Data model management method and system for power industry data medium station

Abstract

The invention discloses a data model management method and system for a power industry data center. The method comprises the following steps: acquiring power data information; extracting format features of the electric power data, judging whether the format features of the electric power data are consistent with preset format features, and if yes, setting the corresponding electric power data as standard electric power data; if not, adjusting the corresponding power data into standard power data; sending the standard electric power data to a preset data model, judging whether the corresponding standard electric power data is normal or not, and if yes, performing classified storage on the corresponding standard electric power data to obtain a storage position of the standard electric power data; if not, warning information is triggered; and sending the warning information to a preset management end for prompting. According to the method, the accuracy of classified storage of the power data is improved, and a guarantee is provided for subsequent application of the power data.

Description

Technical Field

[0001] The present invention relates to the field of power data processing technology, and more specifically, to a data model management method and system for a data center in the power industry. Background Art

[0002] With the development of the power grid, power data has grown exponentially, posing a great challenge to the quality assurance of power data. In terms of data collection, power data comes from many sources, and their structures and systems may be inconsistent, resulting in diverse formats of power data. In addition, the transmission and storage of power data may also produce errors, such as incomplete power data, redundant power data, and erroneous power data, which bring troubles to the subsequent use, search, and calculation of power data. Summary of the invention

[0003] In view of the above problems, the purpose of the present invention is to provide a data model management method and system for the power industry data center, which can improve the accuracy of classified storage of power data and provide a guarantee for the subsequent application of power data.

[0004] A first aspect of the present invention provides a data model management method for a data center in the electric power industry, comprising:

[0005] Obtain power data information;

[0006] Extracting the format characteristics of the power data, and determining whether the format characteristics of the power data are consistent with the preset format characteristics, if yes, setting the corresponding power data as standard power data; if no, adjusting the corresponding power data to standard power data;

[0007] Send the standard power data to a preset data model to determine whether the corresponding standard power data is normal. If so, classify and store the corresponding standard power data to obtain the storage location of the standard power data; if not, trigger a warning message;

[0008] Send the warning information to the preset management terminal for prompting.

[0009] In this solution, after setting the corresponding power data as standard power data or adjusting the corresponding power data to standard power data, it also includes:

[0010] Extract keywords from standard power data;

[0011] According to the keywords in the standard power data, a preset keyword classification table is searched to obtain the type of the keywords in the corresponding standard power data;

[0012] Group the keywords of the same type together and record the quantity of the keywords of the same type.

[0013] The weight score of the keywords of the same type is obtained by multiplying the number of keywords of the same type by the preset score of the corresponding keyword type and the weight coefficient of the corresponding keyword type;

[0014] Determine whether the weight score of the same type of keywords is greater than a preset score threshold, and if so, identify the type of the corresponding keyword to obtain an identified type;

[0015] The identification types are combined to construct a classification type corresponding to the standard power data, and the label of the corresponding classification type is matched, and the standard power data is identified with the label of the corresponding classification type.

[0016] In this solution, the step of combining the identification types to construct the classification type corresponding to the standard power data specifically includes:

[0017] Sort the identification types according to their corresponding weight scores from large to small to obtain the initial sequence number of the corresponding identification type;

[0018] Sequentially extract the initial sequence number of the identification type and set it as the base number of the identification type;

[0019] Sort the identification types according to the initial sequence numbers to obtain the initial classification types of the corresponding standard power data;

[0020] If the initial classification type of the corresponding standard power data and the preset classification type are compared and analyzed, if there is a consistency, the preset classification type with consistency is set as the classification type of the standard power data, and the identification type combination is stopped;

[0021] If there is no consistency, the reference number of the identification type is adjusted to obtain the initial classification type of the adjusted standard power data, and compared and analyzed with the preset classification type until there is a consistent preset classification type or all combinations of identification types are compared and analyzed.

[0022] In this solution, the method of identifying the type of the corresponding keyword and obtaining the identification type further includes:

[0023] Get the quantity value of the identification type;

[0024] Determine whether the quantity value of the identification type is greater than a preset quantity threshold. If so, sort the identification types from large to small according to the corresponding weight scores, and extract the identification types with the preset quantity threshold at the front for combination;

[0025] Setting the identification type after the preset quantity threshold as the backup identification type;

[0026] When the comparison and analysis of all combinations of identification types are completed and the classification type of the standard power data is not determined, the spare identification types are used to replace the previously combined identification types in turn to re-combine.

[0027] In this solution, the step of replacing the previously combined identification types with the spare identification types in sequence to re-combine specifically includes:

[0028] Extract the backup identification type with the largest weight score;

[0029] The backup identification type with the largest weight score replaces the identification type with the smallest weight score among the identification types previously combined to perform a first round of re-combination;

[0030] If the classification type of the standard power data is not determined after the first round of regrouping, the identification type deleted in the first round of regrouping is restored, and the identification type with the second smallest weight score is deleted to perform the second round of regrouping;

[0031] If the classification type of the standard power data is not determined after the second round of regrouping, the identification type deleted in the second round of regrouping is restored, and the identification type with the third smallest weight score is deleted to perform the third round of regrouping until the identification type with the largest weight score is deleted;

[0032] If the classification type of the standard power data has not been determined after the identification type with the largest weight score is deleted and recombined, the two identification types with the largest weight scores will replace the two identification types with the smallest weight scores in the previously combined identification types for recombining, and so on, until there is a consistent preset classification type or all combinations of identification types have completed comparative analysis.

[0033] In this solution, the step of determining whether the corresponding standard power data is normal specifically includes:

[0034] Extract the electricity consumption units and corresponding electricity consumption in standard electricity data;

[0035] According to the power consumption unit in the standard power data, matching the historical power consumption of the corresponding power consumption unit in a preset first time period;

[0036] Calculate the average of the historical electricity consumption during the preset first time period to obtain the historical average electricity consumption;

[0037] Subtract the historical average electricity consumption from the standard electricity data and take the absolute value to get the electricity consumption difference;

[0038] Divide the difference in electricity consumption by the average amount of historical electricity consumption to obtain the electricity consumption fluctuation index;

[0039] Determine whether the power consumption fluctuation index is within the preset index range. If so, the corresponding standard power data is normal; if not, the corresponding standard power data is abnormal.

[0040] In this solution, after obtaining the storage location of the standard power data, the method further includes:

[0041] Extracting a tag of a storage location of standard power data;

[0042] Compare and analyze the label of the storage location of the standard power data and the label of the classification type of the corresponding standard power data. If they are consistent, the storage location of the corresponding standard power data is normal; if they are inconsistent, the storage location of the corresponding standard power data is abnormal;

[0043] If the storage location of the standard power data is abnormal, the preset management terminal authenticates and signs the classification tag of the standard power data;

[0044] The classification label of the standard power data is authenticated and signed according to the preset management terminal, the classification type label of the standard power data is adjusted, and the storage location of the corresponding standard power data is adjusted.

[0045] A second aspect of the present invention provides a data model management system for a data center in the electric power industry, including a memory and a processor, wherein the memory stores a data model management method program for a data center in the electric power industry, and when the data model management method program for a data center in the electric power industry is executed by the processor, the following steps are implemented:

[0046] Obtain power data information;

[0047] Extracting the format characteristics of the power data, and determining whether the format characteristics of the power data are consistent with the preset format characteristics, if yes, setting the corresponding power data as standard power data; if no, adjusting the corresponding power data to standard power data;

[0048] Send the standard power data to a preset data model to determine whether the corresponding standard power data is normal. If so, classify and store the corresponding standard power data to obtain the storage location of the standard power data; if not, trigger a warning message;

[0049] Send the warning information to the preset management terminal for prompting.

[0050] In this solution, after setting the corresponding power data as standard power data or adjusting the corresponding power data to standard power data, it also includes:

[0051] Extract keywords from standard power data;

[0052] According to the keywords in the standard power data, a preset keyword classification table is searched to obtain the type of the keywords in the corresponding standard power data;

[0053] Group the keywords of the same type together and record the quantity of the keywords of the same type.

[0054] The weight score of the keywords of the same type is obtained by multiplying the number of keywords of the same type by the preset score of the corresponding keyword type and the weight coefficient of the corresponding keyword type;

[0055] Determine whether the weight score of the same type of keywords is greater than a preset score threshold, and if so, identify the type of the corresponding keyword to obtain an identified type;

[0056] The identification types are combined to construct a classification type corresponding to the standard power data, and the label of the corresponding classification type is matched, and the standard power data is identified with the label of the corresponding classification type.

[0057] In this solution, the step of combining the identification types to construct the classification type corresponding to the standard power data specifically includes:

[0058] Sort the identification types according to their corresponding weight scores from large to small to obtain the initial sequence number of the corresponding identification type;

[0059] Sequentially extract the initial sequence number of the identification type and set it as the base number of the identification type;

[0060] Sort the identification types according to the initial sequence numbers to obtain the initial classification types of the corresponding standard power data;

[0061] If the initial classification type of the corresponding standard power data and the preset classification type are compared and analyzed, if there is a consistency, the preset classification type with consistency is set as the classification type of the standard power data, and the identification type combination is stopped;

[0062] If there is no consistency, the reference number of the identification type is adjusted to obtain the initial classification type of the adjusted standard power data, and compared and analyzed with the preset classification type until there is a consistent preset classification type or all combinations of identification types are compared and analyzed.

[0063] The present invention discloses a data model management method and system for a data center in the electric power industry, which improves the accuracy of classified storage of electric power data and provides a guarantee for the subsequent application of electric power data. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A flow chart of a data model management method for a data center in the electric power industry according to the present invention is shown;

[0065] Figure 2 A block diagram of a data model management system for a data center in the electric power industry according to the present invention is shown. DETAILED DESCRIPTION

[0066] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0067] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0068] Figure 1 A flow chart of a data model management method for a data center in the electric power industry according to the present invention is shown.

[0069] like Figure 1 As shown, the present invention discloses a data model management method for a data center in the electric power industry, including:

[0070] S101, obtaining power data information;

[0071] S102, extracting the format feature of the power data, and determining whether the format feature of the power data is consistent with the preset format feature, if so, setting the corresponding power data as standard power data; if not, adjusting the corresponding power data to standard power data;

[0072] S103, sending the standard power data to a preset data model, determining whether the corresponding standard power data is normal, if so, classifying and storing the corresponding standard power data to obtain the storage location of the standard power data; if not, triggering a warning message;

[0073] S104, sending the warning information to the preset management terminal for prompting.

[0074] According to an embodiment of the present invention, the equipment for collecting power data may be provided by different manufacturers, which may cause differences in the format characteristics of the collected power data. Therefore, the format characteristics of the power data are normalized by preset format characteristics. For example, the format characteristics of the power data include time, place and power value in sequence. If one of the format characteristics is missing in the collected power data, the corresponding power data is incomplete power data, and incomplete prompt information of the corresponding format characteristics is generated, and the incomplete prompt information of the format characteristics is sent to the preset management terminal for prompting; if the format characteristics in the collected power data are relatively chaotic, the format characteristics of the corresponding collected power data are adjusted according to the preset format characteristics to obtain standard power data.

[0075] According to an embodiment of the present invention, after setting the corresponding power data as standard power data or adjusting the corresponding power data to standard power data, the method further includes:

[0076] Extract keywords from standard power data;

[0077] According to the keywords in the standard power data, a preset keyword classification table is searched to obtain the type of the keywords in the corresponding standard power data;

[0078] Group the keywords of the same type together and record the quantity of the keywords of the same type.

[0079] The weight score of the keywords of the same type is obtained by multiplying the number of keywords of the same type by the preset score of the corresponding keyword type and the weight coefficient of the corresponding keyword type;

[0080] Determine whether the weight score of the same type of keywords is greater than a preset score threshold, and if so, identify the type of the corresponding keyword to obtain an identified type;

[0081] The identification types are combined to construct a classification type corresponding to the standard power data, and the label of the corresponding classification type is matched, and the standard power data is identified with the label of the corresponding classification type.

[0082] It should be noted that the preset keyword classification table stores various keywords and the corresponding keyword types. Different preset scores and weight coefficients are set for each keyword type. The classification of the standard power data is determined by the weight scores corresponding to the keywords in the standard power data. The classification type of the corresponding standard power data is obtained by combining the identification types of the keywords, and each classification type of the standard power data corresponds to a storage location.

[0083] According to an embodiment of the present invention, the step of combining identification types to construct classification types corresponding to standard power data specifically includes:

[0084] Sort the identification types according to their corresponding weight scores from large to small to obtain the initial sequence number of the corresponding identification type;

[0085] Sequentially extract the initial sequence number of the identification type and set it as the base number of the identification type;

[0086] Sort the identification types according to the initial sequence numbers to obtain the initial classification types of the corresponding standard power data;

[0087] If the initial classification type of the corresponding standard power data and the preset classification type are compared and analyzed, if there is a consistency, the preset classification type with consistency is set as the classification type of the standard power data, and the identification type combination is stopped;

[0088] If there is no consistency, the reference number of the identification type is adjusted to obtain the initial classification type of the adjusted standard power data, and compared and analyzed with the preset classification type until there is a consistent preset classification type or all combinations of identification types are compared and analyzed.

[0089] It should be noted that, for example, the keyword identification types are divided into a, b and c, and the corresponding weight scores are also sorted from large to small as a, b and c, then the identification type a with the largest weight score is used as the base number, and the resulting combination is abc. If the initial classification type and the preset classification type corresponding to the combination abc are inconsistent, the base number positions are adjusted in turn to obtain the combination bac. If the initial classification type and the preset classification type corresponding to the combination bac are inconsistent, the position of the base number a is continued to be adjusted until the position of the base number a cannot be adjusted. If the classification type of the standard power data cannot be determined, the identification type b with the second largest maximum weight score is used as the base number, and the position of the base number is adjusted to obtain a new combination. The above operation is repeated until the position of the base number b cannot be adjusted, and so on, traversing the initial sequential numbering of the entire identification type.

[0090] According to an embodiment of the present invention, after identifying the type of the corresponding keyword and obtaining the identification type, the method further includes:

[0091] Get the quantity value of the identification type;

[0092] Determine whether the quantity value of the identification type is greater than a preset quantity threshold. If so, sort the identification types from large to small according to the corresponding weight scores, and extract the identification types with the preset quantity threshold at the front for combination;

[0093] Setting the identification type after the preset quantity threshold as the backup identification type;

[0094] When the comparison and analysis of all combinations of identification types are completed and the classification type of the standard power data is not determined, the spare identification types are used to replace the previously combined identification types in turn to re-combine.

[0095] It should be noted that the classification type of standard power data is composed of the identification types of keywords in the standard power data. For example, the classification type of standard power data is composed of the identification types of up to 3 keywords, and the corresponding preset quantity threshold is 3. When the number of identification types of the standard power data exceeds 3, it is impossible to combine identification types that exceed the preset quantity threshold. Therefore, the identification types are sorted from large to small according to the corresponding weight scores, and the identification types that are close to the preset quantity threshold are given priority, and other identification types are set as backup identification types.

[0096] According to an embodiment of the present invention, the step of replacing the previously combined identification types with the spare identification types in sequence to re-combine specifically includes:

[0097] Extract the backup identification type with the largest weight score;

[0098] The backup identification type with the largest weight score replaces the identification type with the smallest weight score among the identification types previously combined to perform a first round of re-combination;

[0099] If the classification type of the standard power data is not determined after the first round of regrouping, the identification type deleted in the first round of regrouping is restored, and the identification type with the second smallest weight score is deleted to perform the second round of regrouping;

[0100] If the classification type of the standard power data is not determined after the second round of regrouping, the identification type deleted in the second round of regrouping is restored, and the identification type with the third smallest weight score is deleted to perform the third round of regrouping until the identification type with the largest weight score is deleted;

[0101] If the classification type of the standard power data has not been determined after the identification type with the largest weight score is deleted and recombined, the two identification types with the largest weight scores will replace the two identification types with the smallest weight scores in the previously combined identification types for recombining, and so on, until there is a consistent preset classification type or all combinations of identification types have completed comparative analysis.

[0102] It should be noted that when alternative identification types are needed to combine and determine the classification type of standard power data, the identification types previously combined are replaced in sequence. For example, if there are alternative identification types d and e, and the weight score corresponding to the alternative identification type d is greater than the alternative identification type e, then the alternative identification type d is preferentially replaced with the identification type with the smallest weight score in the identification type previously combined for combination, that is, the first round of reorganization and combination to obtain the initial classification type; if the classification type of the standard power data cannot be determined after all the alternative identification types d are combined, it is set to be the end of the first round of reorganization, and the alternative identification type e is replaced by the alternative identification type d for combination in sequence, that is, the second round of reorganization to obtain the initial classification type, and the classification type of the standard power data cannot be determined after all the alternative identification types d are combined, and after all other alternative identification types are replaced individually for combination, the alternative identification types are combined and replaced, for example, the two identification types with the smallest weight scores in the identification types previously combined are replaced with alternative identification types d and e at the same time for combination, and so on, until there is a consistent preset classification type or all combinations of identification types have completed comparative analysis.

[0103] According to an embodiment of the present invention, the step of determining whether the corresponding standard power data is normal specifically includes:

[0104] Extract the electricity consumption units and corresponding electricity consumption in standard electricity data;

[0105] According to the power consumption unit in the standard power data, matching the historical power consumption of the corresponding power consumption unit in a preset first time period;

[0106] Calculate the average of the historical electricity consumption during the preset first time period to obtain the historical average electricity consumption;

[0107] Subtract the historical average electricity consumption from the standard electricity data and take the absolute value to get the electricity consumption difference;

[0108] Divide the difference in electricity consumption by the average amount of historical electricity consumption to obtain the electricity consumption fluctuation index;

[0109] Determine whether the power consumption fluctuation index is within the preset index range. If so, the corresponding standard power data is normal; if not, the corresponding standard power data is abnormal.

[0110] It should be noted that the data model stores a large amount of historical electricity data. Through the large amount of historical electricity data, each electricity consumption unit is evaluated, a preset index range is set for each electricity consumption unit, and the electricity consumption fluctuation index is determined. When the electricity consumption fluctuation index exceeds the preset index range, the corresponding standard electricity data is set to abnormal, that is, the electricity consumption is abnormal.

[0111] According to an embodiment of the present invention, after obtaining the storage location of the standard power data, the method further includes:

[0112] Extracting a tag of a storage location of standard power data;

[0113] Compare and analyze the label of the storage location of the standard power data and the label of the classification type of the corresponding standard power data. If they are consistent, the storage location of the corresponding standard power data is normal; if they are inconsistent, the storage location of the corresponding standard power data is abnormal;

[0114] If the storage location of the standard power data is abnormal, the preset management terminal authenticates and signs the classification tag of the standard power data;

[0115] The classification label of the standard power data is authenticated and signed according to the preset management terminal, the classification type label of the standard power data is adjusted, and the storage location of the corresponding standard power data is adjusted.

[0116] It should be noted that when there is a difference between the label of the storage location of the standard power data and the label of the classification type of the corresponding standard power data, the storage location of the corresponding standard power data will be marked as abnormal, and the preset management end will be notified to perform an authentication signature on the marked storage location. The authentication signature includes the signature of the corresponding preset management end and feedback. The feedback includes whether the abnormal storage location of the corresponding standard power data is accurate. If so, the storage location of the standard power data is corrected; if inaccurate, the classification of the standard power data of the data model is marked as wrong once, and based on the preset second time period, the total number of times the corresponding data model is marked as wrong is extracted. If the total number of times the corresponding data model is marked as wrong is greater than the preset number threshold, the weight coefficient of the keyword type of the data model is adaptively adjusted.

[0117] Figure 2 A block diagram of a data model management system for a data center in the electric power industry according to the present invention is shown.

[0118] like Figure 2 As shown, the second aspect of the present invention provides a data model management system 2 for a data center in the electric power industry, including a memory 21 and a processor 22, wherein the memory stores a data model management method program for a data center in the electric power industry, and the data model management method program for a data center in the electric power industry is executed by the processor to implement the following steps:

[0119] Obtain power data information;

[0120] Extracting the format characteristics of the power data, and determining whether the format characteristics of the power data are consistent with the preset format characteristics, if yes, setting the corresponding power data as standard power data; if no, adjusting the corresponding power data to standard power data;

[0121] Send the standard power data to a preset data model to determine whether the corresponding standard power data is normal. If so, classify and store the corresponding standard power data to obtain the storage location of the standard power data; if not, trigger a warning message;

[0122] Send the warning information to the preset management terminal for prompting.

[0123] According to an embodiment of the present invention, after setting the corresponding power data as standard power data or adjusting the corresponding power data to standard power data, the method further includes:

[0124] Extract keywords from standard power data;

[0125] According to the keywords in the standard power data, a preset keyword classification table is searched to obtain the type of the keywords in the corresponding standard power data;

[0126] Group the keywords of the same type together and record the quantity of the keywords of the same type.

[0127] The weight score of the keywords of the same type is obtained by multiplying the number of keywords of the same type by the preset score of the corresponding keyword type and the weight coefficient of the corresponding keyword type;

[0128] Determine whether the weight score of the same type of keywords is greater than a preset score threshold, and if so, identify the type of the corresponding keyword to obtain an identified type;

[0129] The identification types are combined to construct a classification type corresponding to the standard power data, and the label of the corresponding classification type is matched, and the standard power data is identified with the label of the corresponding classification type.

[0130] According to an embodiment of the present invention, the step of combining identification types to construct classification types corresponding to standard power data specifically includes:

[0131] Sort the identification types according to their corresponding weight scores from large to small to obtain the initial sequence number of the corresponding identification type;

[0132] Sequentially extract the initial sequence number of the identification type and set it as the base number of the identification type;

[0133] Sort the identification types according to the initial sequence numbers to obtain the initial classification types of the corresponding standard power data;

[0134] If the initial classification type of the corresponding standard power data and the preset classification type are compared and analyzed, if there is a consistency, the preset classification type with consistency is set as the classification type of the standard power data, and the identification type combination is stopped;

[0135] If there is no consistency, the reference number of the identification type is adjusted to obtain the initial classification type of the adjusted standard power data, and compared and analyzed with the preset classification type until there is a consistent preset classification type or all combinations of identification types are compared and analyzed.

[0136] The present invention discloses a data model management method and system for a data center in the electric power industry, which improves the accuracy of classified storage of electric power data and provides a guarantee for the subsequent application of electric power data.

[0137] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0138] 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 on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0139] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0140] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical disks, and other media that can store program codes.

[0141] Alternatively, if the above-mentioned integrated unit of the present invention 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 technical solution of the embodiment of the present invention, or the part that contributes to the prior art, can be implemented in the form of a software function module and sold or used as an independent product.

[0142] The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: a mobile storage device, ROM, RAM, a magnetic disk, or an optical disk, etc., which can store program codes.

Claims

1. A data model management method for the data center of the power industry, characterized in that: include: Obtain power data information; Extracting the format characteristics of the power data, and determining whether the format characteristics of the power data are consistent with the preset format characteristics, if yes, setting the corresponding power data as standard power data; if no, adjusting the corresponding power data to standard power data; Send the standard power data to a preset data model to determine whether the corresponding standard power data is normal. If so, classify and store the corresponding standard power data to obtain the storage location of the standard power data; if not, trigger a warning message; Send the warning information to the preset management terminal for prompting.

2. According to claim 1, a data model management method for the data center of the power industry is characterized in that: After setting the corresponding power data as standard power data or adjusting the corresponding power data to standard power data, the method further includes: Extract keywords from standard power data; According to the keywords in the standard power data, a preset keyword classification table is searched to obtain the type of the keywords in the corresponding standard power data; Group the keywords of the same type together and record the quantity of the keywords of the same type. The weight score of the keywords of the same type is obtained by multiplying the number of keywords of the same type by the preset score of the corresponding keyword type and the weight coefficient of the corresponding keyword type; Determine whether the weight score of the same type of keywords is greater than a preset score threshold, and if so, identify the type of the corresponding keyword to obtain an identified type; The identification types are combined to construct a classification type corresponding to the standard power data, and the label of the corresponding classification type is matched, and the standard power data is identified with the label of the corresponding classification type.

3. According to claim 2, a data model management method for the data center of the power industry is characterized in that: The step of combining the identification types to construct the classification type corresponding to the standard power data specifically includes: Sort the identification types according to their corresponding weight scores from large to small to obtain the initial sequence number of the corresponding identification type; Sequentially extract the initial sequence number of the identification type and set it as the base number of the identification type; Sort the identification types according to the initial sequence numbers to obtain the initial classification types of the corresponding standard power data; If the initial classification type of the corresponding standard power data and the preset classification type are compared and analyzed, if there is a consistency, the preset classification type with consistency is set as the classification type of the standard power data, and the identification type combination is stopped; If there is no consistency, the reference number of the identification type is adjusted to obtain the initial classification type of the adjusted standard power data, and compared and analyzed with the preset classification type until there is a consistent preset classification type or all combinations of identification types are compared and analyzed.

4. According to claim 2, a data model management method for the data center of the power industry is characterized in that: After the type of the corresponding keyword is identified and the identified type is obtained, the following steps are further included: Get the quantity value of the identification type; Determine whether the quantity value of the identification type is greater than a preset quantity threshold. If so, sort the identification types from large to small according to the corresponding weight scores, and extract the identification types with the preset quantity threshold at the front for combination; Setting the identification type after the preset quantity threshold as the backup identification type; When the comparison and analysis of all combinations of identification types are completed and the classification type of the standard power data is not determined, the spare identification types are used to replace the previously combined identification types in turn to re-combine.

5. According to claim 4, a data model management method for the data center of the power industry is characterized in that: The step of replacing the previously combined identification types with the spare identification types in sequence to re-combine the identification types specifically includes: Extract the backup identification type with the largest weight score; The backup identification type with the largest weight score replaces the identification type with the smallest weight score among the identification types previously combined to perform a first round of re-combination; If the classification type of the standard power data is not determined after the first round of regrouping, the identification type deleted in the first round of regrouping is restored, and the identification type with the second smallest weight score is deleted to perform the second round of regrouping; If the classification type of the standard power data is not determined after the second round of regrouping, the identification type deleted in the second round of regrouping is restored, and the identification type with the third smallest weight score is deleted to perform the third round of regrouping until the identification type with the largest weight score is deleted; If the classification type of the standard power data has not been determined after the identification type with the largest weight score is deleted and recombined, the two identification types with the largest weight scores will replace the two identification types with the smallest weight scores in the previously combined identification types for recombining, and so on, until there is a consistent preset classification type or all combinations of identification types have completed comparative analysis.

6. According to claim 1, a data model management method for the data center of the power industry is characterized in that: The step of determining whether the corresponding standard power data is normal specifically includes: Extract the electricity consumption units and corresponding electricity consumption in standard electricity data; According to the power consumption unit in the standard power data, matching the historical power consumption of the corresponding power consumption unit in a preset first time period; Calculate the average of the historical electricity consumption during the preset first time period to obtain the historical average electricity consumption; Subtract the historical average electricity consumption from the standard electricity data and take the absolute value to get the electricity consumption difference; Divide the difference in electricity consumption by the average amount of historical electricity consumption to obtain the electricity consumption fluctuation index; Determine whether the power consumption fluctuation index is within the preset index range. If so, the corresponding standard power data is normal; if not, the corresponding standard power data is abnormal.

7. According to claim 1, a data model management method for the data center of the power industry is characterized in that: After obtaining the storage location of the standard power data, the method further includes: Extracting a tag of a storage location of standard power data; Compare and analyze the label of the storage location of the standard power data and the label of the classification type of the corresponding standard power data. If they are consistent, the storage location of the corresponding standard power data is normal; if they are inconsistent, the storage location of the corresponding standard power data is abnormal; If the storage location of the standard power data is abnormal, the preset management terminal authenticates and signs the classification tag of the standard power data; The classification label of the standard power data is authenticated and signed according to the preset management terminal, the classification type label of the standard power data is adjusted, and the storage location of the corresponding standard power data is adjusted.

8. A data model management system for the data center of the power industry, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a data model management method program for a data center in the electric power industry, and when the data model management method program for a data center in the electric power industry is executed by the processor, the following steps are implemented: Obtain power data information; Extracting the format characteristics of the power data, and determining whether the format characteristics of the power data are consistent with the preset format characteristics, if yes, setting the corresponding power data as standard power data; if no, adjusting the corresponding power data to standard power data; Send the standard power data to a preset data model to determine whether the corresponding standard power data is normal. If so, classify and store the corresponding standard power data to obtain the storage location of the standard power data; if not, trigger a warning message; Send the warning information to the preset management terminal for prompting.

9. A data model management system for the data center of the power industry according to claim 8, characterized in that: After setting the corresponding power data as standard power data or adjusting the corresponding power data to standard power data, the method further includes: Extract keywords from standard power data; According to the keywords in the standard power data, a preset keyword classification table is searched to obtain the type of the keywords in the corresponding standard power data; Group the keywords of the same type together and record the quantity of the keywords of the same type. The weight score of the keywords of the same type is obtained by multiplying the number of keywords of the same type by the preset score of the corresponding keyword type and the weight coefficient of the corresponding keyword type; Determine whether the weight score of the same type of keywords is greater than a preset score threshold, and if so, identify the type of the corresponding keyword to obtain an identified type; The identification types are combined to construct a classification type corresponding to the standard power data, and the label of the corresponding classification type is matched, and the standard power data is identified with the label of the corresponding classification type.

10. A data model management system for the data center of the power industry according to claim 9, characterized in that: The step of combining the identification types to construct the classification type corresponding to the standard power data specifically includes: Sort the identification types according to their corresponding weight scores from large to small to obtain the initial sequence number of the corresponding identification type; Sequentially extract the initial sequence number of the identification type and set it as the base number of the identification type; Sort the identification types according to the initial sequence numbers to obtain the initial classification types of the corresponding standard power data; If the initial classification type of the corresponding standard power data and the preset classification type are compared and analyzed, if there is a consistency, the preset classification type with consistency is set as the classification type of the standard power data, and the identification type combination is stopped; If there is no consistency, the reference number of the identification type is adjusted to obtain the initial classification type of the adjusted standard power data, and compared and analyzed with the preset classification type until there is a consistent preset classification type or all combinations of identification types are compared and analyzed.

Images