Maintenance management method, internet of things system and device of smart gas call center

Abstract

The embodiment of the specification provides a kind of maintenance management method, Internet of Things system and device of wisdom gas call center, the system includes wisdom gas user platform, wisdom gas service platform and wisdom gas management platform that interact in turn, the method is executed by processor in wisdom gas management platform, the method includes: by wisdom gas service platform, based on wisdom gas user platform, the call consultation data information of gas user is acquired;Based on call consultation data information, the positioning evaluation value of multiple dimensions of the evaluated staff is generated, the evaluated staff is based on consultation data information and locates gas failure type;Based on call consultation data information, the maintenance evaluation value of multiple dimensions of the evaluated maintenance personnel is generated, the evaluated maintenance personnel is based on gas failure type and carries out maintenance;And based on multiple dimensions of maintenance evaluation value and multiple dimensions of positioning evaluation value, the work order processing range of the evaluated maintenance personnel and the evaluated staff is adjusted.

Description

Technical Field

[0001] This manual relates to the field of gas maintenance management, and in particular to a maintenance management method, Internet of Things system and device for a smart gas call center. Background Technology

[0002] Natural gas is flammable, explosive, and widely used. Gas users can contact gas call center operators, who then identify the gas fault and dispatch appropriate repair personnel. This resolves issues encountered by gas users and ensures normal gas supply. However, in current technology, customer service personnel answering gas user calls and locating faults, as well as the dispatched repair personnel, are typically assigned randomly. Because different customer service personnel have varying abilities to locate gas faults, and each repairman specializes in different types of gas faults, there is a mismatch between the work order processing scope and the capabilities of the repair and call center personnel, leading to customer complaints.

[0003] To address the issue of automatic work order matching, CN2019108789850 discloses a rapid fault reporting and automated work order workflow system. The work order publishing module automatically matches the responsible personnel for handling the issue through multi-dimensional comparisons (e.g., work content comparison, shift schedule comparison, workload comparison). However, this system's work order matching process does not address situations where the work order handling scope of maintenance personnel and call center staff does not match their capabilities; therefore, improvements in handling customer complaints are needed.

[0004] Therefore, this paper aims to provide a smart gas call center maintenance management method, IoT system, and device. This will allow for a better match between the work order processing scope of maintenance personnel and call center agents to be evaluated and their own capabilities, enhancing location accuracy and maintenance quality, and ultimately improving gas user satisfaction. Summary of the Invention

[0005] This specification provides one or more embodiments of a maintenance management method for a smart gas call center. The method is implemented based on a smart gas call center maintenance management IoT system. The IoT system includes a smart gas user platform, a smart gas service platform, and a smart gas management platform that interact sequentially. The method is executed by a processor in the smart gas management platform and includes: obtaining call consultation data information from gas users through the smart gas service platform based on the smart gas user platform; generating multi-dimensional location assessment values ​​for an agent to be evaluated based on the call consultation data information, wherein the agent to be evaluated locates the gas fault type based on the consultation data information; generating multi-dimensional maintenance assessment values ​​for a repair worker to be evaluated based on the call consultation data information, wherein the repair worker to be evaluated performs maintenance based on the gas fault type; and adjusting the work order processing scope of the repair worker to be evaluated and the agent to be evaluated based on the multi-dimensional maintenance assessment values ​​and the multi-dimensional location assessment values.

[0006] This specification provides one or more embodiments of a smart gas call center maintenance management IoT system. The IoT system includes a smart gas user platform, a smart gas service platform, and a smart gas management platform that interact sequentially. The smart gas management platform is used to: obtain call consultation data information of gas users through the smart gas service platform based on the smart gas user platform; generate maintenance evaluation values ​​of multiple dimensions for the maintenance personnel to be evaluated based on the call consultation data information; generate location evaluation values ​​of multiple dimensions for the agent to be evaluated based on the call consultation data information; and adjust the work order processing scope of the maintenance personnel to be evaluated and the agent to be evaluated based on the maintenance evaluation values ​​and the location evaluation values.

[0007] This specification provides one or more embodiments of a maintenance management device for a smart gas call center. The device includes at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least a portion of the computer instructions to implement a maintenance management method for the smart gas call center.

[0008] This invention addresses the problem of better matching the work order processing scope of maintenance personnel and agent seats to their capabilities. By determining multi-dimensional maintenance assessment values ​​and multi-dimensional location assessment values ​​based on gas user call and inquiry data, the work order processing scope of maintenance personnel and agent seats to be assessed can be adjusted. This results in a better match between the work order processing scope and the capabilities of the personnel and agents being assessed, enhancing location accuracy and maintenance quality, improving work order processing efficiency, and ultimately increasing gas user satisfaction. Attached Figure Description

[0009] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0010] Figure 1 This is a schematic diagram illustrating an application scenario of an IoT system for maintenance management of a smart gas call center, based on some embodiments of this specification.

[0011] Figure 2 This is an exemplary flowchart of a maintenance management method for a smart gas call center, as shown in some embodiments of this specification.

[0012] Figure 3 This is an exemplary flowchart illustrating the generation of multi-dimensional maintenance assessment values ​​for a maintenance worker to be evaluated, according to some embodiments of this specification.

[0013] Figure 4 This is an exemplary flowchart illustrating the generation of multi-dimensional positioning assessment values ​​for an agent to be evaluated, according to some embodiments of this specification.

[0014] Figure 5 This is an exemplary flowchart of a method for generating positioning accuracy according to some embodiments of this specification. Detailed Implementation

[0015] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0017] Figure 1 This is a schematic diagram illustrating the application scenario of a smart gas call center maintenance management IoT system according to some embodiments of this specification.

[0018] like Figure 1As shown, in some embodiments, the maintenance management IoT system of a smart gas call center may include a smart gas user platform, a smart gas service platform, a smart gas management platform, a smart gas sensor network platform, and a smart gas object platform.

[0019] In some embodiments, the maintenance management IoT system of a smart gas call center can be applied to various application scenarios such as maintenance management. In some embodiments, the maintenance management IoT system of a smart gas call center can obtain call consultation data from gas users through a smart gas service platform based on a smart gas user platform. Based on the call consultation data, a multi-dimensional location assessment value is generated for the agent to be evaluated, and the agent to be evaluated locates the type of gas fault based on the consultation data. Based on the call consultation data, a multi-dimensional maintenance assessment value is generated for the repair personnel to be evaluated, and the repair personnel to be evaluated perform repairs based on the type of gas fault. Based on the multi-dimensional maintenance assessment value and the multi-dimensional location assessment value, the work order processing scope of the repair personnel and the agent to be evaluated is adjusted.

[0020] Various application scenarios for maintenance management can include a gas company's call center staff locating gas fault types, maintenance personnel repairing gas faults, and adjusting the work order processing scope for maintenance and call center staff. It should be noted that the above scenarios are merely examples and do not limit the specific application scenarios of the maintenance management IoT system for smart gas call centers. Those skilled in the art can apply the maintenance management IoT system for smart gas call centers to any other suitable scenarios based on the content disclosed in this embodiment.

[0021] The following will provide a detailed explanation of the IoT system for maintenance management in the smart gas call center.

[0022] A smart gas user platform can be a platform for interacting with users. In some embodiments, the smart gas user platform can be configured as a terminal device, such as a mobile device, tablet computer, or any combination thereof. In some embodiments, the smart gas user platform can be used to provide users with gas usage-related data and solutions to gas problems. In some embodiments, the smart gas user platform includes a gas user sub-platform, a government user sub-platform, and a regulatory user sub-platform. The gas user sub-platform is for gas users, providing information such as gas usage-related data and solutions to gas problems. Gas users refer to users who use gas (e.g., industrial gas users, commercial gas users, ordinary gas users, etc.). In some embodiments, the gas user sub-platform can correspond to and interact with the smart gas service sub-platform to obtain safe gas usage services. The government user sub-platform can be for government users, providing gas operation-related data. Government users refer to users of government gas operation-related departments. In some embodiments, the government user sub-platform can correspond to and interact with the smart operation service sub-platform to obtain gas operation services. The regulatory user sub-platform is for regulatory users, monitoring the operation of the entire smart gas call center's maintenance management IoT system. Regulatory users refer to users of the safety department. In some embodiments, the regulatory user sub-platform can correspond to and interact with the smart regulatory service sub-platform to obtain services related to safety regulatory needs. In some embodiments, the smart gas user platform can interact bidirectionally with the smart gas service platform, sending gas user call information to the smart gas service sub-platform and receiving customer service feedback information uploaded by the smart gas service sub-platform. In some embodiments, the smart gas user platform can send gas maintenance management information query instructions to the smart operation service sub-platform and receive gas maintenance management information uploaded by the smart operation service sub-platform. Gas maintenance management information may include assessment information and dispatch information of maintenance personnel and / or call center staff.

[0023] A smart gas service platform can be a platform for receiving and transmitting data and / or information. For example, a smart gas service platform can receive gas maintenance management information query instructions issued by a government user sub-platform, and send gas maintenance management information to the government user sub-platform. In some embodiments, the smart gas service platform has a smart gas usage service sub-platform, a smart operation service sub-platform, and a smart supervision service sub-platform. In some embodiments, the smart gas service platform can interact with a smart gas management platform. For example, the smart gas service platform can interact with the smart gas management platform, issuing gas maintenance management information query instructions to the smart gas data center and receiving gas maintenance management information uploaded by the smart gas data center, etc.

[0024] A smart gas management platform can refer to a platform that coordinates and integrates the connections and collaboration between various functional platforms, aggregating all information from the Internet of Things (IoT) and providing sensing, management, and control functions for the IoT operating system. For example, a smart gas management platform can acquire and provide gas maintenance management information.

[0025] In some embodiments, the smart gas management platform may include a smart customer service management sub-platform, a smart operation management sub-platform, and a smart gas data center. Each management sub-platform can interact bidirectionally with the smart gas data center. The smart gas data center aggregates and stores all system operational data, while each management sub-platform can obtain data from the smart gas data center and provide relevant operational information. For example, the smart customer service management sub-platform can obtain and analyze customer feedback information from the smart gas data center, and send the processed maintenance personnel data to the smart gas data center. Maintenance personnel data may include assessment information of maintenance personnel determined based on customer feedback (such as capability assessment and maintenance result assessment). As another example, the smart gas data center can send maintenance personnel data and gas equipment data to the smart operation management sub-platform for processing. The smart operation management sub-platform then sends the processed maintenance management information (e.g., pipeline engineering management information, such as personnel arrangement and scheduling) to the smart gas data center for aggregation and processing before further sending it to the smart gas service platform. In some embodiments, the smart customer service management sub-platform can be used for revenue management, business registration management, application management, customer service management, message management, and customer analysis management. Message management can be used to view customer calls, inquiries, feedback, complaints, etc., while customer service management can be used to respond to and process customer feedback. In some embodiments, the intelligent operation management sub-platform can be used for gas procurement management, gas reserve management, gas usage scheduling management, purchase-sales difference management, pipeline engineering management, and comprehensive office management. Pipeline engineering management can be used to view pipeline engineering work order information, personnel configuration, progress, and manage pipeline engineering. In some embodiments, the intelligent operation management sub-platform and the intelligent service management sub-platform can interact with the intelligent gas service platform and the intelligent gas sensor network platform through the intelligent gas data center. In some embodiments, the intelligent gas data center can receive query instructions for gas maintenance management information and customer feedback information issued by the intelligent gas service platform, and upload gas maintenance management information to the intelligent gas service platform. In some embodiments, the intelligent gas data center can issue instructions to obtain gas equipment-related data to the intelligent gas sensor network platform, and receive gas equipment-related data uploaded by the intelligent gas sensor network platform.

[0026] A smart gas sensor network platform can be a functional platform for managing sensor communication. It can be configured as a communication network and gateway, enabling functions such as network management, protocol management, command management, and data parsing. In some embodiments, the smart gas sensor network platform may include a sub-platform for indoor gas equipment sensing and a sub-platform for gas pipeline equipment sensing, corresponding to the sub-platforms for indoor gas equipment and gas pipeline equipment respectively, and used to acquire relevant data from indoor equipment and pipeline equipment. In some embodiments, the smart gas sensor network platform can connect to a smart gas management platform and a smart gas object platform to achieve sensing communication of perception information and sensing communication of control information. For example, the smart gas sensor network platform can receive instructions from the smart gas data center to acquire relevant data of gas equipment, upload relevant data of gas equipment to the smart gas data center, send instructions to the smart gas object platform to acquire relevant data of gas equipment, and receive the uploaded relevant data of gas equipment.

[0027] The intelligent gas target platform can be a functional platform for generating sensing information and executing control information, and can be configured to include gas equipment and other devices. Gas equipment can include indoor equipment and pipeline equipment. Other devices can include monitoring equipment, temperature sensors, pressure sensors, etc. In some embodiments, the intelligent gas target platform can also include a sub-platform for indoor gas equipment and a sub-platform for pipeline equipment. The sub-platform for indoor gas equipment can include indoor equipment, such as gas user metering equipment. The sub-platform for pipeline equipment can include pipeline equipment, such as pressure regulating equipment, gas gate compressors, gas flow meters, valve control equipment, thermometers, barometers, etc. In some embodiments, the intelligent gas target platform can receive instructions from the intelligent gas sensor network platform to acquire relevant data of gas equipment, and upload the relevant data of gas equipment to the corresponding sensor network sub-platform.

[0028] It should be noted that the smart gas user platform in this embodiment can be a desktop computer, tablet computer, laptop computer, mobile phone, or other electronic device capable of data processing and communication, and is not limited in many ways. It should be understood that the data processing process mentioned in this embodiment can be performed by the server's processor, and the data stored on the server can be stored on the server's storage devices, such as hard drives. In specific applications, the smart gas sensor network platform can employ multiple gateway servers or multiple smart routers, and is not limited in many ways. It should be understood that the data processing process mentioned in this embodiment can be performed by the gateway server's processor, and the data stored on the gateway server can be stored on the gateway server's storage devices, such as hard drives and SSDs.

[0029] In some embodiments of this specification, the transmission or control of customer feedback information, gas equipment-related data, and emergency response plans for gas emergencies are realized through the IoT functional architecture of five platforms, completing the closed loop of information flow and making IoT information processing smoother and more efficient.

[0030] Figure 2 This is an exemplary flowchart of a maintenance management method for a smart gas call center, according to some embodiments of this specification. In some embodiments, process 200 may be executed by a smart gas management platform. Figure 2 As shown, process 200 includes the following steps 210-240.

[0031] Step 210: Obtain gas user call and inquiry data information through the smart gas service platform based on the smart gas user platform.

[0032] Call-based inquiry data refers to data related to gas malfunctions obtained through communication with gas users. In some embodiments, call-based inquiry data may include one or more of the following: gas malfunction characteristic data, service personnel data, and gas customer feedback data.

[0033] Gas fault characteristic data refers to relevant data that reflects the characteristics of gas faults. For example, gas fault characteristic data may include gas meter fault codes, the number of gas faults, etc.

[0034] Service personnel data refers to the personnel involved in handling this gas fault. For example, service personnel may include call center agents who answer inquiries and maintenance personnel responsible for repairing this gas fault.

[0035] Gas customer feedback data refers to data provided by gas customers based on the handling of a gas fault. For example, customer feedback data may include customer evaluations of call center staff and repair personnel.

[0036] In some implementations, call consultation data may also include primary related data.

[0037] The first associated data refers to data related to determining the type of gas fault. In some embodiments, the first associated data may include one or more of the following: gas user's gas usage characteristics, average gas consumption rate when the gas user uses gas, gas calorific value, etc.

[0038] In some implementations, the first associated data includes at least the gas user's gas usage characteristics information.

[0039] Gas user usage characteristics refer to the characteristics related to a gas user's gas usage.

[0040] In some implementations, gas user usage characteristics information may include the frequency of gas usage. Gas usage frequency can be defined as the ratio of the time period during which gas usage rates exceed a threshold to the total number of time periods during which gas usage is statistically recorded.

[0041] In some embodiments, the smart gas data center in the smart gas management platform can obtain call consultation data information based on the smart gas user platform through the smart gas service platform.

[0042] Step 220: Based on the call consultation data, generate location assessment values ​​for the agents to be evaluated across multiple dimensions.

[0043] The agent to be evaluated refers to an agent who is awaiting evaluation to determine the type of gas fault. In some embodiments, the agent to be evaluated may determine the type of gas fault based on consultation data.

[0044] The location assessment value refers to the value that reflects the level of ability of the operator being assessed to locate the type of gas fault based on consultation data.

[0045] In some embodiments, each of the multiple dimensions corresponds to a location complexity. For example, the multiple dimensions may include three preset dimensions. Specifically, the three preset dimensions may include a preset work order processing range for easily located gas fault types, a preset work order processing range for medium-difficulty gas fault types, and a preset work order processing range for complex gas fault types. For the definition of the work order processing range, please refer to the description below, which will not be repeated here.

[0046] The positioning evaluation value in multiple dimensions refers to the positioning evaluation value under the positioning complexity corresponding to each of the multiple dimensions.

[0047] In some embodiments, the location assessment value of each dimension of the agent to be assessed can be manually evaluated based on call consultation data.

[0048] In some embodiments, the intelligent gas management platform can generate second data information from call inquiry data. Then, based on the second data information, it generates location assessment values ​​across multiple dimensions. The second data information includes relevant data information generated by the agent being assessed during fault location within a target time period. For more details on this section, please refer to [link to relevant documentation]. Figure 4 The specific details will not be elaborated here.

[0049] Step 230: Based on the call consultation data, generate multi-dimensional maintenance assessment values ​​for the maintenance personnel to be evaluated.

[0050] The service personnel to be evaluated refers to gas fault service personnel awaiting evaluation. In some embodiments, the service personnel to be evaluated may perform repairs based on the type of gas fault.

[0051] The maintenance assessment value refers to the value that reflects the level of ability of the maintenance personnel being assessed to perform maintenance based on the type of gas fault.

[0052] In some embodiments, each of the multiple dimensions corresponds to a repair complexity. For example, the multiple dimensions may include three preset dimensions. Specifically, the three preset dimensions may include a preset work order processing range for simple repair tasks, a preset work order processing range for medium repair tasks, and a preset work order processing range for complex repair tasks.

[0053] In some embodiments, the maintenance assessment value of each dimension of the maintenance personnel to be assessed can be manually evaluated based on call consultation data.

[0054] In some embodiments, the intelligent gas management platform can generate first data information from call inquiry data, and generate multi-dimensional maintenance assessment values ​​based on the first data information. The first data information may include relevant data generated by the maintenance personnel being assessed during a target time period. For more details on this section, please refer to [link to relevant documentation]. Figure 3 Its description will not be repeated here.

[0055] Step 240: Based on the maintenance assessment values ​​and location assessment values ​​of multiple dimensions, adjust the work order processing scope of the maintenance personnel and the call center personnel to be assessed.

[0056] A work order is a simple maintenance plan consisting of one or more tasks. In some embodiments, a work order can correspond to an overall process of "a user making a call for consultation based on a gas fault; an agent extracting abnormal characteristics of the gas fault based on the inquiry and the customer's answer to the inquiry, thereby collecting abnormal information; an agent locating the gas fault based on the collected abnormal information; and a maintenance worker performing on-site (or remote) gas fault repair based on the located fault."

[0057] The scope of a work order refers to the range of tasks that can be accepted. For example, the work order processing scope for agent A1 can be simple location tasks, while the work order processing scope for agent A2 can be medium-difficulty location tasks. Similarly, the work order processing scope for maintenance worker B1 can be simple repair tasks, while the work order processing scope for maintenance worker B2 can be medium or complex repair tasks.

[0058] In some embodiments, based on historical data, the maintenance assessment value for each of the multiple dimensions of the maintenance personnel to be evaluated and the maximum maintenance assessment value can be determined, as can the location assessment value for each of the multiple dimensions of the agent to be evaluated and the maximum location assessment value. If the work order processing range currently corresponding to the maintenance personnel to be evaluated is not within the dimension corresponding to the maximum maintenance assessment value, then the work order processing range currently corresponding to the maintenance personnel to be evaluated is adjusted to be within the dimension corresponding to the maximum maintenance assessment value. If the work order processing range currently corresponding to the agent to be evaluated is not within the dimension corresponding to the maximum location assessment value, then the work order processing range currently corresponding to the agent to be evaluated is adjusted to be within the dimension corresponding to the maximum location assessment value.

[0059] In some embodiments of this specification, multi-dimensional maintenance assessment values ​​and multi-dimensional location assessment values ​​are determined based on gas user call and inquiry data, thereby adjusting the work order processing scope of the maintenance personnel and agent seats to be assessed. This further ensures that the work order processing scope of the maintenance personnel and agent seats to be assessed is better matched to their capabilities, enhancing location accuracy and maintenance quality, improving work order processing efficiency, and increasing gas user satisfaction.

[0060] Figure 3 This is an exemplary flowchart illustrating the generation of multi-dimensional maintenance assessment values ​​for a maintenance worker to be evaluated, according to some embodiments of this specification. In some embodiments, process 300 may be executed by a smart gas management platform. Figure 3 As shown, process 300 includes the following steps 310-320.

[0061] Step 310: Generate first data information from the call consultation data information.

[0062] The first data information refers to data information related to the competence of the maintenance personnel to be evaluated. In some embodiments, the first data information may include relevant data information generated by the maintenance personnel to be evaluated during maintenance within a target time period.

[0063] The target time period refers to a specified period of time. For example, the target time period could be the previous month, the previous two months, or the previous six months, etc.

[0064] The relevant data generated during maintenance refers to the data generated by the personnel assessing the maintenance during one or more maintenance operations within a target time period. For example, the relevant data generated during maintenance may include one or more of the following: maintenance complexity, total maintenance time, number of round trips, customer complaint status (e.g., complained about, not complained about), and the time interval between each maintenance operation and the time of the complaint. For a definition of maintenance complexity, please refer to the corresponding description below; it will not be repeated here.

[0065] In some embodiments, the smart gas management platform can filter relevant data information generated by the maintenance personnel to be evaluated within a target time period from the call consultation data information as the first data information.

[0066] Step 320: Based on the first data information, generate maintenance assessment values ​​in multiple dimensions.

[0067] In some embodiments, the intelligent gas management platform can generate one or more maintenance feature vectors for the maintenance personnel to be evaluated based on the first data information. Then, based on the one or more maintenance feature vectors, a multi-dimensional maintenance evaluation value is generated.

[0068] A maintenance feature vector is a vector constructed based on the first data information. In some embodiments, one maintenance feature vector can correspond to one maintenance operation.

[0069] In some embodiments, the smart gas management platform can construct feature vectors based on the first data information in various ways. For example, the smart gas management platform can construct a maintenance feature vector (a1, a2, a3, a4, a5) based on the first data information. Here, a1 represents the maintenance complexity of a single maintenance, a2 represents the total maintenance time, a3 represents the number of round trips during maintenance, a4 represents customer complaint status (e.g., 1 indicates a complaint, 2 indicates no complaint), and a5 represents the interval between maintenance time and complaint time.

[0070] In some embodiments, the intelligent gas management platform can calculate a first maintenance assessment value for each maintenance feature vector under each dimension based on one or more maintenance feature vectors. Then, the multiple first maintenance assessment values ​​calculated for all maintenance feature vectors under each dimension are weighted and summed to generate a maintenance assessment value for multiple dimensions.

[0071] In some embodiments, the dimension of the maintenance feature vector can be determined based on the maintenance complexity corresponding to the maintenance task. For example, the dimension of the maintenance feature vector corresponding to a simple maintenance task is the simple maintenance task dimension, the dimension of the maintenance feature vector corresponding to a medium maintenance task is the medium maintenance task dimension, and the dimension of the maintenance feature vector corresponding to a complex maintenance task is the complex maintenance task dimension.

[0072] Maintenance complexity refers to the level of difficulty for each maintenance task. For example, maintenance complexity can include simple maintenance tasks, medium-difficulty maintenance tasks, and complex maintenance tasks. In some embodiments, the maintenance complexity for a particular maintenance task is generated based on the distribution of gas faults and the complexity of the gas pipeline network for that maintenance task.

[0073] The gas fault distribution can include the number of different types of gas faults in the gas user's historical gas faults. For example, if a gas user's historical gas faults show that fault A occurred 5 times, fault B occurred 3 times, and fault C occurred 6 times, then the gas fault distribution for that gas user could be: (5, 3, 6).

[0074] In some embodiments, if the number of gas faults A, B, C, etc., occurring in a gas user's historical gas faults is relatively even and the time distribution is irregular (rather random), then the gas fault distribution is complex, and the maintenance complexity can be considered high. This is because maintenance for this gas user may involve repairing various fault problems, and any gas fault could occur in future work orders received from this gas user.

[0075] In some embodiments, if a gas user's historical gas faults have only involved fault A, the distribution of gas faults is relatively simple, and the maintenance complexity can be considered very low. This is because maintenance for this gas user only involves repairing fault A, and future work orders received from this gas user are also highly likely to involve fault A. Maintenance personnel can then rely entirely on past maintenance experience to repair this fault.

[0076] The complexity of a gas pipeline network can be determined based on the gas source distribution density, number of pipeline branches, and total length of transmission and distribution pipelines of the gas user's pipeline network and its upstream transmission and distribution network. In some embodiments, the higher the gas source distribution density, the more pipeline branches, and the longer the total length of transmission and distribution pipelines, the greater the complexity of the gas pipeline network can be.

[0077] In some embodiments, the intelligent gas management platform can establish a first lookup table based on historical data to determine the maintenance complexity corresponding to different gas fault distributions and gas pipeline network complexities. Then, by searching the first lookup table, the maintenance complexity corresponding to different gas fault distributions and gas pipeline network complexities is determined, thereby determining the dimension of the maintenance feature vector.

[0078] The first maintenance assessment value refers to the value that reflects the level of maintenance ability of the maintenance personnel being assessed in a maintenance task.

[0079] In some embodiments, the first maintenance assessment value can be obtained using various calculation methods. For example, the formula for calculating the first maintenance assessment value can be k = k1×a1 - k2×a2 - k3×a3 - k4×a4 + k5×a5. Where a1 is the maintenance complexity in a single maintenance task, a2 is the total maintenance time, a3 is the number of round trips for the maintenance, a4 is the customer complaint status for the maintenance (e.g., 1 indicates a complaint, 2 indicates no complaint), a5 is the interval between the maintenance time and the complaint time, k5 is the gas usage frequency in the first associated data for the maintenance, and k1, k2, k3, and k4 are preset values. These preset values ​​can be set by those skilled in the art based on experience. Gas usage frequency refers to the number of times a gas user uses gas within a preset time period. For example, if user A's gas usage frequency is once a month, then k5 is substituted with 1. For example, the formula for calculating the first maintenance assessment value can be k = a1 × (k2 × a2 - k3 × a3 - k4 × a4 + k5 × a5).

[0080] In some embodiments, the intelligent gas management platform can generate a multi-dimensional maintenance evaluation value by weighted summation of multiple first maintenance evaluation values ​​calculated from all maintenance feature vectors under each dimension.

[0081] In some embodiments, the weights of the weighted summation are related to the positioning accuracy of the positioning feature vector. The positioning accuracy of this positioning feature vector corresponds to the maintenance feature vector corresponding to the first maintenance assessment value.

[0082] In some embodiments, if the positioning accuracy of the positioning feature vector corresponding to a certain maintenance is higher, the weight of the first maintenance evaluation value of the maintenance feature vector corresponding to that maintenance is greater.

[0083] In some embodiments of this specification, the higher the positioning accuracy, the smaller the impact of inaccurate positioning on the maintenance assessment, and thus the corresponding maintenance feature vector can more accurately reflect the maintenance personnel's capabilities. Therefore, the weights of the weighted summation are related to the positioning accuracy of the positioning feature vector. The weight of the first maintenance assessment value of the maintenance feature vector corresponding to a positioning feature vector with higher positioning accuracy can be set higher to make the determined maintenance assessment value more accurate.

[0084] In some embodiments of this specification, maintenance assessment values ​​across multiple dimensions are determined based on gas user call and inquiry data, thereby adjusting the work order processing scope of the maintenance personnel to be assessed. This ensures that the work order processing scope of the maintenance personnel to be assessed is more closely matched with their capabilities, improving maintenance quality, work order processing efficiency, and gas user satisfaction.

[0085] Figure 4This is an exemplary flowchart illustrating the generation of multi-dimensional positioning assessment values ​​for an agent to be evaluated, according to some embodiments of this specification. In some embodiments, process 400 may be executed by a smart gas management platform. Figure 4 As shown, process 400 includes the following steps 410-420.

[0086] Step 410: Generate second data information from the call consultation data information.

[0087] The second data information refers to data information related to the location capabilities of the agent being evaluated. In some embodiments, the second data information may include relevant data generated by the agent being evaluated during fault location within a target time period.

[0088] The relevant data information generated during fault location refers to the data generated during the fault location process of one or more work orders handled by the agent being evaluated within a target time period. For example, the relevant data information generated during fault location may include the number of features extracted from the user by the agent being evaluated during each repair, the duration of the call communication between the agent and the user, the ambiguity of the model output, customer complaint status (e.g., 1 indicates a complaint, 2 indicates no complaint), and the distribution of gas faults. For a definition of gas fault distribution, please refer to [link to definition]. Figure 3 The relevant descriptions are omitted here. For the definition of model output ambiguity, please refer to the relevant description below; they will not be repeated here.

[0089] The number of features extracted from the user side by the agent being evaluated refers to the amount of gas-related data extracted by the agent through communication with the gas user. For example, the number of features extracted from the user side by the agent being evaluated could be 1, 2, or 3, etc.

[0090] In some embodiments, the intelligent gas management platform can filter relevant data information generated by the agent to be evaluated in fault location within a target time period from the call consultation data information as the second data information.

[0091] Step 420: Based on the second data information, generate positioning evaluation values ​​in multiple dimensions.

[0092] In some embodiments, the intelligent gas management platform can generate one or more location feature vectors for the agent to be evaluated based on the second data information. Then, based on the one or more location feature vectors, a multi-dimensional location evaluation value is generated.

[0093] A location feature vector is a vector constructed based on second data information. In some embodiments, one location feature vector can correspond to one fault location.

[0094] In some embodiments, the smart gas management platform can construct feature vectors based on the second data information in various ways. For example, the smart gas management platform can construct location feature vectors (b1, b2, b3, b4, b5) based on the second data information. Here, b1 can represent the number of features extracted from the user by the agent being evaluated in a single maintenance request; b2 is the call communication duration between the agent and the user; b3 is the model output ambiguity; b4 is the customer complaint status (e.g., 1 indicates a complaint, 2 indicates no complaint); and b5 is the gas fault distribution. For the definition of model output ambiguity, please refer to [link to relevant documentation]. Figure 5 The corresponding descriptions are not repeated here. For the definition of gas fault distribution, please refer to [link to relevant documentation]. Figure 3 The details and their corresponding descriptions will not be elaborated here.

[0095] In some embodiments, the intelligent gas management platform can calculate a first positioning evaluation value and positioning accuracy for each positioning feature vector in each dimension based on one or more positioning feature vectors. Then, it can perform a weighted summation of the multiple first positioning evaluation values ​​calculated for all positioning feature vectors in each dimension to generate a multi-dimensional positioning evaluation value.

[0096] In some embodiments, the dimension of the localization feature vector is determined based on the localization complexity corresponding to that localization task. For example, the dimension of the localization feature vector corresponding to a simple localization task is the simple localization task dimension, the dimension of the localization feature vector corresponding to a medium-difficulty localization task is the medium-difficulty localization task dimension, and the dimension of the localization feature vector corresponding to a complex localization task is the complex localization task dimension.

[0097] Location complexity refers to the difficulty of locating the type of gas fault for each fault location. For example, location complexity can include simple location tasks, medium-difficulty location tasks, and complex location tasks.

[0098] In some embodiments, the positioning complexity corresponding to this positioning is generated based on the model output ambiguity corresponding to the positioning feature vector and the gas fault distribution.

[0099] Model output ambiguity is a value reflecting the degree of ambiguity of the fault types generated by the gas fault prediction model. In some embodiments, the larger the sum of the differences between the maximum value and other element values ​​in the multidimensional probability vector output by the gas fault prediction model, the lower the ambiguity of the gas fault prediction model. In some embodiments, the sum of the differences between the maximum value and other element values ​​in the multidimensional probability vector output by the gas fault prediction model can be calculated, and then the model output ambiguity can be determined. For example, if the gas fault prediction model output vector is (0.05, 0.05, 0.8, 0.05, 0.05), then the ambiguity of the model output is determined to be y1 = (0.8 - 0.05) + (0.8 - 0.05) + (0.8 - 0.05) + (0.8 - 0.05) = 3. In this output case, the probability of the third type of fault occurring is 0.8, which is much higher than other types, and the ambiguity of the gas fault prediction model output is low. For example, if the output vector of a gas fault prediction model is (0.2, 0.3, 0.2, 0.1, 0.2), then the ambiguity of the model output is y2 = (0.3-0.2) + (0.3-0.3) + (0.3-0.2) + (0.3-0.1) + (0.3-0.2) = 0.5. In this output scenario, the probabilities of various faults are relatively close, making it difficult to determine the specific fault, resulting in high ambiguity in the gas fault prediction model output.

[0100] In some embodiments, a second lookup table can be established based on historical data to determine the location complexity corresponding to different model output ambiguities and gas fault distributions. Then, by searching the second lookup table, the location complexity corresponding to different model output ambiguities and gas fault distributions is determined, thereby determining the dimension of the location feature vector.

[0101] In some embodiments, the dimension of the location feature vector can be generated based on clustering. Elements in the cluster feature vector can include model output ambiguity, gas fault distribution, user-side gas characteristic data, and gas user type. The number of clusters is a preset value (e.g., three, four, etc.).

[0102] User-side gas characteristic data refers to the gas usage characteristics extracted by the agent in question through communication with the gas user. For example, user-side gas characteristic data may include the appearance of the gas flame, whether there are any abnormal sounds during gas usage, whether there are any unusual odors during gas usage, and the ambient temperature during gas usage.

[0103] Gas user type refers to the classification of gas users. For example, gas user types can include residential gas users, commercial gas users, and industrial gas users.

[0104] In some embodiments, the dimension of the location feature vector can be generated by clustering the clustering feature vectors based on model output ambiguity, gas fault distribution, gas user gas usage characteristics, and gas user type (e.g., k-means clustering, mean-shift clustering, etc.). After clustering, the location feature vector corresponding to the clustering feature vector in each cluster belongs to one dimension.

[0105] In some embodiments of this specification, clustering feature vectors based on clustering can quickly determine the dimension of the localization feature vectors.

[0106] The first positioning assessment value refers to the positioning assessment value corresponding to a single fault location by the operator being evaluated.

[0107] Location accuracy refers to the degree of closeness between the predicted gas fault type determined by the operator being assessed and the actual gas fault type in a single fault location operation.

[0108] In some embodiments, the intelligent gas management platform can obtain the first location assessment value using various calculation methods. For example, the calculation formula for the first location assessment value can be h = c1 × b1 - c2 × b2 - c3 × b3 - c4 × b4 - c5 × b5. Where b1 is the number of features extracted from the user side by the agent to be assessed during a maintenance call, b2 is the call communication duration between the agent and the user, b3 is the model output fuzziness, b4 is the customer complaint status (e.g., 1 indicates a complaint, 2 indicates no complaint), b5 is the gas fault distribution, and c1, c2, c3, c4, and c5 are preset coefficients. These preset coefficients can be set by those skilled in the art based on experience. Another example is that the calculation formula for the first location assessment value can be h = b3 × (c1 × b1 - c2 × b2 - c4 × b4 - c5 × b5).

[0109] In some embodiments, the smart gas management platform can determine user-side gas characteristic data, gas composition characteristics, gas entry characteristics, and upstream gas transportation characteristics based on second data information. Then, these user-side gas characteristic data, gas composition characteristics, gas entry characteristics, and upstream gas transportation characteristics are input into a gas fault prediction model. The gas fault prediction model processes these user-side gas characteristic data (gas composition characteristics, gas entry characteristics, and upstream gas transportation characteristics) and outputs a predicted gas fault type. This gas fault prediction model is a machine learning model. Finally, based on the predicted gas fault type and the actual gas fault type, a location accuracy is generated. For more details on this section, please see below. Figure 5 Its description will not be repeated here.

[0110] In some embodiments of this specification, multiple dimensions of location assessment values ​​are determined based on gas user call and inquiry data, thereby adjusting the work order processing scope of the agent to be assessed. This ensures that the work order processing scope of the agent to be assessed is more closely matched with their capabilities, enhancing location accuracy. This helps the maintenance personnel to be assessed to perform efficient and rapid repairs on accurately located gas faults, thereby improving work order processing efficiency and increasing gas user satisfaction.

[0111] Figure 5 This is an exemplary flowchart of a method for generating positioning accuracy according to some embodiments of this specification.

[0112] In some embodiments, process 500 can be executed by a smart gas management platform. For example... Figure 5 As shown, process 500 includes the following steps 510-530.

[0113] Step 510: Based on the second data information, determine the user-side gas characteristic data, gas composition characteristics, gas entry characteristics, and upstream gas transportation characteristics.

[0114] In some embodiments, user-side gas characteristic data can be multidimensional data with preset dimensions. In some embodiments, the agent to be evaluated can ask the gas user questions based on visual (e.g., the appearance of the gas flame), auditory (e.g., whether there are abnormal sounds during gas use), olfactory (e.g., whether there are unusual odors during gas use), and tactile (e.g., the ambient temperature during gas use). Based on the user's answers, user-side gas characteristic data is constructed.

[0115] The composition characteristics of gas refer to the components of gas. In some embodiments, the composition of gas can be analyzed based on existing commonly used gas composition analysis methods (e.g., gas chromatography).

[0116] Gas entry characteristics refer to the pressure, flow rate, and temperature of gas at multiple points along the gas entry route. In some embodiments, the smart gas management platform can directly obtain gas entry characteristics from second data information.

[0117] Upstream gas transportation characteristics refer to the pressure, flow rate, and temperature of gas at multiple points along the upstream gas transportation route. In some embodiments, the intelligent gas management platform can directly obtain upstream gas transportation characteristics from the second data information.

[0118] Step 520: Input the user-side gas characteristic data, gas composition characteristics, gas entry characteristics, and upstream gas transportation characteristics into the gas fault prediction model. Use the gas fault prediction model to process the user-side gas characteristic data, gas composition characteristics, gas entry characteristics, and upstream gas transportation characteristics, and output the predicted gas fault type. The gas fault prediction model is a machine learning model.

[0119] In some embodiments, the gas fault prediction model can determine the predicted gas fault type based on user-side gas characteristic data, gas composition characteristics, gas entry characteristics, and upstream gas transportation characteristics. In some embodiments, the gas fault prediction model can be a machine learning model, such as a neural network model (NN), a deep neural network model (DNN), or any combination thereof.

[0120] In some embodiments, the input to the gas fault prediction model may include user-side gas characteristic data, gas composition characteristics, gas delivery characteristics, and upstream gas transportation characteristics. For example, the input to the gas fault prediction model may be a vector constructed based on user-side gas characteristic data, gas composition characteristics, gas delivery characteristics, and upstream gas transportation characteristics.

[0121] In some embodiments, the input to the gas fault prediction model may further include first correlation data. The first correlation data may include gas user usage characteristic information. Please refer to the above text for a definition of gas user usage characteristic information. Figure 2 The details and their corresponding descriptions will not be elaborated here.

[0122] In some embodiments, the output of the gas fault prediction model can be a prediction of the type of gas fault.

[0123] In some embodiments, the gas fault prediction model can be trained based on multiple labeled training samples.

[0124] Training samples may include user-side gas characteristic data, gas composition characteristics, gas delivery characteristics, and upstream gas transportation characteristics of historical gas users. Training labels may include known gas fault types of historical gas users. In some embodiments, training labels can be obtained from historical data stored in a smart gas data center or through manual annotation.

[0125] In some embodiments, the training samples may also include first association data of historical gas users.

[0126] In some embodiments, multiple labeled training samples can be input into an initial gas fault prediction model, and a loss function can be constructed using the labels and the results of the initial gas fault prediction model. Based on the loss function, the parameters of the initial gas fault prediction model are iteratively updated using gradient descent or other methods to obtain a trained gas fault prediction model. Model training is complete when preset conditions are met, resulting in a trained gas fault prediction model. These preset conditions may include loss function convergence, the number of iterations reaching a threshold, etc.

[0127] Step 530: Based on the predicted gas fault type and the actual gas fault type, generate the location accuracy.

[0128] Actual gas fault type refers to the type of gas fault actually confirmed by the maintenance personnel on-site during maintenance, based on historical data.

[0129] In some embodiments, the intelligent gas management platform can use the negative of the Euclidean distance between the predicted gas fault type obtained from the gas fault prediction model and the actual gas fault type corresponding to the current maintenance as the positioning accuracy. For example, if the output vector of the gas fault prediction model is (0.05, 0.05, 0.8, 0.05, 0.05), and the vector of the actual gas fault type corresponding to the current maintenance is (0, 0, 1, 0, 0), then the positioning accuracy is... For example, if the output vector of the gas fault prediction model is (0.2, 0.3, 0.2, 0.1, 0.2), and the vector of the actual gas fault type corresponding to this repair is (0, 1, 0, 0, 0), then the location accuracy is...

[0130] In some embodiments, the positioning accuracy can also be correlated with the model output ambiguity corresponding to the positioning feature vector. For example, the lower the model output ambiguity, the lower the positioning accuracy.

[0131] In some embodiments of this specification, lower model output ambiguity indicates more accurate fault identification by the model. If a positioning error still occurs, it suggests a higher probability that the features extracted by the operator are incorrect, causing the model to obtain incorrect results based on flawed input, thus reducing positioning accuracy. By considering the model output ambiguity corresponding to the feature vector in this positioning, the determined positioning accuracy is made more precise.

[0132] In some embodiments of this specification, the gas fault prediction model can more quickly and accurately predict the type of gas fault, thereby determining the accurate location accuracy.

[0133] In some embodiments, the maintenance management device of the smart gas call center includes a processor and a memory; the memory is used to store instructions, which, when executed by the processor, cause the device to implement the maintenance management method of the smart gas call center.

[0134] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0135] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A maintenance management method for a smart gas call center, characterized in that, This is implemented using an IoT system for maintenance management based on a smart gas call center. The IoT system includes a smart gas user platform, a smart gas service platform, and a smart gas management platform that interact sequentially. The method is executed by a processor in the smart gas management platform and includes: The smart gas service platform obtains gas user call and inquiry data information based on the smart gas user platform. Based on the call consultation data, a multi-dimensional positioning evaluation value is generated for the agent to be evaluated, and the agent to be evaluated locates the gas fault type based on the call consultation data. The process of generating multi-dimensional location assessment values ​​for the agent to be evaluated based on the call consultation data includes: A second data information is generated from the call consultation data information, the second data information including relevant data information generated by the fault location of the agent to be evaluated within the target time period; Based on the second data information, the positioning evaluation values ​​of the multiple dimensions are generated; The step of generating the positioning evaluation values ​​of the multiple dimensions based on the second data information includes: generating one or more positioning feature vectors of the agent to be evaluated based on the second data information; and generating the positioning evaluation values ​​of the multiple dimensions based on the one or more positioning feature vectors. Each of the multiple dimensions corresponds to a positioning complexity, and one positioning feature vector corresponds to one fault location. Generating positioning evaluation values ​​for the multiple dimensions based on the one or more positioning feature vectors includes: Based on the one or more positioning feature vectors, a first positioning evaluation value and positioning accuracy are calculated for each positioning feature vector in each dimension; Multiple first positioning evaluation values ​​calculated from all positioning feature vectors under each dimension are weighted and summed to generate positioning evaluation values ​​for the multiple dimensions. The weights of the weighted summation are related to the corresponding positioning accuracy. The dimension of the positioning feature vector is determined based on the positioning complexity corresponding to this positioning. The positioning complexity corresponding to this positioning is generated based on the model output ambiguity and gas fault distribution corresponding to this positioning feature vector. The positioning accuracy is determined based on the predicted gas fault type and the actual gas fault type. The predicted gas fault type is obtained by inputting user-side gas characteristic data, gas composition characteristics, gas entry characteristics, and gas upstream transportation characteristics into the gas fault prediction model for processing and output. The user-side gas characteristic data refers to the data extracted by the operator to be evaluated through communication with gas users. The gas fault prediction model is a machine learning model. The dimension of the location feature vector is generated based on clustering, and the elements in the clustering feature vector include the model output ambiguity, the gas fault distribution, the user-side gas feature data, and the gas user type. Based on the call consultation data, a multi-dimensional maintenance assessment value is generated for the maintenance personnel to be evaluated, and the maintenance personnel to be evaluated perform maintenance based on the gas fault type; and Based on the maintenance assessment values ​​and location assessment values ​​of the multiple dimensions, the work order processing scope of the maintenance personnel and the call center staff to be assessed is adjusted.

2. The method according to claim 1, characterized in that, The Internet of Things system also includes a smart gas sensor network platform and a smart gas object platform that interact sequentially.

3. The method according to claim 1, characterized in that, The call consultation data information also includes first associated data, which includes at least the gas user's gas usage characteristic information.

4. The method according to claim 1, characterized in that, The process of generating multi-dimensional maintenance evaluation values ​​for the maintenance personnel to be evaluated based on the call consultation data includes: First data information is generated from the call consultation data information, and the first data information includes relevant data information generated by the maintenance personnel to be evaluated during the target time period. Based on the first data information, maintenance assessment values ​​for the multiple dimensions are generated; The step of generating the maintenance assessment values ​​across multiple dimensions based on the first data information includes: Based on the first data information, generate one or more maintenance feature vectors for the maintenance personnel to be evaluated; and Based on the one or more maintenance feature vectors, maintenance evaluation values ​​of the multiple dimensions are generated.

5. The method according to claim 4, characterized in that, Each of the multiple dimensions corresponds to a maintenance complexity, and one maintenance feature vector corresponds to one maintenance operation. Generating maintenance evaluation values ​​for the multiple dimensions based on the one or more maintenance feature vectors includes: Based on the one or more maintenance feature vectors, a first maintenance evaluation value is calculated for each maintenance feature vector under each dimension; and The maintenance evaluation values ​​for the multiple first maintenance evaluation values ​​calculated from all maintenance feature vectors under each dimension are weighted and summed to generate maintenance evaluation values ​​for the multiple dimensions. The dimension of the maintenance feature vector is determined based on the maintenance complexity corresponding to the maintenance, and the maintenance complexity corresponding to the maintenance is generated based on the gas fault distribution and gas pipeline complexity corresponding to the maintenance.

6. A smart gas call center maintenance management IoT system, characterized in that, It includes a smart gas user platform, a smart gas service platform, and a smart gas management platform that interact sequentially. The smart gas management platform is used for: The smart gas service platform obtains gas user call and inquiry data information based on the smart gas user platform. Based on the call consultation data, a multi-dimensional maintenance assessment value is generated for the maintenance personnel to be evaluated, and the maintenance personnel to be evaluated perform maintenance based on the type of gas fault. Based on the call consultation data, a multi-dimensional positioning evaluation value is generated for the agent to be evaluated, and the agent to be evaluated locates the gas fault type based on the call consultation data. The process of generating multi-dimensional location assessment values ​​for the agent to be evaluated based on the call consultation data includes: A second data information is generated from the call consultation data information, the second data information including relevant data information generated by the fault location of the agent to be evaluated within the target time period; Based on the second data information, the positioning evaluation values ​​of the multiple dimensions are generated; The step of generating the positioning evaluation values ​​of the multiple dimensions based on the second data information includes: generating one or more positioning feature vectors of the agent to be evaluated based on the second data information; and generating the positioning evaluation values ​​of the multiple dimensions based on the one or more positioning feature vectors. Each of the multiple dimensions corresponds to a positioning complexity, and one positioning feature vector corresponds to one fault location. Generating positioning evaluation values ​​for the multiple dimensions based on the one or more positioning feature vectors includes: Based on the one or more positioning feature vectors, a first positioning evaluation value and positioning accuracy are calculated for each positioning feature vector in each dimension; Multiple first positioning evaluation values ​​calculated from all positioning feature vectors under each dimension are weighted and summed to generate positioning evaluation values ​​for the multiple dimensions. The weights of the weighted summation are related to the corresponding positioning accuracy. The dimension of the positioning feature vector is determined based on the positioning complexity corresponding to this positioning. The positioning complexity corresponding to this positioning is generated based on the model output ambiguity and gas fault distribution corresponding to this positioning feature vector. The positioning accuracy is determined based on the predicted gas fault type and the actual gas fault type. The predicted gas fault type is obtained by inputting user-side gas characteristic data, gas composition characteristics, gas entry characteristics, and gas upstream transportation characteristics into the gas fault prediction model for processing and output. The user-side gas characteristic data refers to the data extracted by the operator to be evaluated through communication with gas users. The gas fault prediction model is a machine learning model. The dimension of the location feature vector is generated based on clustering, and the elements in the clustering feature vector include the model output ambiguity, the gas fault distribution, the user-side gas feature data, and the gas user type. Based on the maintenance assessment values ​​and location assessment values ​​of the multiple dimensions, the work order processing scope of the maintenance personnel and the call center staff to be assessed is adjusted.

7. A maintenance management device for a smart gas call center, characterized in that, The device includes at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is configured to execute at least a portion of the computer instructions to implement the method as described in any one of claims 1 to 5.

Images