Charging pile intelligent operation and maintenance management method and system based on artificial intelligence

Abstract

The invention provides a charging pile intelligent operation and maintenance management method and system based on artificial intelligence. The method comprises the steps of obtaining basic identification data and environmental parameter data of each charging pile in a target area and operation parameter data of each component; inputting the environment parameter data and the operation parameter data into a fault prediction model to obtain a potential fault identification result; based on the potential fault identification result, the corresponding basic identification information and a pre-constructed operation and maintenance resource database, determining operation and maintenance scheduling resources adapted to the potential fault charging pile, and based on the current position information and the basic identification information of each operation and maintenance worker in the operation and maintenance scheduling resources, determining an optimal operation and maintenance path corresponding to each operation and maintenance worker; and determining an operation and maintenance task work order based on the skill attribute of each operation and maintenance personnel in the operation and maintenance scheduling resources in combination with the optimal operation and maintenance path corresponding to each operation and maintenance personnel. The charging experience of a user is improved, and the operation and maintenance efficiency and the utilization rate of the charging pile are improved.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to an intelligent operation and maintenance management method and system for charging piles based on artificial intelligence. Background Technology

[0002] With the rapid popularization and continuous growth of new energy vehicles, the number of charging piles, as an important energy supply facility, is also gradually increasing. Therefore, their operational stability and maintenance efficiency directly affect the user experience and the economic benefits of operators. Existing intelligent operation and maintenance management methods for charging piles mostly rely on a combination of regular manual inspections and user fault feedback. This means that maintenance personnel conduct regular inspections of charging piles according to schedule, or, after a charging pile sends a fault and triggers an early warning signal, the operation and maintenance platform dispatches maintenance personnel to the site for handling, sometimes even investigating and determining the cause on-site before carrying out maintenance and repairs.

[0003] However, existing methods, with their fixed manual inspection cycles, cannot capture sudden charging pile failures (such as charging module overload or poor interface contact) in real time, resulting in delayed fault response. They also lack real-time analysis and prediction of the charging pile's operating status, requiring maintenance personnel to conduct on-site troubleshooting when a fault occurs. This makes it difficult to quickly and accurately locate the faulty component (e.g., it's hard to distinguish between a main control board failure and a charging gun failure), thus increasing maintenance costs and time. Furthermore, they cannot coordinate maintenance management based on the charging pile's geographical location and the distribution of maintenance resources, further leading to slow operational response and long fault diagnosis and repair cycles. This not only affects the user's charging experience but also reduces the maintenance efficiency and utilization rate of the charging pile. Summary of the Invention

[0004] This invention provides an intelligent operation and maintenance management method and system for charging piles based on artificial intelligence, which can improve the user charging experience and increase the operation and maintenance efficiency and utilization rate of charging piles.

[0005] In a first aspect, the present invention provides an intelligent operation and maintenance management method for charging piles based on artificial intelligence, comprising: Acquire basic identification data, environmental parameter data, and operational parameter data of each component for each charging pile within the target area; Environmental parameter data and operational parameter data are input into a trained fault prediction model to identify potential faults, and the potential fault identification results output by the fault prediction model are obtained. Based on the potential fault identification results, the corresponding basic identification information, and the pre-built operation and maintenance resource database, the operation and maintenance scheduling resources adapted to the potential faulty charging pile are determined. Based on the current location information of each operation and maintenance personnel in the operation and maintenance scheduling resources, the regional location information of the potential faulty charging pile, and the basic identification information, the optimal operation and maintenance path corresponding to each operation and maintenance personnel is determined. Based on the skill attributes of each maintenance personnel in the maintenance scheduling resources, the potential fault risk level in the potential fault identification results, and the optimal maintenance path, maintenance task work orders are determined, and each maintenance personnel execute maintenance management tasks according to the maintenance task work orders.

[0006] Secondly, the present invention also provides an AI-based intelligent operation and maintenance management system for charging piles, applied to the AI-based intelligent operation and maintenance management method for charging piles as described in the first aspect; the AI-based intelligent operation and maintenance management system for charging piles includes: The data acquisition module is used to acquire basic identification data, environmental parameter data, and operating parameter data of each component for each charging pile within the target area. The potential fault prediction module is used to input environmental parameter data and operating parameter data into the trained fault prediction model to identify potential faults and obtain the potential fault identification results output by the fault prediction model. The operation and maintenance path determination module is used to determine the operation and maintenance scheduling resources that the potentially faulty charging pile is compatible with based on the potential fault identification results, the corresponding basic identification information and the pre-built operation and maintenance resource database, and to determine the optimal operation and maintenance path for each operation and maintenance personnel based on the current location information of each operation and maintenance personnel in the operation and maintenance scheduling resources, the regional location information of the potentially faulty charging pile and the basic identification information. The operation and maintenance task execution module is used to determine operation and maintenance task work orders based on the skill attributes of each operation and maintenance personnel in the operation and maintenance scheduling resources, the potential fault risk level in the potential fault identification results, and the optimal operation and maintenance path, and to enable each operation and maintenance personnel to execute operation and maintenance management tasks according to the operation and maintenance task work orders.

[0007] Thirdly, the present invention also provides an electronic device, comprising: a memory for storing computer software programs; and a processor for reading and executing the computer software programs, thereby realizing the intelligent operation and maintenance management method for charging piles based on artificial intelligence as described above.

[0008] Fourthly, the present invention also provides a non-transitory computer-readable storage medium storing a computer software program, which, when executed by a processor, implements the artificial intelligence-based intelligent operation and maintenance management method for charging piles as described above.

[0009] Fifthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the artificial intelligence-based intelligent operation and maintenance management method for charging piles as described above.

[0010] The intelligent operation and maintenance management method for charging piles based on artificial intelligence provided in this invention identifies potential faults by combining acquired environmental parameter data and operational parameter data of each component with a trained fault prediction model. This method determines the potential fault identification result for each charging pile, breaking the fixed cycle limitation of manual periodic inspections. It can capture abnormal signals related to sudden faults in charging piles in real time, achieving accurate prediction of potential faults and precise location of faulty components. This solves the problems of delayed fault response and lack of real-time analysis and prediction in existing methods. Furthermore, based on the potential fault identification results and basic identification information combined with an operation and maintenance resource database, it determines the appropriate operation and maintenance scheduling resources for the potentially faulty charging pile, and then combines these with the operational and maintenance resource database... The system determines the optimal maintenance path based on the current location information of maintenance personnel, basic identification information, and the regional location information of potentially faulty charging piles. This enables precise matching of maintenance resources, avoids blind scheduling of resources, and reduces maintenance costs and time. Finally, maintenance task work orders are generated based on the skill attributes of maintenance personnel, the level of potential fault risk, and the optimal maintenance path. This allows maintenance personnel to execute tasks according to the work orders without having to go to the site to investigate the cause of the fault. It enables quick and accurate location of faulty components. Combined with the overall planning of geographical location and maintenance resource distribution, it significantly improves the fault response speed and shortens the fault investigation and repair cycle. This not only improves the user charging experience but also increases the maintenance efficiency and utilization rate of charging piles. Attached Figure Description

[0011] Figure 1 This is a flowchart illustrating the intelligent operation and maintenance management method for charging piles based on artificial intelligence provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of the intelligent operation and maintenance management system for charging piles based on artificial intelligence provided in an embodiment of the present invention; Figure 3 An embodiment diagram of the electronic device provided in this invention; Figure 4 An embodiment diagram of a computer-readable storage medium provided in accordance with the present invention. Detailed Implementation

[0012] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0013] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0014] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0015] See Figure 1 , Figure 1 This is a flowchart illustrating the AI-based intelligent operation and maintenance management method for charging piles provided by the present invention. In this embodiment, the executing entity of the AI-based intelligent operation and maintenance management method for charging piles is the intelligent operation and maintenance management system. Therefore, the AI-based intelligent operation and maintenance management method for charging piles includes: Step 10: Obtain basic identification data, environmental parameter data, and operating parameter data of each component for each charging pile within the target area.

[0016] Optionally, the intelligent operation and maintenance management system collects basic identification data, environmental parameter data, and operational parameter data of all charging piles within the target area. The basic identification data includes real-time geographic location information, device number, and area information, used to identify the charging pile, locate its spatial position, and determine its management scope. Environmental parameter data reflects the external environmental conditions of the charging pile and data that may affect its operational status, including ambient temperature and humidity data. Operational parameter data reflects the real-time working status of the core functional components within the charging pile and is directly related to the stability of equipment operation, including the operating parameters of core components such as the charging module, main control board, and charging gun.

[0017] Furthermore, when collecting basic identification data, the intelligent operation and maintenance management system obtains real-time geographical location information through positioning modules or chips (such as Beidou positioning chips) integrated inside the charging pile. Device numbers are pre-assigned when the charging pile connects to the system, and each charging pile has a unique device number. The area information is automatically determined based on the area code in the device number. Environmental parameter data is acquired in real-time using parameter sensors (such as temperature and humidity sensors, and precipitation sensors) deployed at corresponding locations on the charging pile's casing. Operating parameter data for each component is communicated with the charging module, main control board, charging gun, metering module, and other core components of the charging pile via the internal controller area network bus or industrial Ethernet. The system reads the operating parameters of each component in real-time and transmits the collected data via 4G / 5G wireless networks or wired networks. In addition, the device number and area information in the basic identification data are static data, which are only collected when the device is first connected or when the information is changed. The real-time geographical location information can be collected once every 30 minutes, the environmental parameter data can be collected once every 10 minutes, and the operating parameter data of each component can be collected once every 1 minute to ensure the real-time and timely nature of the data.

[0018] In one embodiment, the target area is the Zhangjiang High-Tech Park charging station in Pudong New Area, Shanghai, in East China. This area contains 20 AC charging piles (the equipment numbering rule is "HD-SH-PD-ZJ-XX", where "HD" represents East China, "SH" represents Shanghai, "PD" represents Pudong New Area, "ZJ" represents Zhangjiang High-Tech Park, and "XX" represents the equipment serial number, ranging from 01 to 20). During data collection for the AC charging pile numbered "HD-SH-PD-ZJ-05" in this area, the intelligent operation and maintenance management system collects the real-time geographical location information as "31.2156°N, 121.5382°E" through the BeiDou satellite navigation system module inside the charging pile; the equipment number is the pre-assigned "HD-SH-PD-ZJ-05"; and based on the "HD-SH-PD-ZJ" code in the equipment number, the system automatically associates and determines the area information as "Zhangjiang High-Tech Park, Pudong New Area, Shanghai, East China". Meanwhile, the temperature and humidity sensor installed on the top of the charging pile casing collected real-time ambient temperature data of 32℃ and ambient humidity data of 65%; the wind speed sensor installed on the side of the charging pile collected real-time wind speed data of 2.5m / s; and the precipitation sensor installed at the bottom of the charging pile collected real-time precipitation data of 0mm (no precipitation). Furthermore, through communication with various components of the charging pile via the controller area network bus, the following data were collected: charging module output voltage of 220V, output current of 15A, module temperature of 40℃; main control board operating voltage of 5V, data transmission rate of 10Mbps, fault code status of "00" (no fault code); charging gun insertion detection signal of "1" (gun inserted), contact resistance of 0.01Ω, gun head temperature of 35℃; and metering module cumulative charging amount of 1200kWh, real-time metering error of 0.5%.

[0019] Step 20: Input the environmental parameter data and operating parameter data into the trained fault prediction model to identify potential faults and obtain the potential fault identification results output by the fault prediction model.

[0020] Optionally, the intelligent operation and maintenance management system will standardize the collected environmental and operational parameter data (such as data cleaning and normalization) and then input it into a trained fault prediction model for analysis. This model will identify potential faults in the charging piles, resulting in a list of potentially faulty charging piles (including potential fault risk type and risk level). The fault prediction model can be constructed using a deep learning neural network (such as an LSTM long short memory neural network) and trained using historical fault data, corresponding operational parameter data, and environmental parameter data to identify potential faults. The potential fault risk type refers to the specific fault type that the model identifies as likely to occur in the future, corresponding one-to-one with the various fault types that actually occur in the charging pile. The risk level refers to the classification based on the probability of the potential fault occurring and the degree of impact on the charging pile after the fault occurs, used to quantify the urgency of the potential fault.

[0021] Continuing with the above embodiment, taking the AC charging pile numbered "HD-SH-PD-ZJ-05" as an example, the environmental parameter data (ambient temperature 32℃, ambient humidity 65%, wind speed 2.5m / s, precipitation 0mm) and the operating parameter data of each component (charging module output voltage 220V, output current 15A, module temperature 40℃; main control board operating voltage 5V, data transmission rate 10Mbps, fault code status "00"; charging gun insertion detection signal "1", contact resistance 0.01Ω, gun head temperature 35℃; metering module cumulative charging amount 1200kWh, real-time metering error 0.5%) are input into a fault prediction model combining a trained convolutional neural network (CNN) and a long short-term memory network (LSTM) for potential fault identification. The model finally outputs the potential fault identification result as "Potential fault risk type: charging module overload fault; risk level: high risk".

[0022] Step 30: Based on the potential fault identification results, the corresponding basic identification information, and the pre-built operation and maintenance resource database, determine the operation and maintenance scheduling resources suitable for the potential faulty charging pile, and determine the optimal operation and maintenance path for each operation and maintenance personnel based on the current location information of each operation and maintenance personnel in the operation and maintenance scheduling resources, the regional location information of the potential faulty charging pile, and the basic identification information.

[0023] Optionally, the intelligent operation and maintenance management system determines the device number, location, and real-time geographic location of the charging pile with potential faults based on the fault identification results and the basic identification information of the charging pile with potential faults in the fault identification results. Then, based on the potential fault risk type and risk level in the fault identification results, it selects operation and maintenance scheduling resources that can handle the potential fault from the pre-built operation and maintenance resource database, as described in steps 3011-3015.

[0024] Furthermore, after determining the corresponding maintenance scheduling resources for handling potential faults, the intelligent operation and maintenance management system plans the optimal maintenance path for each maintenance personnel to reach the potential faulty charging pile based on the current location information of each maintenance personnel in the maintenance scheduling resources, the regional location information of the potential faulty charging pile, and the basic information identifier, as described in steps 3021-3025.

[0025] Furthermore, the construction of the operations and maintenance resource database involves pre-collecting basic information (name, employee number, skill attributes), current location information (obtained in real time via the GPS module of the smart terminal carried by the operations and maintenance personnel), and information on the operations and maintenance tools and equipment they possess (tool and equipment type, quantity, and status); collecting the model, function, applicable fault types, and inventory quantity of all operations and maintenance tools and equipment; collecting the model, specifications, applicable components, inventory quantity, and storage location information of all spare parts; and storing the above information in the database according to the structure of "Operations and Maintenance Personnel Table," "Operations and Maintenance Tools and Equipment Table," and "Spare Parts Table," to achieve information association and real-time updates (e.g., the location of operations and maintenance personnel is updated every 10 minutes, and the inventory quantity of spare parts is updated in real time when it is issued / received).

[0026] Step 40: Based on the skill attributes of each maintenance personnel in the maintenance scheduling resources, the potential fault risk level in the potential fault identification results, and the optimal maintenance path, determine the maintenance task work order, and enable each maintenance personnel to execute maintenance management tasks according to the maintenance task work order.

[0027] Optionally, after determining the optimal operation and maintenance (O&M) paths for the O&M scheduling resources and each O&M personnel, the intelligent O&M management system further formulates an O&M task work order containing task details, resource allocation, and execution requirements based on the skill attributes (including skill type and skill certification level) of each O&M personnel in the O&M scheduling resources and the potential fault risk level in the potential fault identification results. This is described in steps 401-405. The O&M task work order is a standardized document that records the core information of the O&M task, clearly defining the task object, fault information, resource configuration, path guidance, and execution requirements.

[0028] Furthermore, after the intelligent operation and maintenance management system determines the operation and maintenance task work order, it pushes the work order to the smart terminal of the corresponding operation and maintenance personnel via SMS, APP push, etc., and synchronizes it to the operation and maintenance management backend. When the operation and maintenance personnel receive the work order, they can view the route navigation, confirm the status of spare parts collection, and provide real-time progress feedback (such as "departed", "arrived", "under repair", "completed") through the terminal. The system monitors the status of the work order through the backend. If the primary operation and maintenance personnel do not respond or report that they cannot execute the work order within 30 minutes, the system will automatically push the work order to the secondary priority operation and maintenance personnel to ensure that the task is not interrupted.

[0029] This invention identifies potential faults for each charging pile by combining acquired environmental parameter data and operational parameter data of each component with a trained fault prediction model. This breaks the fixed-cycle limitation of manual periodic inspections, enabling real-time capture of abnormal signals related to sudden charging pile faults. It achieves accurate prediction of potential faults and precise location of faulty components, solving the problems of delayed fault response and lack of real-time analysis and prediction in existing methods. Furthermore, based on the potential fault identification results and basic identification information combined with an operation and maintenance resource database, it determines the appropriate operation and maintenance scheduling resources for the potentially faulty charging pile. Finally, it combines the current location information of the operation and maintenance personnel with basic identification information and other relevant data. The optimal maintenance path is determined by using basic identification information and the regional location information of potentially faulty charging piles. This enables precise matching of maintenance resources, avoids blind scheduling of maintenance resources, and reduces maintenance costs and time. Finally, maintenance task work orders are determined based on the skill attributes of maintenance personnel, the level of potential fault risk, and the optimal maintenance path. This allows maintenance personnel to execute tasks according to the work orders without having to go to the site to investigate the cause of the fault. It enables quick and accurate location of faulty components. Combined with the overall arrangement of geographical location and maintenance resource distribution, it significantly improves the fault response speed and shortens the fault investigation and repair cycle. This not only improves the user charging experience but also increases the maintenance efficiency and utilization rate of charging piles.

[0030] In one embodiment, steps 3011-3015 are described as follows: Step 3011: Based on the potential fault risk types and risk levels contained in the potential fault identification results, and in conjunction with the fault types, risk levels and corresponding relationship tables of operation and maintenance resources stored in the operation and maintenance resource database, determine the list of operation and maintenance tools, skill requirements of operation and maintenance personnel and response time limits required for potential faults of the target charging pile.

[0031] Optionally, the intelligent operation and maintenance management system, based on the identified potential fault risk types (such as charging module overload faults) and risk levels (such as high risk) of the target charging piles (i.e., charging piles with potential faults) in the determined potential fault identification results, performs precise matching in the pre-built operation and maintenance resource database according to the fault type, risk level, and corresponding operation and maintenance resource association table. Using the potential fault risk type and risk level as query conditions, it ultimately determines the corresponding operation and maintenance tool list, operation and maintenance personnel skill requirements, and response time limits from the matched records. The fault type, risk level, and corresponding operation and maintenance resource association table refers to a structured table built in the operation and maintenance resource database, which stores the operation and maintenance tool list, operation and maintenance personnel skill requirements, and response time limits corresponding to each fault-risk combination, ensuring precise matching between operation and maintenance needs and resources. Furthermore, the maintenance tools list refers to the collection of tool and equipment names and models required to handle potential faults; the maintenance personnel skill requirements refer to the minimum requirements for the types of skills and skill certification levels of maintenance personnel to handle potential faults; and the response time limit requirements refer to the maximum allowable time from the identification of a potential fault to the arrival of maintenance personnel at the target charging pile site, in order to ensure the timeliness of fault handling.

[0032] In one embodiment, a target charging pile (equipment number: HD-SH-PD-ZJ-05, potential fault risk type: charging module overload fault, risk level: high risk) is taken as an example. First, based on the potential fault identification results, the potential fault risk type of the target charging pile is extracted and determined to be "charging module overload fault", and the risk level is "high risk". Subsequently, using "charging module overload fault" and "high risk" as joint query conditions, the first record was matched in the association table. From this, the first record matched in the association table was read and determined to be the maintenance tool list, which includes a multimeter (model FLUKE15B+), an oscilloscope (model Tektronix TBS1052), and a charging module testing fixture (model CM-Test-001). The maintenance personnel skill requirements are that the skill type must include "charging module repair skills", and the skill certification level must be no lower than "intermediate". The response time limit requirement is that from the current time (2025-11-12 10:00), the maximum allowed time for maintenance personnel to arrive at the target charging pile site is ≤30 minutes (i.e., the latest arrival time is 2025-11-12 10:30).

[0033] Step 3012: Based on the skill requirements of the maintenance personnel and the skill information of all maintenance personnel in the maintenance resource database, a preliminary group of maintenance personnel in the region who meet the technical requirements is obtained.

[0034] Optionally, the intelligent operation and maintenance management system, based on the determined skill requirements for operation and maintenance personnel (including skill type requirements and skill level requirements), calls the operation and maintenance personnel table in the operation and maintenance resource database. This table contains information such as employee ID, name, region, skill type list, skill certification level list, and current location information. Then, it filters based on whether the region matches the target charging area, whether the skill type list contains the corresponding skill required for that skill type, and whether the certification level corresponding to that skill type in the skill certification level table meets the skill level requirements. This filters out operation and maintenance personnel (including employee ID, name, current location information, and a list of tools they possess) who meet all the filtering criteria, ultimately forming a preliminary group of operation and maintenance personnel who meet the technical requirements for that region. The skill information of the operation and maintenance personnel is stored in the operation and maintenance personnel table of the operation and maintenance resource database, including a skill type list (the names of all skill types possessed by the operation and maintenance personnel, separated by commas) and a skill certification level table (the certification level corresponding to each skill type, such as charging module repair skill - advanced).

[0035] Continuing with the above embodiment, the skill requirements for maintenance personnel include a skill type of charging module repair, a skill level of ≥ intermediate, and the target charging pile's location being the Zhangjiang High-Tech Park in Pudong New Area, Shanghai, East China. The initial filtering criteria are: 1. Location = Zhangjiang High-Tech Park, Pudong New Area, Shanghai, East China; 2. Skill type list includes charging module repair skills; 3. Charging module repair skill level ≥ intermediate in the skill certification level table. Based on the following section from the "Maintenance Personnel Table" in the maintenance resource database:

[0036] During the screening process, YW-008 (located in Jinqiao Development Zone, which does not match the target area) was excluded; YW-012 (the skill type list does not include "charging module repair skills") was also excluded; YW-001: the area matches, the skill type includes "charging module repair skills," and the level is advanced (≥ intermediate), thus meeting the requirements; YW-005: the area matches, the skill type includes "charging module repair skills," and the level is intermediate (≥ intermediate), thus meeting the requirements. The final preliminary maintenance personnel group is YW-001 (Engineer Zhang) and YW-005 (Engineer Li), and includes the corresponding fields: employee number, name, current location information, and a list of tools carried.

[0037] Step 3013: Based on the real-time geographical location information in the target charging pile basic identification data and the location information of each maintenance personnel in the maintenance personnel group in the maintenance resource database, determine the straight-line distance between each maintenance personnel and the target charging pile.

[0038] Optionally, the intelligent operation and maintenance management system uses the Haversine formula to calculate the spherical straight-line distance based on the real-time geographical location information of the target charging pile in the basic identification data, such as latitude and longitude coordinates, and combines the location information of each operation and maintenance personnel in the operation and maintenance resource database, that is, the latitude and longitude coordinates of each operation and maintenance personnel, to finally obtain the straight-line distance between each operation and maintenance personnel and the target charging pile.

[0039] Continuing with the above embodiment, the real-time geographical location information (31.2156°N, 121.5382°E) of the initial maintenance personnel group (YW-001 Zhang, YW-005 Li) and the target charging pile (HD-SH-PD-ZJ-05) is as follows: Longitude coordinates are The latitude coordinates of Zhang Gong (YW-001) are: Longitude coordinates are The latitude coordinates of Engineer Li (YW-005) are: Longitude coordinates are The distance between YW-001 Zhang Gong and the target charging station was calculated using the Haversine formula. km (approximately 637 meters); Calculate the distance between YW-005 Mr. Li and the target charging station. km (approximately 840 meters).

[0040] Step 3014: Based on the straight-line distance between each maintenance personnel and the target charging pile, and combined with the average driving speed corresponding to different road types in the region in the maintenance resource database, determine the estimated arrival time of each maintenance personnel from the current location to the location of the target charging pile.

[0041] Optionally, the intelligent operation and maintenance management system first retrieves the road type-average driving speed mapping table in the region from the operation and maintenance resource database based on the calculated straight-line distance between each operation and maintenance personnel and the target charging pile. Then, it determines the corresponding average driving speed based on the current time (e.g., 10:00 on 2025-11-12, which is an off-peak period). Next, it combines the road network characteristics of the target area (the conversion factor between straight-line distance and actual road distance, which is based on regional road planning statistics. For example, the roads in Zhangjiang High-Tech Park are regular, so the conversion factor is 1.2, i.e., actual road distance = straight-line distance × 1.2) to calculate the actual road driving distance for each operation and maintenance personnel. Then, it calculates the driving time (in hours) by dividing the actual road driving distance by the average driving speed of the corresponding road type, and converts it to minutes. Finally, it adds 5 minutes for departure preparation time to obtain the estimated total time, and then calculates the estimated arrival time based on the current time. The regional road type-average driving speed mapping table is formulated based on historical traffic data of the target area (such as road driving speed statistics during morning, noon and evening peak hours and off-peak hours over the past 6 months). It includes "road type" (such as urban arterial roads, secondary arterial roads, branch roads, and park roads) and the corresponding "average driving speed" (unit: kilometers per hour, km / h), and is marked separately for "off-peak hours" and "peak hours" to ensure that the speed data matches the actual traffic conditions.

[0042] Continuing with the above embodiment, the straight-line distance for YW-001 Zhang Gong is 0.637km, and the straight-line distance for YW-005 Li Gong is 0.84km. The current time is 10:00 on 2025-11-12 (which is determined to be off-peak period; morning peak is 7:30-9:00, and evening peak is 17:30-19:00). The intelligent operation and maintenance management system first retrieves the "Road Type-Average Driving Speed ​​Mapping Table of Zhangjiang High-Tech Park, Pudong New Area, Shanghai, East China" (off-peak period) from the operation and maintenance resource database. Partial data is as follows:

[0043] According to map service analysis, the normal driving routes from the current location of the maintenance personnel to the target charging pile are as follows: YW-001 Zhang Gong's route: Keyuan Road (main road of the park) → Boyun Road (main road of the park), both roads are classified as "main road of the park"; YW-005 Li Gong's route: Zhangjiang Road (main road of the park) → Boyun Road (main road of the park), both roads are classified as "main road of the park". Since the roads in Zhangjiang High-Tech Park are well-organized, the conversion factor between the straight-line distance and the actual road distance is taken as 1.2.

[0044] When calculating the actual road distance and travel time, for Mr. Zhang (YW-001), the actual road distance = straight distance × 1.2 = 0.637km × 1.2 ≈ 0.764km; the average travel speed during off-peak hours = 30km / h; the travel time = actual road distance ÷ average travel speed = 0.764km ÷ 30km / h ≈ 0.0255h ≈ 1.53 minutes; the estimated total travel time = travel time + departure preparation time = 1.53 minutes + 5 minutes ≈ 6.53 minutes (rounded up to 7 minutes). For Mr. Li (YW-005), the actual road distance = straight distance × 1.2 = 0.84km × 1.2 ≈ 1.008km; the average travel speed during off-peak hours = 30km / h; the travel time = 1.008km ÷ 30km / h ≈ 0.0336h ≈ 2.02 minutes; the estimated total travel time = 2.02 minutes + 5 minutes ≈ 7.02 minutes (rounded up to 7 minutes). Therefore, the estimated arrival time of Engineer Zhang (YW-001) is 10:07 (current time 10:00 + 7 minutes); the estimated arrival time of Engineer Li (YW-005) is 10:07 (current time 10:00 + 7 minutes).

[0045] Step 3015: Based on the estimated arrival time, the response time limit requirement, and the list of operation and maintenance tools, filter and match to obtain the operation and maintenance scheduling resources suitable for the potentially faulty charging piles.

[0046] Optionally, the intelligent operation and maintenance management system filters and matches based on the determined estimated arrival time, the obtained response time limit requirements, and the list of operation and maintenance tools, and finally determines the operation and maintenance scheduling resources suitable for the potentially faulty charging pile, as described in steps 30151-30155.

[0047] This invention, through its embodiments, clarifies the list of maintenance tools, personnel skill requirements, and response time limits based on the type and level of potential fault risks, establishing a precise demand benchmark for subsequent resource selection. Then, based on skill requirements, it initially screens maintenance personnel within the region who meet the technical conditions, narrowing the resource selection scope. Next, by calculating the straight-line distance between the maintenance personnel and the target charging pile, and combining the average driving speed of the road type with the straight-line distance, it determines the estimated arrival time, quantifying the maintenance personnel's response capability from both spatial and temporal dimensions, thus achieving precise matching of maintenance resources with potential fault requirements.

[0048] In one embodiment, steps 30151-30155 are described as follows: Step 30151: Based on the response time limit requirements and the expected arrival time of each maintenance personnel, a screening process is performed to obtain candidate maintenance personnel who meet the response time limit requirements.

[0049] Optionally, the intelligent operation and maintenance management system first converts the determined response time limit requirements and the estimated arrival time of each operation and maintenance personnel into a unified time format. Then, it compares the estimated arrival time of each operation and maintenance personnel with the latest arrival time using timestamps (by converting the time to a Unix timestamp and comparing values ​​in seconds, with the smaller value indicating an earlier time). Finally, it filters out operation and maintenance personnel whose "estimated arrival time timestamp is ≤ latest arrival time timestamp" and extracts their information (employee number, name, current location information, list of tools carried, estimated arrival time) into the "candidate operation and maintenance personnel table," completing the initial screening based on the time dimension.

[0050] Continuing with the above embodiment, the response time requirement is the latest arrival time: 2025-11-12 10:30; the estimated arrival time for YW-001 Zhang is 10:07, and the estimated arrival time for YW-005 Li is 10:07. The intelligent operation and maintenance management system converts the latest arrival time to "2025-11-12 10:30", with a corresponding Unix timestamp of 1752342600 seconds; the estimated arrival time for YW-001 Zhang is "2025-11-12 10:07", with a Unix timestamp of 1752340020 seconds; the estimated arrival time for YW-005 Li is "2025-11-12 10:07", with a Unix timestamp of 1752340020 seconds. YW-001 Zhang: 1752340020 seconds ≤ 1752342600 seconds, meeting the response time limit requirement; W-005 Li: 1752340020 seconds ≤ 1752342600 seconds, meeting the response time limit requirement. Therefore, the generated candidate maintenance personnel include YW-001 Zhang and YW-005 Li.

[0051] Step 30152: Based on the list of operation and maintenance tools and the candidate operation and maintenance personnel, and combined with the list of tools that each operation and maintenance personnel can currently carry in the operation and maintenance resource database, a selection of candidate operation and maintenance personnel whose tools meet the requirements is obtained.

[0052] Optionally, the intelligent operation and maintenance management system can construct a tool set based on the extracted list of operation and maintenance tools, using "tool name-model" as a unique identifier. (n is the number of tools), then read the "Employee ID" of each candidate operations and maintenance personnel from the "Candidate Operations and Maintenance Personnel Table", and link it to the "Operations and Maintenance Personnel Table" in the operations and maintenance resource database to retrieve the employee's "Currently Portable Tool List". Similarly, construct a personal tool set using "Tool Name-Model" as the identifier. (i is the candidate operations and maintenance personnel number, and m is the number of tools carried by that personnel), then, determine the tool set. Is it subsets of (i.e.) If the condition is met, it means that the tools carried by the maintenance personnel fully cover the maintenance needs; finally, select those that meet the requirements. The candidate operations and maintenance personnel are identified, and their information is updated in the list of candidates for operations and maintenance personnel to complete the screening based on the tool dimension.

[0053] Continuing with the above embodiments, the list of operation and maintenance tools ( ={Multimeter-FLUKE15B+, Oscilloscope-Tektronix TBS1052, Charging module testing fixture-CM-Test-001}), the candidate maintenance personnel are YW-001 Zhang and YW-005 Li. Therefore, when constructing the maintenance tool set, ={ Multimeter - FLUKE15B+ Oscilloscope - Tektronix TBS1052 :Charging module testing fixture-CM-Test-001}.

[0054] YW-001 Zhang Gong: Associated with the operations and maintenance personnel table; its currently available tool set is... ={ Multimeter - FLUKE15B+ Oscilloscope - Tektronix TBS1052 Charging module testing fixture - CM-Test-001 Screwdriver Set - WERA050735 YW-005 Li Gong: Associated with the operations and maintenance personnel table, the current set of tools that can be carried is... ={ Multimeter - FLUKE15B+ Charging module testing fixture - CM-Test-001 Screwdriver Set - WERA050735 Clamp-on ammeter - FLUKE376}.

[0055] YW-001 Zhang Gong: In , , All included In, that is The tools meet the requirements; YW-005 Li Gong: In Not included In, that is The tools do not meet the requirements. Therefore, the only maintenance personnel to be selected is Engineer Zhang (YW-001).

[0056] Step 30153: Based on the equipment importance level corresponding to the equipment number in the basic identification data of the target charging pile and the priority information of the tasks currently being performed or to be performed by the selected maintenance personnel, determine the suitability priority for each selected maintenance personnel to undertake the maintenance task of the target charging pile; the equipment importance level is determined by the usage frequency, service range and regional importance of the charging pile.

[0057] Optionally, the intelligent operation and maintenance management system first schedules the usage frequency (i.e., average monthly number of charging times) of the target charging pile from the historical usage data of the charging pile. Service scope (i.e., the number of users covered) ) and the importance of the region (regional weight) Level 1 area Secondary region Level 3 area Level 4 region The equipment importance score is calculated using the following formula. : ; Among them, This represents the maximum average number of charging sessions per month at charging stations within the target area. The maximum number of users covered by charging piles within the target area is determined by weights of 0.4 and 0.6, respectively, for usage frequency and service range (based on historical data; for users affected by a fault, service range has a higher weight). Then, the number of tasks currently being executed by the selected maintenance personnel is retrieved from the maintenance task table. Number of tasks to be executed and the priority of all tasks (where the first-level task is denoted as...). Level 2 Level 3 Level 4 ), calculate task load factor : ; and if ,but This prevents the system from accepting new tasks when the load is already saturated. For the first The priority of each task; This represents the maximum number of tasks that an operations and maintenance personnel can handle in a single instance (default value is 5); 1.0 represents the maximum priority value for first-level tasks. The range of values ​​is A higher value indicates a lower task load. Finally, the adaptation priority is determined based on the task load coefficient and the device importance score. ,Right now The range of values ​​is , a higher value indicates a stronger suitability of the candidate operation and maintenance personnel to undertake this task.

[0058] Continuing with the above embodiment, the candidate operation and maintenance personnel (only Engineer Zhang of YW-001), and the target charging pile device number is HD-SH-PD-ZJ-05. When calculating the device importance score, retrieve the basic information of the target charging pile: usage frequency times / month, service scope persons, the affiliated area (Zhangjiang High-tech Park) is a first-level area, and the area weight ; target area parameters: times / month (the highest monthly average charging times in the area, statistically obtained from the historical data of all charging piles in the target area), persons (the maximum number of covered users in the area, statistically obtained from the historical data of all charging piles in the target area); then . When calculating the task load factor of Engineer Zhang of YW-001, retrieve Zhang's task information: the number of tasks being executed (priority level two, ), the number of tasks to be executed (priority level three, ), ; then substitute into the formula to get: , and finally obtain the adaptation priority .

[0059] Step 30154, sort all candidate operation and maintenance personnel based on the adaptation priority of each candidate operation and maintenance personnel to obtain a sorting result, and select the top pre-set number of operation and maintenance personnel with the highest adaptation priority as the target operation and maintenance personnel according to the sorting result.

[0060] Optionally, the intelligent operation and maintenance management system retrieves the pre-set number of target operation and maintenance personnel (such as the pre-set number N = 2 for high-risk faults and N = 1 for medium and low-risk faults) according to the determined potential fault risk level; then, read the "employee number" and "adaptation priority" of all candidate operation and maintenance personnel from the candidate operation and maintenance personnel, and sort them in descending order according to the adaptation priority from high to low (if there are cases where the adaptation priorities are the same, then sort them in ascending order according to the "expected arrival time", and the one with an earlier time is preferred); then, select the first N operation and maintenance personnel according to the sorting result. If the number of candidate operation and maintenance personnel M < N, then select all M operation and maintenance personnel; finally, organize the information of the selected target operation and maintenance personnel (employee number, name, adaptation priority, expected arrival time) into the target operation and maintenance personnel, and associate their tools, skills, etc. information in the operation and maintenance resource database. Continuing with the above embodiment, the candidate maintenance personnel (only YW-001 Zhang Gong, matching priority 48.6) have a high potential fault risk level for the target charging pile. Therefore, the potential fault risk level is high, and the system retrieves the preset rules (number of high-risk fault target maintenance personnel N=2, medium-low risk N=1) to determine that the top 2 maintenance personnel should be selected as the target maintenance personnel. From the candidate maintenance personnel, only YW-001 Zhang Gong is selected, with a matching priority of 48.6. There are no other candidates, so this is directly used as the sorting result (sort 1: YW-001 Zhang Gong, matching priority 48.6). Therefore, all 1 candidate maintenance personnel are automatically selected as the target maintenance personnel, and their skill attributes (skill type: charging module repair skill (advanced), main control board repair skill (intermediate); skill certification level: charging module repair skill advanced) are supplemented from the maintenance resource database to generate the target maintenance personnel.

[0061] Step 30155: Based on the target maintenance personnel, the maintenance tool list, the maintenance personnel skill requirements, response time limit requirements, and the basic identification information of the corresponding target charging pile are integrated to obtain the maintenance scheduling resources suitable for the potentially faulty charging pile.

[0062] Optionally, the intelligent operation and maintenance management system retrieves the basic information of the target operation and maintenance personnel (employee number, name, skill attributes, and a list of tools they possess) from the target operation and maintenance personnel; secondly, it retrieves the operation and maintenance tool list (to verify whether the tools possessed by the target operation and maintenance personnel are fully covered and to ensure consistency), the operation and maintenance personnel skill requirements (to verify whether the skills of the target operation and maintenance personnel are met and to ensure compliance), and the response time limit requirements (latest arrival time); then, it retrieves the basic information of the target charging pile (device number, real-time geographical location, and region) from the basic identification data; finally, it retrieves the operation and maintenance resource data... According to the "Spare Parts List" in the database, the appropriate spare parts information (including name, model, quantity, and storage location) is retrieved based on the potential fault risk type (such as charging module overload fault). The spare parts must be in stock at least 1 and the storage location must be in the area where the target charging pile is located or in a nearby area to ensure timely access. Finally, the above information is integrated according to the structure of "personnel information - tool information - spare parts information - task requirements - equipment information" to generate the "Operation and Maintenance Scheduling Resource Table". Each element must correspond one-to-one (such as associating the target operation and maintenance personnel with their tools, and associating spare parts with the potential fault type).

[0063] Continuing with the above embodiment, the target maintenance personnel (YW-001 Zhang Gong) are combined with the maintenance tool list in step 3011 (multimeter-FLUKE15B+, oscilloscope-TektronixTBS1052, charging module testing fixture-CM-Test-001), maintenance personnel skill requirements (charging module repair skills ≥ intermediate level), response time limit requirements (latest arrival time 10:30), and the target charging pile basic identification information in step 10 (equipment number HD-SH-PD-ZJ-05, real-time geographical location 31.2156°N / 121.5382°E, location: Zhangjiang High-Tech Park, Pudong New Area, Shanghai, East China). The intelligent operation and maintenance management system first retrieves information from various dimensions, including the target operation and maintenance personnel information: YW-001 Zhang Gong (employee number / name), skill attributes (advanced charging module repair skills, intermediate main control board repair skills), and a list of tools he possesses (multimeter-FLUKE15B+, oscilloscope-TektronixTBS1052, charging module testing fixture-CM-Test-001); task requirements information: a list of operation and maintenance tools (consistent with the tools possessed by Zhang Gong), skill requirements for operation and maintenance personnel (charging module repair skills ≥ intermediate, Zhang Gong's skills meet the requirements), and response time requirements (latest arrival time 10:30, Zhang Gong's estimated arrival time). (Availability time 10:07); Equipment basic information: Equipment number HD-SH-PD-ZJ-05, real-time geographical location 31.2156°N / 121.5382°E, location: Zhangjiang High-Tech Park, Pudong New Area, Shanghai, East China; Spare parts information: Retrieve the appropriate spare parts for "charging module overload fault" from the "Spare Parts List", confirming that the charging module power board (model CM-PB-001, 10 in stock, stored in Zhangjiang High-Tech Park spare parts warehouse) and cooling fan (model FS-005, 15 in stock, stored in Zhangjiang High-Tech Park spare parts warehouse) meet the inventory and regional requirements. Finally, integrate all information in a structured manner to generate maintenance and scheduling resources suitable for potentially faulty charging piles.

[0064] This invention addresses the "delayed response" problem in traditional operations and maintenance (O&M) by screening candidate O&M personnel who meet timeliness requirements based on response time limits and estimated arrival times. It then combines an O&M tool list with the tools personnel can carry to screen for suitable personnel, avoiding "secondary trips due to missing tools." Next, it calculates and adapts priorities based on the importance of equipment and the workload of personnel, achieving "prioritized handling of highly important equipment and reasonable allocation of personnel workload." Subsequently, it selects target O&M personnel according to the adaptation priority, clarifying the core execution entities. Finally, it integrates personnel, tools, spare parts, task requirements, and equipment information to form a complete O&M scheduling resource. This effectively solves the technical problems of "chaotic resource matching," "disordered task allocation," and "low O&M efficiency" in traditional O&M models, achieving accurate and efficient matching of O&M scheduling resources with potential fault requirements.

[0065] In one embodiment, steps 3021-3025 are described as follows: Step 3021: Based on the regional location information of the potentially faulty charging pile, a geographic topology network is constructed, with the current location information of each maintenance personnel in the operation and maintenance scheduling resources within the target area and the real-time geographic location of the potentially faulty charging pile in the basic identification information as nodes and the connection path between the two as edges. An initial connection path group is determined based on the geographic topology network. The initial connection path group consists of all possible connection paths from the current location of each maintenance personnel to the real-time geographic location of the potentially faulty charging pile.

[0066] Optionally, the location information of the area to which the potentially faulty charging pile belongs, as determined by the intelligent operation and maintenance management system, is used as the boundary. The current location information of each operation and maintenance personnel in the operation and maintenance scheduling resources is retrieved from the operation and maintenance resource database (e.g., YW-001 Zhang Gong: 31.2200°N / 121.5400°E). The real-time geographical location (31.2156°N / 121.5382°E) of the potentially faulty charging pile (HD-SH-PD-ZJ-05) is retrieved from the basic identification data. All latitude and longitude coordinates are converted into a plane rectangular coordinate system (e.g., Gauss-Kruger projection coordinate system) to facilitate the calculation of the relative positions between nodes. Next, based on the transformed planar coordinates, road network data from integrated map services (such as the Gaode Map Open Platform) is invoked. The current location of the maintenance personnel and the location of the charging pile are designated as "core nodes," and road intersections within a 500-meter radius of the core nodes are designated as "auxiliary nodes." A topological network vertex set containing the core and auxiliary nodes is constructed. According to the road connectivity provided by the map service, adjacent nodes (i.e., two nodes with direct access roads) are connected by "edges," and each edge is labeled with the corresponding actual road information (road name, road type, and length), forming a geographic topological network. Finally, a "Depth-First Search (DFS)" algorithm is used to traverse the geographic topological network. Starting from the current location node of each maintenance personnel, all connected paths that can reach the charging pile location node are searched (the path must consist of continuous "edges" and not repeatedly pass through the same node). The road combination information of each path (such as "Keyuan Road → Boyun Road" or "Keyuan Road → Zhangjiang Road → Boyun Road") is organized into path records. All records constitute the initial connected path group corresponding to the maintenance personnel.

[0067] Step 3022: Based on the road type information contained in each initial connected path in the initial connected path group, determine the road traffic coefficient of each initial connected path, and perform an initial screening of the initial connected path group based on the road traffic coefficient to obtain a first candidate path group; the road traffic coefficient is determined based on the average traffic efficiency of the same type of roads in the same historical period.

[0068] Optionally, the intelligent operation and maintenance management system first retrieves data from the road traffic efficiency table in the operation and maintenance resource database based on the road type information contained in each initial connected path in the initial connected path group: the current date is 2025-11-12 (Wednesday), the time period is 10:00 (off-peak period), and the weather is sunny; and then retrieves data on the same type of road (main road in the park) on Wednesday. If the historical average traffic speed under clear conditions (e.g., 30 km / h) is used, and the maximum design speed for this type of road is 40 km / h, then the formula for calculating the road capacity factor is: ;in This refers to the road traffic capacity factor. This is the historical average traffic speed. To determine the maximum designed traffic speed; if the route includes multiple road types (such as main roads and secondary roads within the park), the traffic coefficient for each type of road is calculated separately, and then the route traffic coefficient is calculated by weighting the road lengths. ;in This is the path mobility coefficient. For the first in the path The traffic capacity of a road segment. For the first The length of the road section Define the number of road segments contained in the path. Also, set a filtering threshold. (Due to the high risk of potential failures, it is necessary to ensure that the path throughput efficiency is not less than 60%), compare each initial path. and ,reserve The paths are used to form the first candidate path group.

[0069] Step 3023: Based on the traffic signal node information of each candidate path in the first candidate path group, determine the traffic signal delay index of each candidate path, and perform a second screening on the first candidate path group based on the traffic signal delay index to obtain a second candidate path group; the traffic signal delay index is the sum of the product of the red light ratio and the traffic light cycle duration of all traffic signal nodes on the candidate path.

[0070] Optionally, to quantify the impact of traffic lights on travel time, the intelligent operation and maintenance management system performs a secondary screening of the first candidate route group, eliminating routes with excessively high delays. The traffic signal node information refers to the location, red light duration, green light duration, and signal cycle duration of all traffic lights along the route (retrieved in real-time from the map service). Based on this, the determined traffic signal delay index is a quantitative indicator reflecting the total delay caused by traffic lights, with the formula as follows: ,in Traffic signal delay index (unit: seconds). This represents the number of traffic signal nodes in the path. For the first The percentage of red lights at each traffic signal node (red light duration and traffic light cycle duration). For the first The signal light cycle duration (in seconds) of each traffic signal node; and during the secondary screening process, a delay index threshold is set (e.g., 1800 seconds, which can be derived by back-calculating the response time limit for high-risk faults), and [the remaining nodes are selected]. The paths that meet the threshold are used to form a second candidate path group. Specifically, the intelligent operation and maintenance management system calls the map service to obtain real-time information (red light duration) of all traffic signal nodes included in each path in the first candidate path group. Green light duration Cycle duration Then, for each route, calculate the percentage of red lights at each traffic signal node. Finally, substitute the values ​​into the formula to calculate the path.

[0071] Step 3024: Based on the real-time traffic congestion level of each candidate path in the second candidate path group, determine the congestion impact coefficient of each candidate path, and perform three screenings on the second candidate path group based on the congestion impact coefficient to obtain the third candidate path group.

[0072] Optionally, the intelligent operation and maintenance management system uses the real-time traffic congestion level of each candidate path in the second candidate path group. This real-time traffic congestion level is retrieved from map services (such as Gaode Maps or Baidu Maps) and includes five levels: smooth traffic (Level 1), basically smooth traffic (Level 2), light congestion (Level 3), moderate congestion (Level 4), and severe congestion (Level 5). Based on this, and according to a preset "congestion level - impact coefficient" mapping table (Level 1 → 0.9, Level 2 → 0.8, Level 3 → 0.6, Level 4 → 0.3, Level 5 → 0.1), it matches a corresponding congestion impact coefficient for each road segment. The congestion impact coefficient is an indicator that quantifies the impact of congestion on the travel speed along a route. Then, the average congestion impact coefficient of the route is calculated by weighting the congestion coefficient by road length. ;in, For the first The length of the road section This defines the number of road segments included in the path. Finally, a threshold for the average congestion impact factor is set. (High-risk faults require ensuring that the overall traffic flow along the route is minimally affected by congestion); compare the performance of each route. and ,reserve The path forms the third candidate path group.

[0073] Step 3025: Based on the third candidate path group and the response time limit requirements of each potentially faulty charging pile, determine the optimal operation and maintenance path for each operation and maintenance personnel.

[0074] Optionally, the intelligent operation and maintenance management system determines the optimal operation and maintenance path for each operation and maintenance personnel based on the third candidate path group and the response time limit requirements of each potentially faulty charging pile, as described in steps 30251-30254.

[0075] This invention constructs a geographic topology network and determines an initial connected path group, providing a complete set of basic paths for path selection. The initial path group undergoes an initial screening to eliminate paths with excessively low traffic efficiency. A second screening, based on traffic signal delay indices, excludes paths with excessively high traffic light delays. A third screening, calculated using congestion impact coefficients based on real-time traffic congestion levels, ensures paths are minimally affected by congestion. Finally, the estimated travel time is calculated based on response time requirements to determine the optimal maintenance path for each maintenance personnel. This achieves precise and efficient planning of maintenance paths, improving the timeliness and efficiency of charging pile maintenance responses and reducing the risk of maintenance delays due to improper path selection.

[0076] In one embodiment, steps 30251-30254 are described as follows: Step 30251: Based on the physical straight-line length of each candidate path in the third candidate path group, determine the estimated travel time for each candidate path; the physical straight-line length is the sum of the actual distances of all edges on the candidate path; the estimated travel time is determined based on the physical straight-line length of the candidate path and the average driving speed of the corresponding road type.

[0077] Optionally, the intelligent operation and maintenance management system calculates the physical straight-line length of each candidate path in the third candidate path group based on the physical straight-line length, where the physical straight-line length is the sum of the actual distances of all edges on the candidate path. Specifically, it retrieves the actual distances of each road segment contained in each candidate path in the third candidate path group from the edge set information of the geographic topology network, and sums them to obtain the physical straight-line length of each path. After determining the physical straight-line length, the average driving speed is determined based on the corresponding road type. If the path contains only a single road type (such as all main roads within the park), the average driving speed corresponding to that road type is directly retrieved. (Unit: km / h); If the route contains multiple road types, the average travel speed of the route is calculated by weighting the length of each road segment: ;in For the first Average driving speed corresponding to the road segment type; For the first The actual distance of the road section; This represents the number of road segments included in the path. Finally, the physical straight-line length is converted to kilometers. Substitute into the formula The estimated travel time is obtained (in minutes; multiply by 60 to convert hours to minutes). This time only includes road travel time and does not include preparation time for departure.

[0078] Step 30252: Based on the estimated travel time of each candidate path in the third candidate path group, compare and judge with the response time limit requirement of each potentially faulty charging pile to obtain a fourth candidate path group that meets the response time limit requirement, and sort the candidate paths in the fourth candidate path group based on the estimated travel time to obtain a first path sequence.

[0079] Optionally, the intelligent operation and maintenance management system, based on the estimated travel time of each candidate path in the third candidate path group, and combined with the response time limit requirement for each potentially faulty charging pile, where meeting the response time limit requirement means that the estimated arrival time corresponding to the path's "total travel time" (estimated travel time + 5 minutes departure preparation time) is not later than the latest arrival time required by the response time limit. Therefore, the total travel time... (5 minutes is the fixed departure preparation time, consistent with step 3014); Estimated arrival time =Current time+ The data is then converted to HH:MM format. Each path is compared to the latest arrival time required by the response time limit. The path with the latest arrival time is retained to form the fourth candidate path group. The paths in the fourth candidate path group are then sorted from shortest to longest estimated travel time; if they are the same, they are sorted from shortest to longest physical straight-line length to obtain the first path sequence.

[0080] Step 30253: Based on the number of road turns in each path in the first path sequence, the first path sequence is re-sorted to obtain a second path sequence sorted by the number of turns.

[0081] Optionally, the intelligent operation and maintenance management system further optimizes the ranking based on the first path sequence, incorporating the number of road turns to obtain a path sequence that better reflects actual driving efficiency. The number of road turns refers to the number of directional changes between adjacent road segments in the candidate path, including left turns, right turns, and U-turns (U-turns count as 2 turns, left turns and right turns each count as 1 turn). This is determined from the road orientation information in the geographic topology network (e.g., Keyuan Road runs east-west, Boyun Road runs north-south, turning from Keyuan Road to Boyun Road counts as 1 turn). Therefore, the system first retrieves the orientation of each road segment within each path (e.g., east-west, north-south, northeast-southwest), compares the orientations of adjacent road segments, determines the turning type, and counts the number of turns. (U-turns count as 2, left turns and right turns each count as 1, straight-ahead turns count as 0). Then, for the paths in the first path sequence, first calculate the estimated travel time, if... Sort from shortest to longest (preserving the time priority of the first sequence), if there exists For the same path, sorted by the number of turns The fewer the number of turns, the smoother the driving path, and the smaller the fluctuation in actual time, the higher the path will be in the order of the second path sequence.

[0082] Step 30254: Select the candidate path ranked first in the path sequence based on the second path sequence as the optimal operation and maintenance path for the corresponding operation and maintenance personnel.

[0083] Optionally, the intelligent operation and maintenance management system selects the top-ranked candidate path from all paths in the determined second path sequence as the optimal operation and maintenance path for the corresponding operation and maintenance personnel. The top-ranked candidate path is the highest priority path in the second path sequence. This path simultaneously meets three core conditions: "shortest estimated travel time", "fewest turning times (under the same time priority)" and "estimated arrival time meets the response time limit". It is the optimal choice that combines time efficiency and driving convenience. Finally, after determining the optimal operation and maintenance path, it generates detailed driving guidance that includes the road names, directions, and turning prompts for each segment of the path (such as "After driving 120m east on Keyuan Road, turn right onto Boyun Road").

[0084] This invention calculates the estimated travel time based on the physical straight-line length of the path and the average driving speed on the road, providing a time-quantifiable basis for path selection. Then, combined with response time limit requirements, feasible paths are selected and sorted by time to obtain a first path sequence, ensuring that the paths meet the timeliness requirements. Next, the sequence is optimized by introducing the number of road turns to obtain a second path sequence, balancing time efficiency and driving convenience. Finally, the first path in the sequence is selected as the optimal maintenance path, and detailed guidance is generated to clarify the final execution plan. This effectively solves the technical problems of traditional path planning, such as "focusing only on distance and ignoring time efficiency," "not considering actual driving convenience," and "inability to accurately match response time limits," achieving scientific and efficient planning of maintenance paths and providing accurate guidance for maintenance personnel to quickly and smoothly reach the fault site.

[0085] In one embodiment, steps 401-405 are described as follows: Step 401: Based on the skill type and skill certification level of each operation and maintenance personnel in the operation and maintenance resource set, determine the skill detail group of each operation and maintenance personnel according to the correspondence between operation and maintenance personnel, skill type and skill certification level.

[0086] Optionally, the intelligent operation and maintenance management system retrieves the "Operator ID," "Skill Type," and "Skill Certification Level" data for each operator based on the operator skill table in the operation and maintenance resource database. This ensures the data matches the operator's current skill status. Then, using the operator ID as the core, it integrates all "Skill Type - Skill Certification Level" correspondences for the same operator to form a detailed skill group for that operator. For example, if operator ID YW-001 corresponds to the skill types of charging module repair and main control board repair, with corresponding skill certification levels of advanced and intermediate, then its detailed skill group would be {YW-001-Charging Module Repair-Advanced, YW-001-Main Control Board Repair-Intermediate}.

[0087] Step 402: Based on the potential fault risk level in the potential fault identification results and the correspondence table between potential fault risk and required skill type in the charging pile management system, the necessary skill type for handling the potential fault risk level is selected to obtain the necessary skill group for potential faults.

[0088] Optionally, the intelligent operation and maintenance management system retrieves complete "potential fault risk level - required skill type" correspondence data from the "fault risk - skill correspondence table" of the charging pile management system based on the potential fault risk level in the potential fault identification results. It then matches all "required skill types" under that risk level in the correspondence table and integrates these skill types to form a necessary skill group for potential faults. The potential fault risk and required skill type correspondence table is a preset rule table stored in the charging pile management system. This table is based on historical fault handling experience and industry maintenance standards, clearly defining the required skill types corresponding to different potential fault risk levels (high, medium, and low). The higher the risk level, the more complex and specialized the required skill types.

[0089] Step 403: Based on the skill details group and the necessary skill group for potential faults of each operation and maintenance personnel, a skill matching operation and maintenance personnel group is obtained.

[0090] Optionally, the intelligent operation and maintenance management system checks each skill type in the potential fault-related necessary skill group for each operation and maintenance personnel (only comparing skill types, not levels). If the operation and maintenance personnel's skill details group contains all skill types of the necessary skill groups, it is determined as "skill matching", and their operation and maintenance personnel number is added to the candidate list. If any necessary skill type is missing, it is determined as "skill mismatch", and the operation and maintenance personnel is excluded. All "skill matching" operation and maintenance personnel numbers are integrated to form a skill matching operation and maintenance personnel group, which includes all operation and maintenance personnel who have the core skills to handle the fault.

[0091] Step 404: Based on the skill matching operation and maintenance personnel group and the skill certification level in the skill details group of each operation and maintenance personnel, sort the operation and maintenance personnel in the skill matching operation and maintenance personnel group to obtain a skill-sorted operation and maintenance personnel list.

[0092] Optionally, the intelligent operation and maintenance management system extracts the skill certification level corresponding to each skill type in the potential fault-related skill group from the skill details group for each operation and maintenance personnel in the skill matching operation and maintenance personnel group. It then determines the "minimum skill certification level" for that operation and maintenance personnel (e.g., if the operation and maintenance personnel is advanced in necessary skill A and intermediate in necessary skill B, the lowest level is intermediate), which serves as the core ranking indicator. Next, the skill certification level is converted into a quantitative value, with the rule being: beginner = 1, intermediate = 2, advanced = 3 (the higher the quantitative value, the higher the skill level). The operation and maintenance personnel are then ranked from highest to lowest according to the quantitative value of the core ranking indicator. If the quantitative values ​​are the same, they are ranked from smallest to largest by the operation and maintenance personnel number (to avoid ties in the ranking), ultimately forming a skill-ranked list of operation and maintenance personnel.

[0093] Step 405: Based on the list of maintenance personnel and the optimal maintenance path information for each maintenance personnel, determine the maintenance task work order.

[0094] Optionally, the intelligent operation and maintenance management system determines the operation and maintenance task work order based on the sorted list of operation and maintenance personnel and the optimal operation and maintenance path information corresponding to each operation and maintenance personnel, as described in steps 4051-4054.

[0095] This invention, through personnel screening, sorting, and work order generation, progressively and collaboratively addresses the technical problems of mismatch between traditional maintenance skills and faults leading to repair failures, failure to prioritize highly skilled personnel for high-risk faults, and incomplete work order information affecting execution efficiency. It achieves precise matching of maintenance personnel with fault requirements and standardized assignment of maintenance tasks, improving the success rate and execution efficiency of charging pile maintenance, reducing secondary repair costs caused by skill mismatches, and ensuring efficient and professional handling of high-risk faults.

[0096] In one embodiment, steps 4051-4054 ​​are described as follows: Step 4051: Based on the optimal operation and maintenance path information corresponding to each operation and maintenance personnel and the operation and maintenance personnel list, extract the optimal path time of each operation and maintenance personnel in the operation and maintenance personnel list to obtain the operation and maintenance personnel path time group.

[0097] Optionally, the intelligent operation and maintenance management system matches the two sets of data based on the determined skill-ranked list of operation and maintenance personnel (including personnel ID and core skill quantification value) and the generated optimal operation and maintenance path information for each personnel (including personnel ID and optimal path time), using the personnel ID as the association key. This ensures a one-to-one correspondence between the skill information and path time information for each operation and maintenance personnel. From the matched data, the system extracts the optimal path time for each personnel, excluding invalid data (such as outliers with path time of 0 or negative values; if present, the path calculation results from step 30 are retrieved again). Finally, using the personnel ID as the core, the system integrates the corresponding core skill quantification value and optimal path time to form a personnel path time group, formatted as "personnel ID - core skill quantification value - optimal path time".

[0098] Step 4052: Based on the list of maintenance personnel and the path time group of maintenance personnel, select the maintenance personnel with the shortest path time from among the maintenance personnel with the same skill certification level, and obtain the maintenance personnel candidate group with priority given to skill level and shortest path time.

[0099] Optionally, the intelligent operation and maintenance management system groups personnel within the path time group according to their "core skill quantification value" from highest to lowest, forming multiple skill level groups (e.g., quantification value 3 is group 1, quantification value 2 is group 2, and quantification value 1 is group 3). For each skill level group, it sorts personnel by "optimal path time" from shortest to longest, selecting the operation and maintenance personnel with the shortest time within the group (if there is only one person in the group, that person is directly selected); if there are two or more people in the group with the same time, they are sorted by "operation and maintenance personnel number" from smallest to largest, selecting the person with the smallest number. Finally, the "shortest-time personnel" selected from each skill level group are integrated to form a candidate group of operation and maintenance personnel with priority based on skill level and shortest time (if there is only one skill level group, the candidate group includes the one person selected from that group; if there are multiple skill level groups, the candidate group includes personnel selected from each skill level group, sorted by skill level priority).

[0100] Step 4053: Based on the candidate group of operation and maintenance personnel and the list of operation and maintenance tools in the operation and maintenance scheduling resources, determine the appropriate operation and maintenance tools carried by each candidate operation and maintenance personnel.

[0101] Optionally, the intelligent operation and maintenance management system first retrieves the list of operation and maintenance tools from the determined operation and maintenance scheduling resources, filters out the tool data corresponding to the candidate operation and maintenance personnel in the candidate group, and retains only the record of "tool status = normal and available"; and retrieves the necessary skill group for potential faults, and clarifies the "required tool function" corresponding to each necessary skill type (such as charging module repair requires "voltage detection function" and "current detection function", and sensor calibration requires "sensor signal calibration function"); compares the "tool function" of the tools carried by the candidate operation and maintenance personnel with the required tool function to determine whether the tools are compatible, and then integrates the "compatible tools" carried by each candidate operation and maintenance personnel to form a "candidate operation and maintenance personnel - compatible operation and maintenance tools" correspondence, and excludes incompatible tools (such as the "charging pile appearance cleaning tool" carried by Zhang Gong of YW-001, which is unrelated to charging module repair and sensor calibration, and is not included in the compatible tools).

[0102] Step 4054: Based on the adaptation maintenance tools carried by the candidate maintenance personnel, the basic identification data of the faulty charging pile, the potential fault identification results, and the optimal maintenance path information, the maintenance task work order is obtained.

[0103] Optionally, the intelligent operation and maintenance management system comprehensively integrates the matching tools for candidate operation and maintenance personnel, basic identification data of faulty charging piles, potential fault identification results, and optimal operation and maintenance path information to generate operation and maintenance task work orders containing complete operational basis, ensuring that operation and maintenance personnel can directly perform fault handling based on the work orders. The integrated information includes: candidate operation and maintenance personnel information (the first person in the candidate group is given priority for execution), a list of matching operation and maintenance tools (clearly specifying tool names and functions), basic identification data of faulty charging piles (equipment number, location coordinates), potential fault identification results (fault type, risk level, fault characteristics), and optimal operation and maintenance path information (path details, estimated time, estimated arrival time). Specifically, the system prioritizes the top-ranked personnel in the maintenance personnel candidate group (highest skill level and shortest completion time at the same level). If this personnel's compatible tools cover all necessary skill requirements (e.g., all tools for charging module repair and sensor calibration are available), they are selected as the work order execution subject. If the tools are missing, subsequent personnel in the candidate group are selected sequentially until an execution subject with complete tools is found. Then, the system retrieves the execution subject's compatible maintenance tool list, basic identification data of the faulty charging pile, potential fault identification results, and optimal maintenance path information. This information is integrated in the order of "basic task information → fault information → resource information → execution requirements" to ensure that there is no duplication or omission of information. Finally, the integrated information is filled in according to a preset template to generate a standardized maintenance task work order, which is automatically assigned a unique task number (format: "YW-region-date-serial number") and synchronized to the maintenance personnel's mobile APP and the charging pile management system database.

[0104] This invention, through its progressive and collaborative approach from data association and personnel screening to tool matching and work order generation, effectively solves the technical problems of traditional operations and maintenance (O&M) that focus solely on skills while neglecting path efficiency, mismatch between tools and faults, and fragmented work order information. It achieves precise matching of O&M personnel, tools, paths, and fault requirements, ensuring that high-risk faults can be handled by highly skilled, efficient personnel with complete tools, thereby improving the success rate and efficiency of fault repair and reducing the waste of O&M resources and the cost of secondary repairs.

[0105] Furthermore, the AI-based intelligent operation and maintenance management system for charging piles provided by the present invention will be described below. The AI-based intelligent operation and maintenance management system for charging piles described below can be referred to in correspondence with the AI-based intelligent operation and maintenance management method for charging piles described above.

[0106] Optional, refer to Figure 2 , Figure 2 This is a schematic diagram of the structure of the AI-based intelligent operation and maintenance management system for charging piles provided by the present invention. The AI-based intelligent operation and maintenance management system for charging piles includes: The data acquisition module 210 is used to acquire basic identification data, environmental parameter data, and operating parameter data of each component for each charging pile within the target area. The potential fault prediction module 220 is used to input environmental parameter data and operating parameter data into the trained fault prediction model to identify potential faults and obtain the potential fault identification results output by the fault prediction model. The operation and maintenance path determination module 230 is used to determine the operation and maintenance scheduling resources that the potentially faulty charging pile is adapted to based on the potential fault identification results, the corresponding basic identification information and the pre-built operation and maintenance resource database, and to determine the optimal operation and maintenance path for each operation and maintenance personnel based on the current location information of each operation and maintenance personnel in the operation and maintenance scheduling resources, the regional location information of the potentially faulty charging pile and the basic identification information. The operation and maintenance task execution module 240 is used to determine operation and maintenance task work orders based on the skill attributes of each operation and maintenance personnel in the operation and maintenance scheduling resources, the potential fault risk level in the potential fault identification results, and the optimal operation and maintenance path, and to enable each operation and maintenance personnel to execute operation and maintenance management tasks according to the operation and maintenance task work orders.

[0107] This invention identifies potential faults for each charging pile by combining acquired environmental parameter data and operational parameter data of each component with a trained fault prediction model. This breaks the fixed-cycle limitation of manual periodic inspections, enabling real-time capture of abnormal signals related to sudden charging pile faults. It achieves accurate prediction of potential faults and precise location of faulty components, solving the problems of delayed fault response and lack of real-time analysis and prediction in existing methods. Furthermore, based on the potential fault identification results and basic identification information combined with an operation and maintenance resource database, it determines the appropriate operation and maintenance scheduling resources for the potentially faulty charging pile. Finally, it combines the current location information of the operation and maintenance personnel with basic identification information and other relevant data. The optimal maintenance path is determined by using basic identification information and the regional location information of potentially faulty charging piles. This enables precise matching of maintenance resources, avoids blind scheduling of maintenance resources, and reduces maintenance costs and time. Finally, maintenance task work orders are determined based on the skill attributes of maintenance personnel, the level of potential fault risk, and the optimal maintenance path. This allows maintenance personnel to execute tasks according to the work orders without having to go to the site to investigate the cause of the fault. It enables quick and accurate location of faulty components. Combined with the overall arrangement of geographical location and maintenance resource distribution, it significantly improves the fault response speed and shortens the fault investigation and repair cycle. This not only improves the user charging experience but also increases the maintenance efficiency and utilization rate of charging piles.

[0108] Please see Figure 3 , Figure 3 An embodiment diagram of an electronic device provided in accordance with the present invention. For example... Figure 3 As shown, this embodiment of the invention provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, it performs the following steps: Acquire basic identification data, environmental parameter data, and operational parameter data of each component for each charging pile within the target area; Environmental parameter data and operational parameter data are input into a trained fault prediction model to identify potential faults, and the potential fault identification results output by the fault prediction model are obtained. Based on the potential fault identification results, the corresponding basic identification information, and the pre-built operation and maintenance resource database, the operation and maintenance scheduling resources adapted to the potential faulty charging pile are determined. Based on the current location information of each operation and maintenance personnel in the operation and maintenance scheduling resources, the regional location information of the potential faulty charging pile, and the basic identification information, the optimal operation and maintenance path corresponding to each operation and maintenance personnel is determined. Based on the skill attributes of each maintenance personnel in the maintenance scheduling resources, the potential fault risk level in the potential fault identification results, and the optimal maintenance path, maintenance task work orders are determined, and each maintenance personnel execute maintenance management tasks according to the maintenance task work orders.

[0109] Please see Figure 4 , Figure 4 An embodiment diagram of a computer-readable storage medium provided in accordance with an embodiment of the present invention is shown. Figure 4 As shown, this embodiment provides a computer-readable storage medium 400 on which a computer program 311 is stored. When the computer program 311 is executed by a processor, it performs the following steps: Acquire basic identification data, environmental parameter data, and operational parameter data of each component for each charging pile within the target area; Environmental parameter data and operational parameter data are input into a trained fault prediction model to identify potential faults, and the potential fault identification results output by the fault prediction model are obtained. Based on the potential fault identification results, the corresponding basic identification information, and the pre-built operation and maintenance resource database, the operation and maintenance scheduling resources adapted to the potential faulty charging pile are determined. Based on the current location information of each operation and maintenance personnel in the operation and maintenance scheduling resources, the regional location information of the potential faulty charging pile, and the basic identification information, the optimal operation and maintenance path corresponding to each operation and maintenance personnel is determined. Based on the skill attributes of each maintenance personnel in the maintenance scheduling resources, the potential fault risk level in the potential fault identification results, and the optimal maintenance path, maintenance task work orders are determined, and each maintenance personnel execute maintenance management tasks according to the maintenance task work orders.

[0110] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the artificial intelligence-based intelligent operation and maintenance management method for charging piles provided by the above methods. The method includes: Acquire basic identification data, environmental parameter data, and operational parameter data of each component for each charging pile within the target area; Environmental parameter data and operational parameter data are input into a trained fault prediction model to identify potential faults, and the potential fault identification results output by the fault prediction model are obtained. Based on the potential fault identification results, the corresponding basic identification information, and the pre-built operation and maintenance resource database, the operation and maintenance scheduling resources adapted to the potential faulty charging pile are determined. Based on the current location information of each operation and maintenance personnel in the operation and maintenance scheduling resources, the regional location information of the potential faulty charging pile, and the basic identification information, the optimal operation and maintenance path corresponding to each operation and maintenance personnel is determined. Based on the skill attributes of each maintenance personnel in the maintenance scheduling resources, the potential fault risk level in the potential fault identification results, and the optimal maintenance path, maintenance task work orders are determined, and each maintenance personnel execute maintenance management tasks according to the maintenance task work orders.

[0111] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0112] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0113] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent operation and maintenance management method for charging piles based on artificial intelligence, characterized in that, include: Acquire basic identification data, environmental parameter data, and operational parameter data of each component for each charging pile within the target area; Environmental parameter data and operational parameter data are input into a trained fault prediction model to identify potential faults, and the potential fault identification results output by the fault prediction model are obtained. Based on the potential fault identification results, the corresponding basic identification information, and the pre-built operation and maintenance resource database, the operation and maintenance scheduling resources adapted to the potential faulty charging pile are determined. Based on the current location information of each operation and maintenance personnel in the operation and maintenance scheduling resources, the regional location information of the potential faulty charging pile, and the basic identification information, the optimal operation and maintenance path corresponding to each operation and maintenance personnel is determined. Based on the skill attributes of each maintenance personnel in the maintenance scheduling resources, the potential fault risk level in the potential fault identification results, and the optimal maintenance path, maintenance task work orders are determined, and each maintenance personnel execute maintenance management tasks according to the maintenance task work orders.

2. The intelligent operation and maintenance management method for charging piles based on artificial intelligence according to claim 1, characterized in that, The potential fault identification results include the potential fault risk type and risk level; the basic identification information includes real-time geographic location information, device number, and region information. The process of determining the appropriate operation and maintenance scheduling resources for charging piles with potential faults based on the potential fault identification results, corresponding basic identification information, and a pre-built operation and maintenance resource database includes: Based on the potential fault risk types and risk levels contained in the potential fault identification results, and combined with the fault types, risk levels and corresponding relationship tables of operation and maintenance resources stored in the operation and maintenance resource database, the list of operation and maintenance tools, skill requirements of operation and maintenance personnel and response time limits required for potential faults of the target charging pile are determined. Based on the skill requirements of the operation and maintenance personnel and the skill information of all operation and maintenance personnel in the operation and maintenance resource database, a preliminary group of operation and maintenance personnel in the region who meet the technical requirements is obtained. Based on the real-time geographic location information in the target charging pile basic identification data and the location information of each maintenance personnel in the maintenance personnel group in the maintenance resource database, the straight-line distance between each maintenance personnel and the target charging pile is determined. Based on the straight-line distance between each maintenance personnel and the target charging pile, combined with the average driving speed corresponding to different road types in the region in the maintenance resource database, the estimated arrival time of each maintenance personnel from the current location to the location of the target charging pile is determined. Based on the estimated arrival time, the response time limit requirement, and the list of operation and maintenance tools, the operation and maintenance scheduling resources suitable for the potentially faulty charging piles are obtained through screening and matching.

3. The intelligent operation and maintenance management method for charging piles based on artificial intelligence according to claim 2, characterized in that, The process of filtering and matching based on the estimated arrival time, the response time limit requirement, and the list of maintenance tools yields maintenance scheduling resources suitable for potentially faulty charging piles, including: Based on the aforementioned response time limit requirements and the estimated arrival time of each maintenance personnel, candidate maintenance personnel who meet the response time limit requirements are selected. Based on the list of operation and maintenance tools and the candidate operation and maintenance personnel, and combined with the list of tools that each operation and maintenance personnel can currently carry in the operation and maintenance resource database, the candidate operation and maintenance personnel whose tools meet the requirements are selected. Based on the equipment importance level corresponding to the equipment number in the basic identification data of the target charging pile and the priority information of the tasks currently being performed or to be performed by the selected maintenance personnel, the suitability priority for each selected maintenance personnel to undertake the maintenance task of the target charging pile is determined; the equipment importance level is determined by the usage frequency, service range and importance of the area to which the charging pile belongs; All candidate maintenance personnel are sorted according to their suitability priority, and the first few maintenance personnel with the highest suitability priority are selected as target maintenance personnel based on the sorting results. Based on the target maintenance personnel, the maintenance tool list, the maintenance personnel skill requirements, response time requirements, and the basic identification information of the corresponding target charging pile, the maintenance scheduling resources adapted to the potentially faulty charging pile are integrated to obtain the maintenance scheduling resources.

4. The intelligent operation and maintenance management method for charging piles based on artificial intelligence according to claim 2, characterized in that, The process of determining the optimal maintenance path for each maintenance personnel based on their current location information, the regional location information of potentially faulty charging piles, and basic identification information within the maintenance scheduling resources includes: Based on the regional location information of the potentially faulty charging pile, a geographic topology network is constructed, with the current location information of each maintenance personnel in the operation and maintenance scheduling resources within the target area and the real-time geographic location of the potentially faulty charging pile in the basic identification information as nodes and the connection path between the two as edges. An initial connection path group is determined based on the geographic topology network. The initial connection path group consists of all possible connection paths from the current location of each maintenance personnel to the real-time geographic location of the potentially faulty charging pile. Based on the road type information contained in each initial connected path in the initial connected path group, the road traffic coefficient of each initial connected path is determined, and the initial connected path group is initially screened based on the road traffic coefficient to obtain the first candidate path group; the road traffic coefficient is determined based on the average traffic efficiency of the same type of roads in the same historical period. Based on the traffic signal node information of each candidate path in the first candidate path group, the traffic signal delay index of each candidate path is determined, and the first candidate path group is further filtered based on the traffic signal delay index to obtain the second candidate path group; the traffic signal delay index is the sum of the product of the red light ratio of all traffic signal nodes on the candidate path and the traffic light cycle duration. Based on the real-time traffic congestion level of each candidate path in the second candidate path group, the congestion impact coefficient of each candidate path is determined, and the second candidate path group is screened three times based on the congestion impact coefficient to obtain the third candidate path group. Based on the third candidate path group and the response time limit requirements of each potentially faulty charging pile, the optimal operation and maintenance path for each operation and maintenance personnel is determined.

5. The intelligent operation and maintenance management method for charging piles based on artificial intelligence according to claim 4, characterized in that, The process of determining the optimal maintenance path for each maintenance personnel based on the third candidate path group and the response time requirement of each potentially faulty charging pile includes: Based on the physical straight-line length of each candidate path in the third candidate path group, the estimated travel time for each candidate path is determined; the physical straight-line length is the sum of the actual distances of all edges on the candidate path; the estimated travel time is determined based on the physical straight-line length of the candidate path and the average driving speed of the corresponding road type. Based on the estimated travel time of each candidate path in the third candidate path group, and the response time limit requirement of each potentially faulty charging pile, a fourth candidate path group that meets the response time limit requirement is obtained. The candidate paths in the fourth candidate path group are then sorted based on the estimated travel time to obtain the first path sequence. The first path sequence is reordered based on the number of road turns in each path to obtain a second path sequence ordered by the number of turns. Based on the second path sequence, the candidate path ranked first in the path sequence is selected as the optimal operation and maintenance path for the corresponding operation and maintenance personnel.

6. The intelligent operation and maintenance management method for charging piles based on artificial intelligence according to claim 1, characterized in that, The skill attributes include skill type and skill certification level; The process of determining maintenance task work orders based on the skill attributes of each maintenance personnel in the maintenance scheduling resources, the potential fault risk level in the potential fault identification results, and the optimal maintenance path includes: Based on the skill type and skill certification level of each operation and maintenance personnel in the operation and maintenance resource set, the skill detail group of each operation and maintenance personnel is determined according to the correspondence between operation and maintenance personnel, skill type and skill certification level; Based on the potential fault risk level in the potential fault identification results and the correspondence table between potential fault risk and required skill type in the charging pile management system, the necessary skill type for handling the potential fault risk level is selected to obtain the necessary skill group for potential faults. Based on the skill details of each operations and maintenance personnel and the necessary skill groups for potential faults, a skill-matched operations and maintenance personnel group is obtained through judgment and screening. Based on the skill matching operation and maintenance personnel group and the skill certification level in the skill details group of each operation and maintenance personnel, the operation and maintenance personnel in the skill matching operation and maintenance personnel group are sorted to obtain a list of operation and maintenance personnel after skill sorting. Based on the list of operations and maintenance personnel and the optimal operations and maintenance path information for each personnel, operations and maintenance task work orders are determined.

7. The intelligent operation and maintenance management method for charging piles based on artificial intelligence according to claim 6, characterized in that, The process of determining maintenance task work orders based on the list of maintenance personnel and the optimal maintenance path information for each personnel includes: Based on the optimal operation and maintenance path information corresponding to each operation and maintenance personnel and the operation and maintenance personnel list, the optimal path time of each operation and maintenance personnel in the operation and maintenance personnel list is extracted to obtain the operation and maintenance personnel path time group. Based on the list of maintenance personnel and the path time group of maintenance personnel, the maintenance personnel with the shortest path time are selected from the maintenance personnel with the same skill certification level, and a candidate group of maintenance personnel with priority in skill level and shortest path time is obtained. Based on the candidate group of operation and maintenance personnel and the list of operation and maintenance tools in the operation and maintenance scheduling resources, determine the appropriate operation and maintenance tools carried by each candidate operation and maintenance personnel; The maintenance task work order is obtained by integrating the adapted maintenance tools carried by the candidate maintenance personnel, the basic identification data of the faulty charging pile, the potential fault identification results, and the optimal maintenance path information.

8. An intelligent operation and maintenance management system for charging piles based on artificial intelligence, characterized in that: The method is applied to the AI-based intelligent operation and maintenance management method for charging piles as described in any one of claims 1 to 7; the AI-based intelligent operation and maintenance management system for charging piles includes: The data acquisition module is used to acquire basic identification data, environmental parameter data, and operating parameter data of each component for each charging pile within the target area. The potential fault prediction module is used to input environmental parameter data and operating parameter data into the trained fault prediction model to identify potential faults and obtain the potential fault identification results output by the fault prediction model. The operation and maintenance path determination module is used to determine the operation and maintenance scheduling resources that the potentially faulty charging pile is compatible with based on the potential fault identification results, the corresponding basic identification information and the pre-built operation and maintenance resource database, and to determine the optimal operation and maintenance path for each operation and maintenance personnel based on the current location information of each operation and maintenance personnel in the operation and maintenance scheduling resources, the regional location information of the potentially faulty charging pile and the basic identification information. The operation and maintenance task execution module is used to determine operation and maintenance task work orders based on the skill attributes of each operation and maintenance personnel in the operation and maintenance scheduling resources, the potential fault risk level in the potential fault identification results, and the optimal operation and maintenance path, and to enable each operation and maintenance personnel to execute operation and maintenance management tasks according to the operation and maintenance task work orders.

9. An electronic device, characterized in that, include: Memory, used to store computer software programs; A processor is configured to read and execute the computer software program, wherein when the processor executes the computer software program, it implements the intelligent operation and maintenance management method for charging piles based on artificial intelligence as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that, The storage medium stores a computer software program, which, when executed by a processor, implements the intelligent operation and maintenance management method for charging piles based on artificial intelligence as described in any one of claims 1 to 7.

Images