Intelligent decision support method and system based on ERP data

Abstract

The invention provides an intelligent decision support method and system based on ERP data, and belongs to the technical field of data processing, and the method specifically comprises the steps: taking a power transmission line where power equipment is located as a matched power transmission line, and determining an observation processing method of the power equipment in an ERP system according to the constitution data of observation power equipment in different matched power transmission lines, the observation processing method and the analysis result of the purchase data of the maintenance accessories are used for identifying the observation power equipment in the power equipment, and the observation data of the power equipment are obtained according to the change data of the observation power equipment in the power transmission line where the observation power equipment is located and the observation data of the power equipment. The output processing method for observing the purchase decision of the power equipment is determined, and the operation reliability of a power system is improved.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, and in particular relates to an intelligent decision support method and system based on ERP data. Background Technology

[0002] By parsing and processing ERP data, it is possible to identify procurement data for power equipment and spare parts, thereby enabling the identification and processing of power equipment with short replacement cycles or frequent maintenance, providing data support for future decision support.

[0003] To address the aforementioned issues, invention patent application CN202110815694.4, "A Method, System, Device, and Storage Medium for Power Equipment Asset Management," utilizes an ERP workflow to supplement the cost centers and monitoring status of equipment assets, creating asset cards. These cards are periodically updated, added to, deleted from, or supplemented based on changes in information. Three-dimensional imaging technology combines ledger information, card information, and physical information, facilitating timely updates to card information during frequent changes in power grid assets. However, the following drawbacks exist: Existing technical solutions neglect to assess the reliability of power equipment operation based on maintenance parts procurement data, and to output targeted procurement decision recommendations. The frequency of maintenance parts procurement for different power equipment on different transmission lines varies in the ERP system. Therefore, how to determine procurement decision recommendations when there are abnormalities in the procurement of maintenance parts for power equipment based on the monitoring of gas in the transmission line where the power equipment is located, thereby ensuring the operational stability of the power system, has become an urgent technical problem to be solved.

[0004] To address the aforementioned technical problems, this application provides an intelligent decision support method and system based on ERP data. Summary of the Invention

[0005] To achieve the objectives of this invention, the following technical solution is adopted: Specifically, this application provides an intelligent decision support method based on ERP data, which includes: S1 uses the parsing results of ERP data to determine the procurement data of maintenance parts for different power equipment. Based on the procurement data, when it is necessary to identify the power equipment to be observed in the power equipment, the interval time data of the procurement data of the same maintenance parts is used to determine the power equipment to be observed. S2 uses the transmission line where the power equipment is located as the matching transmission line. Based on the composition data of the observed power equipment in different matching transmission lines, it determines the observation processing method of the power equipment in the ERP system. Using the observation processing method and the analysis results of the maintenance parts procurement data, it performs the identification processing of the observed power equipment. Based on the change data of the observed power equipment in the transmission line where the observed power equipment is located and the observation data of the power equipment, it determines the output processing method of the procurement decision of the observed power equipment.

[0006] The beneficial effects of this invention are as follows: Based on the interval data of the same maintenance parts procurement data, the power equipment to be monitored is identified. This enables the screening of power equipment that may have abnormal quality risks from the perspective of the quantity and frequency of maintenance parts procurement and processing, and targeted monitoring and processing, thereby improving the efficiency and reliability of anomaly identification and processing, and laying the foundation for the output of targeted procurement decision recommendations.

[0007] Based on the change data of the observed power equipment in the transmission lines where the observed power equipment is located, as well as the observation data of the power equipment, the output processing method for the procurement decision of the observed power equipment is determined. This method not only takes into account the difference in the degree of abnormal risk in the transmission lines due to the difference in the number of observed power equipment in the transmission lines where the observed power equipment is located, but also, by combining the observation data of the power equipment, it also realizes the difference in the observation reliability of the transmission lines where the observed power equipment is located. This lays the foundation for the output of targeted procurement decision recommendations from a systematic perspective.

[0008] Furthermore, the ERP data includes procurement data for power equipment, procurement data for maintenance parts, and electricity sales data.

[0009] Furthermore, the procurement data for the maintenance parts of the power equipment includes the procurement time, procurement type, and procurement quantity of the maintenance parts for the power equipment.

[0010] Furthermore, determining the need for identification processing of the observed power equipment within the power equipment specifically includes: Based on the procurement data, determine the procurement time for maintenance parts for the power equipment; Based on the procurement time of maintenance parts for the power equipment, identify the power equipment for which maintenance parts procurement data exists on different dates; For power equipment with procurement data for maintenance parts on different dates, determine whether the identification process for the observed power equipment in the power equipment needs to be performed.

[0011] Furthermore, the method for determining the observation and processing method of the power equipment in the ERP system is as follows: Using the configuration data of the observed power equipment in different matched transmission lines, the matched transmission lines with observed power equipment are identified and used as the observed transmission lines; Based on the composition data of the observation power equipment in different observation transmission lines, the number of observation power equipment in different observation transmission lines is determined. Based on the observed transmission line data and the number of observed power devices in different observed transmission lines, the observation processing method for the power devices in the ERP system is determined.

[0012] In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the aforementioned intelligent decision support method based on ERP data when running the computer program.

[0013] Other features and advantages will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0014] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0015] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0016] Figure 1 This is a flowchart of an intelligent decision support method based on ERP data; Figure 2 This is a flowchart for determining which power equipment in the power equipment needs to be identified and processed. Figure 3 This is a flowchart of the method for determining the observation power equipment in power equipment. Detailed Implementation

[0017] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that the invention will be thorough and complete, and the concept of the exemplary embodiments will be fully conveyed to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore their detailed description will be omitted.

[0018] The terms “a,” “one,” “the,” and “the” are used to indicate the existence of one or more elements / components / etc.; the terms “including” and “having” are used to indicate an open-ended meaning of inclusion and that other elements / components / etc. may exist in addition to the listed elements / components / etc.

[0019] Example 1 To solve the above problems, according to one aspect of the present invention, such as Figure 1 As shown, this application provides a specific intelligent decision support method based on ERP data, which specifically includes: S1 uses the parsing results of ERP data to determine the procurement data of maintenance parts for different power equipment. Based on the procurement data, when it is necessary to identify the power equipment to be observed in the power equipment, the interval time data of the procurement data of the same maintenance parts is used to determine the power equipment to be observed. S2 uses the transmission line where the power equipment is located as a matching transmission line. Based on the composition data of the observed power equipment in different matching transmission lines, it determines the observation processing method of the power equipment in the ERP system. Using the observation processing method and the analysis results of the procurement data of maintenance parts, it performs the identification processing of the observed power equipment in the power equipment. Based on the change data of the observed power equipment in the transmission line where the observed power equipment is located, it determines the output processing method of the procurement decision of the observed power equipment.

[0020] Furthermore, the ERP data includes procurement data for power equipment, procurement data for maintenance parts, and electricity sales data.

[0021] Furthermore, the procurement data for the maintenance parts of the power equipment includes the procurement time, procurement type, and procurement quantity of the maintenance parts for the power equipment.

[0022] Furthermore, such as Figure 2 As shown, the identification process for the observed power equipment in the power equipment is determined to be required, specifically including: S11 Based on the procurement data, determine the procurement time for maintenance parts of the power equipment; S12 Based on the procurement time of maintenance parts for the power equipment, determine the power equipment for which there is procurement data for maintenance parts on different dates; Specifically, the data on the purchase of maintenance parts refers to the records of purchasing spare parts for the maintenance or repair of a power equipment. Frequent or extensive purchases of spare parts indirectly reflect a high potential failure rate of the equipment.

[0023] S13 determines whether the power equipment for which there is procurement data for maintenance parts on different dates needs to undergo identification processing.

[0024] In the above steps, monitoring electrical equipment refers to specific electrical equipment that needs to be closely monitored and analyzed in order to assess its quality risks and usage status.

[0025] In the steps described above, the purchase records of electrical equipment maintenance parts are analyzed to determine whether a more refined "electrical equipment monitoring" identification process needs to be initiated. The core idea is that when the purchase of maintenance parts is too frequent, a focused approach must be taken to identify key equipment for targeted analysis.

[0026] It is understandable that, for power equipment with procurement data for maintenance parts existing on different dates, determining whether the identification processing of the observed power equipment in the power equipment is required specifically includes: Based on the power equipment for which maintenance parts procurement data exists on different dates, determine the quantity of power equipment for which maintenance parts procurement data exists on different dates; Based on the number of power equipment for which maintenance parts procurement data exists on different dates, determine whether it is necessary to perform identification processing of the observed power equipment among the power equipment.

[0027] Specifically, the above implementation plan includes the following steps: Data extraction: Based on the procurement data of maintenance parts for power equipment, extract the power equipment and its procurement date corresponding to each procurement record.

[0028] Identify target equipment: Filter out electrical equipment with maintenance parts purchase records on different dates (note: not multiple purchases on the same day, but distributed across multiple different dates). This step is to identify equipment that consistently and repeatedly requires maintenance, excluding equipment with single, occasional failures.

[0029] Statistics and Judgment: Count the number (N) of electrical equipment that meets the above conditions, and compare this number N with a pre-set "preset threshold for the number of electrical equipment".

[0030] If N > the threshold, it indicates that a large number of devices are subject to repeated repairs, suggesting a high risk of systemic quality or aging. In this case, conducting a comprehensive procurement decision analysis for all devices is difficult, costly, and inefficient. Therefore, it is necessary to initiate the "monitoring of power equipment" process, selecting the most critical and typical devices from among numerous options for in-depth analysis, providing accurate data support for future procurement strategies (such as new power equipment procurement strategies).

[0031] If N ≤ threshold: This indicates that only a small number of devices have recurring repair issues, and the situation is within a controllable range. In this case, a special identification process can be omitted, or other more conventional management methods can be used.

[0032] Understandably, when the number of power equipment with maintenance parts procurement data on different dates does not meet the requirements, i.e., exceeds the preset power equipment quantity threshold, it is difficult to conduct procurement decision analysis using procurement data for all power equipment. Therefore, it is necessary to identify and process the power equipment under observation, and to specifically identify and analyze the procurement data of the observed power equipment to determine its existing quality risks and defects, thereby providing data support for the procurement of power equipment.

[0033] In one possible specific embodiment, the preset threshold for the number of electrical devices is 5 units, and the analysis period is a review of maintenance parts procurement data from the past year.

[0034] Scene setup and data analysis: Scenario 1: Cases where recognition processing is not required Procurement data: Device-02: Screws were purchased on 2023-05-10; Device-15: Sealing rings were purchased on 2023-08-22 and 2023-11-05; Device-18: Fuses were purchased on 2024-01-30.

[0035] Identification and Statistics: Devices with purchase data on different dates include Device-15 (purchased on two different dates). The number of devices meeting the criteria is N = 1. Decision: N (1) > preset threshold (5)? ​​No. Final conclusion: Only one device shows signs of repeated maintenance, and the problem is not widespread. Therefore, it is not necessary to initiate the identification process for "monitoring power equipment".

[0036] It should be noted that when the identification process for "observing power equipment" is not required, all power equipment will be treated as observation power equipment.

[0037] It should be noted that the power equipment is classified according to the manufacturer and model number, specifically those from the same manufacturer and of the same model number are classified as one type of power equipment.

[0038] Furthermore, such as Figure 3 As shown, the method for determining the observation power equipment in the power equipment is as follows: In this embodiment, from the group of power equipment, those devices whose maintenance parts procurement patterns are abnormal due to their own potential quality defects are identified and designated as "monitored power equipment" for key monitoring and in-depth data analysis.

[0039] S21 determines the quantity of the power equipment to be used based on the procurement data of the power equipment; Number of electrical equipment in use: refers to the total number of equipment of this model / batch in the system.

[0040] S22 determines the interval between adjacent purchase times for the same maintenance parts based on the purchase data of the power equipment for the same maintenance parts, and determines the purchase quantity of maintenance parts in different time periods based on the interval. Time period division: a fixed duration based on the time interval between adjacent purchases of the same repair parts (e.g., if the average interval is 3 months, then the time period is 3 months).

[0041] S23 determines whether the power equipment is a monitoring power equipment based on the number of times the power equipment is used and the purchase volume of different identical maintenance parts in different time periods.

[0042] It should be noted that the quantity of the power equipment used is determined based on the analysis results of the historical procurement data of the power equipment in the ERP system.

[0043] It is understood that, based on the number of times the electrical equipment is used and the time interval between adjacent purchases of different identical maintenance parts, determining whether the electrical equipment is a monitored electrical equipment specifically includes: S231 Obtain the usage quantity of the power equipment, determine whether the usage quantity of the power equipment is greater than a preset usage quantity threshold, if yes, proceed to the next step, if no, determine that the power equipment does not belong to the observed power equipment; In the above steps, a preliminary screening is conducted - based on the equipment inventory, those devices with very low usage are excluded, because fluctuations in the purchase of spare parts for a small number of devices may not be statistically significant and may easily lead to misjudgment. Determine: Is the number of devices in use greater than the preset usage threshold? If not: directly determine it as a non-observable device.

[0044] S232 treats the same maintenance parts as the same part combination, and determines whether there is a part combination in the most recent preset time period whose maintenance parts purchase volume is greater than a preset purchase volume threshold based on the purchase volume of maintenance parts in different time periods of the part combination. If so, proceed to the next step; otherwise, determine that the power equipment does not belong to the power equipment under observation. In the steps above, identify abnormal parts purchases and find out which repair parts have recently experienced unusual purchase spikes.

[0045] Specifically, for each type of accessory, check whether there is any time period in the most recent "divided time periods" where the purchase quantity exceeds the preset purchase quantity threshold. The result is that accessories that meet the conditions are marked as "target accessory combinations", and the corresponding time period is marked as "target time period". If the power equipment does not have accessories in such a target time period, it is determined to be non-observed equipment.

[0046] S233 will take the parts combination that has the purchase quantity of maintenance parts exceeding the preset purchase quantity threshold in the most recent preset time period as the target parts combination. Then, take the target parts combination and the time period in the most recent preset time period that has the purchase quantity of maintenance parts exceeding the preset purchase quantity threshold as the target time period. Determine whether there is a target parts combination with a number of target time periods exceeding the preset target time period number threshold. If not, proceed to the next step. If yes, determine that the power equipment belongs to the observation power equipment. In the steps described above, identifying persistent anomalies involves pinpointing instances where the purchase volume of the same component is abnormal across multiple consecutive time periods. This is a very strong fault signal.

[0047] Judgment: For any "target accessory combination", is the quantity of its "target time period" greater than the preset target time period quantity threshold? If yes: it indicates that the accessory has a continuous consumption anomaly, and the device is directly determined to be an observation device.

[0048] S234 determines the procurement matching factor for different target accessory combinations based on the ratio of the purchase quantity of maintenance parts to the usage quantity of the power equipment within the most recent preset time period for different target accessory combinations, and determines whether the power equipment is an observation power equipment based on the procurement matching factor for different target accessory combinations.

[0049] Specifically, determining whether the power equipment is a monitoring power equipment involves using procurement matching factors based on different combinations of target components, including: S235 determines whether there is a target accessory combination with a purchase matching factor greater than a preset matching factor threshold. If not, proceed to the next step. If yes, determine that the power equipment belongs to the observation power equipment. S236 determines the sum of the procurement matching factors for different target component combinations based on the procurement matching factors for different target component combinations, and determines that the power equipment belongs to the observation power equipment when the sum of the procurement matching factors for different target component combinations is greater than a preset factor threshold.

[0050] The goal of the above steps is to conduct a quantitative assessment of equipment that exhibits non-persistent anomalies but still has serious overall problems.

[0051] S234: Calculate the procurement matching factor: Factor = Total recent procurement volume of parts / Number of devices used. This factor reflects the average quantity of this part consumed per device; a higher ratio indicates a potentially more widespread problem.

[0052] S235: Check the severity of a single component: Is there any target component whose purchase matching factor is greater than the preset matching factor threshold? If yes: Determine it as a monitoring device.

[0053] S236: Check the severity of multiple component overlap: Calculate the sum of the procurement matching factors for all target components and determine if it exceeds the preset factor and threshold. If yes: determine it as an observation device; if no: determine it as a non-observation device.

[0054] In one possible embodiment, a power transformer of model "DT-1000" is evaluated, with the following basic data: Number of devices in use (N): 20 (on the network), analysis time range: the four most recent time periods (assuming each time period is 3 months, i.e., the analysis is for the most recent year).

[0055] The procurement data for its maintenance parts is as follows: Insulating sleeves: Time period 1: 1 unit purchased, Time period 2: 2 units purchased (target time period), Time period 3: 2 units purchased (target time period), Time period 4: 1 unit purchased; Cooling fans: Time period 1: Purchase 1 unit, Time period 2: Purchase 1 unit, Time period 3: Purchase 2 units ← Target time period, Time period 4: Purchase 2 units ← Target time period; Relays: Time period 1: Purchase 2 (target time period), Time period 2: Purchase 1, Time period 3: Purchase 1, Time period 4: Purchase 0; Decision-making process simulation: S231: Number of devices in use 20 > threshold 10? Yes, proceed to the next step.

[0056] S232: Identify the "target accessory combination" and "target time period". Insulating sleeve: Purchase quantity > 5 in time period 2 and time period 3, thus becoming a target accessory combination. Cooling fan: Purchase quantity > 5 in time period 3 and time period 4, thus becoming a target accessory combination. Relay: Purchase quantity > 5 in time period 1, thus becoming a target accessory combination. If a target accessory combination exists, proceed to the next step.

[0057] S233: Determine if there is a target accessory combination with a "target time period" quantity > 2? Insulating sleeve: Target time period quantity = 2, equal to threshold 2? (According to the text "greater than", 2 is not greater than 2, so it is not triggered). Cooling fan: Target time period quantity = 2, similarly, it is not triggered. Relay: Target time period quantity = 1, it is not triggered. There is no direct judgment, so it enters the comprehensive evaluation.

[0058] S234 / S235: Calculate factors and check the severity of individual components, calculate recent total purchase volume (last 4 periods) and purchase matching factor: Insulating sleeves: Total = 6. Factor = 6 / 20 = 0.3; Cooling fans: Total = 6. Factor = 6 / 20 = 0.3; Relays: Total = 4. Factor = 2 / 20 = 0.2; Judgment: Does a target accessory exist with a factor > 0.2? Insulating sleeve (0.3 > 0.2) -> Yes, Cooling fan (0.3 > 0.2) -> Yes, Relay (0.2 > 0.2) -> No.

[0059] Conclusion: Since there are target accessory combinations with a procurement matching factor greater than the threshold, the "DT-1000" transformer was identified as the monitoring power equipment.

[0060] Final conclusion: This model of transformer exhibits high loss rates in multiple maintenance parts, and the average consumption of parts per unit is very high, indicating that there may be widespread quality defects. It must be a key monitoring target, and the quality risks behind its procurement data must be analyzed.

[0061] In the following steps, electrical equipment is observed: electrical equipment identified as having potential quality or aging risks and requiring close monitoring. These serve as the benchmark and input for this method's judgment; Matching transmission lines: refers to the set of all lines in the power grid topology that are on the same circuit path as the power equipment currently under consideration.

[0062] Monitoring Transmission Lines: In a matching transmission line, if it contains at least one "monitoring power device," the line is marked as a monitoring transmission line. This indicates that the "health status" of the line has been flagged as yellow.

[0063] Basic correlation factor: Number of observed transmission lines / Total number of matched transmission lines. This factor reflects the risk level of the direct electrical environment in which the equipment is located. The higher the ratio, the greater the proportion of problematic lines in the line network where the equipment is located, and the higher the risk of the equipment being affected.

[0064] Setting a correlation factor: This is a more stringent indicator. It examines the degree of correlation between the current equipment and "key risk lines" that contain a large number of monitored power devices. It reflects the tightness of the connection between the equipment and the high-risk core area.

[0065] Correlation coefficient: (Basic correlation factor + Set correlation factor) / 2. This is a comprehensive risk indicator that considers both "direct environmental risk" and the correlation with "core risk areas" to make the final decision.

[0066] Furthermore, the method for determining the observation and processing method of the power equipment in the ERP system is as follows: S31 uses the configuration data of the observed power equipment in different matched transmission lines to determine the matched transmission lines where the observed power equipment exists, and uses them as the observed transmission lines. S32 determines the number of observation power devices in different observation transmission lines based on the composition data of the observation power devices in different observation transmission lines; Steps S31 & S32: Data preparation and matching of transmission lines: The GD-2024 device is configured on 5 transmission lines (L1, L2, L3, L4, L5).

[0067] Distribution of power equipment observed: Line L1: Contains observation equipment A and observation equipment B → for observing transmission lines; L2 line: contains observation equipment C, observation equipment D, observation equipment E, and observation equipment F → observes transmission lines (and is a key risk line, because the number 4 > 3); L3 line: No observation equipment; L4 line: Contains observation equipment G → Observation transmission line; Line L5: No observation equipment available; Calculation results: Observed transmission lines: L1, L2, L4 (3 in total), total number of matched transmission lines: 5, key risk line: L2 (1 in total).

[0068] S33 determines the observation processing method for the power equipment in the ERP system based on the observed transmission line data and the number of observed power equipment in different observed transmission lines.

[0069] It is understood that, based on the observed transmission line data and the number of observed power devices in different observed transmission lines, the observation processing method for the power devices in the ERP system is determined, specifically including: S331 obtains the number of observed power devices in the matched transmission line, determines whether there is an observed transmission line in the matched transmission line, if yes, proceeds to the next step, if no, determines that the power device does not need to be observed in the ERP system for the time being. S331: Determine if there are any observed transmission lines? Result: Yes (L1, L2, L4), proceed to the next step.

[0070] S332 Based on the proportion of the observed transmission lines in the matched transmission lines, determine the basic correlation factor of the power equipment, and determine whether the basic correlation factor of the power equipment is greater than the preset correlation factor threshold. If so, determine that the observation processing method of the power equipment in the ERP system is that as long as there is a time period in which the purchase quantity of maintenance parts is greater than the preset purchase quantity threshold, it will be regarded as the observed power equipment. If not, proceed to the next step. In the above steps, the basic correlation factor is calculated and judged. Calculation: Basic correlation factor = 3 / 5 = 0.6. Judgment: 0.6 > threshold T1 (0.5)? Yes. Conclusion: Since the basic correlation factor reaches the threshold, it indicates that the correlation between the equipment and the observed power equipment is high and they are often uniformly configured. Therefore, when outputting the procurement strategy for observed power equipment, it is necessary to consider the operating status of other power equipment that are often used simultaneously in the same transmission line. Therefore, the most stringent strategy is adopted to determine whether it belongs to the observed power equipment.

[0071] Final observation processing method: The most stringent strategy is adopted: as long as the procurement quantity of maintenance parts for the equipment GD-2024 exceeds the preset procurement quantity threshold during the specified time period, it will be regarded as an observation power equipment.

[0072] S333 determines whether there are any observation transmission lines with a number of observation power devices greater than a preset threshold for the number of observation power devices based on the number of observation power devices in different observation transmission lines. If yes, proceed to the next step; otherwise, determine that the power devices do not need to be observed in the ERP system for the time being. (Assuming the scenario changes: if the threshold T1 is set to 0.7, then 0.6 < 0.7, which is judged as "no", and the process will proceed to S333) In the above steps, we determined whether there were "key risk lines," which are transmission lines with a large number of monitored power devices. This illustrates the difference in the need for simultaneous monitoring and processing of power devices on transmission lines. Line L2 contains 4 monitoring devices, exceeding the threshold of 3, therefore it exists. Proceed to the next step.

[0073] S334 determines the setting correlation factor between the power equipment and the observation power equipment based on the proportion of the observation transmission lines that overlap with different observation power equipment in the transmission lines where the observation power equipment is located, and determines the observation processing method of the power equipment in the ERP system based on the setting correlation factor between the power equipment and the observation power equipment and the basic correlation factor of the power equipment.

[0074] After summarizing and calculating the correlation factor in the above steps, the only transmission line that GD-2024 overlaps with observed power equipment A is line L1. Assuming that observed power equipment A itself is located on lines L1, L2, and L4, the correlation factor is set as follows: (Number of overlapping observed transmission lines: 1 line L1) / (Number of all observed transmission lines where GD-2024 is located: 3 lines L1, L2, L4) = 1 / 3 ≈ 0.33.

[0075] Specifically, based on the setting correlation factor between the power equipment and the observed power equipment, as well as the basic correlation factor of the power equipment, the observation processing method for the power equipment in the ERP system is determined, including: The correlation coefficient is determined by the average value of the setting correlation factor of the power equipment and the observation power equipment and the basic correlation factor of the power equipment. It is then determined whether the correlation coefficient is greater than the preset correlation coefficient threshold. If so, the observation processing method of the power equipment in the ERP system is determined to be that when there are multiple time periods in which the purchase quantity of maintenance parts is greater than the preset purchase quantity threshold, the power equipment is regarded as the observation power equipment. If not, the power equipment does not need to be observed in the ERP system for the time being.

[0076] In the above steps, the correlation coefficient is calculated and the final method is determined. The calculation is: Correlation coefficient = (basic correlation factor 0.6 + average value of correlation factor of different observed power equipment 0.33) / 2 = 0.45. The judgment is: 0.45 > threshold T2 (0.4)? The final observation processing method is: adopt the standard strategy: when the equipment GD-2024 has multiple maintenance parts purchase quantities that exceed the preset purchase quantity threshold for the time period, it is considered as an observed power equipment. If the correlation coefficient ≤ 0.4, the conclusion is "no observation processing is required for the time being".

[0077] This method binds the monitoring strategy of a single device to the health of its environment through the power grid topology, thereby enabling dynamic adjustment of the monitored power equipment. This ensures that the output of the monitored power equipment in the procurement decision-making process can comprehensively consider the composition data of the monitored power equipment that is frequently set up and processed simultaneously. It realizes the output of decision recommendations based on the operational stability from one aspect, namely the line network, thereby improving the operational stability and reliability of power transmission lines.

[0078] Specifically, Conclusion B (most stringent): has the highest correlation with the observed power equipment; even a slight abnormality in the equipment will raise the monitoring level. Conclusion C (standard): has a relatively high correlation with the observed power equipment; multiple abnormal signals are required to raise the monitoring level. Conclusion A (lenient): has a weak correlation with the observed power equipment; therefore, it has little impact on the procurement recommendations for the observed power equipment, and no special monitoring will be adopted for the time being.

[0079] Furthermore, the method for determining the output processing method for the procurement decision of the observed power equipment is as follows: S41 takes the transmission line where the observed power equipment is located as the target line, and uses the change data of the observed power equipment in different target lines to determine the number of observed power equipment in different target lines. In the steps described above, to determine the target lines and the number of monitoring devices, the system first queries the power grid topology database for all transmission lines equipped with OB-Device-01. The query results show that this device is part of a network of three critical transmission lines (Line-A, Line-B, Line-C). Subsequently, the system counts the number of "monitoring power devices" on these three "target lines," which are 4, 2, and 5 respectively.

[0080] Target line: refers to the transmission line directly connected to or belonging to the "observation power equipment" currently undergoing procurement decision analysis.

[0081] This step is the spatial positioning of risk assessment. It answers the question, "Where do we assess risk?" By defining the target line, we place an isolated equipment problem within its real-world operational ecosystem for examination. A single piece of equipment may not have a significant problem, but if it's located in a "critical area" (i.e., a line with many monitored power devices), its future risk probability and the probability of potential defects in its model will significantly increase its impact on the overall reliability of the entire transmission line. This step forms the basis for all subsequent local risk analyses.

[0082] S42 Based on the observation data of power equipment in different target lines, identify the power equipment in different target lines that has not been observed and treat it as unobserved power equipment. After identifying three target lines, the system further analyzed the equipment list for each line to identify unobserved electrical equipment. Subtracting the number of marked observed devices from the total number of devices yielded the number of "unobserved electrical devices" for each line: Line-A had 6, Line-B had 6, and Line-C had 7. These unobserved electrical devices represent "unknowns X" in the monitoring system. They may be perfectly healthy or possess potential defects that have not yet been detected by the monitoring system. They represent the uncertainty boundary of the current risk assessment system.

[0083] This step assesses our confidence in the monitoring system. It quantifies our "lack of knowledge." If a high percentage of devices on a line are not monitored, it means our understanding of their true health status is incomplete and limited. In this case, any decision made based on existing (incomplete) observation data carries a higher risk than decisions made in a fully monitored environment. Therefore, this step provides crucial information for subsequent judgments on whether to adopt a "conservative" or "aggressive" decision-making strategy.

[0084] S43 determines the output processing method for the procurement decision of the observed power equipment based on the number of observed power equipment and unobserved power equipment in different target lines, and in conjunction with the observed power equipment data in the ERP system.

[0085] Furthermore, based on the number of observed and unobserved power equipment on different target lines, and in conjunction with the observed power equipment data in the ERP system, the output processing method for the procurement decision of the observed power equipment is determined, specifically including: S431 Based on the observed power equipment data in the ERP system, determine the number of observed power equipment in the ERP system, and determine whether the number of observed power equipment in the ERP system is greater than the preset observation equipment number threshold. If so, the observation processing is more difficult. Therefore, as long as the observed power equipment has maintenance parts whose purchase matching factors do not meet the requirements within the most recent preset time period, the purchase decision is output, that is, no longer purchase power equipment of the same model and manufacturer corresponding to the observed power equipment. If not, proceed to the next step. In the steps described above, a global observation scale assessment is performed. The decision-making system calls the ERP's asset health dashboard to obtain the total number of all "observed power equipment" across the entire company, which is 50 units. The system compares this number with a preset global threshold of 100 units. The observed power equipment data in the ERP system serves as a macro-level barometer of the company's asset health, reflecting the difficulty of the ERP system in observing and processing these power equipment.

[0086] This step represents the highest level of strategic risk assessment. It considers the overall asset reliability of the organization. If this amount exceeds a threshold, it indicates significant challenges in monitoring and processing within the company's ERP system. In such cases, the most decisive and stringent "zero-tolerance" strategy must be adopted (i.e., the S431 decision-making scheme: if power equipment has maintenance parts with unmet matching factors within the most recent preset time period, it indicates not only historical anomalies but also anomalies within the current time period) to prevent further expansion of the problematic assets. This is a globally optimal "cut-the-tails" strategy. In this example, it was not triggered, indicating that the problem has not yet developed into a global crisis.

[0087] Based on the data of the observed power equipment in different target lines, S432 determines the average number of observed power equipment in different target lines and judges whether the average number of observed power equipment in different target lines is greater than the preset value of the number of equipment. If so, then the number of observed power equipment in the transmission line where the observed power equipment is located is large, and therefore the number of power equipment with quality defect risk is large. So as long as the observed power equipment has maintenance parts whose purchase matching factor does not meet the requirements within the most recent preset time period, the purchase decision is output, that is, no longer purchase power equipment of the same model and manufacturer as the observed power equipment. If not, proceed to the next step. Specifically, in the above steps, local fault density is determined by calculating the average number of observed devices across the three target lines where OB-Device-01 is located. (4 + 2 + 5) / 3 = 3.67 devices / line. This average is then compared to the density threshold of 5. The average number of observed power devices is an indicator of risk clustering. It measures the distribution density of risk within the local network to which a specific device belongs.

[0088] This step is a meso-level, network-level risk analysis. It answers the question, "Is the surrounding environment of this device hostile?" Even if the overall situation is good, if there are many problematic devices in a device's vicinity, it strongly suggests that there are a large number of potentially anomaly-prone devices on the target line being processed concurrently with the device. Therefore, any one high-risk device will exacerbate the risk, and procurement in this context should be stopped immediately if anomalies are present. In this example, it was not triggered, indicating that this device model has not yet demonstrated widespread adaptive failure in its immediate environment.

[0089] S433 determines the proportion of unobserved power equipment in different target lines based on the number of unobserved power equipment in different target lines, and uses this as the observation deviation proportion. It then determines whether there are target lines where the observation deviation proportion is greater than a preset deviation proportion threshold. If so, the observation reliability of the transmission line where the observed power equipment is located is poor. Therefore, if the observed power equipment has maintenance parts whose purchase matching factor does not meet the requirements within the most recent preset time period, a purchase decision is output, that is, no longer purchasing power equipment of the same model and manufacturer as the observed power equipment. If not, the output processing method for determining the purchase decision of the observed power equipment is determined based on the observation data of the observed power equipment.

[0090] In the above steps, the reliability of the observation system is assessed by calculating the "observation deviation percentage" for each target line. For Line-B, this is calculated as 6 / 8 = 0.75 (i.e., 75%). It is found that the percentage of Line-B (0.75) is greater than the reliability threshold of 0.7. The observation deviation percentage is a data credibility discount coefficient. It directly reflects the confidence level of decisions made based on existing observation data.

[0091] This step audits the reliability of the decision-making basis itself (i.e., the data). When the observational bias of a line is high, it means our decision-making is being conducted in an "information fog." What we see is only the tip of the iceberg; many more unknown problems may be hidden beneath the surface. In this situation, if we still judge according to conventional standards (i.e., entering S434), we may make overly risky decisions due to incomplete information (e.g., allowing a potentially defective model to be approved). Therefore, this step forces the system to switch to a "conservative decision-making mode" when data reliability is low: that is, for problems that have been discovered (OB-Device-01), a "better safe than sorry" strategy is adopted; as long as there are any abnormal signs, a procurement ban is imposed on that model. This is a risk-avoidance strategy. In this example, it is the trigger and the most critical factor leading to the final decision.

[0092] It should be noted that the most recent preset time period is between three and six months. Specifically, the output processing method for determining the procurement decision of the observed power equipment based on the observed data of the observed power equipment includes: Based on the average value of the procurement matching factors of different maintenance parts for the observed power equipment within the most recent preset time period, a matching coefficient is determined. When the matching coefficient is greater than the preset matching coefficient threshold, a procurement decision is output, that is, the same model and manufacturer of power equipment corresponding to the observed power equipment will no longer be procured.

[0093] In the above steps, focusing on the quantification of the equipment's own risks (assuming S433 is not triggered), the system will calculate the average value of the matching factor for all maintenance parts procurement of OB-Device-01, (0.8 + 0.5 + 0.7) / 3 = 0.667.

[0094] Matching coefficient: This is the ultimate quantification of the inherent failure risk and severity of an individual device. It strips away environmental and system factors, directly answering the question, "Is this device model itself a bad apple?"

[0095] This step represents the most precise and direct micro-level decision-making. When global, local, and environmental data are relatively reliable, the decision is entirely based on the equipment model's own "health check report." A high matching coefficient indicates a high average failure rate for that model, proving inherent defects in its design, materials, or manufacturing processes—making it a "sick" asset. Continuing to procure such assets would only introduce future maintenance burdens and operational risks. Therefore, stopping procurement based on this coefficient represents data-driven precision management.

[0096] Example 2 In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the aforementioned intelligent decision support method based on ERP data when running the computer program.

[0097] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0098] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0099] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. An intelligent decision support method based on ERP data, characterized in that, Specifically, it includes: Based on the analysis results of ERP data, the procurement data of maintenance parts for different power equipment is determined. Based on the procurement data, when it is necessary to identify the power equipment to be observed in the power equipment, the interval time data of the procurement data of the same maintenance parts is used to determine the power equipment to be observed. The transmission line where the power equipment is located is used as a matching transmission line. Based on the composition data of the power equipment observed in different matching transmission lines, the observation processing method of the power equipment in the ERP system is determined. Using the observation processing method and the analysis results of the procurement data of maintenance parts, the observation processing of the power equipment is performed. Based on the change data of the observed power equipment in the transmission line where the observed power equipment is located and the observation data of the power equipment, the output processing method of the procurement decision of the observed power equipment is determined.

2. The intelligent decision support method based on ERP data as described in claim 1, characterized in that, The ERP data includes procurement data for power equipment, procurement data for maintenance parts, and electricity sales data.

3. The intelligent decision support method based on ERP data as described in claim 1, characterized in that, The procurement data for maintenance parts of the power equipment includes the procurement time, procurement type, and procurement quantity of the maintenance parts.

4. The intelligent decision support method based on ERP data as described in claim 1, characterized in that, The process of identifying the power equipment in the power equipment system that needs to be monitored includes: Based on the procurement data, determine the procurement time for maintenance parts for the power equipment; Based on the procurement time of maintenance parts for the power equipment, identify the power equipment for which maintenance parts procurement data exists on different dates; For power equipment with procurement data for maintenance parts on different dates, determine whether the identification process for the observed power equipment in the power equipment needs to be performed.

5. The intelligent decision support method based on ERP data as described in claim 4, characterized in that, For power equipment with procurement data for maintenance parts from different dates, determine whether the identification process for monitored power equipment is required, specifically including: Based on the power equipment for which maintenance parts procurement data exists on different dates, determine the quantity of power equipment for which maintenance parts procurement data exists on different dates; Based on the number of power equipment for which maintenance parts procurement data exists on different dates, determine whether it is necessary to perform identification processing of the observed power equipment among the power equipment.

6. The intelligent decision support method based on ERP data as described in claim 5, characterized in that, When the number of power equipment with maintenance parts procurement data on different dates does not meet the requirements, i.e., exceeds the preset power equipment quantity threshold, it is necessary to perform power equipment identification processing.

7. The intelligent decision support method based on ERP data as described in claim 1, characterized in that, The method for determining the observation power equipment in the power equipment is as follows: Based on the procurement data of the power equipment, determine the quantity of the power equipment in use; Based on the procurement data of the same maintenance parts for the power equipment, determine the interval between adjacent procurement times for the same maintenance parts, and determine the procurement quantity of maintenance parts in different time periods based on the interval. Based on the number of the power equipment in use and the purchase volume of the same maintenance parts in different time periods, it is determined whether the power equipment is a monitoring power equipment.

8. The intelligent decision support method based on ERP data as described in claim 7, characterized in that, The quantity of the power equipment used is determined based on the analysis results of the historical procurement data of the power equipment in the ERP system.

9. The intelligent decision support method based on ERP data as described in claim 1, characterized in that, The method for determining the output processing method for the procurement decision of the aforementioned power equipment is as follows: The transmission line where the observed power equipment is located is taken as the target line. The number of observed power equipment on different target lines is determined by the change data of the observed power equipment on different target lines. Based on the observation data of power equipment in different target lines, identify the power equipment in different target lines that has not been observed and treat it as unobserved power equipment. Based on the number of observed and unobserved power equipment in different target lines, and in conjunction with the observed power equipment data in the ERP system, the output processing method for the procurement decision of the observed power equipment is determined.

10. A computer system, comprising: A memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes an intelligent decision support method based on ERP data as described in any one of claims 1-9.

Images