Intelligent matching method and system for fault cases applied to operation and maintenance technical services

Abstract

This application provides a method and system for intelligent fault case matching applied to the field of operation and maintenance technical services. It involves collecting relevant data from intelligent equipment in chain stores to construct a current fault spatiotemporal evolution model; extracting complete intervention process data from historical fault cases and encoding them to generate an effectiveness coding package; then performing dynamic resource effect balancing and adaptation calculations to determine the intervention effectiveness matching degree; generating a simulation result report based on the intervention effectiveness matching degree; and finally, elastically adjusting and testing cases that meet the threshold to generate a target matching fault case set. This invention comprehensively considers the spatiotemporal evolution of faults and intervention effectiveness, enabling accurate fault case matching and improving operation and maintenance efficiency and quality.

Description

Technical Field

[0001] This application relates to the field of operation and maintenance technical services, and more specifically, to a method and system for intelligent matching of fault cases applied to operation and maintenance technical services. Background Technology

[0002] In the field of operation and maintenance technical services, troubleshooting smart devices in chain stores is a complex and critical issue. Chain stores are widely distributed, and the types of smart devices vary greatly in their operating environments. Once a fault occurs, it is crucial to quickly and accurately match the appropriate fault case to develop an effective intervention plan.

[0003] Currently, traditional fault case matching methods are mainly based on simple fault phenomenon descriptions and experience-based judgments. However, these methods have several shortcomings. Firstly, they do not fully consider the evolution of faults across different time and spatial dimensions. Faults in smart devices in chain stores are often not isolated events; their state changes over time and may be affected by different factors in different spatial locations within the store. Relying solely on simple fault phenomenon descriptions makes it difficult to comprehensively and accurately grasp the essence and development trend of the fault. Secondly, existing methods lack a comprehensive consideration of intervention effectiveness when evaluating the matching degree between historical fault cases and current faults. The intervention process for historical fault cases involves various resource inputs and operational steps, and the intervention effectiveness varies significantly between different cases. Traditional methods cannot effectively measure the actual effect of historical cases in the current fault scenario, leading to potentially unsuitable matched cases, thus affecting the efficiency and quality of fault handling and increasing maintenance costs. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method and system for intelligent matching of fault cases applied to operation and maintenance technical services.

[0005] According to a first aspect of this application, a fault case intelligent matching method for operation and maintenance technical services is provided, the method comprising:

[0006] Collect runtime sequence data, spatial distribution data, and store environment-related data of intelligent devices in chain stores, and construct a spatiotemporal evolution model of the current fault. The spatiotemporal evolution model includes the state change curve of intelligent devices under different time granularities, the spatial influence path within the store, and the intensity of environmental factors.

[0007] Complete intervention process data for each historical fault case is extracted from the fault case database of the technical center. Combined with the large model knowledge base and robot-assisted decision-making logic, intervention effectiveness is encoded for the historical fault cases, generating an effectiveness encoding package for each historical fault case. The complete intervention process data includes the on-site engineer service operation sequence, service network resource input trajectory, and fault mitigation effect sequence. The effectiveness encoding package includes the spatiotemporal adaptation characteristics of the intervention operation, the dynamic distribution characteristics of service resource consumption, and the stage effectiveness characteristics of fault mitigation.

[0008] The spatiotemporal evolution model of the current fault is dynamically balanced and adapted with the efficiency coding packages of each historical fault case. The intervention efficiency matching degree between each historical fault case and the current fault is calculated. The intervention efficiency matching degree is generated based on the matching of the store's smart equipment repair resource demand and on-site engineer scheduling demand at each stage in the spatiotemporal evolution model with the service resource supply capacity and engineer response capacity at the corresponding stage in the efficiency coding package, as well as the matching of the fault status at each stage in the spatiotemporal evolution model with the mitigation effect at the corresponding stage in the efficiency coding package.

[0009] Based on the intervention effectiveness matching degree, the intervention effectiveness simulation is carried out on historical failure cases. The execution process of the intervention plan for each historical failure case in the current failure scenario is simulated. The service resource consumption nodes, failure mitigation nodes and stage goal achievement nodes are recorded in the simulation process, and the simulation result report is generated, including the robot-assisted support logic of the technical center, the scheduling of the nearest service outlets by on-site engineers based on the physical positioning system, and the remote pre-intervention operation of store smart devices.

[0010] For historical fault cases whose simulation results report meets the preset resource effect balance threshold, elastic intervention and adjustment tests are conducted to generate a target matching fault case set for the current fault. The target matching fault case set includes the complete intervention plan, performance coding data and engineer scheduling adaptation records for the corresponding historical fault cases.

[0011] According to a second aspect of this application, a fault case intelligent matching system for operation and maintenance technical services is provided. The fault case intelligent matching system for operation and maintenance technical services includes a machine-readable storage medium and a processor. The machine-readable storage medium stores machine-executable instructions. When the processor executes the machine-executable instructions, the fault case intelligent matching system for operation and maintenance technical services implements the aforementioned fault case intelligent matching method for operation and maintenance technical services.

[0012] Based on any of the above aspects, the technical effect of this application is as follows:

[0013] By collecting runtime sequence data, spatial distribution data, and store environment-related data of intelligent devices in chain stores, a spatiotemporal evolution model of the current fault is constructed. This model can characterize the changes in the state of intelligent devices, the spatial impact path within the store, and the intensity of environmental factors at different time granularities. Complete intervention process data of historical fault cases are extracted from the fault case library of the technology center and their intervention effectiveness is encoded to generate an effectiveness coding package. This package details the spatiotemporal adaptation characteristics of the intervention operation, the dynamic distribution characteristics of service resource consumption, and the stage effectiveness characteristics of fault mitigation, allowing for a quantitative presentation of the intervention effectiveness of historical fault cases. The spatiotemporal evolution model of the current fault is dynamically balanced and adapted with the effectiveness coding package of historical fault cases to calculate the intervention effectiveness matching degree. This allows for a comprehensive evaluation of the compatibility between historical cases and the current fault from multiple dimensions, ensuring the accuracy of the matching. Based on the intervention effectiveness matching degree, intervention effectiveness simulation and deduction are performed, generating a deduction result report that intuitively presents the execution process and effects of historical case intervention solutions in the current scenario. By conducting flexible intervention and adjustment tests on historical fault cases that meet preset thresholds, a set of target-matched fault cases is generated, providing a comprehensive intervention plan and related data records that are highly targeted and feasible for the current fault. This effectively improves the efficiency and quality of fault handling in operation and maintenance technical services and reduces operation and maintenance costs. Attached Figure Description

[0014] Figure 1 A flowchart illustrating the intelligent fault case matching method for operation and maintenance technical services provided in this application embodiment is shown.

[0015] Figure 2 This paper illustrates a schematic diagram of the component structure of an intelligent fault case matching system for operation and maintenance technical services provided in an embodiment of this application. Detailed Implementation

[0016] Figure 1 This paper illustrates a flowchart of a fault case intelligent matching method and system for operation and maintenance technical services provided in an embodiment of this application. The detailed steps include:

[0017] Step S110: Collect runtime sequence data, spatial distribution data of smart devices in chain stores, and related data of store environment, and construct a spatiotemporal evolution model of the current fault.

[0018] This embodiment uses the handling of intelligent equipment failures in a chain restaurant brand store as a scenario. The store is equipped with various intelligent devices such as air conditioning systems, information publishing terminals, and IoT control modules. When the intelligent devices in the store malfunction and affect normal operations, it is necessary to initiate the collection of relevant data and, based on the data, construct a spatiotemporal evolution model that reflects the development and changes of the current failure in time and space.

[0019] Step S111: Collect the operating parameters of the air conditioning equipment in the chain stores, the online status of the information release terminal, and the command response data of the Internet of Things control module at preset time intervals to form the equipment operation sequence data.

[0020] In this chain of restaurants, fixed data collection intervals are pre-set. For air conditioning equipment, the collected operating parameters include the compressor's operating status, condenser pressure, evaporator temperature, and fan speed. The information publishing terminal determines its online status through communication with the server, recording the time of the last successful communication between the terminal and the server, as well as the duration of the terminal's offline state. The IoT control module records the code of each instruction, the time of instruction issuance, the feedback code after instruction execution, and the response delay time from instruction issuance to completion. The collected parameters are categorized according to the different types and numbers of the equipment and arranged in chronological order to form equipment runtime sequence data. For example, for air conditioning equipment numbered KT-01, its runtime sequence data will record the compressor status, condenser pressure, and other parameters at each time point in chronological order.

[0021] Step S112: Combine the service network distribution map system to record the real-time location of engineers around the faulty store, the service network resource reserve status, mark the optimal route for engineers to go to the faulty store and the network resource allocation nodes, and form service resource spatial distribution data.

[0022] The service network distribution map system stores the geographical location information of all service outlets of the chain restaurant brand, as well as relevant information about engineers within a certain range around the faulty store. Engineers' location information is acquired and updated in real time to the map system using their personal positioning devices. The resource reserve status of each service outlet includes the types and quantities of repair tools, spare parts for various smart devices, and the quantity of spare equipment. Based on the real-time location of engineers and the resource reserve status of service outlets, the system's route planning function is used to calculate the optimal route for each engineer to the faulty store, taking into account factors such as real-time traffic conditions, road length, and traffic rules. Simultaneously, transit points that may be encountered during resource allocation, i.e., resource allocation nodes, are identified. Integrating the real-time location of engineers, the resource reserve status of service outlets, the optimal route for engineers to the faulty store, and resource allocation nodes forms the spatial distribution data of service resources.

[0023] Step S113: Collect data on temperature and humidity, customer flow density, and power supply stability in the store. The collection frequency should be synchronized with the data acquisition unit of the equipment. Record the time correlation points between changes in environmental parameters and changes in the fault status of smart devices to form environmental correlation data. The correlation point is determined based on the fact that the change in environmental parameters exceeds the preset threshold of the technical center and the corresponding change in the fault status of the equipment occurs.

[0024] The store is equipped with temperature and humidity sensors, customer flow cameras, and power supply monitoring instruments. These devices collect data at the same time intervals as the equipment's operational sequence data collection. The temperature and humidity sensors collect temperature and relative humidity data from different areas of the store; the customer flow cameras analyze the captured images to calculate the real-time number of customers; and the power supply monitoring instruments record data on power supply stability, such as voltage fluctuations, current levels, and whether power outages have occurred. During data collection, if the change in a certain environmental parameter exceeds a pre-set threshold by the technology center, and the fault status of the smart device changes accordingly after this change, this point in time is recorded as the time correlation point between the environmental parameter change and the smart device's fault status change. All collected environmental parameter data and recorded time correlation points are integrated to form environmental correlation data.

[0025] Step S114: Classify the equipment runtime sequence data according to equipment type. Each type of equipment corresponds to a set of time series parameter sequences. Perform trend analysis on each set of time series parameter sequences to extract the parameter anomaly start time, anomaly change rate and anomaly stabilization stage. Determine the fault state change curve for each type of equipment. The horizontal axis of the fault state change curve is time, and the vertical axis is the parameter anomaly degree. The parameter anomaly degree is calculated based on the deviation ratio between the actual parameter value and the equipment's normal operating range preset by the technical center.

[0026] The equipment runtime sequence data is categorized according to different equipment types, such as air conditioning equipment, information publishing terminals, and IoT control modules, so that each equipment type corresponds to a set of time-series parameters containing various operating parameters of the equipment. Trend analysis is performed on each set of time-series parameter sequences. By observing the changes in parameter values ​​over time, the moment when the parameter begins to show anomalies is determined, i.e., the parameter anomaly onset moment; the rate of change of the parameter from the onset of anomaly to the point where the anomaly reaches its maximum value is calculated, i.e., the anomaly change rate; and the stage in which the parameter anomaly level remains relatively stable, i.e., the anomaly stability stage. Based on the information extracted above, a fault state change curve is plotted with time as the horizontal axis and parameter anomaly level as the vertical axis. The parameter anomaly level is calculated by subtracting the lower limit of the normal operating range preset by the technical center from the actual value of the parameter to obtain the parameter deviation value; then dividing the deviation value by the difference between the upper and lower limits of the normal operating range preset by the technical center, the resulting ratio is the parameter anomaly level.

[0027] Step S115: Perform path analysis on the spatial distribution data of service resources, extract the starting location of engineers, transfer nodes of service outlets and locations of faulty stores, calculate the travel time, resource allocation time and response speed between each node, mark the resource reserve characteristics or road condition factors at each node, and construct a service resource scheduling path map. Different line styles are used in the service resource scheduling path map to represent scheduling paths with different response speeds.

[0028] Path analysis is performed on the spatial distribution data of service resources to extract the engineer's starting location, transit nodes of service outlets in the resource allocation process, and the specific location of the faulty store. Based on the geographical location information of each node, combined with factors such as road traffic conditions and vehicle speed, the travel time between nodes is calculated, i.e., the time required to reach another node from one node; the time required to allocate resources from the service outlet to the faulty store is calculated, i.e., the resource allocation time; the response speed is measured by the sum of the travel time and the resource allocation time. Simultaneously, the resource reserve characteristics at each node are marked, such as a service outlet having a large reserve of air conditioning equipment repair spare parts, or a node experiencing frequent traffic congestion. Based on the above information, a service resource scheduling path map is constructed. In this map, different line styles are used to represent scheduling paths with different response speeds; for example, solid lines represent scheduling paths with faster response speeds, dashed lines represent scheduling paths with medium response speeds, and dotted lines represent scheduling paths with slower response speeds.

[0029] Step S116: Perform factor correlation analysis on the environmental correlation data, count the correlation frequency between the change of each environmental parameter and the change of fault state of the intelligent device, calculate the influence strength of each environmental parameter on the change of fault state, the influence strength is determined based on the product of the correlation frequency and the magnitude of the change of fault state, and form an environmental factor influence strength table, which includes environmental parameter type, influence strength value and correlation time record.

[0030] Factor correlation analysis was performed on changes in environmental parameters and changes in the fault states of intelligent devices in the environmental data. The frequency of correlation was calculated as the number of times the fault state of the intelligent device changed when each environmental parameter (such as temperature, humidity, passenger flow density, power supply stability, etc.) changed. The magnitude of the fault state change refers to the degree of change in the fault state of the intelligent device from a normal state to an abnormal state. For example, the change in temperature at the air outlet of an air conditioner from the normal range to an abnormal temperature is the magnitude of the fault state change. The correlation frequency of each environmental parameter was multiplied by the corresponding magnitude of the fault state change to obtain the strength of the effect of that environmental parameter on the change in the fault state of the intelligent device. The types of environmental parameters, their corresponding strength values, and the time records of the correlation between environmental parameter changes and equipment fault state changes were compiled into a table, forming a table of the strength of environmental factors.

[0031] Step S1161: Extract all environmental parameter change records and corresponding smart device fault status change records from the environmental association data, and establish an environment-fault association data table. Each row in the environment-fault association data table includes the environmental parameter type, environmental parameter change time, environmental parameter change magnitude, corresponding fault status change time, fault status change magnitude, and associated device type.

[0032] The environmental correlation data is traversed, extracting all records of environmental parameter changes and corresponding records of smart device fault state changes. For each environmental parameter change record, the type of environmental parameter (e.g., temperature, humidity), the specific time of the change, and the magnitude of the change (i.e., the difference before and after the change) are recorded. For the corresponding smart device fault state change record, the specific time of the fault state change, the magnitude of the change, and the type of device that failed (e.g., air conditioning equipment, information publishing terminal) are recorded. This information is then organized into a table according to a specific format to create an environmental-fault correlation data table, where each row contains information related to an environmental parameter change record and its corresponding smart device fault state change record.

[0033] Step S1162: Group the records in the environment-fault association data table according to the environmental parameter type, with each group corresponding to all associated records for one type of environmental parameter.

[0034] The records in the environment-fault association data table are grouped according to the type of environmental parameter. All associated records belonging to the same environmental parameter type are grouped into the same group. For example, all associated records related to temperature parameter changes are grouped into one group, all associated records related to humidity parameter changes are grouped into another group, and so on. In this way, each group of associated records corresponds to the relationship between all environmental parameter changes and smart device fault state changes for a specific environmental parameter.

[0035] Step S1163: For each set of associated records, divide the environmental parameter change range and fault state change range of each record by the corresponding normal change benchmark value preset by the technical center, convert them into dimensionless change rates, and then calculate the ratio of the environmental parameter change rate to the fault state change rate of each record. This ratio reflects the proportion of the impact of a single environmental parameter change on the fault state change.

[0036] For each record in each group of associated records, the normal change baseline value of the environmental parameter and the normal change baseline value of the smart device's fault state, pre-set by the technical center, are obtained. The change range of the environmental parameter is divided by the normal change baseline value to obtain the environmental parameter change rate; the change range of the fault state is divided by the normal change baseline value to obtain the fault state change rate. Then, the ratio of the environmental parameter change rate to the fault state change rate is calculated. This ratio represents the proportion of the impact of the environmental parameter change on the change of the smart device's fault state under the given environmental parameter change.

[0037] Step S1164: Calculate the time difference between the change in environmental parameters and the change in fault status in each group of related records. The time difference is the time when the fault status changes minus the time when the environmental parameters change. Filter records whose time difference is within the preset range of the technical center as valid records with direct correlation.

[0038] For each record in each group of related records, calculate the time difference between the time of change in environmental parameters and the time of change in the fault state of the intelligent device. The calculation method is to subtract the time of change in environmental parameters from the time of change in fault state. Compare the calculated time difference with a time range preset by the technical center. If the time difference is within the preset range, it is considered that there is a direct correlation between the change in environmental parameters and the change in the fault state of the intelligent device in that record, and the record is marked as a valid record; otherwise, it is considered that there is no direct correlation between the two, and the record is invalid.

[0039] Step S1165: Calculate the average influence ratio of each group of valid records, whereby the average influence ratio reflects the average degree of influence of the environmental parameter on the change of fault state.

[0040] For each group of associated records, the influence ratio of each valid record (i.e., the ratio of the environmental parameter change rate to the fault state change rate calculated in step S1163) is added together to obtain the sum of the influence ratios of the valid records in that group. Then, the sum of the influence ratios is divided by the number of valid records in that group to obtain the average influence ratio of the valid records in that group. This average influence ratio reflects the average degree of influence of the environmental parameter on the change of the fault state of the intelligent device under multiple valid associations.

[0041] Step S1166: Count the number of valid records in each group, and calculate the proportion of the number of valid records to the total number of records associated with the environmental parameter. The proportion of the number of valid records to the total number of records associated with the environmental parameter reflects the stability of the association between the environmental parameter and the change in fault state.

[0042] The number of valid records in each group of associated records is counted, and the total number of associated records (including valid and invalid records) corresponding to that group of environmental parameters is also calculated. The number of valid records is divided by the total number of associated records to obtain the ratio of valid records to the total number of associated records. The magnitude of this ratio reflects the stability of the correlation between the environmental parameter and the change in the fault state of the smart device; the higher the ratio, the more stable the correlation between the two.

[0043] Step S1167: Multiply the average influence ratio by the ratio of the number of valid records to the total number of records associated with the environmental parameter to obtain the dimensionless influence strength of the environmental parameter on the change of fault state.

[0044] Multiplying the average influence ratio calculated in step S1165 by the ratio of the number of valid records to the total number of associated records calculated in step S1166, the product is the dimensionless influence strength of the environmental parameter on the change of the fault state of the intelligent device. This influence strength comprehensively considers the average influence of the environmental parameter on the change of the fault state and the stability of the correlation between the two.

[0045] Step S1168: Perform range calibration on the calculated action intensity, and map each action intensity to a preset interval through linear transformation.

[0046] As required by the technical center, a preset range for the intensity of action (e.g., 0 to 100) is set. A linear transformation is performed on the intensity of action for each calculated environmental parameter, ensuring that the transformed intensity values ​​all fall within the preset range. The linear transformation method involves first calculating the maximum and minimum values ​​among all intensity values, and then, based on the upper and lower limits of the preset range, converting each intensity value to the preset range through proportional conversion. This facilitates the comparison and analysis of the intensity of action for different environmental parameters.

[0047] Step S117: Integrate the equipment fault state change curve, service resource scheduling path diagram and environmental factor intensity table to establish the correlation between time and space dimensions. Each time node corresponds to a set of service resource scheduling location and environmental influence intensity data to form a spatiotemporal evolution model of the current fault.

[0048] The previously obtained equipment fault state change curves, service resource scheduling path diagrams, and environmental factor intensity tables are integrated. During this integration, a correlation is established between the time and spatial dimensions. Specifically, for each time point in the fault development process, a corresponding set of service resource scheduling location information (such as the location of engineers and service outlets) and environmental influence intensity data (such as the influence intensity values ​​of various environmental parameters) are associated. Through this method, a spatiotemporal evolution model is formed that comprehensively reflects the current fault's development and changes in time and space. This model can dynamically display the development process of the fault from its occurrence to the present moment, as well as the impact of relevant resources and environmental factors.

[0049] Step S118: Assign a stage identifier to each evolution stage in the spatiotemporal evolution model. The stage identifier includes the stage time range, service resource scheduling range, and main environmental influencing factors.

[0050] Based on the process and characteristics of fault development, the spatiotemporal evolution model is divided into different evolution stages, such as the fault occurrence stage, fault propagation stage, and fault stabilization stage. Each evolution stage is assigned a unique stage identifier, which includes the time range of the stage (i.e., the start and end times), the scope of service resource scheduling within that stage (e.g., the range of engineers and service points involved), and the environmental influencing factors that play a major role in the fault development at that stage (e.g., temperature, humidity). Through these stage identifiers, different stages of fault development can be distinguished and managed, facilitating subsequent analysis and matching of fault cases.

[0051] Step S120: Extract complete intervention process data for each historical failure case from the technical center's failure case library, combine the large model knowledge base and robot-assisted decision-making logic, encode the intervention effectiveness of the historical failure cases, and generate an effectiveness coding package for each historical failure case.

[0052] The technical center's fault case library stores a large number of past intelligent device fault cases and corresponding intervention process data. Complete intervention process data for each historical fault case is extracted from this library. This data includes various operational steps taken during the intervention, service resources used, the time sequence of intervention, problems encountered during the intervention, and their solutions. Simultaneously, combined with relevant knowledge about intelligent device fault handling stored in the large model knowledge base (such as fault diagnosis methods, maintenance experience, and equipment principles) and robot-assisted decision-making logic (such as intervention plan selection rules and resource allocation strategies), the intervention effectiveness of historical fault cases is encoded. During the encoding process, various effectiveness indicators during the intervention process (such as the timeliness of intervention, resource utilization rate, and fault mitigation speed) are transformed into specific coding forms, ultimately generating an effectiveness coding package containing relevant information about the intervention effectiveness for each historical fault case.

[0053] Step S121: Retrieve complete intervention process data for each historical fault case from the intervention process database of the technical center's fault case library. This complete intervention process data includes on-site engineer operation records, service outlet resource input records, and fault mitigation monitoring records. The engineer operation records include the execution time, operation content, operating equipment, and execution engineer number for each operation. The resource input records include the input time, quantity, input outlet, and resource type for each type of service resource. The fault mitigation monitoring records include the time, monitoring indicators, indicator values, and equipment status assessment results for each monitoring session.

[0054] The technical center's fault case database is specifically designed to store historical fault case intervention process data. Complete intervention process data for each historical fault case can be retrieved from this database. The on-site engineer operation record details the specific execution time (accurate to the minute), the specific content of the operation (e.g., checking equipment wiring, replacing equipment parts), the equipment targeted (e.g., the specific serial number of the air conditioning unit), and the engineer's serial number for each operation. The service network resource input record includes the time, quantity, service network number, and resource type (e.g., tool type, equipment model) for each type of service resource (e.g., repair tools, spare parts, etc.) from its input to the fault handling process. Finally, the fault mitigation monitoring record records the time of fault mitigation monitoring during the intervention process, the monitored indicators (e.g., equipment operating parameters, equipment status), the specific values ​​of the monitored indicators, and the assessment results of the equipment status based on the monitoring results (e.g., normal, minor abnormality, severe abnormality).

[0055] Step S122: Organize the engineer's operation records in chronological order, arrange all operations in the order of execution time, extract the execution duration, operation interval, and time correlation between operation and fault status change for each operation, and form an operation execution time sequence table. The operation execution time sequence table includes operation number, execution time, execution duration, operation content, and associated fault status change.

[0056] All operations in the engineer's operation log are arranged and organized in chronological order of their execution time. For each operation, the execution duration (i.e., execution end time minus execution start time) is calculated based on the start and end times. The interval between two adjacent operations is calculated (i.e., the start time of the later operation minus the end time of the previous operation). Simultaneously, the temporal correlation between each operation and the change in fault status is analyzed, i.e., the relationship between the time when the fault status changes after the operation and the operation execution time (e.g., the fault status changes immediately after the operation, or the fault status changes after a period of time). The information obtained from the above organization and extraction (including the operation sequence number assigned to each operation, the operation execution time, the execution duration, the operation content, and the associated fault status changes) is organized into a table according to a specific format to form an operation execution sequence table.

[0057] Step S123: Perform trajectory analysis on the resource input records of service outlets, record the input changes of each resource in chronological order, calculate the input amount, input rate and input outlet distribution of each resource at different intervention stages, and form a resource input trajectory map. In the resource input trajectory map, the horizontal axis is time and the vertical axis is input amount. Different resources are represented by different colored curves.

[0058] A trajectory analysis was performed on the resource input records of service outlets. First, the input changes for each service resource were recorded chronologically from the start of input to the end of the troubleshooting process and intervention. Based on the stages of the intervention process (e.g., fault diagnosis, troubleshooting, equipment debugging, etc.), the input amount of each resource in each intervention stage was calculated (i.e., the total amount of resources input in that stage). The input rate of each resource in each intervention stage was also calculated (i.e., the amount of resources input per unit time, which can be obtained by dividing the input amount in that stage by the duration of that stage). Simultaneously, the input quantity of each resource at different service outlets was statistically analyzed to determine the distribution of resources among service outlets (i.e., the proportion of resources input at each outlet). Based on the above calculations and analysis results, a resource input trajectory diagram was plotted. In this diagram, the horizontal axis represents time, and the vertical axis represents the amount of resources input. To distinguish different types of resources, different colored curves were used to represent the input change trajectory of each resource.

[0059] Step S124: Perform time-series analysis on the fault mitigation monitoring records, extract the changing trends of monitoring indicators, determine the key time nodes of fault mitigation, the degree of mitigation at each node, and the final mitigation effect, and form a fault mitigation effect time-series diagram. In the fault mitigation effect time-series diagram, the horizontal axis is time and the vertical axis is the degree of mitigation. The degree of mitigation is calculated based on the ratio of the actual value of the monitoring indicator to the normal operating range of the equipment preset by the technical center.

[0060] A time-series analysis is performed on the fault mitigation monitoring records, which involves arranging and analyzing the records chronologically. Values ​​of monitored indicators (such as equipment operating parameters and equipment status) are extracted from the records, and the trends of these indicators over time are observed (e.g., increase, decrease, or stabilization). Based on these trends, key time points in the fault mitigation process are identified, such as the time when signs of mitigation begin to appear, the time of fastest mitigation, and the time when the fault reaches a stable state. At each key time point, the degree of fault mitigation is calculated by dividing the actual value of the monitored indicator by the upper limit of the corresponding normal operating range of the equipment, preset by the technical center (when the actual value is within the normal range, the degree of mitigation is 1 or close to 1; when the actual value exceeds the normal range, the degree of mitigation is less than 1). Simultaneously, the final mitigation effect (i.e., the degree of mitigation at the end of the intervention) is determined. Based on the above analysis results, a time-series graph of the fault mitigation effect is plotted, with the horizontal axis representing time and the vertical axis representing the degree of mitigation, displaying the change in the degree of fault mitigation over time as a curve.

[0061] Step S125: Based on the operation execution time sequence table and the large model knowledge base, extract the spatiotemporal adaptation features of the intervention operation. The time window adaptability of the operation execution refers to the matching of the operation execution time with the key nodes of the fault state change. The spatial adaptability of the operation object refers to the correlation between the operation location and the distribution location of the faulty equipment.

[0062] Based on the operation execution time sequence table, and combined with relevant knowledge about the spatiotemporal adaptation of intervention operations stored in the large model knowledge base (such as the optimal intervention time for different types of faults, the correlation rules between operation location and faulty equipment, etc.), the spatiotemporal adaptation features of intervention operations are extracted. Among them, the time window adaptability of operation execution refers to the degree of matching between the time when the engineer performs the operation and the key nodes of the fault state change (such as the time of fault occurrence, the time of fault propagation acceleration, etc.). For example, the adaptability is higher when the operation is performed before the fault propagation accelerates, and lower when it is performed after the fault has spread severely. The spatial adaptability of the operation object refers to the degree of correlation between the location targeted by the operation (such as the installation location of the equipment) and the distribution location of the faulty equipment. For example, the adaptability is higher when the operation location is directly located within the distribution area of ​​the faulty equipment, and lower when it is far away from the distribution area of ​​the faulty equipment.

[0063] Step S1251: Extract the execution time of each operation from the operation execution time sequence table, and extract the key nodes of fault state change from the fault mitigation effect time sequence diagram of historical fault cases. The key nodes of fault state change include fault propagation acceleration nodes, fault state stabilization nodes, and fault mitigation initiation nodes.

[0064] The execution time information (accurate to the minute) for each operation is obtained from the operation execution time sequence table. Simultaneously, the fault mitigation effect time sequence diagrams of historical fault cases are analyzed to identify and extract key nodes in the fault state change. The fault propagation acceleration node refers to the point in time when the fault propagation speed begins to increase; the fault state stabilization node refers to the point in time when the fault propagation speed slows down or stops, and the fault state tends to stabilize; the fault mitigation initiation node refers to the point in time when the fault state begins to show signs of mitigation. These key nodes are important bases for analyzing the adaptability of the operation execution time window.

[0065] Step S1252: Calculate the execution time of each operation and the time difference between the critical nodes of each fault state change. The time difference is the operation execution time minus the time of the critical node of the fault state change. When the time difference is within the preset positive range, the operation execution timing is after the critical node of the fault state change and meets the response interval standard. It is determined that the time window adaptability of the operation meets the positive response adaptability standard preset by the technical center. When the time difference is within the preset negative range, the operation execution timing is before the critical node of the fault state change and meets the preparatory interval standard. It is determined that the time window adaptability of the operation meets the negative response adaptability standard preset by the technical center. When the time difference exceeds the preset range, the operation execution timing does not meet the response interval standard. It is determined that the time window adaptability of the operation does not meet the response adaptability standard preset by the technical center.

[0066] For each operation, its execution time is subtracted from the time of a critical node in the fault state change to obtain a time difference. The technical center pre-sets positive and negative time ranges. The positive time range indicates that the operation is executed after the critical node and the time interval between the two nodes is within a reasonable range. The negative time range indicates that the operation is executed before the critical node and the time interval between the two nodes is within a reasonable range. When the calculated time difference falls within the preset positive range, the operation's time window adaptability is determined to meet the positive response adaptability standard; when the time difference falls within the preset negative range, it is determined to meet the negative response adaptability standard; when the time difference exceeds the preset positive and negative ranges, the operation's time window adaptability is determined to fail to meet the response adaptability standard.

[0067] Step S1253: Statistically analyze the time window adaptability judgment results for each operation, calculate the proportions that meet the positive response adaptability standard, the negative response adaptability standard, and the non-compliance of the response adaptability standard, and form the time window adaptability feature value of the operation. The time window adaptability feature value is represented by three digits, which correspond to the proportions that meet the positive response adaptability standard, the negative response adaptability standard, and the non-compliance of the response adaptability standard, respectively.

[0068] The time window adaptability assessment results for each operation at each key node are statistically analyzed. The proportions of operations meeting the positive response adaptation criteria, the negative response adaptation criteria, and the non-compliance criteria are calculated across all key nodes. These three proportions are represented by a single number (e.g., percentages rounded to one decimal place and converted to integers), forming a three-digit time window adaptability feature value. The first digit represents the proportion meeting the positive response adaptation criteria, the second digit represents the proportion meeting the negative response adaptation criteria, and the third digit represents the proportion non-compliance.

[0069] Step S1254: Extract the faulty equipment propagation path from the equipment spatial distribution data of historical fault cases, and determine the key location points in the faulty equipment propagation path. The key location points in the faulty equipment propagation path include the location of the fault-initiating equipment, the location of the equipment in the main propagation direction, and the location of the affected related equipment.

[0070] Historical failure case data on device spatial distribution includes the location information of the devices at the time of the failure and the propagation path information of the failure between devices. The propagation path of the faulty device is extracted from this data; that is, the path by which the failure spreads from the initial device to other devices. Based on the propagation path, key location points are identified. These key location points mainly include the location of the device where the failure initially occurred (the location of the fault initiating device), the locations of each device the failure passed through in the main propagation direction, and the locations of related devices affected by the failure propagation (such as devices that have data interaction or control relationships with the faulty device).

[0071] Step S1255: Extract the execution location information of each operation from the operation execution sequence table, calculate the distance between the execution location and the key location points in the fault equipment propagation path, calculate the number of key location points in the fault equipment propagation path whose distance is within the preset range of the technical center, and the number of key location points in the fault equipment propagation path whose distance is within the preset range of the technical center reflects the degree of correlation between the execution location and the fault equipment propagation path.

[0072] Obtain the execution location information (such as the area where the equipment is located, the specific installation location, etc.) for each operation from the operation execution sequence table. Based on the location information of key points in the fault propagation path and the operation execution location information, calculate the distance between the execution location of each operation and each key point using a spatial distance calculation formula (such as the Euclidean distance formula). Compare the calculated distances with the distance range preset by the technical center, and count the number of key points whose distances fall within the preset range. The higher this number, the stronger the correlation between the operation execution location and the fault propagation path, meaning the operation is more targeted towards the fault propagation path.

[0073] Step S1256: By comparing the number of key points whose distance from the operation execution location to the key location of the faulty equipment is within a preset range with the preset number threshold range, the spatial adaptability level of the operation is determined, and the proportion of each level is statistically calculated based on the determination results of all operations to quantify and characterize its spatial adaptability characteristics.

[0074] Multiple quantity threshold intervals are preset, each interval corresponding to a spatial adaptability level (e.g., high, medium, low). For each operation, the number of key location points whose distances fall within the preset range, calculated in step S1255, is compared with the preset quantity threshold intervals to determine the spatial adaptability level of the operation (e.g., if the number is within a certain interval, it is high; if it is within another interval, it is medium, etc.). The spatial adaptability level determination results of all operations are statistically analyzed, and the proportion of operations at each level to the total number of operations is calculated to quantify and characterize the spatial adaptability features of the intervention operation.

[0075] Step S1257: Combine the time window adaptation feature value and the spatial adaptation feature value of each operation to form the spatiotemporal adaptation feature code of the operation. The spatiotemporal adaptation feature code format is time feature value - spatial feature value.

[0076] The spatiotemporal adaptation feature code for each operation is formed by combining the time window adaptation feature value (three digits) with the spatial adaptation feature value (such as a spatial adaptation level ratio represented by a single number) according to a specific format. The encoding format is set so that the time window adaptation feature value comes first, followed by the spatial adaptation feature value, connected by a hyphen, for example, in the form of "time feature value - spatial feature value". This encoding method can concisely represent the temporal and spatial adaptation characteristics of each operation.

[0077] Step S1258: Arrange the spatiotemporal adaptation feature codes of all operations in the order of operation execution to form the spatiotemporal adaptation feature code sequence of intervention operations. The spatiotemporal adaptation feature code sequence of intervention operations serves as the core content of the spatiotemporal adaptation features of intervention operations in the effectiveness coding package.

[0078] The spatiotemporal adaptation feature codes of all operations are arranged in the order of their execution to form an intervention operation spatiotemporal adaptation feature code sequence. This sequence records the temporal and spatial adaptability characteristics of all operations during the intervention process and serves as the core content of the intervention operation spatiotemporal adaptation features in the effectiveness coding package, so as to facilitate the subsequent evaluation and comparison of the intervention effectiveness of historical failure cases.

[0079] Step S126: Based on the resource input trajectory map, extract the dynamic distribution characteristics of service resource consumption, including the resource input ratio at different intervention stages, the distribution density of resources among service outlets, and the time synchronization between resource input and fault mitigation.

[0080] The resource input trajectory map illustrates the changes in the input of different service resources over time during the intervention process. Based on this trajectory map, the dynamic distribution characteristics of service resource consumption are extracted. The resource input ratio at different intervention stages refers to the proportion of each type of resource input to the total resource input at each intervention stage (such as the fault diagnosis stage, fault troubleshooting stage, etc.). The resource distribution density among service outlets refers to the degree of concentration of resources at each service outlet, which can be measured by calculating the proportion of resource input at each outlet to the total input. The time synchronization between resource input and fault mitigation refers to the degree of coordination between the timing of resource input and the timing of fault mitigation, such as whether fault mitigation begins promptly after resource input, and whether the peak period of resource input coincides with the critical period of fault mitigation.

[0081] Step S127: Based on the time series diagram of fault mitigation effect, extract the stage effectiveness characteristics of fault mitigation, including the mitigation rate, mitigation duration and contribution ratio of stage mitigation effect to the overall mitigation effect of each intervention stage.

[0082] The time series diagram of fault mitigation effect reflects the trend of fault mitigation degree over time. The phase efficacy characteristics of fault mitigation are extracted from this time series diagram. For each intervention phase, the fault mitigation rate is calculated, which is the change in fault mitigation degree per unit time within that phase (obtained by dividing the difference in mitigation degree at the beginning and end of the phase by the phase duration); the mitigation duration of that phase is determined, i.e., the length of time from the start to the end of the phase; the contribution ratio of the phase's mitigation effect to the overall mitigation effect is calculated, i.e., the proportion of the increase in mitigation degree within that phase to the total increase in mitigation degree during the entire intervention process. These characteristics can quantitatively evaluate the efficacy of each intervention phase.

[0083] Step S128: Integrate the spatiotemporal adaptation feature coding of intervention operations, the dynamic distribution feature coding of service resource consumption, and the phased effectiveness feature coding of fault mitigation to form an effectiveness coding package for historical fault cases. Assign a unique coding identifier to each effectiveness coding package. The coding identifier includes the historical fault case number, fault equipment type, intervention time, and effectiveness indicators.

[0084] The system integrates the spatiotemporal adaptation feature coding sequence of intervention operations, the dynamic distribution feature coding of service resource consumption (converting dynamic distribution features into specific coding forms), and the phased effectiveness feature coding of fault mitigation (converting phased effectiveness features into specific coding forms). During the integration process, the above codes are combined according to certain rules, and necessary descriptive information is added to form an effectiveness coding package for historical fault cases. Each performance coding package is assigned a unique identifier, which consists of the historical fault case number, the type of faulty equipment (such as air conditioning equipment, information publishing terminal, etc.), the execution time of the intervention operation, and performance indicators (such as intervention success rate, resource utilization rate, etc.) to facilitate unique identification and management of performance coding packages. Specifically, by retrieving and parsing the raw data such as "on-site engineer service operation sequence", "service network resource input trajectory", and "fault mitigation effect sequence" of historical fault cases, the intervention success rate and resource utilization rate can be automatically calculated based on predefined rules: the intervention success rate is calculated based on whether the final equipment status assessment result in the "fault mitigation monitoring record" reaches the standard state of "normal" or "repair completed"; the resource utilization rate is calculated by the ratio of the actual amount of resources invested in each stage to the theoretical optimal amount of investment in the "service network resource input record", and the calculation result is integrated into the "performance indicators" as a quantitative indicator, which is ultimately reflected in the unique identifier of the performance coding package.

[0085] Step S130: Perform dynamic resource effect balance and adaptation between the spatiotemporal evolution model of the current fault and the effectiveness coding package of each historical fault case, and calculate the intervention effectiveness matching degree between each historical fault case and the current fault.

[0086] The spatiotemporal evolution model of the current fault includes its development and changes in time and space, as well as relevant resource and environmental factors. The effectiveness coding package of historical fault cases contains the relevant feature codes of the intervention effectiveness of historical cases. The spatiotemporal evolution model of the current fault is dynamically balanced and adapted to the effectiveness of each historical fault case. This involves comprehensively considering the resource requirements of the current fault and the resource consumption during the intervention process of historical cases, as well as the expected effect of the current fault and the intervention effect of historical cases, performing dynamic matching and adaptation. By calculating the degree of matching between the two in terms of resource adaptation and effect adaptation, the intervention effectiveness matching degree between each historical fault case and the current fault is obtained.

[0087] Step S131: Extract resource demand data for each evolution stage from the spatiotemporal evolution model of the current fault, including the type of service resources required for each stage, the quantity of resources, the time window for resource input, and the network requirements for resource input, to form a stage resource demand table. The stage resource demand table includes the stage number, time range, resource type, quantity required, time window, and network requirements.

[0088] The spatiotemporal evolution model of the current fault is analyzed to extract resource requirement data for each evolution stage. The resource requirement data for each stage includes the type of service resources needed to handle the fault within that stage (such as repair tools, backup equipment, spare parts, etc.), the required quantity of each resource, the time window for resource deployment (i.e., the time period within which resources need to be deployed), and the requirements for resource deployment locations (such as specifying a particular service location or a location close to the faulty store). This resource requirement data is then organized according to stage number to form a stage resource requirement table. This table includes the stage number, the time range of the stage (start and end times), resource type, required quantity, resource deployment time window, and location requirements.

[0089] Step S132: Extract the dynamic distribution feature code of service resource consumption from the efficiency coding package of historical failure cases, parse the dynamic distribution feature code of service resource consumption to obtain the resource input type, input quantity, input time and input network of the historical failure case in each intervention stage, and form a stage resource supply table. The stage resource supply table includes stage number, time range, resource type, supply quantity, input time and input network.

[0090] The dynamic distribution feature code of service resource consumption is extracted from the efficiency coding package of historical failure cases. This dynamic distribution feature code contains information on the dynamic distribution characteristics of resource consumption during the intervention process of historical cases. The code is parsed to extract information such as the type, quantity, specific time, and service outlets involved in each intervention stage of the historical failure case. This information is then organized according to the intervention stage number to form a stage resource supply table. This stage resource supply table includes the stage number, the time range of the stage, the resource type, the supply quantity (i.e., the quantity invested), the investment time, and the service outlets involved.

[0091] Step S133: Associate the stage resource demand table and the stage resource supply table according to the stage number, and calculate the resource type matching degree, quantity matching degree, time matching degree and network matching degree for each stage. The resource type matching degree is the overlap ratio between the supply resource type and the demand resource type. The quantity matching degree is calculated based on the ratio of the supply quantity to the demand quantity. When the demand quantity is not zero, the quantity matching degree is the ratio of the supply quantity to the demand quantity. When the demand quantity is zero, the quantity matching degree is set to a preset benchmark value. The time matching degree is the overlap ratio between the supply input time and the demand time window. The network matching degree is the compliance ratio between the supply input network points and the demand network point requirements.

[0092] The phased resource demand table and phased resource supply table are linked one-to-one according to the phase number, so that the resource demand and resource supply information of the same phase correspond. For each linked phase, the resource type matching degree is calculated, which is the overlap ratio between the resource types invested in the historical case in this phase and the resource types required in the current fault phase (the number of overlapping resource types divided by the total number of required resource types); the quantity matching degree is calculated, which is the ratio of the resource quantity invested in the historical case in this phase to the current fault quantity when the current fault phase is not zero, and the quantity matching degree is set to a preset baseline value (e.g., 1, indicating a perfect match) when the required quantity is zero (i.e., the resource is not needed); the time matching degree is calculated, which is the proportion of the historical case resource investment time falling within the current fault resource investment time window (the overlap time length divided by the total time window length); and the network matching degree is calculated, which is the proportion of the network points invested in the historical case that meet the current fault network point requirements (the number of network points that meet the requirements divided by the total number of network points invested).

[0093] Step S1331: Based on the degree of influence of each dimension of service resources on the intervention effect, set the weight of each dimension according to the preset weight allocation rules of the technical center, multiply the matching degree of each dimension by the corresponding dimension weight, sum all the product results, and then standardize the sum results to obtain the resource matching sub-score.

[0094] The technical center pre-defined weighting rules for each dimension of service resources (resource type, quantity, time, and location) based on their impact on intervention effectiveness (e.g., higher weight for resource type and lower weight for location requirements). According to these rules, corresponding weight values ​​were assigned to resource type matching, quantity matching, time matching, and location matching. The matching degree of each dimension was multiplied by its corresponding weight to obtain a weighted matching degree for each dimension. The weighted matching degrees of all dimensions were summed to obtain a comprehensive score. This comprehensive score was then standardized (e.g., mapped to a range of 0 to 100) to obtain a resource adaptation sub-score, which reflects the degree of adaptation between historical cases and current faults in terms of resource requirements.

[0095] Step S134: Extract the fault status data of each evolution stage from the spatiotemporal evolution model of the current fault, including the scope of equipment affected by the fault, the severity of the equipment fault, and the fault development trend of each stage, to form a stage fault status table. The stage fault status table includes the stage number, time range, scope of impact, severity, and development trend.

[0096] Analyze the spatiotemporal evolution model of the current fault and extract fault state data for each evolution stage. The fault state data for each stage includes the scope of equipment affected by the fault (e.g., the number and type of equipment involved), the severity of the equipment fault (e.g., minor fault, moderate fault, severe fault), and the development trend of the fault (e.g., propagation, stabilization, mitigation). Organize the above fault state data according to the stage number to form a stage fault state table. This table includes information such as the stage number, the time range of the stage, the scope of the fault's impact, the severity of the equipment fault, and the fault development trend.

[0097] Step S135: Extract the stage efficacy feature code of fault relief from the efficacy code package of historical fault cases, parse the stage efficacy feature code of fault relief to obtain the relief range, relief degree and relief duration of the historical fault case in each intervention stage, and form a stage relief effect table. The stage relief effect table includes stage number, time range, relief range, relief degree and duration.

[0098] The effectiveness feature codes for each stage of fault mitigation are extracted from the effectiveness coding packages of historical fault cases. These codes are then parsed to obtain the mitigation scope (i.e., the degree to which the impact of the fault is reduced after intervention), mitigation degree (i.e., the degree to which the severity of the fault is reduced), and mitigation duration (i.e., the length of time the mitigation effect is maintained) for each intervention stage. This mitigation effect data is then organized according to the intervention stage number to form a stage mitigation effect table. This table includes information such as the stage number, the time range of that stage, the mitigation scope, the mitigation degree, and the duration.

[0099] Step S136: Associate the stage fault status table and the stage mitigation effect table according to the stage number, and calculate the range matching degree, severity matching degree, and trend matching degree for each stage. The range matching degree is the overlap ratio between the mitigation range and the range of equipment affected by the fault. The severity matching degree is calculated based on the ratio of the mitigation degree to the severity of the equipment fault. When the severity of the equipment fault is not zero, the severity matching degree is the ratio of the mitigation degree to the severity of the equipment fault. When the severity of the equipment fault is zero, the severity matching degree is set to a preset baseline value. The trend matching degree is the reversal ratio of the fault development trend during the mitigation period.

[0100] The stage fault status table and stage mitigation effect table are associated according to stage number, so that the fault status and mitigation effect information of the same stage correspond. For each associated stage, the range matching degree is calculated, which is the overlap ratio between the mitigation range of the historical case in this stage and the range of equipment affected by the fault in the current stage (the size of the overlap range divided by the size of the equipment affected by the fault); the severity matching degree is calculated, which is the ratio of the mitigation degree of the historical case in this stage to the severity of the fault in the current stage when the severity of the fault is not zero, and when the severity of the fault is zero (i.e. the fault has been mitigated), the severity matching degree is set to a preset baseline value (e.g., 1); the trend matching degree is calculated, which is the proportion of the current fault's fault development trend reversing from deterioration or spread to stability or mitigation within the mitigation duration of the historical case (the reversal time divided by the mitigation duration).

[0101] Step S1361: Based on the contribution of each dimension of the effect to fault mitigation, set the weight of each dimension according to the preset weight allocation rules of the technical center, multiply the matching degree of each dimension by the corresponding dimension weight, sum all the product results, and then standardize the summation result to obtain the effect fitter score.

[0102] The technical center pre-defined weighting rules for each dimension of effectiveness (range, severity, and trend) to assess their contribution to fault mitigation (e.g., severity of mitigation receives higher weight, trend receives lower weight, etc.). Based on these rules, corresponding weight values ​​were assigned to range matching, severity matching, and trend matching. The matching score for each dimension was multiplied by its corresponding weight to obtain a weighted matching score for each dimension. The weighted matching scores for all dimensions were summed to obtain a comprehensive score. This comprehensive score was then standardized (e.g., mapped to a range of 0 to 100) to obtain an effectiveness fit sub-score, which reflects the degree of fit between historical cases and the current fault in terms of intervention effectiveness.

[0103] Step S137: Based on the degree of influence of resource adaptation and effect adaptation on the overall intervention effectiveness, set the resource adaptation weight and effect adaptation weight according to the preset weight allocation rules of the technical center. Multiply the resource adaptation sub-score with the resource adaptation weight and the effect adaptation sub-score with the effect adaptation weight, and sum the two product results to obtain the comprehensive adaptation score.

[0104] The technical center pre-sets resource adaptation weights and effect adaptation weights (e.g., the weight of effect adaptation is higher than the weight of resource adaptation) based on the degree of impact of resource adaptation and effect adaptation on the overall intervention effectiveness. The resource adaptation sub-score obtained in step S1331 is multiplied by the resource adaptation weight to obtain the resource adaptation weighted score; the effect adaptation sub-score obtained in step S1361 is multiplied by the effect adaptation weight to obtain the effect adaptation weighted score. The resource adaptation weighted score and the effect adaptation weighted score are added together to obtain the comprehensive adaptation score, which comprehensively reflects the overall degree of adaptation between historical cases and the current fault in terms of resources and effects.

[0105] Step S138: Calculate the average comprehensive fit score of all stages. The average comprehensive fit score of all stages is used as the matching degree of intervention effectiveness between the historical failure case and the current failure.

[0106] For all stages of the current fault's evolution, calculate the comprehensive fit score for each stage (as described in step S137). Then, sum the comprehensive fit scores for all stages and divide by the total number of stages to obtain the average comprehensive fit score for all stages. This average comprehensive fit score represents the matching degree of intervention effectiveness between the historical fault case and the current fault. The higher the matching degree, the more suitable the intervention plan of the historical case is for the current fault.

[0107] Step S140: Based on the intervention effectiveness matching degree, conduct intervention effectiveness simulation and extrapolation on historical failure cases, simulate the execution process of the intervention plan for each historical failure case in the current failure scenario, record the service resource consumption nodes, failure mitigation nodes and stage goal achievement nodes in the simulation process, and form a simulation result report.

[0108] Based on the calculated intervention effectiveness matching degree, historical failure cases are screened, and those with high matching degrees are selected for intervention effectiveness simulation. Simulation involves applying the intervention plans from historical failure cases to the current failure scenario, using computer simulation software to simulate the execution process of the intervention plan. During the simulation, service resource consumption nodes (i.e., information such as the time and quantity of service resources consumed during the intervention), failure mitigation nodes (i.e., information such as the time and extent when the failure state begins to alleviate), and stage goal achievement nodes (i.e., information such as whether the goal of each evolution stage is achieved and the time of achievement). The recorded information is compiled into a simulation result report, which details the simulation process and results.

[0109] Step S141: Extract the spatiotemporal adaptation feature code of the intervention operation from the performance coding package of historical fault cases. Combine the robot-assisted decision-making logic of the technical center to analyze the spatiotemporal adaptation feature code of the intervention operation to obtain a complete intervention operation sequence. The intervention operation sequence includes the operation execution order, operation content, operation equipment, execution engineer scheduling logic and service network resource allocation path, forming an intervention operation deduction table. The intervention operation deduction table includes operation number, execution order, operation content, operation equipment, engineer scheduling logic and resource allocation path.

[0110] The spatiotemporal adaptation feature codes of intervention operations are extracted from the performance coding packages of historical failure cases. Combined with the robot-assisted decision-making logic of the technology center (which includes the parsing rules and decision-making process for intervention operations), the spatiotemporal adaptation feature codes are parsed to obtain a complete sequence of intervention operations. This sequence includes the execution order of all operations during the intervention process, the specific content of each operation, the equipment targeted by the operation, the scheduling logic of the executing engineer (e.g., which engineer is selected to perform the operation, the engineer's scheduling priority, etc.), and the allocation path of service network resources (e.g., from which network point to which location resources are allocated). This sequence information is then organized into an intervention operation deduction table, which includes information such as operation number, execution order, operation content, operating equipment, engineer scheduling logic, and resource allocation path.

[0111] Step S142: Extract initial fault state data from the spatiotemporal evolution model of the current fault. The initial fault state data includes the initial fault equipment location, the initial affected equipment range, the initial fault severity, and the initial environmental influence intensity. Use the initial fault state data as the starting state for the deduction.

[0112] The spatiotemporal evolution model of the current fault is analyzed to extract the initial fault state data, i.e., the state data when the fault just occurred. The initial fault state data includes the location of the initially faulty device (i.e., the location of the first device to fail), the initial range of affected devices (i.e., the number and type of devices initially affected by the fault), the initial fault severity (i.e., the degree of damage to the devices at the time of the fault), and the initial environmental influence intensity (i.e., the intensity of the influence of various environmental parameters on the fault at the time of the fault). This initial fault state data is set as the starting state for the intervention effectiveness simulation, meaning the simulation begins executing intervention operations from this state.

[0113] Step S143: Following the execution order of the intervention operation simulation table, simulate the execution process of each operation in turn. Before each operation is executed, record the current fault status data and service resource inventory data. The current fault status data includes the scope of affected equipment, the severity of equipment fault, and the fault development trend. The current service resource inventory data includes the resource type, remaining quantity, and reserve network location.

[0114] Based on the execution order of the operations in the intervention operation simulation table, simulation software is used to simulate the execution process of each operation sequentially. Before simulating the execution of each operation, the current fault status data and service resource inventory data are recorded. The current fault status data includes the scope of equipment affected by the fault (the number and type of equipment affected by the fault at this moment), the severity of the equipment fault (the degree of damage to the equipment at this moment), and the fault development trend (whether the fault is spreading, stabilizing, or mitigating at this moment); the current service resource inventory data includes the types of various service resources, the remaining quantity of each resource, and the location of the resource reserve network.

[0115] Step S144: During the simulation operation, based on the operation content and operating equipment, and combined with the robot-assisted support logic of the technical center, adjust the current fault status data. When the operation targets the fault propagation path, reduce the rate of expansion of the equipment's influence range; when the operation targets the fault root cause equipment, reduce the rate of deepening of the single equipment's fault severity; when the operation targets environmental influencing factors, weaken the intensity of environmental effects.

[0116] During the simulated operation, based on the operation content and equipment in the intervention operation simulation table, and combined with the robot-assisted support logic of the technical center (which includes rules governing the impact of operations on the fault state), the current fault state data is adjusted. If the operation targets the fault propagation path (e.g., setting isolation measures), the rate of expansion of the equipment's influence range is reduced (i.e., the speed of fault propagation slows down); if the operation targets the fault's root cause equipment (e.g., repairing or replacing faulty components), the rate of increase in the severity of a single equipment fault is reduced (i.e., the degree of equipment damage no longer increases rapidly or begins to decrease); if the operation targets environmental influencing factors (e.g., adjusting temperature, humidity, etc.), the intensity of the environmental parameters' effect on the fault is weakened (i.e., the promoting effect of environmental factors on the fault is reduced). Through these adjustments, the changes in the fault state after the simulated operation are observed.

[0117] Step S145: Based on the type and quantity of service resources required for the operation, and in conjunction with the physical location system of the on-site engineer and the service outlet resource data, adjust the current service resource inventory data, reduce the remaining quantity of the corresponding resources, record the time, quantity and reserve outlet location of resource consumption, and form a service resource consumption node record. The service resource consumption node record includes the operation sequence number, consumption time, resource type, consumption quantity and reserve outlet location.

[0118] Based on the service resource types and quantities required for each operation in the intervention operation simulation table, and combined with the on-site engineer physical location system (providing the engineer's real-time location to determine resource availability) and service network resource data (providing resource inventory information for each network), the current service resource inventory data is adjusted, i.e., the remaining quantity of the corresponding resources is reduced. Simultaneously, the resource consumption time (operation execution time), the type and quantity of consumed resources, and the location of the resource reserve network are recorded. This information is compiled into a service resource consumption node record, which details the service resource consumption during each operation.

[0119] Step S146: After each operation is performed, record the adjusted fault status data, compare the changes in fault status before and after the operation, and mark the fault status as a fault relief node when the magnitude of the fault status change reaches the mitigation standard preset by the technical center. The fault relief node record includes the operation number, relief time, relief equipment range, relief degree and corresponding operation content.

[0120] After each operation is completed, the adjusted fault status data is recorded (as described in step S144). The adjusted fault status data is compared with the fault status data before the operation, and the change in fault status is calculated (e.g., the proportion of reduced impact range, the proportion of reduced severity, etc.). When the change in fault status reaches the mitigation standard preset by the technical center (e.g., the impact range is reduced by a certain proportion or the severity is reduced by a certain proportion), the time point of the operation is marked as a fault mitigation node. The fault mitigation node record includes information such as operation sequence number, mitigation time (i.e., the time when the operation was completed), mitigation equipment range (i.e., the equipment range where the fault impact range is reduced), mitigation degree (i.e., the change in fault status), and corresponding operation content.

[0121] Step S147: According to the current spatiotemporal evolution model of the fault, at the end of each stage, compare the preset target of the stage with the actual simulation result. The preset target of the stage includes controlling the scope of the fault-affected equipment within the preset value of the technical center and reducing the severity of the equipment fault to the preset proportion of the technical center. When the actual simulation result reaches the preset target of the stage, it is marked as the stage target achievement node. The stage target achievement node record includes the stage number, achievement time, target content, actual result and achievement conditions.

[0122] According to the stages defined in the current spatiotemporal evolution model of the fault, at the end of each stage (determined based on the stage's time range), the preset goals for that stage are compared with the actual results obtained from the simulation. The preset goals for this stage include controlling the scope of equipment affected by the fault within the technical center's preset values ​​(e.g., the number of affected devices does not exceed a certain value) and reducing the severity of equipment faults to a preset percentage (e.g., a reduction in severity by a certain percentage). When the actual simulation results reach the preset goals for that stage, it is marked as a stage goal achievement node. The stage goal achievement node record includes information such as stage number, achievement time (stage end time), goal content (preset goal), actual result (simulation result), and achievement conditions (e.g., which operations contributed to the goal achievement).

[0123] Step S148: After completing the simulation of all intervention operations, count the total number of service resource consumption nodes, the total number of fault mitigation nodes, and the total number of nodes achieving the stage goals. Calculate the service resource consumption efficiency, fault mitigation rate, and stage goal achievement rate. The service resource consumption efficiency is the ratio of the total mitigation effect to the equivalent value of the total service resource consumption. The equivalent value of the total service resource consumption is a comprehensive value obtained by converting the consumption of different types of service resources according to the resource value coefficient preset by the technical center. The fault mitigation rate is the ratio of the total mitigation degree to the total simulation time. The stage goal achievement rate is the ratio of the number of achieved stages to the total number of stages.

[0124] After all intervention simulations are completed, the service resource consumption nodes, fault mitigation nodes, and stage goal achievement nodes recorded during the simulation are statistically analyzed to obtain the total number of service resource consumption nodes, the total number of fault mitigation nodes, and the total number of stage goal achievement nodes. The service resource consumption efficiency is calculated as the ratio of the total mitigation effect (the sum of the mitigation levels of all fault mitigation nodes) to the total equivalent value of service resource consumption (the sum of the consumption amounts of different types of resources multiplied by their preset resource value coefficients). The fault mitigation rate is calculated as the ratio of the total mitigation degree (the sum of the mitigation degrees of all fault mitigation nodes) to the total simulation time (the total time from the start to the end of the simulation). The stage goal achievement rate is calculated as the ratio of the number of stages that achieved the stage goal to the total number of stages. These indicators are used to evaluate the effectiveness of the intervention plan.

[0125] Step S149: After completing the simulation of all intervention operations, count the total number of service resource consumption nodes, the total number of fault mitigation nodes, and the total number of nodes achieving the stage goals. Calculate the service resource consumption efficiency, fault mitigation rate, and stage goal achievement rate. The service resource consumption efficiency is the ratio of the total mitigation effect to the equivalent value of the total service resource consumption. The equivalent value of the total service resource consumption is a comprehensive value obtained by converting the consumption of different types of service resources according to the resource value coefficient preset by the technical center. The fault mitigation rate is the ratio of the total mitigation degree to the total simulation time. The stage goal achievement rate is the ratio of the number of achieved stages to the total number of stages.

[0126] The simulation results report integrates data such as fault status, service resource inventory, service resource consumption node records, fault mitigation node records, stage goal achievement node records, as well as statistically calculated information such as service resource consumption efficiency, fault mitigation rate, and stage goal achievement rate, to form a simulation results report.

[0127] Step S150: For historical fault cases that meet the preset resource effect balance threshold in the simulation results report, conduct elastic intervention and adjustment tests to generate a target matching fault case set for the current fault.

[0128] The preset resource effectiveness balance thresholds are a series of thresholds set by the technical center based on historical experience and fault handling requirements. These include service resource consumption efficiency thresholds, fault mitigation rate thresholds, and stage goal achievement rate thresholds. The various indicators (service resource consumption efficiency, fault mitigation rate, stage goal achievement rate, etc.) in the simulation results report are compared with the preset resource effectiveness balance thresholds to select historical fault cases that meet the threshold requirements. Flexible intervention and adjustment tests are then conducted on these qualified historical cases. This involves fine-tuning certain parameters in the intervention plan (such as the amount of resources invested, operation execution time, etc.) to test the adaptability and effectiveness of the adjusted plan under different conditions. Based on the test results, a target-matching fault case set is generated for the current fault. This target-matching fault case set contains the most suitable historical fault cases and their intervention plans for the current fault.

[0129] Step S151: Set the resource effect balance threshold. The resource effect balance threshold includes the minimum standard for service resource consumption efficiency, the minimum standard for fault mitigation rate, and the minimum standard for stage target achievement rate. The resource effect balance threshold is set based on the current operational priority of the faulty store, the total amount of available service resources, and the fault handling time requirements.

[0130] Based on the operational priority of the currently malfunctioning store (e.g., the store's sales share, customer traffic, etc.; higher operational priority requires faster fault handling), the total amount of available service resources (e.g., the number of engineers currently available, service network resource reserves, etc.; fewer resources require higher resource consumption efficiency), and the fault handling time requirements (e.g., the required timeframe for restoring equipment to normal operation), a resource effectiveness balance threshold is set. This resource effectiveness balance threshold includes a minimum standard for service resource consumption efficiency (i.e., the resource consumption efficiency of the intervention plan cannot be lower than this standard), a minimum standard for fault mitigation rate (i.e., the speed of fault mitigation cannot be lower than this standard), and a minimum standard for the achievement rate of phase goals (i.e., the proportion of phase goals achieved cannot be lower than this standard). The setting of these thresholds ensures that the intervention plan achieves a balance between resource consumption and effectiveness.

[0131] Step S152: Compare the service resource consumption efficiency, fault mitigation rate, and stage target achievement rate in the simulation results report of each historical fault case with the preset resource effect balance threshold, and retain the historical fault cases in which the service resource consumption efficiency, fault mitigation rate, and stage target achievement rate all reach or exceed the preset resource effect balance threshold to form a flexible test case group.

[0132] Each historical failure case's simulation results report was compared with the preset resource efficiency consumption, failure mitigation rate, and phase target achievement rate against the preset resource effect balance threshold. If all three indicators of a historical case met or exceeded the corresponding minimum standards, the case was retained; otherwise, it was excluded. All retained historical failure cases were combined into a resilience test case group, whose intervention plans demonstrated good resource effect balance performance in the simulation.

[0133] Step S153: Extract factors that may change dynamically from the current fault scenario data. Factors that may change dynamically include changes in the real-time location of the on-site engineer, fluctuations in service outlet resource inventory, and changes in store environmental parameters. Set the change range and change time point for each factor that may change dynamically to form a dynamic change scenario table. The dynamic change scenario table includes scenario number, changing factor, change range, change time point, and parameters after change.

[0134] Analyzing current fault scenario data identifies potentially dynamic factors, including real-time location changes of on-site engineers (e.g., engineers deviating from their planned routes due to traffic), fluctuations in service outlet resource inventory (e.g., resource depletion due to other fault handling), and changes in store environmental parameters (e.g., sudden temperature increases, sudden increases in customer density). For each potentially dynamic factor, various change magnitudes (e.g., distance the engineer deviates from their original location, percentage reduction in resource inventory, numerical changes in environmental parameters) and change time points (e.g., at which stage of the intervention process the change occurs) are defined. These changing factors, magnitudes, time points, and post-change parameter values ​​are compiled into a dynamic change scenario table. This table includes scenario number, changing factor, magnitude, time point, and post-change parameters, used to simulate the effectiveness of intervention plans under different dynamic change conditions.

[0135] Step S154: For each historical failure case in the resilience test case group, based on each scenario in the dynamic change scenario table, adjust the operation execution time, operation content, service resource investment quantity, and engineer scheduling path of the intervention plan.

[0136] For each historical failure case in the resilience test case group, and in conjunction with each dynamic change scenario in the dynamic change scenario table, the intervention plan for that case is adjusted accordingly. If the location of the on-site engineer changes in the scenario, the engineer's scheduling path and operation execution time are adjusted; if the service outlet resource inventory fluctuates, the amount of service resources invested is adjusted (e.g., if inventory decreases, the corresponding resource investment is reduced); if the store environmental parameters change, the operation content is adjusted (e.g., operations targeting environmental factors are added). Through these adjustments, the intervention plan can adapt to dynamically changing scenarios.

[0137] Step S155: Simulate the execution process of the adjusted intervention plan in a dynamically changing scenario, record the service resource consumption node, fault mitigation node and stage goal achievement node in each dynamically changing scenario, and calculate the service resource consumption efficiency, fault mitigation rate and stage goal achievement rate in each dynamically changing scenario.

[0138] Step S1551: For each dynamic change scenario, extract the changing factors, change magnitude, change time point and post-change parameters from the dynamic change scenario table, update the corresponding parameters in the spatiotemporal evolution model of the current fault scenario, and form a scenario-based spatiotemporal evolution model.

[0139] The dynamic change scenario table retrieves the corresponding change factors, such as real-time location changes of on-site engineers, fluctuations in service outlet resource inventory, or changes in store environmental parameters. It also extracts the magnitude of change, the time point of change, and the parameters after the change. Based on this information, the parameters related to the change factor in the spatiotemporal evolution model of the current fault scenario are updated. For example, if the change factor is the real-time location change of the on-site engineer, and the changed parameter is the new latitude and longitude coordinates, then the engineer's location parameter in the spatiotemporal evolution model is updated to these coordinates; if the change factor is fluctuations in service outlet resource inventory, and the changed parameter is the new inventory quantity, then the resource inventory parameters of the corresponding outlet are updated. After parameter updates, a scenario-based spatiotemporal evolution model suitable for this dynamic change scenario is formed.

[0140] Step S1552: Extract the operation execution sequence from the adjusted intervention plan. The operation execution sequence of the adjusted intervention plan includes the adjusted operation execution time, operation content, operation equipment, engineer scheduling path and service network resource allocation rules, forming a scenario-based intervention operation table. The scenario-based intervention operation table includes operation number, execution time, operation content, operation equipment, scheduling path and allocation rules.

[0141] The adjusted intervention plan was analyzed, and the operation execution sequence was extracted. This sequence covers the details of each operation, including the execution time (adjusted according to the changing time points in the dynamic scenario), the specific operation content (such as the added cooling operation in response to changes in environmental parameters), the equipment involved (which may be adjusted due to changes in the scope of the fault), the engineer scheduling path (re-planned based on the changed engineer locations), and the service network resource allocation rules (considering allocation priorities after fluctuations in resource inventory). The information in the above operation execution sequence is organized by operation number to form a scenario-based intervention operation table.

[0142] Step S1553: Use the initial state of the scenario-based spatiotemporal evolution model as the starting state for deduction. The initial state of the scenario-based spatiotemporal evolution model includes the location of the faulty equipment, the scope of impact, the severity, the intensity of environmental effects, and the distribution of service resource inventory corresponding to the changed parameters.

[0143] The state of the scenario-based spatiotemporal evolution model before the point of change is set as the initial state of the simulation. This initial state of the simulation includes various initial data after the dynamic changes in scenario parameters, specifically the location of the faulty equipment (which may change due to diffusion), the scope of the fault's impact (number and type of equipment), the severity of the equipment fault (initial damage level), the intensity of environmental effects (the effect of changed parameters such as temperature and humidity on the fault), and the distribution of service resource inventory (the remaining quantity and location of various resources at each site).

[0144] Step S1554: Following the execution order of the operations in the scenario-based intervention operation table, simulate the execution process of each adjusted operation in sequence. Before the operation is executed, record the fault status data and service resource inventory data in the current scenario-based spatiotemporal evolution model. The fault status data in the current scenario-based spatiotemporal evolution model includes the scope of affected equipment, the severity of equipment faults, the fault development trend, and environmental parameters. The service resource inventory data in the current scenario-based spatiotemporal evolution model includes resource type, remaining quantity, reserve network location, and engineer real-time location.

[0145] According to the order of operations in the scenario-based intervention operation table, each adjusted operation is executed sequentially using simulation software. Before executing each operation, this embodiment automatically records the fault status data and service resource inventory data in the current scenario-based spatiotemporal evolution model. The fault status data covers the scope of equipment currently affected by the fault, the severity of the fault for each device, the development trend of the fault (spreading, stabilizing, or mitigating), and the current environmental parameters (temperature, humidity, etc.); the service resource inventory data includes the type of various resources, the remaining quantity, the specific location of reserve outlets, and the real-time location information of engineers.

[0146] Step S1555: During the simulation operation, based on the adjusted operation content and operating equipment, and combined with the parameters of the scenario-based spatiotemporal evolution model, adjust the fault state data in the current scenario-based spatiotemporal evolution model.

[0147] When simulating the execution of adjusted operations, the fault state data in the model is adjusted accordingly based on the operation content (such as repairing specific equipment components, adjusting environmental control devices, etc.) and the operating equipment (such as the root cause of the fault, environmental control equipment, etc.), combined with the current parameters in the scenario-based spatiotemporal evolution model (such as the current state of the equipment, environmental parameter values, etc.). For example, if the operation content is to replace the compressor of a faulty air conditioner, and the operating equipment is the faulty air conditioner, then the fault severity parameter of the air conditioner is adjusted to reduce its damage degree; if the operation targets environmental parameters, such as turning on the backup air conditioner to cool down, then the temperature effect value in the environmental influence intensity is weakened, thereby affecting the development trend of the fault.

[0148] Step S1556: Based on the adjusted service resource input quantity and engineer scheduling path, adjust the service resource inventory data and engineer location information in the current scenario-based spatiotemporal evolution model, record the service resource consumption time, quantity, reserve network location, and engineer scheduling node, forming a service resource consumption node record under the dynamic change scenario. The service resource consumption node record under the dynamic change scenario includes scenario number, operation number, consumption time, resource type, consumption quantity, reserve network location, and engineer number.

[0149] Based on the adjusted service resource input quantities in the scenario-based intervention operation table (e.g., reducing the input quantity of a certain type of spare parts due to inventory reduction) and the engineer scheduling path (newly planned driving route), the service resource inventory data in the scenario-based spatiotemporal evolution model is updated, reducing the remaining quantity of the corresponding resources. The specific time of resource consumption (operation execution time), the type of resource consumed (e.g., a specific motherboard model), the quantity consumed, and the location of the resource's reserve point are recorded. Simultaneously, the engineer's location information is updated, and engineer scheduling nodes (e.g., departure time, arrival time at transfer point, etc.) are recorded. This information is then associated with the scenario number, operation number, and engineer number to form a service resource consumption node record specific to this dynamically changing scenario.

[0150] Step S1557: After each operation is executed, record the fault state data in the adjusted scenario-based spatiotemporal evolution model, compare the changes in fault state in the scenario-based spatiotemporal evolution model before and after the operation is executed, and mark it as a fault mitigation node in the dynamic change scenario when the magnitude of the fault state change in the scenario-based spatiotemporal evolution model reaches the mitigation standard in the dynamic change scenario. The fault mitigation node record in the dynamic change scenario includes scenario number, operation number, mitigation time, mitigation equipment range, mitigation degree and corresponding operation content. The mitigation standard in the dynamic change scenario is set based on the magnitude of the fault state change in the scenario-based spatiotemporal evolution model.

[0151] After each operation is completed, the updated fault state data in the scenario-based spatiotemporal evolution model is immediately recorded. The fault state data after the operation is executed is compared with the data before the operation, and the magnitude of the change in fault state is calculated, such as the proportion of reduction in the affected equipment range and the numerical value of the reduction in fault severity. Based on the characteristics of the dynamic change scenario in the scenario-based spatiotemporal evolution model (such as the impact of changes in environmental parameters), corresponding mitigation standards are set (such as a reduction in fault severity by a specific proportion as mitigation). When the magnitude of the fault state change reaches the mitigation standard, the time point is marked as a fault mitigation node, and the scenario number, the corresponding operation number, the time of mitigation, the equipment range involved in the mitigation, the degree of mitigation (such as the specific proportion of the reduction in severity), and the corresponding operation content that led to the mitigation are recorded, forming a fault mitigation node record for that dynamic change scenario.

[0152] Step S1558: According to the phase division of the scenario-based spatiotemporal evolution model, at the end of each phase, compare the scenario-based goal of that phase with the actual simulation result. The scenario-based goal of that phase is adjusted based on the dynamic change parameters of the scenario-based spatiotemporal evolution model. When the actual simulation result reaches the scenario-based goal of that phase, it is marked as the phase goal achievement node under the dynamic change scenario. The phase goal achievement node record under the dynamic change scenario includes scenario number, phase number, achievement time, goal content, actual result and achievement conditions.

[0153] Based on the scenario-based spatiotemporal evolution model, fault development stages are divided (e.g., propagation stage, stabilization stage, etc.). At the end of each stage, the scenario-based objective for that stage is compared with the actual results obtained from the simulation. The scenario-based objective is an adjusted objective based on dynamically changing parameters (e.g., resource inventory, engineer location), such as appropriately relaxing the target for controlling the scope of fault impact due to resource reduction. If the actual simulation results (e.g., simulated fault impact scope, severity, etc.) meet the requirements of the scenario-based objective, it is marked as a stage objective achievement node. The scenario number, stage number, achievement time, specific content of the scenario-based objective (e.g., the impact scope is controlled within a specific quantity), actual simulation results, and the conditions met to achieve the objective (e.g., successful execution of a key operation) are recorded to form a stage objective achievement node record for that dynamically changing scenario.

[0154] Step S1559: After completing the simulation of all adjusted operations under the dynamic change scenario, organize the service resource consumption node records, fault mitigation node records, and stage goal achievement node records under the dynamic change scenario to form a summary table of simulation nodes for the dynamic change scenario.

[0155] After the simulation completes all adjusted operations under the dynamic change scenario, the service resource consumption node records, fault mitigation node records, and phase goal achievement node records recorded in the scenario are summarized and organized. These node records are arranged in operation sequence or time order to ensure that all data correspond accurately, forming a simulation node summary table for the dynamic change scenario, which comprehensively reflects the key node status of the intervention plan execution process under the scenario.

[0156] Step S156: Count the number of scenarios in which the service resource consumption efficiency, fault mitigation rate, and stage target achievement rate of each historical fault case reach the preset standards under all dynamic changing scenarios, and calculate the proportion of scenarios that meet the standards. The proportion of scenarios that meet the standards is the ratio of the number of scenarios in which the service resource consumption efficiency, fault mitigation rate, and stage target achievement rate reach the preset standards to the total number of scenarios.

[0157] A set of predefined standards (such as those equal to or slightly lower than the resource efficiency threshold) is used to determine whether the various indicators of the intervention plan meet the standards under dynamically changing scenarios. For each historical failure case, the number of scenarios in the dynamic change scenario table that meet the predefined standards in terms of service resource consumption efficiency, failure mitigation rate, and stage goal achievement rate is counted. The number of compliant scenarios is divided by the total number of scenarios (the total number of scenarios in the dynamic change scenario table) to obtain the compliance scenario ratio. This ratio reflects the adaptability and stability of the intervention plan for historical failure cases under different dynamically changing conditions.

[0158] Step S157: Retain historical fault cases where the proportion of compliant scenarios reaches or exceeds the threshold. Extract complete intervention plans, performance coding data, and engineer scheduling adaptation records from the retained historical fault cases. Integrate the complete intervention plans, performance coding data, and engineer scheduling adaptation records to form a target matching fault case set for the current fault. Each historical fault case in the target matching fault case set for the current fault includes basic case information, a complete intervention plan, and a scheduling adaptation record. The basic case information includes the case number, faulty equipment type, and intervention time. The complete intervention plan includes the operation sequence, resource requirements, and robot-assisted logic. The scheduling adaptation record includes the dynamic scenario, adjustment content, and test results.

[0159] Set a threshold for the proportion of compliant scenarios (e.g., 80%), and retain historical failure cases where the proportion of compliant scenarios reaches or exceeds this threshold. Extract complete intervention plans (including operation sequences, resource requirements, robot-assisted logic, etc.), effectiveness coding data (containing feature codes of intervention effectiveness), and engineer scheduling adaptation records (recording adjustments to engineer scheduling paths and test results under different dynamic scenarios) from these retained historical failure cases. Integrate the extracted information to form a target-matching failure case set for the current failure. Each historical failure case in this target-matching failure case set includes basic case information (case number, type of faulty equipment, intervention time, etc.), a complete intervention plan, and a scheduling adaptation record.

[0160] Figure 2 This application illustrates a fault case intelligent matching system 100 for operation and maintenance technical services, including a processor 1001, a memory 1003, and program code stored in the memory 1003. The processor 1001 executes the program code to implement the steps of the fault case intelligent matching method for operation and maintenance technical services. The processor 1001 and the memory 1003 are connected, for example, via a bus 1002. Optionally, the fault case intelligent matching system 100 may further include a transceiver 1004, which can be used for data interaction between this fault case intelligent matching system and other fault case intelligent matching systems for operation and maintenance technical services, such as sending and / or receiving data. It should be noted that in actual scheduling, the transceiver 1004 is not limited to one, and the structure of this fault case intelligent matching system 100 for operation and maintenance technical services does not constitute a limitation on the embodiments of this application.

[0161] The memory 1003 is used to store program code for executing the embodiments of this application, and its execution is controlled by the processor 1001. The processor 1001 is used to execute the program code stored in the memory 1003 to implement the steps shown in the foregoing method embodiments.

[0162] The above description is only an optional implementation method for some implementation scenarios of this application. It should be noted that for those skilled in the art, other similar implementation methods based on the technical concept of this application, without departing from the technical concept of this application, also fall within the protection scope of the embodiments of this application.

Claims

1. A fault case intelligent matching method applied to operation and maintenance technical services, characterized in that, The method includes: Collect runtime sequence data, spatial distribution data, and store environment-related data of intelligent devices in chain stores, and construct a spatiotemporal evolution model of the current fault; Complete intervention process data for each historical failure case is extracted from the failure case database of the technology center. Combined with the large model knowledge base and robot-assisted decision-making logic, the intervention effectiveness of the historical failure cases is encoded to generate an effectiveness coding package for each historical failure case. The spatiotemporal evolution model of the current fault is dynamically balanced and adapted to the effectiveness coding packages of each historical fault case to calculate the matching degree of intervention effectiveness between each historical fault case and the current fault. Based on the intervention effectiveness matching degree, the intervention effectiveness simulation is performed on historical failure cases. The simulation is performed on the execution process of the intervention plan for each historical failure case in the current failure scenario. The service resource consumption nodes, failure mitigation nodes and stage goal achievement nodes are recorded in the simulation process, and a simulation result report is generated. For historical failure cases that meet the preset resource effect balance threshold in the simulation results report, conduct flexible intervention and adjustment tests to generate a target matching failure case set for the current failure. The process involves elastically intervening and adjusting historical fault cases that meet the preset resource effect balance threshold in the simulation results report, generating a target-matching fault case set for the current fault, including: Set resource effectiveness balance thresholds, which include the minimum standard for service resource consumption efficiency, the minimum standard for fault mitigation rate, and the minimum standard for phase target achievement rate. The resource effectiveness balance thresholds are set based on the current operational priority of the faulty store, the total amount of available service resources, and the fault handling time requirements. The service resource consumption efficiency, fault mitigation rate, and phase target achievement rate in the simulation results report of each historical fault case are compared with the preset resource effect balance threshold. Historical fault cases in which the service resource consumption efficiency, fault mitigation rate, and phase target achievement rate all reach or exceed the preset resource effect balance threshold are retained to form a flexible test case group. Extract factors that may change dynamically from the current fault scenario data. These factors may include changes in the real-time location of the on-site engineer, fluctuations in service outlet resource inventory, and changes in store environmental parameters. Set the change range and change time point for each factor that may change dynamically to form a dynamic change scenario table. The dynamic change scenario table includes scenario number, changing factor, change range, change time point, and parameters after the change. For each historical failure case in the resilience test case group, based on each scenario in the dynamic change scenario table, adjust the operation execution time, operation content, service resource investment quantity and engineer scheduling path of the intervention plan; Simulate the execution process of the adjusted intervention plan in a dynamically changing scenario, record the service resource consumption node, fault mitigation node and stage goal achievement node in each dynamically changing scenario, and calculate the service resource consumption efficiency, fault mitigation rate and stage goal achievement rate in each dynamically changing scenario. For each historical fault case, count the number of scenarios in which service resource consumption efficiency, fault mitigation rate, and stage target achievement rate reach the preset standards under all dynamic changing scenarios, and calculate the proportion of scenarios that meet the standards. The proportion of scenarios that meet the standards is the ratio of the number of scenarios in which service resource consumption efficiency, fault mitigation rate, and stage target achievement rate reach the preset standards to the total number of scenarios. Historical failure cases where the proportion of compliant scenarios reaches or exceeds the threshold are retained. Complete intervention plans, performance coding data, and engineer scheduling adaptation records are extracted from the retained historical failure cases. The complete intervention plans, performance coding data, and engineer scheduling adaptation records are integrated to form a target matching failure case set for the current failure. Each historical failure case in the target matching failure case set for the current failure includes basic case information, a complete intervention plan, and scheduling adaptation records. The basic case information includes the case number, the type of faulty equipment, and the intervention time. The complete intervention plan includes the operation sequence, resource requirements, and robot-assisted logic. The scheduling adaptation records include the dynamic scenario, adjustment content, and test results.

2. The fault case intelligent matching method for operation and maintenance technical services according to claim 1, characterized in that, The process of collecting runtime sequence data, spatial distribution data, and store environment-related data of intelligent devices in chain stores, and constructing a spatiotemporal evolution model of the current fault, includes: Collect operating parameters of air conditioning equipment, online status of information publishing terminals, and command response data of IoT control modules in chain stores at preset time intervals to form equipment operation sequence data; By combining the service network distribution map system, the real-time location of engineers around the faulty store and the service network resource reserve status are recorded, the optimal route for engineers to go to the faulty store and the network resource allocation nodes are marked, forming service resource spatial distribution data; Collect data on temperature and humidity, customer flow density, and power supply stability in the store. The collection frequency is synchronized with the data acquisition unit of the equipment. Record the time correlation points between changes in environmental parameters and changes in the fault status of smart devices to form environmental correlation data. The correlation point is determined based on the fact that the change in environmental parameters exceeds the preset threshold of the technical center and the corresponding change in the fault status of the equipment. The equipment runtime sequence data is classified according to equipment type. Each type of equipment corresponds to a set of time series parameter sequences. Trend analysis is performed on each set of time series parameter sequences to extract the parameter anomaly start time, anomaly change rate and anomaly stabilization stage. The fault state change curve of each type of equipment is determined. The horizontal axis of the fault state change curve is time, and the vertical axis is the parameter anomaly degree. The parameter anomaly degree is calculated based on the deviation ratio between the actual parameter value and the equipment's normal operating range preset by the technical center. Path analysis is performed on the spatial distribution data of service resources to extract the starting location of engineers, transfer nodes of service outlets and locations of faulty stores. The travel time, resource allocation time and response speed between each node are calculated, the resource reserve characteristics or road condition factors at each node are marked, and a service resource scheduling path map is constructed. Different line styles are used in the service resource scheduling path map to represent scheduling paths with different response speeds. Factor correlation analysis is performed on environmental data to count the correlation frequency between changes in each environmental parameter and changes in the fault state of intelligent devices. The strength of the effect of each environmental parameter on the change in fault state is calculated. The strength of the effect is determined based on the product of the correlation frequency and the magnitude of the change in fault state, forming an environmental factor strength table. The environmental factor strength table includes environmental parameter type, strength value and correlation time record. By integrating the equipment fault status change curve, service resource scheduling path diagram and environmental factor intensity table, a correlation between time and space dimensions is established. Each time node corresponds to a set of service resource scheduling location and environmental intensity data, forming a spatiotemporal evolution model of the current fault. Each evolution stage in the spatiotemporal evolution model is assigned a stage identifier, which includes the stage's time range, service resource scheduling range, and main environmental influencing factors.

3. The fault case intelligent matching method for operation and maintenance technical services according to claim 2, characterized in that, The calculation of the effect of each environmental parameter on the change in fault state includes: Extract all environmental parameter change records and corresponding smart device fault status change records from the environmental correlation data, and establish an environmental-fault correlation data table. Each row in the environmental-fault correlation data table includes the environmental parameter type, environmental parameter change time, environmental parameter change range, corresponding fault status change time, fault status change range, and associated device type. The records in the environment-fault association data table are grouped by environmental parameter type, with each group corresponding to all associated records for one type of environmental parameter; For each set of related records, the environmental parameter change range and fault state change range of each record are divided by the corresponding normal change benchmark value preset by the technical center to convert them into dimensionless change rates. Then, the ratio of the environmental parameter change rate to the fault state change rate of each record is calculated. This ratio reflects the proportion of the impact of a single environmental parameter change on the fault state change. Calculate the time difference between environmental parameter changes and fault state changes in each group of related records. The time difference is the time of fault state change minus the time of environmental parameter change. Filter records whose time difference is within the preset range of the technical center as valid records with direct correlation. Calculate the average impact ratio of each group of valid records. The average impact ratio reflects the average degree of influence of the environmental parameter on the change of fault state. The number of valid records in each group is counted, and the proportion of valid records to the total number of records associated with the environmental parameter is calculated. The proportion of valid records to the total number of records associated with the environmental parameter reflects the stability of the association between the environmental parameter and the change in fault state. Multiply the average influence ratio by the ratio of the number of valid records to the total number of records associated with the environmental parameter to obtain the dimensionless influence strength of the environmental parameter on the change of fault state. The calculated intensity of action is calibrated to a range, and each intensity of action is mapped to a preset range through linear transformation.

4. The fault case intelligent matching method for operation and maintenance technical services according to claim 1, characterized in that, The complete intervention process data of each historical failure case is extracted from the failure case database of the technology center. Combined with the large model knowledge base and robot-assisted decision-making logic, the intervention effectiveness of the historical failure cases is encoded to generate an effectiveness encoding package for each historical failure case, including: The complete intervention process data for each historical fault case is retrieved from the intervention process database of the technical center's fault case library. This complete intervention process data includes on-site engineer operation records, service network resource input records, and fault mitigation monitoring records. The engineer operation records include the execution time, operation content, operating equipment, and execution engineer number for each operation. The resource input records include the input time, quantity, input network, and resource type for each type of service resource. The fault mitigation monitoring records include the time, monitoring indicators, indicator values, and equipment status assessment results for each monitoring session. The engineer's operation records are organized chronologically, and all operations are arranged in the order of execution time. The execution duration, operation interval, and time correlation between the operation and the change of fault status are extracted for each operation to form an operation execution time sequence table. The operation execution time sequence table includes operation number, execution time, execution duration, operation content, and associated fault status change. Trajectory analysis is performed on the resource input records of service outlets. The input changes of each resource are recorded in chronological order. The input amount, input rate and distribution of each resource at different intervention stages are calculated to form a resource input trajectory map. In the resource input trajectory map, the horizontal axis is time and the vertical axis is input amount. Different resources are represented by curves of different colors. Time-series analysis is performed on fault mitigation monitoring records to extract the changing trends of monitoring indicators, determine the key time nodes for fault mitigation, the degree of mitigation at each node, and the final mitigation effect, and form a fault mitigation effect time-series diagram. In the fault mitigation effect time-series diagram, the horizontal axis is time and the vertical axis is the degree of mitigation. The degree of mitigation is determined based on the ratio of the actual value of the monitoring indicator to the normal operating range of the equipment preset by the technical center. Based on the operation execution time sequence table and the large model knowledge base, the spatiotemporal adaptation features of the intervention operation are extracted. The time window adaptability of the operation execution refers to the matching of the operation execution time with the key nodes of the fault state change, and the spatial adaptability of the operation object refers to the correlation between the operation location and the distribution location of the faulty equipment. Based on the resource input trajectory map, the dynamic distribution characteristics of service resource consumption are extracted, including the resource input ratio at different intervention stages, the distribution density of resources among service outlets, and the time synchronization between resource input and fault mitigation. Based on the time series diagram of fault mitigation effect, the stage effectiveness characteristics of fault mitigation are extracted, including the mitigation rate, mitigation duration and contribution ratio of stage mitigation effect to the overall mitigation effect of each intervention stage. The spatiotemporal adaptation feature coding of intervention operations, the dynamic distribution feature coding of service resource consumption, and the phased effectiveness feature coding of fault mitigation are integrated to form an effectiveness coding package for historical fault cases. Each effectiveness coding package is assigned a unique coding identifier, which includes the historical fault case number, fault equipment type, intervention time, and effectiveness indicators.

5. The intelligent fault case matching method for operation and maintenance technical services according to claim 4, characterized in that, The process of extracting spatiotemporal adaptation features of intervention operations based on the operation execution time sequence table and the large model knowledge base includes: Extract the execution time of each operation from the operation execution time sequence table, and extract the key nodes of fault state change from the fault mitigation effect time sequence diagram of historical fault cases. The key nodes of fault state change include fault propagation acceleration nodes, fault state stabilization nodes, and fault mitigation initiation nodes. Calculate the execution time of each operation and the time difference between the critical nodes of each fault state change. The time difference is the operation execution time minus the time of the critical node of the fault state change. When the time difference is within the preset positive range, the operation execution timing is after the critical node of the fault state change and meets the response interval standard. The time window adaptability of the operation is determined to meet the positive response adaptability standard preset by the technical center. When the time difference is within the preset negative range, the operation execution timing is before the critical node of the fault state change and meets the preparatory interval standard. The time window adaptability of the operation is determined to meet the negative response adaptability standard preset by the technical center. When the time difference exceeds the preset range, the operation execution timing does not meet the response interval standard. The time window adaptability of the operation is determined to not meet the response adaptability standard preset by the technical center. The time window adaptability assessment results for each operation are statistically analyzed. The proportions that meet the positive response adaptability standard, the negative response adaptability standard, and the non-compliance of the response adaptability standard are calculated to form the time window adaptability feature value of the operation. The time window adaptability feature value is represented by three digits, which correspond to the proportions that meet the positive response adaptability standard, the negative response adaptability standard, and the non-compliance of the response adaptability standard, respectively. Extract the faulty equipment propagation path from the equipment spatial distribution data of historical fault cases, and determine the key location points in the faulty equipment propagation path. The key location points in the faulty equipment propagation path include the location of the faulty starting equipment, the location of the equipment in the main propagation direction, and the location of the affected related equipment. Extract the execution location information of each operation from the operation execution sequence table, calculate the distance between the execution location and the key location points in the fault equipment propagation path, calculate the number of key location points in the fault equipment propagation path whose distance is within the preset range of the technology center, and the number of key location points in the fault equipment propagation path whose distance is within the preset range of the technology center reflects the degree of correlation between the execution location and the fault equipment propagation path. By comparing the number of key points whose distance from the operation execution location to the critical location of the faulty equipment falls within a preset range with the preset number threshold range, the spatial adaptability level of the operation is determined. Based on the determination results of all operations, the proportion of each level is statistically analyzed to quantify and characterize its spatial adaptability features. The temporal window adaptability feature value and spatial adaptability feature value of each operation are combined to form the spatiotemporal adaptability feature code of the operation. The spatiotemporal adaptability feature code format is temporal feature value - spatial feature value. All spatiotemporal adaptation feature codes of operations are arranged in the order of operation execution to form the spatiotemporal adaptation feature code sequence of intervention operations. The spatiotemporal adaptation feature code sequence of intervention operations serves as the core content of the spatiotemporal adaptation features of intervention operations in the effectiveness coding package.

6. The intelligent fault case matching method for operation and maintenance technical services according to claim 1, characterized in that, The process of dynamically balancing and adapting the spatiotemporal evolution model of the current fault with the performance coding packages of each historical fault case, and calculating the intervention performance matching degree between each historical fault case and the current fault, includes: Resource demand data for each evolution stage is extracted from the spatiotemporal evolution model of the current fault, including the type of service resources required for each stage, the quantity of resources, the time window for resource input, and the network requirements for resource input, forming a stage resource demand table. The stage resource demand table includes stage number, time range, resource type, quantity required, time window, and network requirements. Extract the dynamic distribution feature code of service resource consumption from the efficiency coding package of historical failure cases, and parse the dynamic distribution feature code of service resource consumption to obtain the resource input type, input quantity, input time and input network of the historical failure case in each intervention stage, forming a stage resource supply table. The stage resource supply table includes stage number, time range, resource type, supply quantity, input time and input network. The phased resource demand table and phased resource supply table are linked by phase number. The resource type matching degree, quantity matching degree, time matching degree, and network matching degree are calculated for each phase. The resource type matching degree is the overlap ratio between the supply resource type and the demand resource type. The quantity matching degree is calculated based on the ratio of supply quantity to demand quantity. When the demand quantity is not zero, the quantity matching degree is the ratio of supply quantity to demand quantity. When the demand quantity is zero, the quantity matching degree is set to a preset benchmark value. The time matching degree is the overlap ratio between the supply input time and the demand time window. The network matching degree is the compliance ratio between the supply input network points and the demand network point requirements. Based on the degree of influence of each dimension of service resources on the intervention effect, the weights of each dimension are set according to the preset weight allocation rules of the technology center. The matching degree of each dimension is multiplied by the corresponding dimension weight, all product results are summed, and the summation results are standardized to obtain the resource matching sub-score. The fault status data of each evolution stage is extracted from the spatiotemporal evolution model of the current fault, including the scope of equipment affected by the fault, the severity of the equipment fault, and the fault development trend of each stage, to form a stage fault status table. The stage fault status table includes the stage number, time range, scope of impact, severity, and development trend. Extract the stage efficacy feature codes of fault mitigation from the efficacy coding package of historical fault cases, parse the stage efficacy feature code content of fault mitigation to obtain the mitigation range, mitigation degree and mitigation duration of the historical fault case in each intervention stage, and form a stage mitigation effect table. The stage mitigation effect table includes stage number, time range, mitigation range, mitigation degree and duration. The stage fault status table and the stage mitigation effect table are associated by stage number. The range matching degree, severity matching degree and trend matching degree of each stage are calculated. The range matching degree is the overlap ratio between the mitigation range and the range of equipment affected by the fault. The severity matching degree is calculated based on the ratio of the mitigation degree to the severity of the equipment fault. When the severity of the equipment fault is not zero, the severity matching degree is the ratio of the mitigation degree to the severity of the equipment fault. When the severity of the equipment fault is zero, the severity matching degree is set to a preset baseline value. The trend matching degree is the reversal ratio of the fault development trend during the mitigation period. Based on the contribution of each dimension of the effect to fault mitigation, the weights of each dimension are set according to the preset weight allocation rules of the technical center. The matching degree of each dimension is multiplied by the corresponding dimension weight, all product results are summed, and the summation results are standardized to obtain the effect fitter score. Based on the degree of influence of resource adaptation and effect adaptation on the overall intervention effectiveness, resource adaptation weight and effect adaptation weight are set according to the preset weight allocation rules of the technical center. The resource adaptation sub-score is multiplied by the resource adaptation weight, and the effect adaptation sub-score is multiplied by the effect adaptation weight. The two product results are summed to obtain the comprehensive adaptation score. Calculate the average comprehensive fit score across all stages, and use the average comprehensive fit score across all stages as the matching degree of intervention effectiveness between the historical failure case and the current failure.

7. The intelligent fault case matching method for operation and maintenance technical services according to claim 1, characterized in that, The intervention effectiveness simulation based on the intervention effectiveness matching degree is used to simulate the execution process of the intervention plan for each historical failure case in the current failure scenario. The simulation records the service resource consumption nodes, failure mitigation nodes, and stage goal achievement nodes during the simulation process, generating a simulation result report, including: The spatiotemporal adaptation feature codes of intervention operations are extracted from the performance coding packages of historical failure cases. Combined with the robot-assisted decision-making logic of the technology center, the spatiotemporal adaptation feature codes of intervention operations are analyzed to obtain a complete sequence of intervention operations. The sequence of intervention operations includes the execution order, operation content, operation equipment, scheduling logic of the executing engineer, and resource allocation path of the service network. An intervention operation deduction table is formed, which includes the operation number, execution order, operation content, operation equipment, engineer scheduling logic, and resource allocation path. Initial fault state data is extracted from the spatiotemporal evolution model of the current fault. The initial fault state data includes the initial fault location, the initial range of affected equipment, the initial fault severity, and the initial environmental influence intensity. The initial fault state data is used as the starting state for the deduction. Following the execution order of the intervention operation simulation table, simulate the execution process of each operation in turn. Before each operation is executed, record the current fault status data and service resource inventory data. The current fault status data includes the scope of affected equipment, the severity of equipment failure, and the failure development trend. The current service resource inventory data includes resource type, remaining quantity, and reserve network location. During the simulation, the current fault status data is adjusted based on the operation content and equipment, combined with the robot-assisted support logic of the technical center. When the operation targets the fault propagation path, the rate of expansion of the equipment's influence range is reduced; when the operation targets the fault root cause equipment, the rate of deepening of the fault severity of a single equipment is reduced; when the operation targets environmental influencing factors, the intensity of environmental effects is weakened. Based on the type and quantity of service resources required for the operation, and combined with the physical location system of the on-site engineer and the resource data of the service outlet, the current service resource inventory data is adjusted to reduce the remaining quantity of the corresponding resources. The time, quantity and reserve outlet location of resource consumption are recorded to form a service resource consumption node record. The service resource consumption node record includes the operation number, consumption time, resource type, consumption quantity and reserve outlet location. After each operation is performed, the adjusted fault status data is recorded. The changes in fault status before and after the operation are compared. When the magnitude of the change in fault status reaches the mitigation standard preset by the technical center, it is marked as a fault mitigation node. The fault mitigation node record includes the operation number, mitigation time, mitigation equipment range, mitigation degree and corresponding operation content. According to the current spatiotemporal evolution model of the fault, at the end of each stage, the preset goals of the stage are compared with the actual simulation results. The preset goals of the stage include controlling the scope of equipment affected by the fault within the preset value of the technical center and reducing the severity of equipment faults to the preset proportion of the technical center. When the actual simulation results reach the preset goals of the stage, it is marked as the stage goal achievement node. The stage goal achievement node record includes the stage number, achievement time, goal content, actual results and achievement conditions. After completing the simulation of all intervention operations, the total number of service resource consumption nodes, the total number of fault mitigation nodes, and the total number of nodes achieving the stage goals are counted. The service resource consumption efficiency, fault mitigation rate, and stage goal achievement rate are calculated. The service resource consumption efficiency is the ratio of the total mitigation effect to the equivalent value of the total service resource consumption. The equivalent value of the total service resource consumption is a comprehensive value obtained by converting the consumption of different types of service resources according to the resource value coefficient preset by the technical center. The fault mitigation rate is the ratio of the total mitigation degree to the total simulation time. The stage goal achievement rate is the ratio of the number of achieved stages to the total number of stages. The simulation results report is formed by integrating the initial state of the simulation, the records of the intervention operation simulation process, the records of service resource consumption nodes, the records of fault mitigation nodes, the records of the stage goal achievement nodes, statistical data and calculation results. The simulation results report includes a simulation overview, detailed process records, key node analysis and simulation effect evaluation.

8. The intelligent fault case matching method for operation and maintenance technical services according to claim 1, characterized in that, The simulated and adjusted intervention plan is executed in a dynamically changing scenario, recording the service resource consumption nodes, fault mitigation nodes, and stage goal achievement nodes for each scenario, including: For each dynamically changing scenario, the changing factors, the magnitude of change, the time point of change, and the parameters after the change are extracted from the dynamic changing scenario table. The corresponding parameters in the spatiotemporal evolution model of the current fault scenario are then updated to form a scenario-based spatiotemporal evolution model. The operation execution sequence is extracted from the adjusted intervention plan. The operation execution sequence of the adjusted intervention plan includes the adjusted operation execution time, operation content, operation equipment, engineer scheduling path and service network resource allocation rules, forming a scenario-based intervention operation table. The scenario-based intervention operation table includes operation number, execution time, operation content, operation equipment, scheduling path and allocation rules. The initial state of the scenario-based spatiotemporal evolution model is used as the starting state for the deduction. The initial state of the scenario-based spatiotemporal evolution model includes the location of the faulty equipment, the scope of impact, the severity, the intensity of environmental effects, and the distribution of service resource inventory corresponding to the changed parameters. Following the execution order of the scenario-based intervention operation table, the execution process of each adjusted operation is simulated sequentially. Before the operation is executed, the fault status data and service resource inventory data in the current scenario-based spatiotemporal evolution model are recorded. The fault status data in the current scenario-based spatiotemporal evolution model includes the scope of affected equipment, the severity of equipment failure, the failure development trend, and environmental parameters. The service resource inventory data in the current scenario-based spatiotemporal evolution model includes resource type, remaining quantity, reserve network location, and engineer real-time location. During the simulation operation, the fault status data in the current scenario-based spatiotemporal evolution model is adjusted according to the adjusted operation content and operation equipment, combined with the parameters of the scenario-based spatiotemporal evolution model. Based on the adjusted service resource input quantity and engineer scheduling path, adjust the service resource inventory data and engineer location information in the current scenario-based spatiotemporal evolution model, record the service resource consumption time, quantity, reserve network location and engineer scheduling node, and form a service resource consumption node record under this dynamic change scenario. The service resource consumption node record under this dynamic change scenario includes scenario number, operation number, consumption time, resource type, consumption quantity, reserve network location and engineer number. After each adjusted operation is executed, the fault state data in the adjusted scenario-based spatiotemporal evolution model is recorded. The changes in the fault state in the scenario-based spatiotemporal evolution model before and after the operation are compared. When the magnitude of the change in the fault state in the scenario-based spatiotemporal evolution model reaches the mitigation standard under the dynamic change scenario, it is marked as a fault mitigation node under the dynamic change scenario. The fault mitigation node record under the dynamic change scenario includes scenario number, operation number, mitigation time, mitigation equipment range, mitigation degree and corresponding operation content. The mitigation standard under the dynamic change scenario is set based on the magnitude of the change in the fault state in the scenario-based spatiotemporal evolution model. According to the phase division of the scenario-based spatiotemporal evolution model, at the end of each phase, the scenario-based goal of that phase is compared with the actual simulation result. The scenario-based goal of that phase is adjusted based on the dynamic change parameters of the scenario-based spatiotemporal evolution model. When the actual simulation result reaches the scenario-based goal of that phase, it is marked as the phase goal achievement node under the dynamic change scenario. The phase goal achievement node record under the dynamic change scenario includes scenario number, phase number, achievement time, goal content, actual result and achievement conditions. After completing the simulation of all adjusted operations under this dynamic change scenario, the service resource consumption node records, fault mitigation node records, and stage goal achievement node records under this dynamic change scenario are compiled to form a summary table of simulation nodes for this dynamic change scenario. Repeat the above process for all dynamically changing scenarios to form a summary table of deduction nodes for each dynamically changing scenario.

9. A fault case intelligent matching system applied to operation and maintenance technical services, characterized in that, The method includes a processor and a computer-readable storage medium storing machine-executable instructions, which, when executed by the processor, implement the fault case intelligent matching method for operation and maintenance technical services as described in any one of claims 1-8.

Images