottom-up and top-down approaches. First, an "intermediate level" is selected and forecasts are generated for all series at that level. For series above the middle level, a bottom-up approach is used to generate consensus forecasts by aggregating forecasts from the "middle level" upwards. For series below the "intermediate level", a top-down approach is used to generate consensus forecasts by disaggregating the forecast for the "intermediate level" downwards. The "optimal reconciliation" method is to first obtain the prediction results of all levels, and then process the prediction results through the optimal linear weighted reconciliation method, and then obtain the final result.

The three methods of "top-down", "bottom-up", and "intermediate breakthrough" are currently the most used methods. These methods use only a single level of data to make predictions, and then obtain other data by splitting or aggregation. Although the hierarchical forecasting results are simple and convenient to use, they usually lead to relatively low forecasting accuracy. The main disadvantages are as follows: First, these three forecasting methods only use the single-level forecasting results, and do not use The information contained in the forecast data of other levels leads to the loss of accuracy; secondly, when the forecast results are aggregated up or decomposed down, additional forecast errors will be introduced. In addition, since the results obtained by using different single levels are different, it not only depends on manual experience in the selection of levels, but also leads to loss of accuracy.

In order to solve the above-mentioned technical problem of low prediction accuracy of the prediction model, the embodiment of the present application also provides a data prediction method, please refer to Figure 1, which is an optional schematic flow chart of the data prediction method provided by the embodiment of the present application , will be described in conjunction with the steps shown in FIG. 1 .

S101. Acquire hierarchical time series data; the hierarchical time series data are multiple sets of data corresponding to the time series of each level, wherein the sum of the data of the sub-levels of each level in each level is equal to the data of the corresponding parent level.

In this embodiment of the application, the server acquires hierarchical time series data. Among them, the hierarchical time series data are multiple sets of data corresponding to each hierarchical time series. The sum of the data of the sub-levels of each level in each level is equal to the data of the corresponding parent level.

In this embodiment of the present application, the server establishes communication connections with clients corresponding to each level in advance. The server obtains multiple sets of data of various levels corresponding to multiple historical time periods from the client through the communication connection with the clients of each level. That is, the server obtains multiple sets of data corresponding to the time series of each level from the clients of each level.

In the embodiment of the present application, the server acquires the pre-stored hierarchical time series data in its own database.

Wherein, any set of data among the multiple sets of data may include: a combination of data corresponding to each level of any time series. That is, any set of data among multiple sets of data may include: a combination of data at various levels corresponding to any one of multiple historical time periods. Wherein, one data in a group of data may be any one of sales data, logistics data, and user age data of a corresponding level. Wherein, the logistics flow data may be one of the corresponding total logistics pieces, total logistics weight and total logistics volume.

Exemplarily, the time series may be three time series respectively corresponding to three months before the current moment. The time series may also be three time series respectively corresponding to the three days before the current moment, and in the embodiment of the present application, the time series are not limited.

In this embodiment of the application, the sub-level may be the city level, and the parent level may be the provincial level corresponding to the sub-level. A provincial level can correspond to multiple city levels. The parent level can also be a first-level agent, and the sub-level can be multiple second-level agents corresponding to the parent level. One first-level agent can correspond to multiple second-level agents. The sum of the data of multiple sub-levels is the data of the corresponding parent level.

In the embodiment of the present application, the server first collects hierarchical time series data to be predicted. The value of the i-th time series observed by the server at time 1-T is recorded as y _i =(y ^t _i ,...,y ^T _i ) ^T , i=1,...,n. Wherein, y _i =(y ^t _i , . . . , y ^T _i ) ^T represents the data of each level in 1-T time periods, and 1, . . . , n are n levels.

Among them, the hierarchical time series data satisfies that the sum of the data of each sub-level is equal to the data of the corresponding parent level. Referring to FIG. 2 , the hierarchical structure satisfies y ₁ =y ₂ +y ₃ . Among them, y ₁ is the parent level data corresponding to y ₂ and y ₃ , and y ₂ and y ₃ are the child level data corresponding to y ₁ .

Referring to FIG. 3 , the hierarchical structure of hierarchical time series data satisfies y ₁ =y ₂ +y ₃ , y ₂ =y ₄ +y ₅ , and y ₃ =y ₆ +y ₇ . Among them, y ₂ is the parent level data corresponding to y ₄ and y ₅ , and y ₃ is the parent level data corresponding to y ₆ and y ₇ . The task of hierarchical time series forecasting is to predict the value of all time series in the future period t+h given the observation data at time 1,...,t ₀

where y is the data in the time series data. When the time series is a day dimension, it is the daily volume. For example, from July 1st to 5th, y_Beijing = (10, 20, 30, 40, 50), y_Hebei Province = (30, 40, 50, 60, 10). In the research and application of hierarchical time series, the constraint condition is often expressed graphically by the hierarchical structure diagram shown. This type of constraint is the basic feature of hierarchical time series, and it is also the embodiment of the meaning of "layered". This type of constraint is the natural law satisfied by each variable within the statistical range, such as Y_National=sum(Y_Beijing,Y_Hebei,… ), Y_Beijing = sum(Y_Haidian, ..., Y_Xicheng).

S102. Use the preset data prediction model to predict the hierarchical time series data, and determine the prediction results in the preset time period after multiple historical time periods; wherein, the preset data prediction model is based on the hierarchical time series data Among them, the prediction errors of multiple sets of training data in the historical preset time period, and the errors between the various levels are jointly trained.

In the embodiment of the present application, the server uses the preset data prediction model to predict the hierarchical time series data, and determines the prediction results in the preset time period after multiple historical time periods; wherein, the preset data prediction model is based on In the hierarchical time series data, the prediction errors of multiple sets of training data in the historical preset time period, and the errors between the various levels are jointly trained.

In the embodiment of the present application, the server divides multiple sets of data into a training set and a test set. The server iteratively trains the initial prediction model by combining the training data with the loss function. The server obtains multiple prediction models corresponding to multiple iterations through iterative training. The server compares the forecast data of each iteration with the corresponding real data to obtain the forecast error of each iteration. The server determines that the prediction model corresponding to the number of iterations with the smallest error is the preset data prediction model.

In the embodiment of the present application, by obtaining hierarchical time series data; hierarchical time series data are multiple sets of data corresponding to time series of each level, wherein the sum of the sub-level data of each level in each level is equal to that of the corresponding parent level Data; use the preset data forecasting model to predict the hierarchical time series data, and determine the forecast results in the preset time period after multiple historical time periods; wherein, the preset data forecasting model is based on the hierarchical time series data Among them, the prediction errors of multiple sets of training data in the historical preset time period, and the errors between the various levels are jointly trained. Since the preset data prediction model is based on the prediction error of multiple sets of training data in the historical time period and the error training between each level, not only the accuracy of the prediction error but also the difference between each level are taken into account during training. Error, so the pre-set data prediction model trained to predict the data is more accurate.

In some embodiments, refer to FIG. 4, which is an optional flowchart of the data prediction method provided by the embodiment of the present application. S101 shown in FIG. 1 also includes the implementation of S103 to S105, which will be described in conjunction with each step .

S103. Standardize the multiple sets of data of the hierarchical time series data, and divide the standardized multiple sets of data into a training set and a test set according to preset historical time periods.

In the embodiment of the present application, the server standardizes multiple sets of data of hierarchical time series data, and divides the multiple sets of standardized data into a training set and a test set according to preset historical time periods. Wherein, the training set includes: multiple sets of training data. The test set includes: multiple sets of test data.

In the embodiment of this application, the server can delete redundant data in multiple sets of data and fill them with the average data of the corresponding levels, or the server can fill the blank data of each level in the multiple sets of data with the average data of the corresponding levels to obtain the processed multiple sets of data. Since multiple sets of data correspond to multiple historical time periods. The server determines a preset historical time period in multiple historical time periods, and the server determines several sets of training data corresponding to the preset historical time period as a training set. The server determines the corresponding sets of test data after the preset historical time period as the test set.

Among them, the training set is the data set used to train the initial prediction model. The test set is the data set used to determine the preset data prediction model.

In the embodiment of the present application, the server preprocesses multiple sets of data, deletes outliers and fills in missing values, and standardizes the data. Then take a certain time t ₀ for the preprocessed data, and divide it into a training set (t=1, . . . , t0) and a test set (t=t0+1, . . . , T) according to usage.

S104. Use the loss function of the initial prediction model to calculate the prediction error of the training set and the error between each level, and iteratively adjust the model parameters of the initial prediction model according to the prediction error and the error between each level until the training conditions are met. Stop, get the first prediction data set corresponding to the test set.

In the embodiment of this application, the server uses the loss function of the initial prediction model to calculate the prediction error of the training set and the error between each level, and iteratively adjusts the model parameters of the initial prediction model according to the prediction error and the error between each level. Stop until the training condition is satisfied, and obtain the first prediction data set corresponding to the test set. Wherein, the first prediction data set includes: multiple prediction data in the iterative process of each level corresponding to each historical time period of the test set.

In the embodiment of the present application, the server inputs multiple sets of training data in the training set into the initial prediction model. A second forecast data set is obtained. The second forecast data set includes: forecast data of various levels in multiple historical time periods. Based on the second prediction data set and the multiple sets of training data, the server calculates the prediction errors of the multiple sets of training data and the errors between levels by combining the loss function. The server solves the loss function to obtain the model parameters for this training. The server adjusts the initial prediction model according to the model parameters to obtain a new prediction model. The server continues to train multiple sets of training data through the new prediction model, and stops when the training conditions are met, to obtain the final prediction model. At the same time, the first prediction data set corresponding to the test set in the iterative process is also obtained.

Wherein, satisfying the training condition may be: reaching a preset number of training times or convergence of a loss function value.

S105. Using multiple sets of test data to compare with the first prediction data set, determine a preset data prediction model.

In the embodiment of the present application, the server compares multiple sets of test data with the first prediction data set to determine a preset data prediction model.

In the embodiment of the present application, since the first prediction data set includes: multiple prediction data corresponding to multiple iterations of the test set. The server compares the data of each level in each time period in multiple sets of test data with the corresponding data in each forecast data to determine the error of each level, and then adds the errors of each level to obtain the error of each forecast data . Furthermore, multiple errors corresponding to multiple forecast data can be determined. The server determines that the predictive model corresponding to the iteratively adjusted primary predictive data with the smallest error is the preset data predictive model.

Exemplarily, the server subtracts the data of each level in each time period in multiple sets of test data from the corresponding data in a certain forecast data to obtain the error of the data in each level corresponding to each time period. The server adds the errors of the data of each level in each time period to obtain the error corresponding to the forecast data.

In the embodiment of the present application, the server iteratively adjusts the prediction model through the prediction error and the error between each level, and obtains multiple prediction models in the iterative process. The server then compares the multiple sets of test data with the first prediction data set to determine a preset data model. Since the preset data prediction model is based on the prediction error of multiple sets of training data in the historical time period and the error training between each level, not only the accuracy of the prediction error but also the difference between each level are taken into account during training. Error, so the pre-set data prediction model trained to predict the data is more accurate.

In some embodiments, refer to FIG. 5, which is an optional flowchart of the data prediction method provided by the embodiment of the present application. S104 shown in FIG. 4 can also be implemented through S106 to S110, which will be described in conjunction with each step .

S106. Input multiple sets of training data into the initial prediction model to obtain a second prediction data set.

In the embodiment of the present application, the server inputs multiple sets of training data into the initial prediction model to obtain the second prediction data set of the first iteration in the iterative process. Wherein, the second forecast data set includes: forecast data of various levels in multiple historical time periods.

In the embodiment of the present application, the server inputs multiple sets of training data into the initial prediction model to obtain the second prediction data set for the first training. The server calculates the prediction error and the error between each level according to the first second prediction data set and the loss function. The server obtains the model parameters according to the prediction error and the error between each level, adjusts the initial prediction model, and obtains the next updated prediction model. The server again inputs multiple sets of training data into the prediction model to be updated next time, and then executes the above process to complete the iteration.

S107. Based on the second prediction data set and multiple sets of training data, combine the loss function to calculate prediction errors and errors between levels.

In the embodiment of the present application, the server calculates the prediction error and the error between each level based on the second prediction data set and multiple sets of training data in combination with a loss function. Among them, the loss function is the function corresponding to the initial prediction model.

In the embodiment of the present application, the server calculates prediction errors corresponding to multiple sets of training data in multiple first time periods based on the second prediction data set and multiple sets of training data in combination with a loss function. Wherein, the multiple first time periods are the time periods before the preset historical time period among the multiple historical time periods. The prediction error characterizes the error between the predicted data and the corresponding data in multiple sets of training data.

In the embodiment of the present application, based on the second prediction data set, the server calculates errors between levels in the second prediction data set for multiple second time periods in combination with a loss function. Wherein, the multiple second time periods are time ends after the preset historical time period among the multiple historical time periods. The error between the various levels represents the error between the data of the parent level and the data of the corresponding child level in the second predicted data set.

S108. Perform a gradient solution to the loss function by using the prediction error and the error between each level to obtain model parameters in the iterative process, thereby obtaining an updated prediction model.

In the embodiment of the present application, the server uses the prediction error and the error between each level to solve the gradient of the loss function to obtain the model parameters in the iterative process, thereby obtaining an updated prediction model.

In the embodiment of the present application, during the iterative process, the server uses the prediction error and the error between each level to solve the loss function gradient after each iteration, and obtains the model parameters of each iteration in the iterative process. The server adjusts the current forecasting model through each model parameter to obtain an updated forecasting model.

S109. Using the updated prediction model, continue to train multiple sets of training data until the training conditions are met, and stop to obtain a final prediction model, thereby obtaining multiple prediction models in the iterative process.

In the embodiment of the present application, the server continues to train multiple sets of training data by using the updated prediction model, and stops when the training conditions are met to obtain the final prediction model, thereby obtaining multiple prediction models in the iterative process.

In the embodiment of this application, the network structure of the prediction model will be based on the prediction error and the error between each layer through the output layer, and then back-transmit layer by layer to the intermediate layer and input layer, and correct the weights of each layer in the way of gradient descent. When the weights of each layer of the network structure of the prediction model are corrected, a new prediction model is obtained. The network structure of the new prediction model will continue to train the training set until the training conditions are met and stop, and multiple prediction models in the iterative process will be obtained.

S110. From each corresponding second prediction data set obtained by using multiple prediction models, extract the prediction data of each level corresponding to each historical time period of the test set, and then obtain the first prediction data set in the iterative process.

In the embodiment of the present application, the server extracts the prediction data of each level in each historical time period of the corresponding test set from each of the corresponding second prediction data sets obtained by using multiple prediction models, and then obtains the first prediction data in the iterative process. A prediction data set.

In the embodiment of the present application, the server extracts the prediction data of each level corresponding to each historical time period of the test set from each second prediction data set, and obtains a prediction data set corresponding to each iteration. The server combines the prediction data set of each iteration to form the first prediction data set.

In the embodiment of the present application, the server inputs multiple sets of training data into the initial prediction model to obtain the second set of prediction data. The server then calculates the prediction error and the error between each level through the second prediction data set. The server iteratively adjusted the prediction model through the prediction error and the error between each level, and obtained multiple prediction models in the iterative process. At the same time, the server may extract the first prediction data set from the multiple second prediction data sets in the iterative process for comparison. Since the preset data prediction model is based on the prediction error of multiple sets of training data in the historical time period and the error training between each level, not only the accuracy of the prediction error but also the difference between each level are taken into account during training. Error, so the pre-set data prediction model trained to predict the data is more accurate.

In some embodiments, refer to FIG. 6, which is an optional flowchart of the data prediction method provided by the embodiment of the present application. S107 shown in FIG. 5 can also be implemented through S111 to S112, which will be described in conjunction with each step .

S111. Calculate a prediction error based on the first prediction data in the second prediction data set and multiple sets of training data.

In the embodiment of the present application, the server calculates the prediction error based on the first prediction data in the second prediction data set and multiple sets of training data.

Wherein, the first forecast data is the forecast data of each level in the plurality of first time periods in the second forecast data set. The multiple first time periods are time periods before the preset historical time period among the multiple historical time periods.

S112. Calculate errors between levels based on the second prediction data in the second prediction data set.

In this embodiment of the present application, the server calculates errors between levels based on the second prediction data in the second prediction data set.

Wherein, the second forecast data is the forecast data of each level in the multiple second time periods in the second forecast data set. The multiple second time periods are time periods after the preset historical time period among the multiple historical time periods.

In the embodiment of this application, the server builds a DeepAR-based hierarchical time series prediction model. The DeepAR model is a time series forecasting model based on a recurrent neural network, which can be used for general time series forecasting, but cannot be directly used for hierarchical time series forecasting. Therefore, for the hierarchical time series prediction task, the improved loss function (1) designed by the present application for hierarchical time series prediction is:

in,

is the prediction error loss,

is the loss function of the DeepAR model, without loss of generality, it is assumed here that

is the inter-level harmonic error loss, where λ is the harmonic error penalty term hyperparameter. C is a set of constraints derived from the hierarchical structure.

is the predicted value of the "parent node" time series in constraint c at time t,

is the predicted value of the "leaf node" time series in constraint c at time t, and J(c) is the number of "leaf nodes". Taking the hierarchical time series data with the structure shown in Figure 3 as an example, the constraints satisfied by the hierarchical structure are C={y ₁ =y ₂ +y ₃ , y ₂ =y ₄ +y ₅ , y ₃ =y ₆ + y ₇ }.

in,

for the predicted value.

for

corresponding training data. n is the number of each level, and _t0 is the number of multiple first time periods. T is the number of multiple second time periods.

In some embodiments, refer to FIG. 7, which is an optional schematic flowchart of the data prediction method provided by the embodiment of the present application. S111 to S112 shown in FIG. 6 can also be realized through S113 to S115, and each step will be combined Be explained.

S113. Calculate the sum of the squares of the differences between the first prediction data in the same first time period and the training data of the corresponding level, and then obtain the first sum of each level in the same first time period, and combine the first sums corresponding to the multiple first time periods A plurality of first sums are added to obtain a prediction error.

In the embodiment of the present application, the server calculates the sum of squares of the differences between the first prediction data in the same first time period and the training data of the corresponding level, and then obtains the first sum of each level in the same first time period. The server adds the multiple first sums corresponding to the multiple first time periods to obtain the prediction error.

Exemplarily, the multiple first time periods include: two first time periods. Each level includes: a parent level (a first-level agent) and two corresponding sub-levels (two second-level agents). The server calculates the sum of the squares of the difference between the data of the parent level and the corresponding forecast data in the first first time period, calculates the sum of the squares of the differences between the data of the two sub-levels and the corresponding forecast data, and then the server calculates the sum of the squares of the difference between the data of the parent level and the corresponding forecast data The sum of squares is added to the sum of squares of the differences corresponding to the two sublevels, resulting in a first sum corresponding to the first first time period. Similarly, the server uses the same method to calculate the first sum corresponding to the second time period. The server adds the two first sums to get the prediction error.

S114. Calculate the sum of the squares of the differences between the forecast data of each parent level in the second forecast data of each layer in the same second time period and the forecast data sums of the corresponding sub-levels, and combine the multiple second time periods The sums of squares are added to get the second sum.

In the embodiment of the present application, the server calculates the sum of the squares of the differences between the forecast data of each parent level of each layer in the second forecast data in the same second time period and the sum of the forecast data of the corresponding sub-levels, and combines the multiple The multiple sums of squares for the two time periods are added to obtain a second sum.

Exemplarily, the multiple second time periods include: two second time periods. Each level includes: a parent level (a first-level agent) and two corresponding sub-levels (two second-level agents). The server calculates the sum of squares of differences between the data of the parent level and the sum of predicted data of corresponding sub-levels in the first second time period. Similarly, the server uses the same method to calculate the sum of squares corresponding to the second time period. The server adds the two sums of squares to get the second sum.

S115. Multiply the multiple second sums by the hyperparameter of the harmonic error penalty term to obtain the inter-level error.

In the embodiment of the present application, the server obtains the error between various levels by using multiple hyperparameters of the second sum and harmonic error penalty term.

Among them, the harmonic error penalty hyperparameter can be any positive number.

Compared with ordinary time series forecasting, hierarchical time series forecasting essentially adds consistency constraints between levels to the final forecasting results, namely:

It is very difficult to directly solve such a large-scale optimization problem, and by adding constraints as penalty items to the loss function, we can solve formula (1) through methods such as stochastic gradient descent, for any given The difference penalty term hyperparameter λ, the inconsistency of prediction results between layers will decrease as the value of the loss function decreases during training.

For hierarchical time series forecasting, the time series of each level in the future must meet the consistency between levels. By adding the penalty term of the harmonization error loss, from the perspective of the parameter iteration process, this is equivalent to requiring the network parameters of DeepAR to take into account both the prediction deviation and the hierarchical structure deviation during the optimization process. From the results, this is equivalent to a lower bound on the optimization test set error. Taking the hierarchical timing in Figure 2 as an example, according to Cauchy's inequality:

Therefore, it can be seen that the hierarchical structure deviation term in the loss function is essentially a lower bound of the prediction error. Intuitive understanding means that although the prediction results that satisfy the consistency between levels do not necessarily guarantee the highest prediction accuracy, since the future The real data must meet the consistency, then if the error between the levels of the prediction results is large, then the prediction accuracy rate must not be very high, so adding this item to the loss function can help improve the layering time Predictive Performance for Sequence Forecasting.

In the embodiment of the present application, the server calculates the prediction error and the error between levels respectively by using the first prediction data and the second prediction data in the second prediction data set. Since the server considers the error between each level in the process of calculating the error in combination with the loss function, the prediction model adjusted by the model parameters of the loss function is more accurate in predicting the data.

In some embodiments, refer to FIG. 8 , which is an optional flowchart of the data prediction method provided by the embodiment of the present application. S103 shown in FIG. 3 can be implemented through S116 to S118 , which will be described in conjunction with each step.

S116. Utilize the average data of each level to update the abnormal value in each level.

In the embodiment of the present application, the server uses the average data of each level to update the abnormal value in each level.

Wherein, the average data is the average value of the data of multiple levels in multiple historical time periods of the level corresponding to the abnormal value.

S117. Using the average data corresponding to the levels with blank data, fill the blank data corresponding to each level in the multiple sets of data, and then obtain multiple sets of processed data corresponding to the time series of each level.

In the embodiment of the present application, the server uses the average data corresponding to the levels with blank data to fill the blank data corresponding to each level in multiple sets of data, and then obtain multiple sets of processed data corresponding to the time series of each level.

S118. Determine a preset historical time period in a plurality of historical time periods, combine multiple sets of first processed data corresponding to a plurality of first time periods before the preset historical time period into a training set, and combine the preset historical time period Multiple groups of second processed data corresponding to multiple second time periods after the period are combined into a test set.

In the embodiment of the present application, the server determines a preset historical time period in a plurality of historical time periods, and combines multiple sets of first processed data corresponding to a plurality of first time periods before the preset historical time period into a training set, Multiple groups of second processed data corresponding to multiple second time periods after the preset historical time period are combined into a test set.

Exemplarily, the multiple historical time periods may include: 12 time periods corresponding to January to December. The server may determine September as the preset historical time period. When the server determines that September is the preset historical time period, the multiple first time periods are 8 time periods corresponding to January-August, and the multiple second time periods can also be 3 corresponding to October-December period.

In the embodiment of the present application, the server standardizes multiple sets of data, deletes outliers and fills in blank data, thereby making the data structure of multiple sets of data more complete, which is beneficial to model training.

In some embodiments, refer to FIG. 8 , which is an optional flowchart of the data prediction method provided by the embodiment of the present application. S105 shown in FIG. 3 can be implemented through S119 to S122 , which will be described in conjunction with each step.

S119. Comparing multiple sets of test data with multiple prediction data in the first prediction data set respectively, and determining multiple comparison errors corresponding to multiple prediction data.

In the embodiment of the present application, the server compares multiple sets of test data with multiple prediction data in the first prediction data set, and determines multiple comparison errors corresponding to the multiple prediction data. Each prediction data is the prediction data of each level of each historical time period obtained in each iteration training process.

In the embodiment of the present application, the server compares the test data of each level in each time period in multiple sets of test data with the corresponding forecast data in a certain forecast data set of the first forecast data set. The server determines the errors corresponding to the test data of each level in each time period. The server adds the errors corresponding to the test data of each level in each time period to obtain the error corresponding to each time period, that is, the error of each set of test data is obtained. The server then adds the errors corresponding to each set of test data to obtain the error corresponding to the predicted data. Furthermore, multiple comparison errors of multiple prediction data can be obtained.

S120. Determine a target comparison error within a preset error range from the multiple comparison errors.

In the embodiment of the present application, the server determines a target comparison error within a preset error range from the multiple comparison errors.

S121. Determine the target iteration number corresponding to the target number of prediction data corresponding to the target comparison error.

In the embodiment of the present application, the server determines the target iteration number corresponding to the target number of prediction data corresponding to the target comparison error.

S122. Determine a preset data prediction model corresponding to the target iteration number among multiple prediction models.

In the embodiment of the present application, multiple prediction models are formed in the iterative process. The server determines a preset data prediction model corresponding to the target iteration number among multiple prediction models.

In the embodiment of the present application, due to the formation of multiple prediction models in the iterative process, the server determines the preset data prediction model corresponding to the target iteration number with the smallest error of multiple sets of test data, and because the preset data prediction model does not affect the test set The prediction accuracy is high, and then the hierarchical time series data can be processed through the preset data prediction model, and the prediction result with high prediction accuracy can be obtained.

In some embodiments, refer to FIG. 9 . FIG. 9 is an optional schematic flowchart of the data prediction method provided in the embodiment of the present application, which will be described in combination with various steps.

S123. Obtain multiple sets of logistics cargo volume data corresponding to multiple historical time periods.

In the embodiment of the present application, the server acquires multiple sets of logistics cargo volume data corresponding to multiple historical time periods.

Among them, multiple sets of logistics cargo volume data include: shipment volume data and hierarchical relationships of the whole country, each region, and each province.

S124. Using a preset data prediction model to process multiple sets of logistics cargo volume data to obtain predicted logistics cargo volume data for a preset time period after multiple historical time periods.

In the embodiment of the present application, the server uses a preset data prediction model to process multiple sets of logistics cargo volume data to obtain predicted logistics cargo volume data for preset time periods after multiple historical time periods.

In the embodiment of this application, the server uses the preset data prediction model to process multiple sets of logistics cargo data. Since the preset data prediction model is based on the prediction errors of multiple sets of training data in the historical preset time period, and the The error between them is obtained by training together. Furthermore, by using the preset data prediction model to predict multiple sets of logistics cargo volume data, a prediction result with high accuracy can be obtained.

The embodiment of the present application also provides a logistics cargo volume forecasting device 600 for implementing the data forecasting method provided in FIG. 9 . Please refer to FIG. 10 , which is a schematic structural diagram of the logistics cargo volume forecasting device provided in the embodiment of the present application.

The embodiment of the present application provides a logistics volume forecasting device 600 , including: a data acquisition module 601 , a data preprocessing module 602 , a target prediction model training module 603 and a data prediction model 604 .

The data acquisition module 601 is used to acquire the hierarchical relationship between the historical time series data of logistics cargo volume and time series. For example, the shipment data and hierarchical relationship of the whole country, each region, and each province. The data acquisition module 601 is used to execute S123.

The data preprocessing module 602 is used for preprocessing the data, removing outliers and filling missing values, and standardizing the data. Then the preprocessed data is divided into training set and test set.

The target prediction model training module 603 is used to train the initial network model by using the historical time series data to obtain the target prediction model of the time series data.

The data prediction module 604 is configured to use the target prediction model to predict the data of the time series data in the future time period to obtain a prediction result, and store and display the prediction result.

In some embodiments, referring to FIG. 11 , FIG. 11 is an optional schematic flowchart of the data prediction method provided in the embodiment of the present application, which will be described in combination with each step.

S201. Collect hierarchical time series data to be predicted.

Exemplarily, with reference to FIG. 12 , the data acquisition module 701 in the data prediction device 700 is used to acquire the hierarchical relationship between historical time series data and time series.

S202. Data preprocessing, removing outliers and filling in missing values; data segmentation, dividing training set and test set.

Exemplarily, the data preprocessing module 702 in the data forecasting device 700 is used to preprocess the historical time series data, remove outliers and fill in missing values, and standardize the data. Then the preprocessed data is divided into training set and test set.

S203. Construct a DeepAR time series prediction model.

S204, training set input.

S205. Setting hyperparameters of layered loss items.

S206. Update the parameters of the DeepAR model by using an adaptive learning rate Adam optimization algorithm.

S207. Whether the training reaches the preset number of times of training.

Exemplarily, the target prediction model training module 703 in the data prediction device 700 is configured to use historical time series data to train an initial network model to obtain a target prediction model for time series data. That is the final model.

S208, taking the final model and outputting a prediction result for the future period.

Exemplarily, the data prediction module 704 in the data prediction device 700 is used to use the target prediction model (final model) to predict the data of the time series data in the future time period to obtain the prediction results, and store and display the prediction results .

Since the DeepAR time series prediction model is constructed based on the prediction errors of multiple sets of training data in the hierarchical time series data in the historical time period, and the errors between each level, not only the prediction error is taken into account when training the DeepAR time series prediction model Accuracy also takes into account the errors between the various levels, so the final model trained is more accurate in predicting the data.

Exemplarily, the embodiment of the present application further provides a data prediction device 700 for executing the data prediction method provided in FIG. 11 . Please refer to FIG. 12 , which is a first structural diagram of the data prediction device provided in the embodiment of the present application.

The embodiment of the present application provides a data prediction device 700 , including: a data acquisition module 701 , a data preprocessing module 702 , a target prediction model training module 703 and a data prediction model 704 .

The data acquisition module 701 is used to acquire the hierarchical relationship between historical time series data and time series.

The data preprocessing module 702 is used for preprocessing the historical time series data, removing outliers and filling in missing values, and standardizing the data. Then the preprocessed data is divided into training set and test set. Module details are in S202 in the flow of the above prediction method.

The target prediction model training module 703 is used to train the initial network model by using the historical time series data to obtain the target prediction model of the time series data. Module details are in S203 to S207 in the flow of the above prediction method.

The data prediction module 704 is used to use the target prediction model to predict the data of the time series data in the future time period to obtain a prediction result, and store and display the prediction result. Module details are in S208 in the flow of the above prediction method.

Please refer to FIG. 13 , which is a second structural schematic diagram of a data prediction device provided by an embodiment of the present application.

The embodiment of the present application also provides a data prediction device 800 , including: a data acquisition unit 803 and a prediction unit 804 .

The data acquisition unit 803 is used to acquire hierarchical time series data; the hierarchical time series data are multiple sets of data corresponding to the time series of each level, wherein the sum of the sub-level data of each level in each level is equal to that of the corresponding parent level data;

The prediction unit 804 is configured to use a preset data prediction model to predict hierarchical time series data, and determine the prediction results within a preset time period after multiple historical time periods; wherein,

The preset data prediction model is obtained by joint training based on the prediction errors of multiple sets of training data in the historical preset time period in the hierarchical time series data, and the errors between each level.

In the embodiment of the present application, the data prediction device 800 is used to standardize multiple sets of data of hierarchical time series data, and divide the standardized multiple sets of data into training sets and test sets according to preset historical time periods; training The set includes: multiple sets of training data; the test set includes: multiple sets of test data; use the loss function of the initial prediction model to calculate the prediction error of the training set, and the error between each level, and based on the prediction error, and the error between each level. The model parameters of the initial prediction model are iteratively adjusted until the training conditions are met, and the first prediction data set corresponding to the test set is obtained; the first prediction data set includes: the iterative process of each level of each historical time period corresponding to the test set Multiple prediction data; use multiple sets of test data to compare with the first prediction data set, and determine a preset data prediction model.

In the embodiment of the present application, the data prediction device 800 is used to input multiple sets of training data into the initial prediction model to obtain the second prediction data set; the second prediction data set includes: prediction data of various levels in multiple historical time periods; based on the first Two prediction data sets and multiple sets of training data, combined with the loss function to calculate the prediction error and the error between each level; use the prediction error and the error between each level to solve the gradient of the loss function, and obtain the model parameters in the iterative process, so as to be updated prediction model; using the updated prediction model, continue to train multiple sets of training data until the training conditions are met, and stop to obtain the final prediction model, thereby obtaining multiple prediction models in the iterative process; when using multiple prediction models, From each corresponding second prediction data set, the prediction data of each level in each historical time period corresponding to the test set is extracted, and then the first prediction data set in the iterative process is obtained.

In the embodiment of the present application, the data prediction device 800 is used to calculate the prediction error based on the first prediction data in the second prediction data set and multiple sets of training data; the first prediction data is a plurality of first prediction data in the second prediction data set. The forecast data of each level in the time period; the multiple first time periods are the time periods before the preset historical time period in the multiple historical time periods; based on the second forecast data in the second forecast data set, calculate the time period between each level The error; the second forecast data is the forecast data of each level in the multiple second time periods in the second forecast data set; the multiple second time periods are the time periods after the preset historical time period among the multiple historical time periods.

In the embodiment of the present application, the data prediction device 800 is used to calculate the sum of the squares of the difference between the first prediction data in the same first time period and the training data of the corresponding level, and then obtain the first sum of each level in the same first time period , adding the multiple first sums corresponding to the multiple first time periods to obtain the prediction error.

In the embodiment of the present application, the data prediction device 800 is used to calculate the sum of the squares of the difference between the forecast data of each parent level of each layer in the second forecast data in the same second time period and the sum of the forecast data of the corresponding sub-levels , adding multiple sums of squares in multiple second time periods to obtain the second sum; multiplying the multiple second sums with the hyperparameter of the harmonic error penalty term to obtain the error between levels.

In the embodiment of the present application, the data prediction device 800 is used to compare multiple sets of test data with multiple prediction data in the first prediction data set, and determine multiple comparison errors corresponding to multiple prediction data; Determine the target comparison error within the preset error range from the comparison error; determine the target iteration number corresponding to the target prediction data corresponding to the target comparison error; determine the preset data prediction model corresponding to the target iteration number in multiple prediction models .

In the embodiment of the present application, the multiple sets of training data include: multiple sets of first processed data; multiple sets of test data include: multiple sets of second processed data; the data prediction device 800 is used to update each Outliers in the hierarchy; use the average data corresponding to the hierarchy with blank data to fill in the blank data corresponding to each hierarchy in multiple sets of data, and then obtain multiple sets of processed data corresponding to the time series of each hierarchy; in multiple historical time periods Determine the preset historical time period, combine multiple sets of first processed data corresponding to multiple first time periods before the preset historical time period into a training set, and combine multiple second time periods after the preset historical time period The corresponding sets of second processed data are combined into a test set.

In the embodiment of the present application, the data acquisition unit 803 in the data prediction device 800 is used to obtain multiple sets of logistics cargo volume data corresponding to multiple historical time periods; the prediction unit 804 in the data prediction device 800 is used to use the preset data prediction model Multiple sets of logistics cargo volume data are processed to obtain forecasted logistics cargo volume data for preset time periods after multiple historical time periods.

In the embodiment of the present application, the hierarchical time series data is obtained through the data acquisition unit 803; the hierarchical time series data are multiple sets of data corresponding to the time series of each level, wherein the sum of the sub-level data of each level in each level is equal to Corresponding to the data of the parent level; then use the preset data prediction model to predict the hierarchical time series data through the prediction unit 804, and determine the prediction results in the preset time period after multiple historical time periods; wherein, the preset data The prediction model is based on the hierarchical time series data, the prediction errors of multiple sets of training data in the historical preset time period, and the errors between each level are jointly trained. Since the preset data prediction model is based on the prediction error of multiple sets of training data in the historical time period and the error training between each level, not only the accuracy of the prediction error but also the difference between each level are taken into account during training. Error, so the pre-set data prediction model trained to predict the data is more accurate.

It should be noted that, in the embodiment of the present application, if the above-mentioned data prediction method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solutions of the embodiments of the present application or the part that contributes to the related technologies can be embodied in the form of software products. The computer software products are stored in a storage medium and include several instructions to make A data prediction device (which may be a personal computer, etc.) executes all or part of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes such as U disk, mobile hard disk, read-only memory (Read Only Memory, ROM), magnetic disk or optical disk. Thus, embodiments of the present application are not limited to any specific combination of hardware and software.

Correspondingly, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above method are implemented.

Correspondingly, the embodiment of the present application provides a data prediction device, including a memory 802 and a processor 801, the memory 802 stores a computer program that can be run on the processor 801, and the processor 801 implements when executing the program. steps in the method above.

It should be noted here that: the descriptions of the above storage medium and device embodiments are similar to the descriptions of the above method embodiments, and have similar beneficial effects to those of the method embodiments. For technical details not disclosed in the storage medium and device embodiments of the present application, please refer to the description of the method embodiment of the present application for understanding.

It should be noted that FIG. 14 is a schematic diagram of a hardware entity of the data prediction device provided in the embodiment of the present application. As shown in FIG. 14 , the hardware entity of the data prediction device 800 includes: a processor 801 and a memory 802, wherein;

The processor 801 generally controls the overall operation of the data prediction device 800 .

The memory 802 is configured to store instructions and applications executable by the processor 801, and can also cache data to be processed or processed by each module in the processor 801 and the data prediction device 800 (for example, image data, audio data, voice communication data) and video communication data), which can be implemented by flash memory (FLASH) or random access memory (Random Access Memory, RAM).

It should be understood that reference throughout the specification to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic related to the embodiment is included in at least one embodiment of the present application. Thus, appearances of "in one embodiment" or "in an embodiment" in various places throughout the specification are not necessarily referring to the same embodiment. Furthermore, the particular features, structures or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in various embodiments of the present application, the size of the sequence numbers of the above-mentioned processes does not mean the order of execution, and the execution order of each process should be determined by its functions and internal logic, and should not be used in the embodiments of the present application. The implementation process constitutes any limitation. The serial numbers of the above embodiments of the present application are for description only, and do not represent the advantages and disadvantages of the embodiments.

It should be noted that, in this document, the term "comprising", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element.

In the several embodiments provided in this application, it should be understood that the disclosed devices and methods may be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or May be integrated into another system, or some features may be ignored, or not implemented. In addition, the coupling, or direct coupling, or communication connection between the various components shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms. of.

The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed to multiple network units; Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be used as a single unit, or two or more units can be integrated into one unit; the above-mentioned integration The unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

Those of ordinary skill in the art can understand that all or part of the steps to realize the above method embodiments can be completed by hardware related to program instructions, and the aforementioned programs can be stored in computer-readable storage media. When the program is executed, the execution includes The steps of the above-mentioned method embodiments; and the aforementioned storage medium includes: various media that can store program codes such as removable storage devices, read-only memory (Read Only Memory, ROM), magnetic disks or optical disks.

Alternatively, if the above-mentioned integrated units of the present application are realized in the form of software function modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solutions of the embodiments of the present application or the part that contributes to the related technologies can be embodied in the form of software products. The computer software products are stored in a storage medium and include several instructions to make A computer device (which may be a personal computer, a server, or a network device, etc.) executes all or part of the methods described in the various embodiments of the present application. The aforementioned storage medium includes various media capable of storing program codes such as a removable storage device, ROM, magnetic disk or optical disk. The above is only the embodiment of the present application, but the scope of protection of the present application is not limited thereto. Anyone familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, and should covered within the scope of protection of this application. Therefore, the protection scope of the present application should be determined by the protection scope of the claims.

Industrial Applicability

In the embodiment of the present application, the server obtains hierarchical time series data; the hierarchical time series data is multiple sets of data corresponding to the time series of each level, wherein the sum of the sub-level data of each level in each level is equal to the data of the corresponding parent level ; Use the preset data forecasting model to predict the hierarchical time series data, and determine the forecasting results in the preset time period after multiple historical time periods; wherein, the preset data forecasting model is based on the hierarchical time series data , which is obtained by jointly training the prediction errors of multiple sets of training data within the historical preset time period, and the errors between each level. Since the preset data prediction model not only takes into account the accuracy of the prediction error, but also considers the errors between various levels during training, the preset data prediction model obtained by the server training is more accurate in predicting data.

Claims (12)

1. A data prediction method comprising:

   Acquiring hierarchical time series data; the hierarchical time series data is a plurality of sets of data corresponding to each hierarchical time series, wherein the sum of the sub-level data of each level in each level is equal to the data of the corresponding parent level;

   Using a preset data prediction model to predict the hierarchical time series data, and determine the prediction results within a preset time period after multiple historical time periods; wherein,

   The preset data prediction model is obtained through joint training based on the prediction errors of multiple sets of training data in the historical preset time period in the hierarchical time series data, and the errors between each level.
2. The data forecasting method according to claim 1, wherein said using the preset data forecasting model to predict the hierarchical time series data, and determine the forecast results within the preset time period after a plurality of historical time periods Before, after the acquisition of hierarchical time series data, the method further includes:

   Performing standardization processing on multiple sets of data of the layered time series data, and dividing the multiple sets of standardized data into training sets and test sets according to preset historical time periods; the training set includes: multiple sets of training data; The test set includes: multiple sets of test data;

   Using the loss function of the initial prediction model to calculate the prediction error of the training set and the error between the various levels, and iteratively adjust the model parameters of the initial prediction model according to the prediction error and the error between the various levels. , stop until the training condition is satisfied, and obtain the first prediction data set corresponding to the test set; the first prediction data set includes: multiple times in the iterative process of each level of each historical time period corresponding to the test set forecast data;

   The preset data prediction model is determined by comparing the multiple sets of test data with the first prediction data set.
3. The data prediction method according to claim 2, wherein said using the loss function of the initial prediction model to calculate the prediction error of the training set, and the error between each level, and based on the prediction error, and the each level The model parameters of the initial prediction model are iteratively adjusted until the training conditions are met, and the first prediction data set corresponding to the test set is obtained, including:

   Inputting the multiple sets of training data into the initial forecasting model to obtain a second forecasting data set; the second forecasting data set includes: forecasting data at various levels of the multiple historical time periods;

   calculating the prediction error and the error between the various levels in combination with the loss function based on the second prediction data set and the plurality of sets of training data;

   performing a gradient solution to the loss function by using the prediction error and the errors between the various levels to obtain model parameters in the iterative process, thereby obtaining an updated prediction model;

   Using the updated prediction model, continue to train the multiple sets of training data until the training conditions are met, and stop to obtain the final prediction model, thereby obtaining multiple prediction models in the iterative process;

   In each of the corresponding second prediction data sets obtained by using the plurality of prediction models, the prediction data of each level corresponding to each historical time period of the test set is extracted, and then the above-mentioned in the iterative process is obtained. The first forecast data set.
4. The data prediction method according to claim 3, wherein, based on the second prediction data set and the multiple sets of training data, the prediction error and the error between the various levels are calculated in combination with the loss function, include:

   Calculate the prediction error based on the first prediction data in the second prediction data set and the multiple sets of training data; the first prediction data is a plurality of first time periods in the second prediction data set The forecast data of each level in the above; the plurality of first time periods are the time periods before the preset historical time period in the plurality of historical time periods;

   Based on the second prediction data in the second prediction data set, calculate the error between the various levels; the second prediction data is the prediction of each level in a plurality of second time periods in the second prediction data set Data; the multiple second time periods are time periods after the preset historical time period among the multiple historical time periods.
5. The data prediction method according to claim 4, wherein, calculating the prediction error based on the first prediction data in the second prediction data set and the plurality of sets of training data includes:

   Calculating the sum of squares of the differences between the first prediction data in the same first time period and the training data of the corresponding level, and then obtaining the first sum of each level in the same first time period, combining the multiple first time periods The corresponding multiple first sums are added to obtain the prediction error.
6. The data prediction method according to claim 4, wherein said calculating the errors between the various levels based on the second prediction data in the second prediction data set includes:

   calculating the sum of the squares of the differences between the forecast data of each parent level in the second forecast data in the same second time period and the forecast data sums of the corresponding sub-levels, and combining the multiple second time periods Multiple sums of squares are added to obtain the second sum;

   The multiple second sums are multiplied by the hyperparameter of the harmonic error penalty term to obtain the errors between the various levels.
7. The data prediction method according to claim 3, wherein said comparing the multiple sets of test data with the first prediction data set to determine the preset data prediction model includes:

   Comparing the plurality of sets of test data with the multiple prediction data in the first prediction data set respectively, and determining the multiple comparison errors corresponding to the multiple prediction data;

   Determining a target comparison error within a preset error range among the multiple comparison errors;

   Determining a target iteration number corresponding to the target number of prediction data corresponding to the target comparison error;

   The preset data prediction model corresponding to the target iteration number is determined among the plurality of prediction models.
8. The data prediction method according to claim 2, wherein the multiple sets of training data include: multiple sets of first processed data; the multiple sets of test data include: multiple sets of second processed data;

   The multiple sets of data of the hierarchical time series data are standardized, and the multiple sets of standardized data are divided into training sets and test sets according to preset historical time periods, including:

   updating the outliers in each stratum with the average data for each stratum;

   Filling the blank data corresponding to each level in the multiple sets of data by using the average data corresponding to the levels with blank data, and then obtaining multiple sets of processed data corresponding to the time series of each level;

   A preset historical time period is determined in the multiple historical time periods, and the multiple sets of first processed data corresponding to the multiple first time periods before the preset historical time period are combined into the training set Combining the plurality of sets of second processed data corresponding to the plurality of second time periods after the preset historical time period into the test set.
9. The data prediction method according to claim 1, wherein the method further comprises:

   Obtain multiple sets of logistics cargo volume data corresponding to the multiple historical time periods;

   The multiple sets of logistics cargo volume data are processed by using the preset data prediction model to obtain predicted logistics cargo volume data for a preset time period after the multiple historical time periods.
10. A data prediction device, comprising:

    The data acquisition module is configured to acquire hierarchical time series data; the hierarchical time series data is a plurality of sets of data corresponding to each hierarchical time series, wherein the sum of the sub-level data of each level in each level is equal to Corresponding to the data of the parent level;

    The prediction module is configured to use a preset data prediction model to predict the hierarchical time series data, and determine the prediction results within a preset time period after a plurality of historical time periods; wherein,

    The preset data prediction model is obtained through joint training based on the prediction errors of multiple sets of training data in the historical preset time period in the layered time series data, and the errors between each level.
11. A data prediction device, comprising a memory and a processor, the memory stores a computer program that can run on the processor, and the processor implements the method described in any one of claims 1 to 9 when executing the program step.
12. A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the method of any one of claims 1 to 9 are implemented.

Images