Event data processing method and device and electronic equipment

Abstract

The invention discloses an event data processing method and device and electronic equipment, and belongs to the technical field of resource scheduling. The event data processing method comprises the following steps: acquiring first feature information of each candidate object resource in a candidate object resource library, and acquiring second feature information of a to-be-processed event; in response to a processing request corresponding to the to-be-processed event, matching the candidate object resources with the to-be-processed event by taking at least one of the highest skill matching degree, the shortest processing time, the least resource consumption and the lowest risk diffusion degree as a target to obtain a resource matching scheme; and outputting target processing information of the to-be-processed event based on the resource matching scheme. According to the method, the conversion from local response to global optimization can be realized, and the event handling accuracy and efficiency are remarkably improved.

Description

Technical Field

[0001] This application belongs to the field of resource scheduling technology, and in particular relates to a method, apparatus and electronic device for processing event data. Background Technology

[0002] In large public buildings (such as subway hubs, highway service areas, airport terminals, and stadiums), the electromechanical systems (including HVAC, water supply and drainage, power distribution, lighting, elevators, and fire protection) are massive in scale and highly coupled. If a fault or abnormal event occurs, and appropriate resources (such as professional maintenance personnel, spare parts, emergency power supplies, or remote control strategies) cannot be matched in a timely manner, it can easily lead to cascading system failures, service interruptions, and even security risks. Therefore, building an efficient event and resource matching mechanism within the integrated monitoring and management platform for electromechanical systems not only helps to achieve rapid fault location and accurate response but also optimizes human resource scheduling, reduces maintenance costs, and inhibits the spread of risks, which is of great significance for ensuring the safe, stable, and efficient operation of public buildings.

[0003] Currently, resources are typically allocated to events based on the principle of proximity. This may lead to skill mismatch, resource overload, or low processing efficiency, neglecting global optimization and thus affecting the overall response effect. Summary of the Invention

[0004] This invention aims to address at least one of the technical problems existing in the prior art. To this end, this invention proposes a method, apparatus, and electronic device for processing event data, which can realize a shift from local response to global optimization, significantly improving the accuracy and efficiency of event handling.

[0005] Firstly, this application provides a method for processing event data, including: Obtain the first feature information of each candidate object resource in the candidate object resource library, and obtain the second feature information of the event to be processed; In response to the processing request corresponding to the pending event, with the goal of at least one of the following: highest skill matching degree, shortest processing time, least resource consumption, and lowest risk diffusion degree, the candidate object resources are matched with the pending event to obtain a resource matching scheme. Based on the resource matching scheme, the target processing information of the event to be processed is output.

[0006] According to the event data processing method of this application, by obtaining the first feature information of candidate object resources and the second feature information of the event to be processed, when responding to the event processing request, multi-dimensional intelligent matching is performed with the goal of at least one of the following: highest skill matching degree, shortest processing time, least resource consumption, and lowest risk diffusion degree. This generates a better resource matching scheme and outputs target processing information, which can realize the transformation from local response to global optimization and significantly improve the accuracy and efficiency of event handling.

[0007] According to one embodiment of this application, the candidate object resources are divided into personnel object resources and equipment object resources. The first feature information is divided into first feature sub-information of the personnel object resources and second feature sub-information of the equipment object resources. Obtaining the first feature information of each candidate object resource in the candidate object resource library includes: Obtain the identity information, skill qualification information, real-time status information, and historical event processing information of the personnel object resources; Based on the identity information, the skill qualification information, the real-time status information, and the historical event processing information, the first feature sub-information is obtained; Obtain the attribute information, real-time operation information, location distribution information, and historical maintenance information of the device object resources; The second feature sub-information is obtained based on the attribute information, the real-time operation information, the location distribution information, and the historical maintenance information.

[0008] According to one embodiment of this application, obtaining the first feature sub-information based on the identity information, the skill qualification information, the real-time status information, and the historical event processing information includes: The identity information is directly used as the first feature sub-information corresponding to the identity information; The skill types in the skill qualification information are numbered, the skill levels in the skill qualification information are represented by numerical values, and the skill proficiency is calculated based on the skill qualification information to obtain the first feature sub-information corresponding to the skill qualification information. The skill proficiency is determined based on the number of successful event processing, the average event processing score, and the event processing complexity in the skill qualification information. The on-duty status in the real-time status information is represented by a binary value, the event identifier of the current task in the real-time status information is identified, the location coordinate value in the real-time status information is retained, and the continuous working duration is calculated based on the real-time status information to obtain the first feature sub-information corresponding to the real-time status information. The types of historical events in the historical event processing information are encoded and statistically analyzed. Based on the historical event processing information, the historical handling success rate and the historical average handling time are calculated to obtain the first feature sub-information corresponding to the historical event processing information.

[0009] According to one embodiment of this application, the skill proficiency is determined through the following steps: Based on the event processing complexity, a first weight coefficient is assigned to the number of successful event processing, and a second weight coefficient is assigned to the average event processing score. The first weight coefficient is positively correlated with the event processing complexity, and the sum of the first weight coefficient and the second weight coefficient is equal to a first value. The skill proficiency is determined based on the number of successful event handlings, the average event handling score, the first weighting coefficient, and the second weighting coefficient.

[0010] According to one embodiment of this application, obtaining the second feature sub-information based on the attribute information, the real-time operation information, the location distribution information, and the historical maintenance information includes: The attribute information is directly used as the second feature sub-information corresponding to the attribute information; The operation data and energy consumption data in the real-time operation information are retained, and the fault warning data in the real-time operation information is represented in binary to obtain the second feature sub-information corresponding to the real-time operation information; The installation location coordinates in the location distribution information are retained, and the region and associated scene in the location distribution information are numbered to obtain the second feature sub-information corresponding to the location distribution information; The historical maintenance information is directly used as the second feature sub-information corresponding to the historical maintenance information.

[0011] According to one embodiment of this application, obtaining the second feature information of the event to be processed includes: Obtain the technical complexity, spatial complexity, time complexity, and risk diffusion information of the event to be processed; The second feature information is obtained based on the technical complexity information, the spatial complexity information, the time complexity information, and the risk diffusion information.

[0012] According to one embodiment of this application, the step of matching the candidate resources with the event to be processed to obtain a resource matching scheme, with at least one of the following as the objective: highest skill matching degree, shortest processing time, least resource consumption, and lowest risk diffusion degree, includes: The candidate resource is matched with the event to be processed by weighting and summing the reciprocal of skill matching degree, processing time, resource consumption and risk diffusion degree, with the goal of minimizing the weighted sum.

[0013] According to one embodiment of this application, the step of outputting the target processing information of the event to be processed based on the resource matching scheme includes: The resource matching scheme will be simulated in a digital twin environment; Based on at least one key indicator output from the deduction process of the resource matching scheme, the resource matching scheme is optimized, and the target processing information includes the optimized resource matching scheme; Output the target processing information.

[0014] Secondly, this application provides an event data processing apparatus, the apparatus comprising: The acquisition module is used to acquire the first feature information of each candidate object resource in the candidate object resource library and to acquire the second feature information of the event to be processed. The first processing module is used to respond to the processing request corresponding to the event to be processed, and to match the candidate object resources with the event to be processed with at least one of the following as objectives: highest skill matching degree, shortest processing time, least resource consumption, and lowest risk diffusion degree, to obtain a resource matching scheme. The second processing module is used to output the target processing information of the event to be processed based on the resource matching scheme.

[0015] According to the event data processing apparatus of this application, by acquiring the first feature information of candidate object resources and the second feature information of the event to be processed, when responding to an event processing request, multi-dimensional intelligent matching is performed with the goal of at least one of the following: highest skill matching degree, shortest processing time, least resource consumption, and lowest risk diffusion degree. This generates a better resource matching scheme and outputs target processing information, which can realize the transformation from local response to global optimization and significantly improve the accuracy and efficiency of event handling.

[0016] Thirdly, this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the event data processing method described in the first aspect above.

[0017] Fourthly, this application provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the event data processing method described in the first aspect above.

[0018] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the event data processing method as described in the first aspect above.

[0019] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0020] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1 This is one of the flowcharts illustrating the event data processing method provided in the embodiments of this application; Figure 2 This is a second schematic flowchart of the event data processing method provided in the embodiments of this application; Figure 3 This is the third flowchart illustrating the event data processing method provided in the embodiments of this application; Figure 4 This is the fourth flowchart illustrating the event data processing method provided in the embodiments of this application; Figure 5 This is a schematic diagram of the structure of the event data processing device provided in the embodiments of this application; Figure 6 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0021] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0022] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0023] The following description, in conjunction with the accompanying drawings, details the event data processing method, event data processing apparatus, electronic device, and readable storage medium provided in the embodiments of this application through specific examples and application scenarios.

[0024] The event data processing method can be applied to the terminal, and can be executed by the hardware or software in the terminal.

[0025] The event data processing method provided in this application embodiment can be executed by an electronic device or a functional module or entity in an electronic device that can implement the event data processing method. The electronic devices mentioned in this application embodiment include, but are not limited to, mobile phones, tablets, computers, cameras, and wearable devices. The event data processing method provided in this application embodiment will be described below using an electronic device as the execution subject as an example.

[0026] like Figure 1 As shown, the method for processing the event data includes steps 110, 120, and 130.

[0027] Step 110: Obtain the first feature information of each candidate object resource in the candidate object resource library, and obtain the second feature information of the event to be processed.

[0028] Among them, the candidate object resource library is a collection of resources that can be used to process events, the candidate object resource refers to the individual among these resources, the first feature information is data describing the attributes of the candidate object resource, the event to be processed refers to the task or situation that needs to be solved or processed, and the second feature information is data describing the attributes of the event to be processed.

[0029] In this step, attribute data of candidate object resources can be extracted from databases, sensors, manual input, or natural language processing to obtain first feature information, and descriptive data of the event to be processed can be extracted to obtain second feature information.

[0030] Step 120: In response to the processing request corresponding to the event to be processed, with the goal of at least one of the following: highest skill matching degree, shortest processing time, least resource consumption, and lowest risk diffusion degree, the candidate object resources are matched with the event to be processed to obtain a resource matching scheme.

[0031] In this embodiment, when a processing request for an event is received, the system focuses on one or more of the following factors: highest skill matching degree, shortest processing time, least resource consumption, and lowest risk diffusion. It also combines the specific needs of the event to be processed (such as required skills, processing time limit, and tolerable resource consumption) with the attributes of candidate resources (such as skills possessed, historical processing speed, resource occupation cost, and risk control capabilities) to determine the most suitable resource allocation scheme, thereby achieving efficient, economical, and low-risk event handling.

[0032] Step 130: Based on the resource matching scheme, output the target processing information of the events to be processed.

[0033] Among them, target processing information refers to the disposal instructions or decision-making content generated based on the resource matching scheme to guide the specific execution of the pending events, including information such as allocated resources, action plans, and time arrangements.

[0034] In this step, based on the resource matching scheme, the matching results are transformed into specific execution instructions or decision content, thereby generating target processing information for the events to be processed, in order to guide subsequent event handling actions.

[0035] According to the event data processing method provided in the embodiments of this application, by obtaining the first feature information of candidate object resources and the second feature information of the event to be processed, when responding to the event processing request, multi-dimensional intelligent matching is performed with the goal of at least one of the following: highest skill matching degree, shortest processing time, least resource consumption, and lowest risk diffusion degree. This generates a better resource matching scheme and outputs target processing information, which can realize the transformation from local response to global optimization and significantly improve the accuracy and efficiency of event handling.

[0036] In some embodiments, candidate object resources are divided into personnel object resources and equipment object resources, and the first feature information is divided into first feature sub-information of personnel object resources and second feature sub-information of equipment object resources. Obtaining the first feature information of each candidate object resource in the candidate object resource library includes: Obtain the identity information, skill qualification information, real-time status information, and historical event processing information of personnel resources; Based on identity information, skill qualification information, real-time status information, and historical event processing information, the first feature sub-information is obtained; Obtain the attribute information, real-time operation information, location distribution information, and historical maintenance information of the device object resources; The second feature sub-information is obtained based on attribute information, real-time operation information, location distribution information, and historical maintenance information.

[0037] Among them, identity information is used to identify the basic identity of personnel resources (such as name, employee number, and affiliated unit), skill qualification information describes the professional ability and certification qualifications of personnel resources, real-time status information reflects the current availability and location of personnel resources, and historical event processing information records the types, performance, and handling effects of past events in which personnel resources participated.

[0038] In this embodiment, by performing structured integration and feature encoding on identity information, skill qualification information, real-time status information, and historical event processing information, a first feature sub-information for matching calculation of personnel object resources is formed.

[0039] In this embodiment, attribute information describes the basic specifications and functional characteristics of the device object resource, real-time operation information reflects the current working status and performance parameters of the device object resource, location distribution information indicates the physical or logical deployment location of the device object resource, and historical maintenance information records the past maintenance, upkeep, and fault handling of the device object resource.

[0040] In this embodiment, by performing structured integration and feature encoding on attribute information, real-time operation information, location distribution information, and historical maintenance information, a second feature sub-information for matching calculation of device object resources is formed.

[0041] In some embodiments, the first feature sub-information is obtained based on identity information, skill qualification information, real-time status information, and historical event processing information, including: The identity information is directly used as the first feature sub-information corresponding to the identity information; The skill types in the skill qualification information are numbered, the skill levels in the skill qualification information are represented by numerical values, and the skill proficiency is calculated based on the skill qualification information to obtain the first feature sub-information corresponding to the skill qualification information. Among them, the skill proficiency is determined based on the number of successful event processing, the average event processing score, and the event processing complexity in the skill qualification information. The on-duty status in the real-time status information is represented by binary values. The event identifier of the current task in the real-time status information is identified. The location coordinate values ​​in the real-time status information are retained. The continuous working duration is calculated based on the real-time status information to obtain the first feature sub-information corresponding to the real-time status information. The types of historical events in the historical event processing information are encoded and statistically analyzed. Based on the historical event processing information, the historical success rate and the historical average processing time are calculated to obtain the first feature sub-information corresponding to the historical event processing information.

[0042] In this embodiment, the first feature sub-information of the corresponding dimension is constructed by directly retaining the identity information, numbering and quantifying the skill qualification information and calculating the skill proficiency, converting the real-time status information into binary, event identifier, coordinate and continuous working duration, and encoding and statistically processing the historical event processing information.

[0043] In some embodiments, skill proficiency is determined by the following steps: Based on the complexity of event processing, a first weight coefficient is assigned to the number of successful event processing, and a second weight coefficient is assigned to the average event processing score. The first weight coefficient is positively correlated with the complexity of event processing, and the sum of the first weight coefficient and the second weight coefficient is equal to the first value. Skill proficiency is determined based on the number of successful event handlings, the average event handling score, the first weighting coefficient, and the second weighting coefficient.

[0044] In this embodiment, firstly, based on the complexity of event processing, a first weighting coefficient is configured for the number of successful event processing attempts, and a second weighting coefficient is configured for the average event processing score (wherein the first weighting coefficient increases with the complexity of event processing, and the sum of the first weighting coefficient and the second weighting coefficient is equal to a preset first value); then, by combining the number of successful event processing attempts, the average event processing score, and the first and second weighting coefficients configured above, the corresponding skill proficiency is calculated through weighted calculation.

[0045] In some embodiments, the second feature sub-information is obtained based on attribute information, real-time operation information, location distribution information, and historical maintenance information, including: The attribute information is directly used as the second feature sub-information corresponding to the attribute information; The operation data and energy consumption data in the real-time operation information are retained, and the fault warning data in the real-time operation information are represented in binary to obtain the second feature sub-information corresponding to the real-time operation information. The installation location coordinates in the location distribution information are retained, and the region and associated scene in the location distribution information are numbered to obtain the second feature sub-information corresponding to the location distribution information. Historical maintenance information is directly used as the second feature sub-information corresponding to historical maintenance information.

[0046] In this embodiment, attribute information is directly used as its corresponding second feature sub-information; operation data and energy consumption data are extracted from real-time operation information, and fault warning data is converted into binary form and integrated as the second feature sub-information corresponding to real-time operation information; the installation location coordinates in the location distribution information are retained, and the region and associated scene are numbered to form the second feature sub-information corresponding to the location distribution information; historical maintenance information is directly used as its corresponding second feature sub-information, and finally, the complete second feature sub-information is obtained.

[0047] In some embodiments, obtaining second characteristic information of the event to be processed includes: Obtain information on the technical complexity, spatial complexity, time complexity, and risk diffusion of the event to be processed; The second feature information is obtained based on the technical complexity information, spatial complexity information, time complexity information, and risk diffusion information.

[0048] Among them, technical complexity information reflects the technical difficulty and professional capabilities required for the event to be processed; spatial complexity information reflects the storage or resource consumption required during the processing of the event to be processed; time complexity information reflects the processing time or response delay of the event to be processed; and risk diffusion information reflects the potential impact range and propagation speed of the event.

[0049] In this embodiment, the technical complexity, spatial complexity, temporal complexity, and risk diffusion information of the event to be processed are collected respectively. Then, the above four types of information are fused or weighted to form a structured comprehensive representation, namely the second feature information, which is used for subsequent analysis, classification, or decision support.

[0050] In some embodiments, a resource matching scheme is obtained by matching candidate resources with events to be processed, with the goal of achieving the highest skill matching degree, the shortest processing time, the least resource consumption, and the lowest risk diffusion. This includes: The reciprocal of skill matching degree, processing time, resource consumption, and risk diffusion degree are weighted and summed. The goal is to minimize the weighted sum and match candidate resources with events to be processed.

[0051] In this embodiment, the reciprocal of skill matching degree, processing time, resource consumption and risk diffusion degree are assigned corresponding weights and then summed in a weighted manner to construct a comprehensive cost function. The optimal resource matching scheme is solved by an optimization algorithm with the goal of minimizing the weighted sum result.

[0052] In some embodiments, based on a resource matching scheme, target processing information for the events to be processed is output, including: The resource matching scheme will be simulated in a digital twin environment; Based on at least one key indicator output from the deduction process of the resource matching scheme, optimize the resource matching scheme, and the target processing information includes the optimized resource matching scheme. Output target processing information.

[0053] In this embodiment, based on the resource matching scheme, it is first dynamically simulated in a digital twin environment to simulate the actual handling process of candidate resources for the events to be processed. During the simulation, at least one key indicator (such as actual processing time, resource load balancing, risk suppression effect, or task completion rate) is collected. Subsequently, the original resource matching scheme is iteratively optimized based on the feedback of the key indicator (e.g., adjusting weights, replacing inefficient resources, or reallocating tasks) to generate an optimized resource matching scheme. The final output target processing information includes the optimized resource matching scheme and its corresponding expected processing efficiency.

[0054] The following is a specific implementation of an event data processing method.

[0055] In related technologies, personnel scheduling uses "shortest path" or "nearest distance" as the core rule to push event information to the geographically closest staff member; status monitoring uses GPS / Bluetooth ID cards to determine whether staff are on duty or stationary for extended periods, providing only visual display without a closed loop with the scheduling algorithm; resource profiling only creates static or quasi-static attribute lists (job type, certificate, equipment model) for personnel and equipment, with the event side only containing three fields: "level + coordinates + type," resulting in coarse matching granularity; 3D visualization overlays Geographic Information System (GIS) maps with BIM models to achieve alarm point location and video surveillance linkage, but subsequent handling processes rely entirely on human experience, with no automated decision-making capabilities on the platform side.

[0056] Missing event-side information: Events are treated as "black boxes," making it impossible to distinguish between scenarios of "similar complexity but different levels," leading to high-complexity events being incorrectly assigned to low-skilled personnel and high rework rates; rigid proximity-based dispatching: ignoring multiple constraints such as skill matching, equipment compatibility, team synergy, and operational windows, resulting in two inefficient scenarios: "people arrive on-site but cannot perform tasks" or "missing downtime windows"; broken decision-making chain: 3D visualization is only used for "viewing," not for "calculation," "performance," or "optimization," making it impossible to quantify the quality of dispatching plans, and the platform lacks a self-evolution mechanism; lack of closed-loop feedback: the results of each handling (time consumption, cost, operational impact) are not automatically written back, and profiles and rules remain static for a long time, unable to adapt to dynamic environments such as equipment aging, personnel changes, and operational map adjustments.

[0057] The event data processing method provided in this application is geared towards the integrated monitoring and management platform for electromechanical systems of large public buildings (such as subway hubs, highway service areas, airport terminals, and stadiums). It addresses four common shortcomings of traditional event handling methods: rigid assignment based on proximity, event opacity, reliance on experience for decision-making, and lack of evolutionary feedback loops. It offers an integrated intelligent decision-making method and device combining "event-resource dual profiling + 3D GIS + Building Information Modeling (BIM) + digital twin simulation." By transforming "events" from a black box into quantifiable, predictable, and predictable objects, and by pre-validating handling plans in a digital twin, the platform can formulate optimal scheduling strategies based on a three-dimensional framework of "time-risk-cost" in a very short time, significantly reducing misassignment rates, shortening handling time, and minimizing operational impact.

[0058] like Figure 2 As shown, this is the overall solution module, which combines event profiling, resource profiling, and the corresponding processing flow of the 3D GIS+BIM model.

[0059] Dynamic Resource Pool Module: As the data foundation support module of the system, its core function is to realize the full life cycle management of personnel and equipment-related data, including real-time collection, classification and storage, dynamic updating and data verification of personnel information (such as skills and qualifications, work status, team affiliation, etc.) and equipment information (such as equipment model, operating parameters, location distribution, maintenance records, etc.).

[0060] The profile modeling module takes data output from the dynamic resource pool module as input and constructs a bidirectionally linked profile of resources and events. On one hand, it generates "personnel profiles" based on personnel data, including dimensions such as skill specialties, work efficiency, compatible equipment types, and skill proficiency. On the other hand, it generates "equipment profiles" based on equipment data, including dimensions such as equipment performance, applicable scenarios, and required operating skills, and establishes a correlation mapping relationship between the two (e.g., the compatibility between a certain type of skilled personnel and a certain type of equipment). Based on task / event data, it generates "event profiles," with core dimensions including event type (e.g., equipment maintenance, inspection, emergency response), core requirements (e.g., completion deadlines, quality standards, safety requirements), resource dependencies (required core skills, essential equipment models), scenario attributes (e.g., work location, environmental conditions), and historical handling records (past personnel / equipment combinations and effects), accurately defining the resource requirements and compatibility standards of events.

[0061] Multi-objective optimization matching module: Receives the "personnel-equipment" bidirectional profile output by the profile modeling module, combines it with business scenario requirements (such as task type, schedule requirements, cost budget, etc.), adopts multi-objective optimization algorithms (such as taking into account resource utilization, task completion efficiency, cost control, etc.) to achieve the optimal combination and matching of personnel and equipment resources, and outputs the matching solution.

[0062] The digital twin simulation module takes the resource matching scheme output by the multi-objective optimization matching module as its core input, and simultaneously receives the 3D scene model imported by the 3D GIS+BIM fusion module through an interface to construct a digital twin environment consistent with the real scene. Within this environment, the execution process of the resource matching scheme is simulated (such as the workflow of personnel operating equipment, the trajectory of equipment in the scene, and the time nodes for task completion), and the simulation process data is output (such as resource idle rate, task delay risk, and equipment wear and tear prediction).

[0063] 3D GIS+BIM Fusion Module: This module focuses on the technical support for the fusion of geographic information and building information modeling. By integrating 3D GIS (Geographic Information System, which has the ability to process geographic data such as spatial location and topography) and BIM (Building Information Modeling, which includes detailed model data such as building components and equipment layout) technologies, it constructs high-precision, visualized 3D scene models (such as engineering sites, park environments, and building interior spaces), and imports the fused model into the digital twin simulation module through an interface.

[0064] Automatic optimization module: Using the simulation process data and disposal result data output by the digital twin simulation module as learning samples, it analyzes the patterns and problems in the data through machine learning algorithms (such as decision trees, neural networks, etc.) (such as which matching combinations are more efficient, which rules lead to resource waste, etc.), and automatically updates the system's resource matching rules and data screening criteria based on the analysis results. At the same time, it feeds back the optimized rules and data to the relevant modules.

[0065] like Figure 3 As shown, the overall business process begins with the collection of dynamic resource data.

[0066] Among them, personnel resource data collection covers the information required for the entire life cycle management of personnel, including basic identity information (name, number, department, contact information), skill qualification information (skill type, skill level certificate, training record), real-time status information (on-the-job / off-the-job status, current task progress, location coordinates, continuous working hours), and historical handling information (types of events participated in, handling success rate, average handling time, and past compatible device records).

[0067] Data collection method: It is achieved through a combination of multi-system linkage and manual supplementation. Specifically, basic information is imported in batches through the system; skill qualification information is submitted manually through the certificate upload module and verified by the system; real-time status information is synchronized through access control system, mobile terminal positioning, and task management system; historical handling information is automatically recorded and transmitted back by the event handling platform.

[0068] Among them, equipment resource data collection covers the information required for the entire life cycle management of equipment, including basic attribute information (equipment model, specifications, manufacturer, department, rated performance indicators), real-time operation information (current operation parameters, load rate, fault warning signals, energy consumption data), location distribution information (installation location coordinates, region, associated scenarios), and maintenance history information (maintenance time, maintenance content, replaced parts, fault repair records, etc.).

[0069] Data collection method: mainly automated data collection, supplemented by manual assistance. Specifically, real-time operation information is transmitted in real time between equipment sensors and the Internet of Things (IoT) platform using the OPC-UA protocol; basic attributes and location information are entered into the 3D GIS system for positioning and calibration through the equipment ledger system; maintenance history information is manually entered into the equipment management system for maintenance records, and the system automatically associates fault repair order data; the import format of the 3D GIS+BIM model is (IFC standard format).

[0070] Then, a multi-dimensional dynamic resource profile is constructed. For personnel resource data and equipment resource data in the dynamic resource pool, features are extracted and profile models are constructed respectively.

[0071] Step 1: Quantify the characteristics of personnel resource profiles. Basic attributes: direct mapping (name, number, organization); skill attributes: skill type is coded according to the preset classification system (e.g., high voltage electrician = 001, HVAC maintenance = 002); skill level directly uses the values ​​of 1-5; skill proficiency is calculated by the formula: proficiency = (number of successful handlings × weight 1 + average score × weight 2) / total number of handlings (weights 1 and 2 are dynamically adjusted based on the complexity of the event).

[0072] Among them, weight 1 (successful handling weight) is 0.6, 0.7 and 0.8 corresponding to event complexity levels 1-3 (the higher the complexity, the higher the successful handling weight); weight 2 (average score weight) is complementary to weight 1, that is, weight 2 = 1 - weight 1.

[0073] The average score is the quality score (1-5 points) after a single handling is completed. The average of historical scores is taken. Table 1 is the basis for judging the complexity level of the event.

[0074] Table 1

[0075] The technical operation difficulty coefficients mentioned in Table 1 are based on historical handling data of electromechanical incidents and are automatically assigned by the system (1-10 points). The assignment criteria include: the complexity of the operation steps (e.g., single step = 1-3 points, multi-step linkage = 4-7 points, cross-system collaboration = 8-10 points). The following are different weight ratios corresponding to the event complexity level.

[0076] Table 2

[0077] Status attributes: On-duty / Off-duty is represented in binary (1=On-duty, 0=Off-duty); Current task status is associated with the event ID (empty if there is no task); Location coordinates retain latitude and longitude values; Continuous working duration = current time - previous task end time (if on-duty and has a task). Historical attributes: The frequency of historical event types is counted by code; Success rate = Number of successful events / Total number of events; Average processing time = Total time / Total number of events.

[0078] Step 2: Quantification of equipment resource profile features.

[0079] Basic attributes: Direct mapping (equipment model, specifications, manufacturer, department); Operating attributes: Current operating parameters and energy consumption data retain their original values; fault warning signals are represented in binary (1 = warning exists, 0 = no warning). Location distribution attributes: Installation location coordinates retain latitude and longitude values; the region and associated scene are coded according to a preset classification system (e.g., region code: East Zone = 01, West Zone = 02; scene code: computer room = 001, power distribution room = 002). Maintenance history attributes include maintenance time, maintenance content, replaced parts, fault repair records, and other information.

[0080] Step 3: Dynamic resource profile construction.

[0081] Based on the quantitative features from step two, a personnel profile library and an equipment profile library are constructed. Each profile is indexed by a unique ID (personnel number / equipment number) and stores multi-dimensional feature values ​​to form a structured data model. Personnel profile structure: {Personnel ID:{Basic Attributes:{}, Skill Attributes:{}, Status Attributes:{}, Historical Attributes:{}}} Device profile structure: {Device ID:{Basic attributes:{}, Operational attributes:{}, Location distribution attributes:{}, Maintenance history attributes:{}}} Step 4: Dynamically update the profile.

[0082] The system periodically retrieves the latest data from the dynamic resource pool to update personnel and equipment resource profiles. At the same time, it will automatically trigger updates to historical attributes and other information when an event is handled. For example, the updated personnel profile will include the type of event handled in the past (adding the current event code), the handling success rate (recalculated), the average handling time (recalculated), and the skill proficiency (if the current event involves the corresponding skill).

[0083] Then, an event profiling model is constructed.

[0084] Based on historical event data, event characteristics are quantified from multiple dimensions to construct event profiles. The event profiles include four core dimensions, each with specific quantitative indicators: Technical complexity: The quantitative indicators are the number of required skill types (1-3 types), skill level requirements (1-5 levels), and technical operation difficulty coefficient (based on the complexity score of handling similar historical events, 1-10 points). Spatial complexity: The quantitative indicators are the type of space to be dealt with (high-altitude / ground / small space), spatial accessibility score (1-10 points, calculated based on 3D GIS+BIM model), and the degree of interference from the surrounding environment (e.g., whether it is close to flammable areas, level 1-5). Time complexity: Quantitative indicators include urgency level (levels 1-4: urgent / urgent / general / low urgency), impact on operational time threshold (if it exceeds 30 minutes, it will affect venue operation, unit: minutes), and handling time window (must be completed within the specified time, unit: minutes). Risk diffusion: The indicators are the probability of cascading failures (calculated based on historical data, 0-100%), the radius of influence (calculated based on 3D GIS+BIM model, unit: meters), and the estimated amount of loss (unit: yuan). Then, as Figure 4 As shown, a dynamic matching algorithm with multi-objective optimization.

[0085] The multi-objective optimization dynamic matching algorithm is mainly designed for the handling of electromechanical systems (power supply and distribution, HVAC, fire protection, elevators, etc.) in large public buildings (such as subway hubs, highway service areas, airport terminals, stadiums, etc.).

[0086] Solving the three major technical problems of traditional algorithms in this type of scenario: Skills matching ignores the operation and maintenance qualifications for equipment specific to large public buildings (such as large HVAC units and high-load power distribution rooms which require special operation certification), resulting in personnel arriving on site but being unable to operate the specific equipment; The time estimates did not take into account the building's operating hours (such as sporting events and non-operating hours) and the real-time status of the equipment, resulting in delays in handling that affected public use or commercial operations; Spatial calculations failed to incorporate the building's specific spatial constraints (access control for equipment rooms, peak-hour pedestrian congestion, and temporary closed passageways), resulting in path planning that deviated from the actual site conditions.

[0087] The following is the core logic of the dynamic matching algorithm: The four objectives are: highest skill matching degree, shortest processing time, least resource consumption, and lowest risk diffusion degree. Each objective is assigned a weight (which can be adjusted according to the actual scenario; for example, the shortest processing time in the subway integrated monitoring scenario is weighted at 0.4, and the others at 0.2).

[0088] The single-dimensional matching degree is calculated as follows: Skill matching rate: the overlap rate between personnel skill types and event-required skill types × skill level satisfaction rate; where, overlap rate = (number of successfully matched skill types / total number of skill types required for the event) × 100%, skill level satisfaction rate = 100% (if personnel skill level ≥ minimum event requirement level), otherwise it is (personnel skill level / minimum event requirement level) × 100% (example: event requires skill level ≥ 3, personnel skill level is 4, satisfaction rate is 100%). Time matching degree: 1 - (estimated handling time / event handling time window); if the calculation result < 0, it is directly judged as mismatch (match degree is recorded as 0). The estimated handling time is dynamically calculated based on the historical handling efficiency of personnel, equipment operating parameters and event complexity. The event handling time window is the preset maximum allowable handling time limit. Spatial matching degree: 1 - Optimal path time / preset maximum reachable time × spatial accessibility score; where, the optimal path time is calculated in real time from the current location of personnel resources to the point of occurrence of the event through the 3D GIS+BIM fusion model, and the spatial accessibility score is dynamically assigned based on the path congestion coefficient and access restriction conditions (such as access control, temporary road closure) (0-100 points).

[0089] Among them, the optimal path duration is the shortest travel time calculated by the 3D GIS+BIM model (unit: minutes).

[0090] Preset maximum reachable time: The maximum allowed arrival time set by the system (unit: minutes).

[0091] Spatial accessibility score: 1-10 points, converted to a coefficient of 0.1-1.0 for calculation.

[0092] The overall score is calculated as follows: Based on the matching degree of each single dimension and the corresponding target weight above, the comprehensive score of resource-event matching (out of 100 points) is calculated. The calculation formula is: comprehensive score = Σ single dimension matching degree × corresponding target weight; where the single dimension matching degree score is uniformly 0-100 points.

[0093] The following is the matching process of the dynamic matching algorithm: Once an event is triggered, extract the four dimensions of the event profile (technical complexity, space complexity, time complexity, and risk diffusion). Filter resources from the dynamic resource pool that meet basic conditions (such as skill type matching, status attribute matching, historical attribute matching, etc.); Substitute the values ​​into the optimization algorithm to calculate the overall score (score = skill matching degree × 0.4 + time matching degree × 0.3 + space matching degree × 0.3). Output the resources of the top three personnel with the highest overall scores.

[0094] The digital twin simulation of the handling process integrates 3D GIS and BIM models to construct a digital twin of the electromechanical system, and performs pre-simulation and optimization of the matching solution. The specific process is as follows: Based on a 3D GIS+BIM model, the resource movement path is simulated, and the actual arrival time is calculated (considering factors such as elevator and passageway congestion).

[0095] Based on event profiles and resource profiles, simulate the handling steps (such as equipment debugging, fault diagnosis, and repair) and estimate the time required for each step. Simulate potential anomalies during the handling process (such as sudden personnel situations or equipment failures), calculate the probability of anomaly occurrence and the response time.

[0096] Output simulation results: For each candidate solution, output four key indicators: estimated total handling time, resource consumption cost, risk diffusion control rate, and duration of impact on operations; Solution optimization: Select the solution with the best simulation results as the final execution solution; if the simulation finds that the solution has risks (such as the estimated handling time exceeds the time window), automatically adjust the matching solution (such as increasing the number of personnel or replacing with higher performance equipment), and re-simulate until the requirements are met.

[0097] Automatically optimize resources and event profiles, and achieve self-evolution of plans and rules based on data from the entire event handling process.

[0098] Data collection: Record complete data for each incident handling, including incident profile data, matching solution data, digital twin simulation data, and actual handling data (actual time consumption, handling results, resource consumption, and abnormal situations).

[0099] Data analysis: Compare the simulation results with the actual results, calculate the error rate (such as the difference rate between the estimated processing time and the actual processing time). If the error rate is >20%, adjust the parameter model of the digital twin simulation (such as correcting the path time calculation coefficient). Analyze the accuracy of resource profiles: If the actual success rate of personnel handling the situation deviates from the skill proficiency score in the profile by more than 15%, update the skill proficiency calculation algorithm; Analyze the rationality of the matching rules: If the actual overall effect of the matching scheme (success rate of handling, resource utilization rate) is less than 80%, adjust the weight of the matching objective function or the single-dimensional matching degree calculation method. Rule updates: After every 100 event handlings are completed, optimized resource profile model parameters and matching rules are automatically generated, and the system configuration is updated; at the same time, event profile parameters are dynamically adjusted based on event data.

[0100] The following is a specific implementation of an event data processing method.

[0101] The handling of an electrical fault event in the electromechanical system of a certain stadium is used as an example.

[0102] The application scenario in the implementation is the handling of incidents involving the electromechanical systems (power supply and distribution system, HVAC system, fire protection system, etc.) of a stadium center; the system configuration is that a 3D GIS+BIM model has been built, covering all building structures, electromechanical equipment locations, passages, elevators and other spatial information of the stadium center; the dynamic resource pool contains 20 handling personnel and 30 handling equipment.

[0103] The specific implementation steps are as follows: Step 1: Event Triggering and Event Profile Building On [Date], a short circuit fault occurred in the high-voltage distribution cabinet on the east side of the 10th floor of the stadium's central competition venue, triggering an automatic alarm from the sensors (event triggered). The system collects basic event data: fault type (short circuit in high-voltage distribution cabinet), location of occurrence (coordinates X=120.1234°, Y=30.1234°, 10th floor), and preliminary assessment of the scope of impact (3 surrounding distribution cabinets). Construct an event profile, and assess its technical complexity: required skill type (high voltage electrician, electrical testing), skill level requirement (≥4 level), and technical operation difficulty coefficient (8 points). Spatial complexity: handling space type (high altitude, 10-story power distribution cabinet height 3 meters), spatial accessibility score (7 points, requires taking a freight elevator + pedestrian passage), surrounding environment interference level (level 4, close to the stadium audience seats). Time complexity: urgency level (level 2, urgent), impact on operational time threshold (20 minutes), and response time window (≤30 minutes). Risk diffusion: probability of cascading failure (60%), radius of impact (10 meters), estimated loss amount (50,000 yuan).

[0104] Step 2: Dynamic resource pool and resource profile update. Dynamic resource pool update: The status monitoring module provides real-time feedback. Currently, out of 20 personnel, 18 are on duty and 2 are off duty; out of 30 devices, 28 are available and 2 are faulty (high voltage detector). Personnel resource profile screening: Three personnel (A, B, and C) were selected who were “skilled in high-voltage electrician and electrical testing, with a skill level of ≥4, currently employed, and currently without tasks”. Their profile key data are shown in Table 3.

[0105] Equipment resource profile screening: Three devices (equipment 1, 2, and 3) were selected as high voltage detectors, available, and compatible with skill level ≥ 4. Their profile key data are shown in Table 4.

[0106] Table 3

[0107] Table 4

[0108] Step 3: Multi-objective optimization matching, setting matching target weights: In the case of urgent / emergency events, the shortest handling time has a weight of 0.4, the highest skill matching degree has a weight of 0.3, the least resource consumption has a weight of 0.15, and the risk diffusion control rate has a weight of 0.15.

[0109] Calculate the single-dimensional matching degree and the overall score: Personnel B + Equipment 2 combination: Skill matching degree 100% (skill level 5 ≥ 4, type fully matched), time matching degree 90% (estimated arrival time 5 minutes, processing time 20 minutes, total time 25 minutes ≤ 30 minutes), spatial matching degree 85% (optimal path, good accessibility), overall score = 100%×0. + 90%×0. + 85%×0.15 + 95%×0.15 = 92.5 points; Personnel A + Equipment 1 combination: Overall score 88 points; Personnel C + Equipment 3 combination: Overall score 82 points; The top 3 candidate solutions were output, with the combination of personnel B and equipment 2 scoring the highest.

[0110] Step 4: Digital Twin Simulation and Solution Optimization. Import the scenario of Personnel B carrying Equipment 2 to the incident location into the digital twin: Path simulation: Based on the 3D GIS+BIM model, the path of person B from the 12th floor to the 10th floor is simulated (taking elevator 2, walking corridor 2). Considering the current elevator usage, the estimated arrival time is about 5 minutes. Simulation of handling: Simulates high voltage detection, fault diagnosis, and short circuit repair steps, with an estimated handling time of 20 minutes; The simulation results are as follows: the estimated total duration is 25 minutes, the resource consumption cost (equipment usage cost + personnel cost) is 200 yuan, the risk diffusion control rate is 95%, and the duration of impact on operations is 0 (within the time window). The simulation results meet the requirements, and this plan is determined to be the final implementation plan.

[0111] Table 5

[0112] Step 5: Execution and Data Feedback. The system sends task instructions (including event profile, handling steps, route navigation, etc.) to personnel B.

[0113] The status monitoring module tracks in real time: Personnel B arrives at the scene 5 minutes later, equipment 2 is working normally, there are no abnormalities in the handling process, the actual handling time is 22 minutes, and the fault is successfully repaired; record the data of the whole process: event profile data, matching solution data, simulation data (estimated 25 minutes), actual data (22 minutes), and handling result (success).

[0114] Step Six: After accumulating 100 self-evolutionary optimization actions, the system analyzes the data: The average duration error rate of the digital twin simulation is 10% (the error in this case is 3 minutes / 25 minutes = 12%), and no adjustment of the simulation parameters is required; Personnel B's skill proficiency score improved from 95 to 96 (this operation was successful and quick). In the matching rules, the weight of the risk diffusion control rate is adjusted to 0.2 (originally 0.15) in high-voltage failure events, thereby increasing the priority of risk control.

[0115] Update the resource profiling model and matching rules to achieve self-evolution.

[0116] Table 5 shows the definitions of each variable.

[0117] The event data processing method provided in this application transforms the event from a static description into a computable object. The platform quantifies technical complexity, spatial complexity, temporal complexity, risk diffusion, and environmental coupling through a five-dimensional vector. The system automatically generates handling requirements and pushes them to the dispatch interface, eliminating the need for on-duty personnel to consult paper-based plans.

[0118] The scheduling logic has been changed from assigning orders based on proximity to a multi-objective optimization. The algorithm simultaneously considers skills, distance, equipment compatibility, operational window, and team synergy, generating multiple feasible solutions within seconds and presenting the trade-off results using a risk-cost-duration three-axis graph, significantly reducing reliance on human experience.

[0119] Digital twins provide pre-implementation capabilities. The system runs default and alternative solutions in parallel in a virtual environment, exposing risks such as customer congestion, window overload, or cascading shutdowns in advance. Users can adjust resource configurations before implementation to avoid on-site rework.

[0120] A closed-loop update mechanism ensures continuous evolution. Each real-world action result is automatically written back to the model, and the profile weights and simulation parameters are fine-tuned synchronously. The longer the platform runs, the higher the recommendation accuracy.

[0121] The modular architecture shortens the delivery cycle. Event profiling, matching engine, and twin rendering are all independently encapsulated. On-site deployment only requires importing BIM, GIS, and equipment lists, significantly reducing the project implementation cycle.

[0122] The lightweight version supports SaaS deployment. The core algorithm is decoupled from the front-end; 3D browsing can be achieved using WebGL alone, eliminating the need for high-end graphics workstations and allowing for subscription-based pricing.

[0123] It integrates seamlessly with existing systems. The platform reads existing IBMS, FAS, and BAS alarms via a standard RESTful / OPC-UA interface and embeds them as an "intelligent scheduling plugin," making it channel-friendly and minimizing replacement risk.

[0124] The event profiling and matching algorithm is decoupled from the device type, which can be quickly ported to scenarios such as airports, hospitals, data centers, and urban utility tunnels. The same engine can cover multiple industries, with low marginal development costs, providing a technical foundation for the subsequent launch of a general middleware for intelligent facility scheduling.

[0125] The event data processing method provided in this application represents a breakthrough in three dimensions: depth of technical collaboration, breadth of business coverage, and granularity of innovation. In terms of technological collaboration, it is not a single application of a single technology, but a deep integration of digital twins, BIM+GIS, machine learning, and multi-objective optimization algorithms to form an integrated technology cluster of "spatial positioning + data extrapolation + intelligent scheduling". For example, digital twins can be used to simulate the effect of event handling, combined with BIM+GIS to realize three-dimensional spatial resource scheduling, and multi-objective optimization algorithms can be used to complete the precise matching of resources and events.

[0126] In terms of business coverage, it breaks through the limitations of a single field, starting from the operation and maintenance of electromechanical systems in all scenarios (industrial, venues, etc.), covering the dynamic management of multiple resources such as equipment, personnel, and spare parts, and running through the entire life cycle of event monitoring, analysis, scheduling, handling and self-evolution, rather than being limited to the planning / monitoring of a single device, a single system or a single venue.

[0127] In terms of innovation granularity, it features dual innovations at the algorithm and system levels: it constructs an algorithm system of resource profiling, event profiling, and multi-objective optimization matching to achieve precise bidirectional scheduling of resources and events; it creates original modules such as dynamic resource pools, digital twin simulations, and self-evolving contingency plans to form an intelligent decision-making closed loop, far exceeding the depth of existing papers' technical reviews, single system operation and maintenance, or planning research.

[0128] The event data processing method provided in this application can be executed by an event data processing device. This application uses an event data processing device executing the event data processing method as an example to illustrate the event data processing device provided in this application.

[0129] This application also provides an event data processing apparatus.

[0130] like Figure 5 As shown, the device for processing the event data includes: The acquisition module 510 is used to acquire the first feature information of each candidate object resource in the candidate object resource library and to acquire the second feature information of the event to be processed. The first processing module 520 is used to respond to the processing request corresponding to the event to be processed, and to match the candidate object resources with the event to be processed with at least one of the following as the goal: the highest skill matching degree, the shortest processing time, the least resource consumption, and the lowest risk diffusion degree, so as to obtain a resource matching scheme. The second processing module 530 is used to output the target processing information of the event to be processed based on the resource matching scheme.

[0131] According to the event data processing apparatus provided in the embodiments of this application, by acquiring the first feature information of candidate object resources and the second feature information of the event to be processed, when responding to the event processing request, it performs multi-dimensional intelligent matching with at least one of the following as the target: the highest skill matching degree, the shortest processing time, the least resource consumption, and the lowest risk diffusion degree, thereby generating a better resource matching scheme and outputting target processing information. This can realize the transformation from local response to global optimization, significantly improving the accuracy and efficiency of event handling.

[0132] In some embodiments, candidate object resources are divided into personnel object resources and equipment object resources. The first feature information is divided into first feature sub-information of personnel object resources and second feature sub-information of equipment object resources. The acquisition module 510 is used to acquire the identity information, skill qualification information, real-time status information and historical event processing information of personnel object resources. Based on identity information, skill qualification information, real-time status information, and historical event processing information, the first feature sub-information is obtained; Obtain the attribute information, real-time operation information, location distribution information, and historical maintenance information of the device object resources; The second feature sub-information is obtained based on attribute information, real-time operation information, location distribution information, and historical maintenance information.

[0133] In some embodiments, the acquisition module 510 is used to directly use the identity information as the first feature sub-information corresponding to the identity information. The skill types in the skill qualification information are numbered, the skill levels in the skill qualification information are represented by numerical values, and the skill proficiency is calculated based on the skill qualification information to obtain the first feature sub-information corresponding to the skill qualification information. Among them, the skill proficiency is determined based on the number of successful event processing, the average event processing score, and the event processing complexity in the skill qualification information. The on-duty status in the real-time status information is represented by binary values. The event identifier of the current task in the real-time status information is identified. The location coordinate values ​​in the real-time status information are retained. The continuous working duration is calculated based on the real-time status information to obtain the first feature sub-information corresponding to the real-time status information. The types of historical events in the historical event processing information are encoded and statistically analyzed. Based on the historical event processing information, the historical success rate and the historical average processing time are calculated to obtain the first feature sub-information corresponding to the historical event processing information.

[0134] In some embodiments, the modulus 510 is obtained to assign a first weight coefficient to the number of successful event processing based on the event processing complexity, and to assign a second weight coefficient to the average event processing score, wherein the first weight coefficient is positively correlated with the event processing complexity, and the sum of the first weight coefficient and the second weight coefficient is equal to the first value. Skill proficiency is determined based on the number of successful event handlings, the average event handling score, the first weighting coefficient, and the second weighting coefficient.

[0135] In some embodiments, the acquisition module 510 is used to directly use the attribute information as the second feature sub-information corresponding to the attribute information. The operation data and energy consumption data in the real-time operation information are retained, and the fault warning data in the real-time operation information are represented in binary to obtain the second feature sub-information corresponding to the real-time operation information. The installation location coordinates in the location distribution information are retained, and the region and associated scene in the location distribution information are numbered to obtain the second feature sub-information corresponding to the location distribution information. Historical maintenance information is directly used as the second feature sub-information corresponding to historical maintenance information.

[0136] In some embodiments, the acquisition module 510 is used to acquire technical complexity information, spatial complexity information, time complexity information and risk diffusion information of the event to be processed; The second feature information is obtained based on the technical complexity information, spatial complexity information, time complexity information, and risk diffusion information.

[0137] In some embodiments, the first processing module 520 is used to perform a weighted summation of the reciprocal of the skill matching degree, the processing time, the resource consumption, and the risk diffusion degree, with the goal of minimizing the weighted summation result, to match candidate object resources with events to be processed.

[0138] In some embodiments, the second processing module 530 is used to simulate resource matching schemes in a digital twin environment; Based on at least one key indicator output from the deduction process of the resource matching scheme, optimize the resource matching scheme, and the target processing information includes the optimized resource matching scheme. Output target processing information.

[0139] The event data processing device in this application embodiment can be an electronic device or a component within an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices besides a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine, etc. This application embodiment does not specifically limit the device.

[0140] The event data processing device in this application embodiment can be a device with an operating system. The operating system can be a Microsoft (Windows) operating system, an Android operating system, an iOS operating system, or other possible operating systems; this application embodiment does not specifically limit the specific operating system.

[0141] The event data processing device provided in this application embodiment can achieve... Figures 1 to 4 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.

[0142] In some embodiments, such as Figure 6 As shown, this application embodiment also provides an electronic device 600, including a processor 601, a memory 602, and a computer program stored in the memory 602 and executable on the processor 601. When the program is executed by the processor 601, it implements the various processes of the above-described event data processing method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0143] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0144] This application also provides a non-transitory computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described event data processing method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0145] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0146] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-mentioned method for processing event data.

[0147] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0148] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described event data processing method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0149] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0150] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0151] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the related technology, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0152] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

[0153] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0154] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

Claims

1. A method for processing event data, characterized in that, include: Obtain the first feature information of each candidate object resource in the candidate object resource library, and obtain the second feature information of the event to be processed; In response to the processing request corresponding to the pending event, with the goal of at least one of the following: highest skill matching degree, shortest processing time, least resource consumption, and lowest risk diffusion degree, the candidate object resources are matched with the pending event to obtain a resource matching scheme. Based on the resource matching scheme, the target processing information of the event to be processed is output.

2. The event data processing method according to claim 1, characterized in that, The candidate object resources are divided into personnel object resources and equipment object resources. The first feature information is divided into first feature sub-information of the personnel object resources and second feature sub-information of the equipment object resources. Obtaining the first feature information of each candidate object resource in the candidate object resource library includes: Obtain the identity information, skill qualification information, real-time status information, and historical event processing information of the personnel object resources; Based on the identity information, the skill qualification information, the real-time status information, and the historical event processing information, the first feature sub-information is obtained; Obtain the attribute information, real-time operation information, location distribution information, and historical maintenance information of the device object resources; The second feature sub-information is obtained based on the attribute information, the real-time operation information, the location distribution information, and the historical maintenance information.

3. The event data processing method according to claim 2, characterized in that, The first feature sub-information is obtained based on the identity information, the skill qualification information, the real-time status information, and the historical event processing information, including: The identity information is directly used as the first feature sub-information corresponding to the identity information; The skill types in the skill qualification information are numbered, the skill levels in the skill qualification information are represented by numerical values, and the skill proficiency is calculated based on the skill qualification information to obtain the first feature sub-information corresponding to the skill qualification information. The skill proficiency is determined based on the number of successful event processing, the average event processing score, and the event processing complexity in the skill qualification information. The on-duty status in the real-time status information is represented by a binary value, the event identifier of the current task in the real-time status information is identified, the location coordinate value in the real-time status information is retained, and the continuous working duration is calculated based on the real-time status information to obtain the first feature sub-information corresponding to the real-time status information. The types of historical events in the historical event processing information are encoded and statistically analyzed. Based on the historical event processing information, the historical handling success rate and the historical average handling time are calculated to obtain the first feature sub-information corresponding to the historical event processing information.

4. The event data processing method according to claim 3, characterized in that, The skill proficiency level is determined through the following steps: Based on the event processing complexity, a first weight coefficient is assigned to the number of successful event processing, and a second weight coefficient is assigned to the average event processing score. The first weight coefficient is positively correlated with the event processing complexity, and the sum of the first weight coefficient and the second weight coefficient is equal to a first value. The skill proficiency is determined based on the number of successful event handlings, the average event handling score, the first weighting coefficient, and the second weighting coefficient.

5. The method for processing event data according to claim 2, characterized in that, The second feature sub-information is obtained based on the attribute information, the real-time operation information, the location distribution information, and the historical maintenance information, including: The attribute information is directly used as the second feature sub-information corresponding to the attribute information; The operation data and energy consumption data in the real-time operation information are retained, and the fault warning data in the real-time operation information is represented in binary to obtain the second feature sub-information corresponding to the real-time operation information; The installation location coordinates in the location distribution information are retained, and the region and associated scene in the location distribution information are numbered to obtain the second feature sub-information corresponding to the location distribution information; The historical maintenance information is directly used as the second feature sub-information corresponding to the historical maintenance information.

6. The event data processing method according to claim 1, characterized in that, The acquisition of the second characteristic information of the event to be processed includes: Obtain the technical complexity, spatial complexity, time complexity, and risk diffusion information of the event to be processed; The second feature information is obtained based on the technical complexity information, the spatial complexity information, the time complexity information, and the risk diffusion information.

7. The method for processing event data according to any one of claims 1-6, characterized in that, The process of matching candidate resources with the event to be processed, with the goal of achieving the highest skill matching degree, shortest processing time, least resource consumption, and lowest risk diffusion, to obtain a resource matching scheme includes: The candidate resource is matched with the event to be processed by weighting and summing the reciprocal of skill matching degree, processing time, resource consumption and risk diffusion degree, with the goal of minimizing the weighted sum.

8. The method for processing event data according to any one of claims 1-6, characterized in that, The step of outputting the target processing information for the event to be processed based on the resource matching scheme includes: The resource matching scheme will be simulated in a digital twin environment; Based on at least one key indicator output from the deduction process of the resource matching scheme, the resource matching scheme is optimized, and the target processing information includes the optimized resource matching scheme; Output the target processing information.

9. An event data processing device, characterized in that, include: The acquisition module is used to acquire the first feature information of each candidate object resource in the candidate object resource library and to acquire the second feature information of the event to be processed. The first processing module is used to respond to the processing request corresponding to the event to be processed, and to match the candidate object resources with the event to be processed with at least one of the following as objectives: highest skill matching degree, shortest processing time, least resource consumption, and lowest risk diffusion degree, to obtain a resource matching scheme. The second processing module is used to output the target processing information of the event to be processed based on the resource matching scheme.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the event data processing method as described in any one of claims 1-8.

Images