Power grid multi-service domain informatization project group prediction method and device based on time sequence

Through the time series-based multi-service domain information project group prediction method, the project status prediction is achieved using LSTM or Prophet model, which solves the problem of traditional project management models that are difficult to adapt to the complex management needs in the context of digital transformation, and achieves more efficient project management and resource utilization.

CN118917480AInactive Publication Date: 2024-11-08GONGCHENG MANAGEMENT CONSULTING
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411015190.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-26
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The traditional project management model is difficult to adapt to the complex management needs of the multi-business domain information project group in the context of digital transformation, especially in the case of independent data sources and diversified system development tools, which increases the management difficulty and cannot be effectively monitored and Predict the project progress.

Method used

Using the time series-based multi-service domain information project group prediction method, the target data is collected and integrated, and the overall project status prediction is predicted by using LSTM or Prophet model, combining big data technology and low Code architecture, build data bases, improve data utilization and management efficiency.

Benefits of technology

This method improves the efficiency of project management, and by forming progress monitoring strategies from multiple angles, saving costs and resources, improving operational management efficiency, and adapting to the complex management needs of the power grid information project group.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917480A_ABST
    Figure CN118917480A_ABST
Patent Text Reader

Abstract

The invention relates to a power grid multi-service domain informatization project group prediction method and device based on a time series, and the method comprises the steps: carrying out the data collection, data preprocessing, data feature extraction, weight calculation and prediction of a result on various data in the construction process of a power project, the electric power informatization project data features and the time sequence subsets are correspondingly provided with training models for classification modeling, a period of time of data is divided into time periods with the same length, and finally the time periods with the same length are combined and summarized together, so that the positive sample number of user behavior data is increased, and the user behavior data are more accurate. The positive sample ratio is improved, certain inclination is reduced, and generalization training is performed through several training models, so that the accuracy of the training models is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of a method for predicting a power grid multi-service domain informatization project group, and in particular to a method and device for predicting a power grid multi-service domain informatization project group based on a time series. Background Art

[0002] The power grid multi-business domain informatization project group refers to a collection of informatization projects implemented in multiple business fields in order to improve the power grid operation efficiency and enhance the level of power grid intelligence. These projects usually cover all aspects of the power grid, such as power generation, transmission, transformation, distribution, and power consumption, and aim to achieve the intelligence, digitization, and automation of the power grid through informatization.

[0003] In the context of the digital transformation of the power industry and the iterative development of the construction of new power systems, the construction and stable operation of the power system are indispensable supports and guarantees for the country's economic development, social order stability, and the quality of life of the people. At present, the power system is at a critical node of digital transformation. Its digital construction needs form a large-scale project group, and the project management is becoming increasingly intelligent. In order to meet the increasing management needs of users, the power system construction early project establishment, construction period forecasting, and project process control process aim to save manpower, material resources, and financial resources, and gradually build a modern artificial intelligence management system. Through a comprehensive inventory of the construction status of power informatization projects, a comprehensive analysis of the current status monitoring of power informatization project groups is conducted to find the optimal management method for power grid multi-business domain informatization project groups. However, the different business domains, independent source data, and diversified system development tools of informatization projects increase the difficulty of managing power grid informatization project groups. The traditional project management model can no longer adapt to the project group management under the background of digital transformation. Summary of the invention

[0004] Based on this, it is necessary to provide a method and device for predicting power grid multi-business domain informatization project groups based on time series.

[0005] The technical solution of the present invention to solve the above technical problem is as follows: a prediction method for a power grid multi-service domain informatization project group based on time series, comprising:

[0006] Collect target data from process data of power informatization project group, and integrate the collected target data to obtain information data;

[0007] Taking pre-processing measures on the information data to obtain processed data;

[0008] Performing feature extraction on the processed data to obtain feature data;

[0009] The characteristic data is input into a prediction model to predict the overall status of the project to obtain prediction information, and the prediction information is analyzed for rationality to obtain a prediction result.

[0010] In one embodiment, in the step of taking pre-processing measures on the information data to obtain processed data, the pre-processing measures include de-duplication, de-noising, filtering and data completion.

[0011] In one embodiment, the data completion method is any one of removing unique attributes, mean interpolation and same type mean interpolation.

[0012] In one embodiment, in the step of extracting features from the processed data to obtain feature data, distributed computing is used to decompose the processed data into many small parts, which are allocated to multiple devices for synchronous feature extraction.

[0013] In one embodiment, the feature extraction method includes: data standardization and regularization processing.

[0014] In one embodiment, after the step of extracting features from the processed data to obtain feature data, the step further includes: displaying the feature data in the form of a data chart, and analyzing the approximate trend of the data based on the chart to obtain a preliminary prediction.

[0015] In one embodiment, the prediction model is a LSTM (Long Short-Term Memory) model or a Prophet model.

[0016] A time series-based power grid multi-business domain information project group prediction device, comprising:

[0017] The acquisition module is used to collect target data from the process data of the power informatization project group and integrate the collected target data to obtain information data;

[0018] A preprocessing module, used for taking preprocessing measures on the information data to obtain processed data;

[0019] A feature extraction module, used to extract features from the processed data to obtain feature data;

[0020] The result prediction module is used to input the characteristic data into the prediction model to predict the overall status of the project, obtain prediction information, and perform rationality analysis on the prediction information to obtain prediction results.

[0021] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0022] Collect target data from process data of power informatization project group, and integrate the collected target data to obtain information data;

[0023] Taking pre-processing measures on the information data to obtain processed data;

[0024] Performing feature extraction on the processed data to obtain feature data;

[0025] The characteristic data is input into a prediction model to predict the overall status of the project to obtain prediction information, and the prediction information is analyzed for rationality to obtain a prediction result.

[0026] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0027] Collect target data from process data of power informatization project group, and integrate the collected target data to obtain information data;

[0028] Taking pre-processing measures on the information data to obtain processed data;

[0029] Performing feature extraction on the processed data to obtain feature data;

[0030] The characteristic data is input into a prediction model to predict the overall status of the project to obtain prediction information, and the prediction information is analyzed for rationality to obtain a prediction result.

[0031] The beneficial effects of the present invention are as follows: the present invention provides a prediction method for a power grid multi-business domain informationization project group based on time series. In terms of data collection and analysis, the method builds a data base in the process of informationization project construction through a combination of big data technology and low-code architecture. The data base is used for data collection, storage, analysis and prediction, etc., which improves the utilization rate and practicality of the data. In terms of data processing and application: the data is pre-processed by removing unique attributes, mean interpolation, and similar mean interpolation, and then the processed data is standardized and regularized, and data features are extracted. The extracted feature data is then predicted using a prediction model under the overall state of the project, and a rationality analysis is performed. Compared with the traditional project management model, this method can form a progress monitoring strategy from multiple angles such as cost, investment, business management, and revenue cycle, thereby improving business management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 A schematic diagram of a flow chart of a method for predicting a power grid multi-business domain informatization project group based on time series in an embodiment;

[0034] Figure 2 It is a schematic diagram of a flow chart of a device for predicting a power grid multi-business domain informatization project group based on time series in one embodiment;

[0035] Figure 3 1 is a diagram of the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0036] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. The preferred embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thoroughly understood.

[0037] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only and do not represent the only implementation method.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0039] Embodiment 1

[0040] In this embodiment, if Figure 1 As shown, a prediction method for a power grid multi-business domain informatization project group based on time series includes:

[0041] Step 110, collecting target data from process data of the power information project group, and integrating the collected target data to obtain information data.

[0042] In one embodiment, the target data in the process data of the current power informationization project group in the webpage is crawled by a crawler, and the target data is collected and integrated. The target data includes the bidding announcement, bid opening, bid winning announcement, bid winning notice, contract signing, kick-off meeting, demand review and other related data of the power informationization project.

[0043] Step 120: taking pre-processing measures on the information data to obtain processed data.

[0044] In one embodiment, in the step of taking pre-processing measures on the information data to obtain processed data, the pre-processing measures include de-duplication, de-noising, filtering and data completion.

[0045] In one embodiment, the data completion method is any one of removing unique attributes, mean interpolation and homogeneous mean interpolation. Removing unique attributes is usually not used directly to deal with missing values, but refers to deleting features with only unique values ​​(or almost unique values) in the data preprocessing stage. Mean interpolation is a simple and commonly used method for dealing with missing values. In this method, for missing values ​​of numerical features, the average value of all non-missing values ​​of the feature is usually used to fill. Homogeneous mean interpolation is an improved method of mean interpolation, which takes into account the grouping or classification information of the data. In this method, the data is first grouped according to one or some classification variables, and then for the numerical features in each group, the average value of the non-missing values ​​of the feature in the group is used to fill the missing values ​​in the group. This method is more accurate than simple mean interpolation because it takes into account the grouping structure within the data and reduces the deviation caused by the global average value.

[0046] Step 130: extract features from the processed data to obtain feature data.

[0047] In one embodiment, distributed computing is used to decompose the processed data into many small parts and distribute them to multiple devices for synchronous feature extraction.

[0048] In one embodiment, the characteristic data in the power informationization project group includes a time series subset, and the data characteristics in the power informationization project group are set with a training model corresponding to the time series subset, and classification modeling is performed. By dividing a period of characteristic data into multiple time periods of the same length, these multiple time periods of the same length are combined and summarized. Through the above operation, the number of positive samples of user behavior data can be increased, the proportion of positive samples can be increased, a certain degree of "skewness" can be reduced, and generalization training can be performed through several training models, thereby improving the accuracy of the training model.

[0049] In one embodiment, the feature extraction method includes: data standardization and regularization processing. Data standardization is to convert data according to certain rules so that it has the same standard and range for data comparison and analysis. The main methods of data standardization include:

[0050] Min-max normalization linearly maps the data to a specified range (usually [0,1]).

[0051] Z-score standardization transforms the data into a standard normal distribution (mean 0 and variance 1).

[0052] Decimal scaling standardization adjusts the range of data by moving the position of the decimal point.

[0053] Normalization converts each sample vector into a unit vector.

[0054] In one embodiment, after step 130, the method further includes: displaying the characteristic data in the form of a data chart, and analyzing the approximate trend of the data based on the chart to obtain a preliminary prediction.

[0055] Step 140, input the characteristic data into the prediction model to predict the overall status of the project to obtain prediction information, and perform rationality analysis on the prediction information to obtain a prediction result.

[0056] In one embodiment, the prediction model is an LSTM model or a Prophet model. A rationality analysis is performed based on the prediction information of the LSTM model or the Prophet model to obtain a prediction result.

[0057] Embodiment 2

[0058] In this embodiment, a time series-based prediction method for a power grid multi-service domain informatization project group includes:

[0059] Step 1: Collect target data from process data of the power informatization project group, and integrate the collected target data to obtain information data.

[0060] Step 2: taking pre-processing measures on the information data to obtain processed data.

[0061] Step three, extracting features from the processed data to obtain feature data.

[0062] Step 4: Input the characteristic data into the prediction model to predict the overall status of the project, obtain prediction information, and perform rationality analysis on the prediction information to obtain a prediction result.

[0063] In one embodiment, this method combines multi-source data acquisition robot technology and low-code platform architecture to build a data base for data acquisition, storage, analysis, and prediction in the process of information project construction. The data base improves data utilization and practicality, and provides a good data foundation for the digital upgrade of the power system and the construction of a new power system.

[0064] In one embodiment, the time series-based power grid multi-business domain informatization project group prediction method provided in the present application comprehensively checks the construction status of the power informatization project, conducts a comprehensive analysis of the current status monitoring of the power informatization project group, and finds out the pain points in the management process of the power informatization group.

[0065] In one embodiment, a time series-based prediction method for a power grid multi-service domain informatization project group includes:

[0066] Data collection, through the collection and integration of target data in the existing power information project group process data. Target data includes project bidding announcements, bid openings, winning announcements, winning notices, contract signings, kick-off meetings, demand reviews and other related data.

[0067] Data cleaning, using measures such as deduplication, denoising, filtering, and data completion to process the collected data and identify time series data information that is effective for identification.

[0068] Data analysis uses data mining algorithms to mine target time series data information from large amounts of data according to needs.

[0069] Data distributed computing uses distributed computing to break down big data into many small parts and distribute them to multiple computers for processing, saving overall computing time and greatly improving computing efficiency.

[0070] Data display, using data calculation and processing data, using data charts to display, using graphics to analyze the approximate trend of the data to obtain preliminary predictions.

[0071] Data prediction processing, based on the time series processed by big data analysis technology, is input into the LSTM model for processing, and trend charts such as contract bidding announcements, bid opening, and winning announcements of similar project groups are output to obtain prediction information.

[0072] In one embodiment, the data prediction working steps of the LSTM model are as follows:

[0073] The attention mechanism based on different moments is to assign different weights to the hidden layer outputs at different moments, and then obtain a LSTM context vector by weighted summation. The attention mechanism based on different features is to assign different attention weights to different dimensions of the output vector.

[0074] In the LSTM unit, the input information of the LSTM unit at the tth moment is calculated by the forget gate and the nonlinear activation function sigmoid to obtain the forget gate state information f at the tth moment. t :

[0075] f t =σ(W f [h t-1 +x t ]+b f )

[0076] Forget the gate state information f t The value ranges from 0 to 1. t A value of 1 means retaining all cell states C at time t-1 t-1 The amount of information, f t A value of 0 means abandoning all cell states C at time t-1 t-1 The amount of information, the forget gate is used to selectively discard the information in the storage unit; where σ is the sigmoid function, W f is the weight matrix of the forget gate, b f is the forget gate network bias term;

[0077] In the LSTM unit, the input gate is used to determine the input gate state i in the LSTM network at time t. t and the amount of information stored in the memory cell satisfy:

[0078] i t =σ(W i [h t-1 +x t ]+b i )

[0079]

[0080] The input gate is used to selectively extract information from the storage unit; i is the weight matrix of the input gate, b i is the input gate network bias term; tanh represents the bidirectional tangent function, W c is the update gate weight matrix, b c is the storage unit network bias term;

[0081] In the LSTM unit, the forget gate and the input gate are combined to form an update gate to update the accumulated information in the storage unit, so as to realize the storage unit C at the tth moment. t Modification and replacement of information:

[0082]

[0083] Among them, C t-1 is the storage unit C at time t-1 t Information t Indicates the amount of information about the forgotten gate state at time t;

[0084] In the LSTM unit, the output gate information o is obtained through the output gate t , output gate information amount o t Combined storage unit C t Calculated with the nonlinear activation function, the output information h of the hidden layer at time t is obtained t , that is, the human feature vector information output by the hidden layer at time t:

[0085] o t =σ(W o [h t-1 +x t ]+b o )

[0086] h t =o t ×tanh(C t )

[0087] Among them, W o is the weight matrix of the output gate, b o is the forget gate network bias term.

[0088] It is characterized in that the human feature vector information h(t) output by the hidden layer of the LSTM network is input into the Softmax classifier for classification to obtain the final test classification result, specifically:

[0089] The output classification function expression is:

[0090] y=softmax(W×h(t)+b)

[0091] Among them, y is the output classification information, Softmax() classification function, W is the LSTM network weight, b is the bias of the LSTM network, and h(t) is the feature vector information of the output of the hidden layer of the LSTM network.

[0092] Embodiment 3

[0093] In this embodiment, Figure 2 As shown, a time series-based power grid multi-business domain information project group prediction device includes:

[0094] The acquisition module 210 is used to acquire target data from the process data of the power information project group, and integrate the acquired target data to obtain information data;

[0095] A preprocessing module 220, used to take preprocessing measures on the information data to obtain processed data;

[0096] A feature extraction module 230 is used to extract features from the processed data to obtain feature data;

[0097] The result prediction module 240 is used to input the feature data into the prediction model to predict the overall status of the project, obtain prediction information, and perform rationality analysis on the prediction information to obtain prediction results.

[0098] In one embodiment, the pre-processing module 220 includes: a de-duplication unit, a denoising unit, a filtering unit, and a data completion unit;

[0099] The deduplication unit is used to perform data deduplication on the information data;

[0100] The denoising unit is used to perform data denoising on the information data;

[0101] The filtering unit is used to filter the information data;

[0102] The data completion unit is used to complete the information data.

[0103] In one embodiment, the data completion method used by the data completion unit is any one of exclusive attribute, mean interpolation and same type mean interpolation.

[0104] In one embodiment, the feature extraction module 230 uses distributed computing to decompose the processed data into many small parts and assign them to multiple modules to perform feature extraction synchronously.

[0105] In one embodiment, the feature extraction module 230 includes: a data normalization unit and a regularization processing unit;

[0106] The data standardization unit is used to perform standardization processing on the processed data;

[0107] The regularization processing unit is used to perform regularization processing on the processed data.

[0108] In one embodiment, the feature extraction module 230 further includes a preliminary prediction module;

[0109] The preliminary prediction module is used to display the characteristic data in the form of data charts, and analyze the approximate trend of the data based on the charts to obtain a preliminary prediction.

[0110] In one embodiment, the result prediction module 240 includes an LSTM model unit and a Prophet model unit;

[0111] The LSTM model unit is used to input the feature data into the LSTM model to predict the overall status of the project and obtain prediction information.

[0112] The Prophet model unit is used to input the characteristic data into the Prophet model to predict the overall status of the project and obtain prediction information.

[0113] Regarding the specific limitations of the prediction device for the power grid multi-service domain informatization project group based on time series, please refer to the limitations of the prediction method for the power grid multi-service domain informatization project group based on time series in the above text, which will not be repeated here. Each unit in the above-mentioned prediction device for the power grid multi-service domain informatization project group based on time series can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned units can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned units.

[0114] Embodiment 4

[0115] In this embodiment, a computer device is provided. Its internal structure diagram can be shown as follows: Figure 3As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program, and the non-volatile storage medium is deployed with a database, which is used to store information data, processing data, feature data and prediction results. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with other computer devices deployed with application software. When the computer program is executed by the processor, a method for processing data of goods entering and leaving the warehouse is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0116] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0117] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0118] Collect target data from process data of power informatization project group, and integrate the collected target data to obtain information data;

[0119] Taking pre-processing measures on the information data to obtain processed data;

[0120] Performing feature extraction on the processed data to obtain feature data;

[0121] The characteristic data is input into a prediction model to predict the overall status of the project to obtain prediction information, and the prediction information is analyzed for rationality to obtain a prediction result.

[0122] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0123] In the step of taking pre-processing measures on the information data to obtain processed data, the pre-processing measures include de-duplication, de-noising, filtering and data completion.

[0124] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0125] The data completion method is any one of unique attribute, mean interpolation and same type mean interpolation.

[0126] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0127] In the step of extracting features from the processed data to obtain feature data, distributed computing is used to decompose the processed data into many small parts, which are allocated to multiple devices for synchronous feature extraction.

[0128] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0129] The feature extraction method includes: data standardization and regularization processing.

[0130] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0131] After the step of extracting features from the processed data to obtain feature data, the method further includes: displaying the feature data in the form of data charts, and analyzing the approximate trend of the data based on the charts to obtain a preliminary prediction.

[0132] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0133] The prediction model is an LSTM model or a Prophet model.

[0134] Embodiment 5

[0135] In this embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0136] Collect target data from process data of power informatization project group, and integrate the collected target data to obtain information data;

[0137] Taking pre-processing measures on the information data to obtain processed data;

[0138] Performing feature extraction on the processed data to obtain feature data;

[0139] The characteristic data is input into a prediction model to predict the overall status of the project to obtain prediction information, and the prediction information is analyzed for rationality to obtain a prediction result.

[0140] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0141] In the step of taking pre-processing measures on the information data to obtain processed data, the pre-processing measures include de-duplication, de-noising, filtering and data completion.

[0142] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0143] The data completion method is any one of unique attribute, mean interpolation and same type mean interpolation.

[0144] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0145] In the step of extracting features from the processed data to obtain feature data, distributed computing is used to decompose the processed data into many small parts, which are allocated to multiple devices for synchronous feature extraction.

[0146] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0147] The feature extraction method includes: data standardization and regularization processing.

[0148] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0149] After the step of extracting features from the processed data to obtain feature data, the method further includes: displaying the feature data in the form of data charts, and analyzing the approximate trend of the data based on the charts to obtain a preliminary prediction.

[0150] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0151] The prediction model is an LSTM model or a Prophet model.

[0152] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0153] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0154] The above-mentioned embodiments only express several embodiments of the present application, and the description is relatively specific and detailed, but it cannot be understood as limiting the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present application, which all belong to the protection scope of the present application. Therefore, the protection scope of the patent of this application shall be based on the attached claims.

Claims

1. A prediction method for power grid multi-business domain informatization project group based on time series, It is characterized in that include: Collect target data from process data of power informatization project group, and integrate the collected target data to obtain information data; Taking pre-processing measures on the information data to obtain processed data; Performing feature extraction on the processed data to obtain feature data; The characteristic data is input into a prediction model to predict the overall status of the project to obtain prediction information, and the prediction information is analyzed for rationality to obtain a prediction result.

2. The method according to claim 1, It is characterized in that In the step of taking pre-processing measures on the information data to obtain processed data, The preprocessing measures include deduplication, denoising, filtering and data completion.

3. The method according to claim 2, It is characterized in that The data completion method is any one of unique attribute, mean interpolation and same type mean interpolation.

4. The method according to claim 1, It is characterized in that In the step of extracting features from the processed data to obtain feature data, Distributed computing is used to decompose the processed data into many small parts and distribute them to multiple devices for synchronous feature extraction.

5. The method according to claim 1, It is characterized in that The feature extraction method includes: data standardization and regularization processing.

6. The method according to claim 1, It is characterized in that After the step of extracting features from the processed data to obtain feature data, the method further includes: The characteristic data is displayed in the form of data charts, and the general trend of the data is analyzed based on the graphs to obtain a preliminary prediction.

7. The method according to claim 1, It is characterized in that The prediction model is an LSTM model or a Prophet model.

8. A prediction device for power grid multi-business domain information project group based on time series, It is characterized in that include: The acquisition module is used to collect target data from the process data of the power informatization project group and integrate the collected target data to obtain information data; A preprocessing module, used for taking preprocessing measures on the information data to obtain processed data; A feature extraction module, used to extract features from the processed data to obtain feature data; The result prediction module is used to input the characteristic data into the prediction model to predict the overall status of the project, obtain prediction information, and perform rationality analysis on the prediction information to obtain prediction results.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Service progress monitoring method, device and system and computer readable storage medium

    CN110782129A

  • Power load prediction method and device based on A-TCN, computer equipment and storage medium

    CN111260030A

  • Variable project management method, system, equipment and medium

    CN117333124A