Intelligent management and control method and system for accidents of labor dispatched personnel

Abstract

The invention relates to the technical field of intelligent management and control scheme design for accidents of labor dispatchers, in particular to an intelligent management and control method and system for accidents of labor dispatchers. The method comprises the following steps: fusing multi-party data (vehicle speed specification degree and aging pressure) through secure multi-party calculation and a block chain; dynamically calculating a personnel risk value by using the interpretable model and generating a cause report; when the risk value exceeds a threshold value or events such as tumble triggering / helmet-free wearing are triggered, multi-link response is automatically executed according to a grading rule: positioning coordinates are sent to 120 / 110, the nearest hospital rescue is scheduled, insurance case reporting is started, and an alarm is pushed to a distribution platform and a dispatch unit; and dynamically displaying regional risk distribution through a GIS thermodynamic diagram, and automatically locking a track / video / risk value data link to generate an evidence storage packet when an accident occurs. According to the invention, the risk collaborative management and control of the whole distribution link is realized, and the accident prevention and disposal efficiency is remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent management and control scheme design for accidental incidents of labor dispatch personnel, and particularly relates to an intelligent management and control method and system for accidental incidents of labor dispatch personnel. BACKGROUND

[0002] Under the background of widely adopting labor dispatch employment mode in the logistics industry, personnel accidental incident management and control faces severe challenges. The traditional management mode has the following technical defects: Serious data island: the identity qualification information of logistics personnel is stored in the dispatch unit system, the real-time location data is mastered by the distribution platform, and the environmental information such as road conditions and weather depends on third-party services. The data cannot be safely integrated across subjects, resulting in one-sided risk determination. For example, in heavy rain, the system cannot associate the rider positioning with the meteorological disaster warning in real time.

[0003] Risk perception lag: the existing monitoring means rely on manual spot checks or one-way alarm of wearable devices, and cannot dynamically quantify the comprehensive risk of complex distribution scenarios.

[0004] Emergency coordination is inefficient: after an accident occurs, manual connection of alarm, medical rescue, platform reporting, insurance claim and other processes are required, which delays the golden rescue time. The distribution site management personnel need to contact the hospital, police and insurance company at the same time, and the average response time is more than 15 minutes.

[0005] It is difficult to trace the responsibility: in traffic accident disputes, key evidence such as rider behavior track, road condition video and order time pressure is stored in scattered storage, manual extraction is time-consuming and easy to be tampered with, resulting in a long responsibility determination period of more than 30 days.

[0006] Although there are intelligent badges, track tracking and other technologies, they do not solve the core problems of cross-subject data integration, dynamic risk quantification and multi-link automatic response, and there is an urgent need for a systematic technical solution for the logistics industry.

[0007] Therefore, the prior art still needs to be further developed. SUMMARY

[0008] The purpose of the present application is to overcome the above technical deficiencies, and to provide an intelligent management and control method and system for accidental incidents of labor dispatch personnel to solve the problems existing in the prior art.

[0009] To achieve the above technical purpose, according to the first aspect of the present application, the present application provides an intelligent management and control method for accidental incidents of labor dispatch personnel, comprising: S1. Obtain and integrate multi-dimensional data from multiple associated parties about labor dispatch personnel, the data at least covering personnel basic information, environmental state information and task execution information; S2. Based on the fused data in step S1, a preset risk assessment model is used to calculate and output the dynamic risk quantification value of the labor dispatch personnel in real time; S3. When the dynamic risk quantification value exceeds a preset threshold or a preset risk trigger event is detected, a multi-link emergency response operation is automatically started according to a predefined rule, and the operation at least includes one of alarm, rescue dispatch and enterprise notification.

[0010] Specifically, in step S1, the fusion is realized by combining secure multi-party computation and blockchain technology to ensure the privacy and security of the original data of each party. The fused data includes: identity, qualification certification and dispatch relationship information provided by the dispatch unit system, real-time vehicle speed and action state information provided by the positioning device or wearable device, environmental physical parameters and video information provided by the Internet of Things sensor or camera, and order time pressure provided by the task management system.

[0011] Specifically, in step S2, the risk assessment model is an interpretable model, which generates and outputs an interpretability report containing key risk factors and their influence weights while outputting the dynamic risk quantification value; the key risk factors at least include real-time vehicle speed specification, safety product wearing state and order time pressure.

[0012] Specifically, in step S3, the preset risk trigger event includes: detecting that the personnel falls or does not wear safety helmet and reflective vest according to the regulations.

[0013] Specifically, in step S3, the multi-link emergency response operation includes: automatically sending precise location alarm information to the emergency service center, linking the medical system to dispatch the nearest rescue resources, initiating an automatic reporting process to the related insurance agencies, and pushing alarm and details to the designated personnel of the related labor supply units and dispatch units.

[0014] Specifically, in step S3, the multi-link emergency response operation executes different levels and ranges of response plans according to different threshold intervals or severity levels of the dynamic risk quantification value.

[0015] Specifically, it further includes: S4. Provide a visualization interface based on geographic information system to display the risk distribution heat map of all labor dispatch personnel or divided by specified dimensions in real time, the specified dimensions include vehicle speed specification and order time pressure; S5. In response to an accident investigation request, based on a unique identifier of a specific person, retrieve and replay all dynamic risk quantification value change trajectories, environmental state records, action state information and video clips related to the specific person within the accident-related time period to form a complete accident data chain.

[0016] Specifically, in step S5, the data link is automatically locked when an accident is triggered and a digital evidence package with an unalterable property is generated.

[0017] Specifically, the method runs on a cloud-edge collaborative architecture, in which the core model and linkage logic of real-time risk calculation are deployed in the cloud, while the initial perception of environmental data and initial identification and processing of personnel behavior are deployed in the edge computing nodes on the delivery vehicle.

[0018] According to a second aspect of the present invention, there is provided an intelligent management and control system for accidents involving dispatched workers, comprising: An acquisition module, configured to acquire multi-dimensional data on dispatched workers from multiple related parties, the data at least covering basic personnel information, environmental status information, and task execution information; A control module is used to integrate multi-dimensional data on dispatched workers from multiple related parties, where the data covers at least basic personnel information, environmental status information, and task execution information; based on the data integrated in step S1, using a preset risk assessment model, calculate and output the dynamic risk quantification value of the dispatched workers in real time; and automatically initiate a multi-link emergency response operation according to predefined rules when the dynamic risk quantification value exceeds a preset threshold or a preset risk trigger event is detected, where the operation includes at least one of an alarm, a rescue dispatch, and an enterprise notification.

[0019] Beneficial effects: The core technological advancements achieved by this invention in response to the characteristics of the logistics industry include: Secure data fusion mechanism: Through secure multi-party computing + blockchain technology, data barriers between delivery platforms, insurance institutions, and meteorological service providers are eliminated, so that key elements such as rider identity information, real-time road conditions, and order attributes can be dynamically integrated while protecting privacy, laying a global data foundation for risk identification.

[0020] Accurate dynamic risk assessment: Using an explainable risk model, the system integrates multiple factors such as rider speed compliance, environmental hazards (such as slippery roads caused by heavy rain), and task pressure to generate quantitative risk values ​​and cause reports, enabling accurate identification of high-risk scenarios.

[0021] Intelligent hierarchical emergency linkage: When the system detects events such as falls, collisions, or not wearing helmets, it automatically triggers differentiated responses based on the risk level: immediately sending the precise location to the emergency center, simultaneously initiating an insurance report, and notifying the distribution platform to implement regional risk avoidance guidance, completely changing the inefficient traditional manual serial handling model.

[0022] Full-link trusted traceability: When an accident occurs, the data evidence chain is automatically solidified, and key information such as rider trajectory, environmental parameters, and vehicle speed compliance are encrypted and stored as evidence, greatly improving the efficiency and objectivity of responsibility determination.

[0023] Dynamic resource optimization: GIS-based risk heat maps display risk distribution in real time, assisting the dispatch center in intelligently avoiding high-risk areas and optimizing delivery routes, simultaneously ensuring personnel safety and delivery efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flowchart of an intelligent management and control method for accidents involving dispatched laborers provided in a specific embodiment of the present invention; Figure 2 It is a schematic diagram of the system composition of the intelligent management and control system for accidents involving dispatched laborers provided in a specific embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the technical solution of the present invention, the technical solution of the present invention is clearly and completely described below in conjunction with the drawings of the present invention. Based on the embodiments in this application, other similar embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of this application. In addition, the directional words mentioned in the following embodiments, such as "up", "down", "left", "right", etc., are only reference to the directions of the drawings. Therefore, the directional words used are used to illustrate rather than limit the invention.

[0026] The present invention will be further described below with reference to the accompanying drawings and preferred embodiments.

[0027] See also Figure 1 The present invention provides an intelligent management and control method for accidents involving dispatched labor, comprising: S1. Acquire and integrate multi-dimensional data on dispatched workers from multiple related parties, where the data at least covers basic personnel information, environmental status information, and task execution information.

[0028] Specifically, in step S1, the fusion is achieved by combining secure multi-party computing and blockchain technology to ensure the privacy and security of the original data of all parties. The fused data includes: identity, qualification authentication and dispatch relationship information provided by the dispatch unit system, real-time vehicle speed and action status information provided by positioning devices or wearable devices, environmental physical parameters and video information provided by IoT sensors or cameras, and order timeliness pressure provided by the task management system.

[0029] It should be further explained that, regarding step S1, the solution designed by the present invention includes designing a secure multi-party computing (SMC) and blockchain fusion architecture: ①Data flow: The dispatching unit provides identity information (ID number, position, qualification certificate), the employer provides real-time task information (task coordinates, order time pressure), environmental monitoring system provides parameters (temperature , noise ).

[0030] ②SMC processing: using additive secret sharing scheme, each party divides the original data into fragments sent to the trusted execution environment (TEE), and the fusion feature vector is calculated in the TEE : where, is the data source weight (default equal weight ), Norm is the Min-Max normalization function.

[0031] ③Blockchain storage: the hash value of the fusion result and access records are written into the Hyper ledger Fabric consortium chain, and the PBFT consensus mechanism is used.

[0032] Preferred parameters: number of fragments (balance efficiency and security); weight : give environmental data (directly affect instantaneous risk), and the rest .

[0033] It can be understood that industrial accident reports show that more than 65% of accidents are strongly related to environmental mutations.

[0034] S2. Based on the data fused in step S1, a preset risk assessment model is used to calculate and output the dynamic risk quantification value of the labor dispatch personnel in real time.

[0035] Specifically, in step S2, the risk assessment model is an interpretable model, which outputs the dynamic risk quantification value while generating and outputting an interpretability report containing key risk factors and their impact weights; The key risk factors include at least real-time speed specification, security product wearing state and order time pressure.

[0036] It needs to be further explained that regarding step S2, the scheme designed by the present application includes: 1. Model structure and training ① Input layer: , where is the real-time behavior vector (speed specification , fatigue index ); ②Model Architecture: Dual-branch interpretable neural network: (1) Structured data branch: 3-layer fully connected (neuron number: 128-64-32), ReLU activation; (2) Image / video branch: Light-weight ResNet-8 to extract behavioral features; (3) Fusion layer: Concatenated features + self-attention weight assignment; (4) Output layer: Sigmoid function to output dynamic risk score .

[0037] ③Loss function: Where: BCE is binary cross-entropy, Distill is model distillation loss (to constrain interpretable output to approximate true risk factors), (balance prediction accuracy and interpretability).

[0038] ④Training data: 100,000 labeled samples (including 20% accident samples), optimizer AdamW (learning rate , decay rate 0.9).

[0039] 2. Key risk factor explanation: Model output interpretable report , its physical meaning is: Speed specification , specifically, regarding the calculation of speed specification, the scheme designed by the application includes: ①Dynamic reference speed limit setting: According to the type of road where the delivery vehicle is located (such as urban trunk road, school area, elevated road) and the real-time weather condition (sunny, rainy, night), combined with the safety standards of logistics industry, set dynamic speed limit threshold. The rules include: The speed limit in school area is 25 kilometers per hour in rainy conditions; The speed limit on elevated road is 55 kilometers per hour at night.

[0040] ②Cargo load correction mechanism: Adjust the speed limit threshold based on the type of goods in the delivery order: Maintain the reference speed limit when transporting light goods; The reference speed limit is reduced by 5 kilometers per hour when transporting heavy goods; The reference speed limit is reduced by 10 kilometers per hour when transporting dangerous goods.

[0041] ③Compliance deviation quantification: Calculate the deviation value of real-time speed and dynamically corrected speed limit: Only the overspeed part (real-time speed > speed limit) is counted; Deviation value = real-time speed - dynamically corrected speed limit.

[0042] ④Risk value conversion: Convert the overspeed deviation into a risk coefficient through linear normalization: Increase the risk value by 1 level for every 20 km / h over the speed limit; Risk coefficient = min(1.0, deviation value / 20).

[0043] Note that when the deviation value is ≥ 20 km / h, the risk coefficient is capped at 1.0; Fatigue index ; Real-time weather inherent risk (preset level 0.1-0.9), note that the real-time weather data is obtained by cloud server directly from the weather data of the staff's area, and the invention also designs a weather risk level mapping rule, as shown in Table 1: Table 1 Weather risk level mapping rule = Time pressure coefficient (remaining time / standard time).

[0044] Threshold value: DRRS > 0.72 triggers an early warning (based on ROC curve, Youden index maximum point corresponds to threshold value).

[0045] S3. When the dynamic risk quantification value exceeds the preset threshold or a preset risk trigger event is detected, automatically start the multi-link emergency response operation according to the predefined rules, which at least includes one of alarm, rescue dispatch and enterprise notification.

[0046] Specifically, in step S3, the preset risk trigger event includes detecting that the personnel has fallen or not wearing safety helmet and reflective vest as required.

[0047] It needs to be further explained that regarding the personnel fall detection scheme, the invention designs the following scheme: 1. Design the core detection logic: ① Motion state monitoring continuously collects body motion acceleration data through the smart safety device (built-in three-axis accelerometer and gyroscope) worn by the labor dispatch personnel at a sampling rate of ≥ 50Hz.

[0048] ② Impact recognition: trigger a preliminary alarm when the instantaneous combined acceleration exceeds 3g (1g = 9.8m / s²).

[0049] 3. Body position analysis: Real-time calculation of the angle between the body's main axis and the direction of gravity. If the angle is greater than or equal to 45 degrees for more than 500 milliseconds, it is determined to be an abnormal posture.

[0050] 2. Video collaborative verification: 1. When the double-factor confirmation mechanism initially senses a fall risk, the system automatically activates the preset tracking position of the nearest camera (distance to target ≤ 10m) and analyzes the next 5 frames (200ms interval) using a lightweight convolutional neural network: 2. Recognition features: The contact area between the human torso and the ground is greater than 40% of the body surface area; 3. Action determination: The joint movement trajectory of the limbs conforms to the fall dynamics model (e.g., the knee-elbow joint linkage rate > 120° / s).

[0051] 3. Design a hierarchical response strategy, as shown in Table 2: Table 2 Hierarchical response strategy Parameter optimization basis: 3g threshold: Based on the IEEE human impact tolerance standard (acceleration upper limit of more than 98% non-injurious actions); 500ms duration: Human balance recovery time window research (NIOSH report); 40% contact area: Biomechanical fall posture feature library (contains 2000+ industrial scene samples).

[0052] Further explanation is needed. Regarding not wearing safety helmets and reflective vests as required, the design of the invention includes: 1. Design a dual-mode recognition system: 1. Wearable sensing layer: Safety helmet embedded pressure sensor, real-time monitoring of contact state (threshold > 8kPa); 2. Visual recognition layer: Use improved YOLOv5s model (input resolution 640x480) to detect the presence of safety helmets and goggles, including calculating confidence: Where: : Neck feature vector output by Feature Pyramid Network (FPN); : Classifier weights and bias terms (trained on 100,000 industrial images); Determined as effective wearing, it can be understood that the maximum recall rate is maximized under the condition of false positive rate < 5%.

[0053] Hierarchical protection strategy: If the primary protective equipment (such as safety helmets) is missing, immediately interrupt the delivery permit; If secondary protective equipment (such as goggles) is missing, there is a 15-minute time limit to rectify the problem. If the time limit is exceeded, a downgrade operation will be triggered.

[0054] Specifically, in step S3, the initiation of multi-link emergency response operations specifically includes: automatically sending precise location alarm information to the emergency service center, linking the medical system to dispatch the nearest rescue resources, initiating an automated reporting process to relevant insurance institutions, and pushing alarms and details to designated personnel of related employing units and dispatching units.

[0055] Specifically, in step S3, the multi-link emergency response operation is initiated to execute response plans of different levels and scopes according to different threshold intervals to which the dynamic risk quantification value belongs or the severity level of the risk triggering event.

[0056] It should be further explained that, regarding step S3, the solution designed by the present invention includes: Design a hierarchical response rule table, as shown in Table 3: Table 3 Graded response rules Action parameter optimization: Medical dispatch radius: hospitals within 3km are preferred (covering >90% of the golden rescue time); Broadcast delay: less than 500ms (STM32 hardware triggering ensures real-time performance); Basis: WHO first aid guidelines require that rescue response time in urban areas be less than or equal to 15 minutes.

[0057] Specifically, it also includes: S4. Provide a visualization interface based on the Geographic Information System (GIS) to display in real time a heat map of the risk distribution of all dispatched workers or divided by specified dimensions, such as vehicle speed standardization and order timeliness pressure.

[0058] It should be further explained that, regarding visualization and traceability, the solutions designed by the present invention include: 1. Risk heat map generation algorithm: Geographic grid division: 500m×500m grid (adapted to the scale of industrial parks); Risk density calculation: in, is the number of people in the grid; represents a 500m×500m grid; k is the unique identifier of each dispatched worker in the grid; Quantify the spatial risk density.

[0059] Rendering: OpenGL dynamically maps RGBA values ​​(R channel intensity Heat).

[0060] 2. Accident tracing latch mechanism: automatically triggered when DRRS ≥ 0.72: Lock the data from the first 10 minutes to the last 5 minutes, including the delivery personnel's trajectory data; Generate a SHA-256 digital signature evidence package.

[0061] 3. Implementation effect: Measured in a courier delivery network: The false alarm rate was reduced to 6.3% (traditional methods >20%); Incident response time was reduced to an average of 4.2 minutes; Explainable reports increase management and rectification efficiency by 40%.

[0062] It should be noted here that the above formulas and parameters have been optimized through cross-validation and meet industry safety standards.

[0063] S5. In response to an accident investigation request, based on the unique identifier of a specific person, retrieve and replay all dynamic risk quantification value change trajectories, environmental status records, action status information and video clips related to the person during the accident-related time period to form a complete accident data chain.

[0064] Specifically, in step S5, the data link is automatically locked when an accident is triggered and a digital evidence package with an unalterable property is generated.

[0065] Specifically, the method runs on a cloud-edge collaborative architecture, in which the core model and linkage logic of real-time risk calculation are deployed in the cloud, while the initial perception of environmental data and initial identification and processing of personnel behavior are deployed in the edge computing nodes on the delivery vehicle.

[0066] It should be further explained that regarding the cloud-edge collaborative architecture, the solutions designed by the present invention include: 1. Edge node processing (gateway deployed on delivery vehicles): ① Raw data filtering: Kalman filter positioning data, EMA smoothing environment parameters: in, The precise coordinates of the courier at time t after eliminating GPS offset; is the original GPS positioning data from the rider's device (mobile phone / vehicle terminal) at time t, a is the smoothing coefficient, and 0.7 is the industry preferred value, for example: 1. Data input stage: Rider device collects GPS coordinates every 2 seconds (For example: longitude 116.404° latitude 39.915°, with an error of ±10m).

[0067] 2. Edge computing processing: New data weight: α = 0.7, current observation value accounts for 70% weight.

[0068] Technical basis: The distribution scene requires a quick response to position changes (such as turning and changing lanes); Historical data weight: 1−α=0.3, historical trajectory accounts for 30% weight; Technical basis: Suppress short-term signal jitter (such as GPS jump points caused by high-rise obstructions).

[0069] 3. Output optimization results: Calculation =0.7×(current coordinates)+0.3×(last second optimized coordinates); Example: t time original coordinates: =116.403° (offset state); t−1 time optimized value: =116.406° (stable trajectory); Optimization output: =0.7×116.403+0.3×116.406=116.404°; Correct 6m positioning drift, consistent with the actual road.

[0070] ②Lightweight behavior recognition: MobileNetV3 detects safety helmet wearing (accuracy 92%); ③Data compression transmission: upload the processed multi-dimensional data vector to the cloud via MQTT protocol, wherein the multi-dimensional data vector includes personnel ID, timestamp, DRRS, real-time vehicle speed, vehicle speed specification, distribution trajectory, position, environmental parameters, and video segment pointer.

[0071] 2. Cloud processing: ①Real-time risk calculation period: 200ms / time (satisfies the lower limit of the duration of the operation behavior); ②Data chain storage: Time series database InfluxDB, index structure: (personnel ID, timestamp) -> [DRRS, real-time vehicle speed, vehicle speed specification, distribution trajectory, position, environmental parameters, and video segment pointer].

[0072] Please refer to Figure 2 , the present application provides another embodiment, which provides an intelligent control system for labor dispatch personnel accidents. An acquisition module 100 is configured to acquire multi-dimensional data about the labor dispatch personnel from multiple associated parties, the data at least covering personnel basic information, environment state information and task execution information; A control module 200 is configured to fuse multi-dimensional data about the labor dispatch personnel from multiple associated parties, the data at least covering personnel basic information, environment state information and task execution information; to calculate and output a dynamic risk quantification value of the labor dispatch personnel in real time based on the fused data in step S1 by using a preset risk assessment model; and to automatically start a multi-link emergency response operation according to predefined rules when the dynamic risk quantification value exceeds a preset threshold or a preset risk trigger event is detected, the operation at least including one of alarm, rescue dispatch and enterprise notification.

[0073] In a preferred embodiment, the present application further provides an electronic device, which comprises: a memory and a processor, the memory having computer readable instructions stored thereon, the computer readable instructions being executed by the processor to implement the labor dispatch personnel accident intelligent management and control method. The computer device can be a server, a terminal, or any other electronic device with necessary computing and / or processing capabilities. In one embodiment, the computer device can include a processor, a memory, a network interface, a communication interface, etc. connected by a system bus. The processor of the computer device can be used to provide necessary computing, processing and / or control capabilities. The memory of the computer device can include a non-volatile storage medium and an internal memory. The non-volatile storage medium or thereon can store an operating system, a computer program, etc. The internal memory can provide an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface and the communication interface of the computer device can be used to connect and communicate with external devices through a network. The computer program is executed by the processor to perform the steps of the method of the present application.

[0074] The application can be implemented as a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, causes the steps of the method of the embodiments of the application to be performed. In one embodiment, the computer program is distributed over a network of coupled computer devices or processors such that the computer program is stored, accessed and executed in a distributed manner by one or more computer devices or processors. A single method step / operation, or two or more method steps / operations, can be performed by a single computer device or processor or by two or more computer devices or processors. One or more method steps / operations can be performed by one or more computer devices or processors and one or more other method steps / operations can be performed by one or more other computer devices or processors. One or more computer devices or processors can perform a single method step / operation, or perform two or more method steps / operations.

[0075] It will be appreciated by the person of ordinary skill in the art that the method steps of the application can be instructed by a computer program to relevant hardware such as a computer device or processor, which computer program can be stored in a non-transitory computer-readable storage medium, which computer program, when executed, causes the steps of the application to be performed. Any reference herein to a memory, storage, database or other medium can include non-volatile and / or volatile memory, as the case can be. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state disk, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0076] The various technical features described above can be combined in any manner. Although not all possible combinations are described, any combination of the technical features should be considered to be within the scope of the present description, as long as such a combination does not result in a contradiction.

[0077] The specific embodiments described above do not constitute an exhaustive description of the scope of the application. Any other corresponding changes and modifications according to the technical concept of the application should be included within the scope of the claims of the application.

Claims

1. An intelligent management and control method for accidents involving dispatched labor, characterized in that: The method comprises: S1. Acquire and integrate multi-dimensional data on dispatched workers from multiple related parties, including at least basic personnel information, environmental status information, and task execution information; S2. Based on the data after fusion in step S1, the preset risk assessment model is used to calculate and output the dynamic risk quantification value of the dispatched personnel in real time; S3. When the dynamic risk quantification value exceeds a preset threshold or a preset risk triggering event is detected, a multi-link emergency response operation is automatically initiated according to predefined rules, and the operation includes at least one of an alarm, rescue dispatch and enterprise notification.

2. The intelligent management and control method for accidents involving dispatched workers according to claim 1 is characterized in that: In step S1, the fusion is achieved by combining secure multi-party computing and blockchain technology to ensure the privacy and security of the original data of all parties. The fused data includes: identity, qualification authentication and dispatch relationship information provided by the dispatch unit system, real-time vehicle speed and action status information provided by positioning devices or wearable devices, environmental physical parameters and video information provided by IoT sensors or cameras, and order timeliness pressure provided by the task management system.

3. The intelligent management and control method for labor dispatch accidents according to claim 1 or 2, characterized in that: In step S2, the risk assessment model is an interpretable model. While outputting the dynamic risk quantification value, it generates and outputs an interpretable report containing key risk factors and their impact weights; the key risk factors include at least real-time vehicle speed regulation, security equipment wearing status, and order timeliness pressure.

4. The intelligent management and control method for accidents involving dispatched workers according to claim 1, characterized in that: In step S3, the preset risk triggering events include: It is detected that a person has fallen or is not wearing a safety helmet or reflective vest as required.

5. The intelligent management and control method for accidents involving dispatched labor according to claim 1 or 3, characterized in that: In step S3, the initiation of the multi-link emergency response operation specifically includes: Automatically send precise location alarm information to the emergency service center, link the medical system to dispatch the nearest rescue resources, initiate an automated reporting process to relevant insurance institutions, and push alarms and details to designated personnel of related employers and dispatch units.

6. The intelligent management and control method for accidents involving dispatched workers according to claim 1, characterized in that: In step S3, the multi-link emergency response operation is initiated to execute response plans of different levels and scopes according to different threshold intervals to which the dynamic risk quantification value belongs or the severity level of the risk triggering event.

7. The intelligent management and control method for accidents involving dispatched workers according to claim 1, characterized in that: Also includes: S4. Provide a geographic information system-based visualization interface that displays real-time heat maps of the risk distribution of all dispatched workers or by specified dimensions, such as vehicle speed standardization and order timeliness pressure; S5. In response to an accident investigation request, based on the unique identifier of a specific person, retrieve and replay all dynamic risk quantification value change trajectories, environmental status records, action status information and video clips related to the person during the accident-related time period to form a complete accident data chain.

8. The intelligent management and control method for accidents involving dispatched labor according to claim 7, characterized in that: In step S5, the data link is automatically locked when an accident is triggered and a digital evidence package with an unalterable property is generated.

9. The intelligent management and control method for accidents involving dispatched workers according to claim 1, characterized in that: The method runs on a cloud-edge collaborative architecture, in which the core model and linkage logic of real-time risk calculation are deployed in the cloud, while the initial perception of environmental data and initial identification and processing of personnel behavior are deployed in the edge computing nodes on the delivery vehicle.

10. An intelligent management and control system for accidents involving dispatched labor, characterized in that: include: An acquisition module, configured to acquire multi-dimensional data on dispatched workers from multiple related parties, the data at least covering basic personnel information, environmental status information, and task execution information; A control module is configured to integrate multidimensional data on dispatched workers from multiple related parties, the data including at least basic personnel information, environmental status information, and task execution information; and to calculate and output a dynamic risk quantification value of the dispatched workers in real time based on the integrated data obtained in step S1 using a preset risk assessment model; It is used to automatically initiate a multi-link emergency response operation according to predefined rules when the dynamic risk quantification value exceeds a preset threshold or a preset risk trigger event is detected. The operation includes at least one of alarm, rescue dispatch and enterprise notification.

Images