CN-121010141-B - Personnel intelligent scheduling management method and system based on Internet of things

CN121010141BCN 121010141 BCN121010141 BCN 121010141BCN-121010141-B

Abstract

The invention relates to the technical field of the Internet of things, in particular to a personnel intelligent scheduling management method based on the Internet of things, which comprises the steps of acquiring multisource data such as personnel positions, physiology, behaviors and the like, and calculating individual risk scores by fusing surrounding personnel and historical relations; and analyzing risk peaks in the graph, matching optimal executors through a multi-objective optimization algorithm, and generating a scheduling instruction. According to the invention, discrete individual risks are converted into visual global risk views, and the automation and optimization of scheduling decisions are realized based on the dynamic analysis of risk situations, so that the risk early warning accuracy and the emergency response efficiency are improved.

Inventors

ZHANG LINLIN
DUAN ZHAOJUN
Yin le
CHEN YANG

Assignees

南京道图信息技术有限公司

Dates

Publication Date: 20260505
Application Date: 20250807

Claims (5)

1. The intelligent personnel scheduling management method based on the Internet of things is characterized by comprising the following steps of: the method comprises the steps of acquiring multisource data of each person in a monitoring area in real time, wherein the multisource data comprises real-time position data, physiological data and behavior data of each person, dynamically calculating a current individual risk score for each person based on a situation-related risk assessment model, and integrating multisource data acquired by the person, real-time multisource data of other persons in a peripheral area and a dynamically updated person relationship knowledge graph by calculating the individual risk score; The situation-associated risk assessment model comprises a data input and preprocessing unit, an individual state assessment unit, a social situation analysis unit and a risk fusion decision unit, wherein the data input and preprocessing unit is used for receiving multi-source data, cleaning, normalizing and extracting characteristics of the multi-source data to generate a standardized input data stream, the individual state assessment unit is used for calculating a basic risk grade of a target person in an isolated state based on the standardized input data stream of the target person, the social situation analysis unit is used for inquiring nodes and relations of the target person and surrounding persons in the person relation knowledge graph according to the real-time position of the target person, analyzing and quantifying potential risk influence of a current social environment through graph calculation and reasoning to generate a situation risk correction factor, and the risk fusion decision unit is used for fusing the basic risk grade output by the individual state assessment unit and the situation risk correction factor output by the social situation analysis unit, calculating through a weighting algorithm and outputting an individual risk score of the target person; The method comprises the steps of discretizing a physical space of a monitoring area into a two-dimensional and/or three-dimensional digital grid formed by a plurality of grid points, carrying out zero setting treatment on initial risk values of all the grid points, taking the current real-time position of each person in the monitoring area as a center, taking the individual risk score of each person as an amplitude, applying a preset kernel function to construct a risk distribution function representing the influence range and the intensity of the individual risk of the person in space, traversing each grid point in the digital grid, calculating and accumulating function values of the risk distribution function of all the person on the grid point to obtain an accumulated aggregate risk value of all the grid points, rendering all the grid points and the corresponding aggregate risk values to generate an aggregate risk topological graph, and carrying out visual presentation on different aggregate risk values through different color gradients; The method comprises the steps of analyzing the aggregate risk topological graph in real time, identifying a risk peak value region with a risk value higher than a preset threshold value, judging the risk cause type and the dynamic evolution trend of the risk peak value region, and matching an optimal executor and generating a scheduling instruction containing a recommended response grade through a multi-objective optimization scheduling algorithm based on the risk peak value region, the risk grade, the risk type and the dynamic evolution trend.
2. The intelligent personnel scheduling management method based on the Internet of things is characterized by comprising the steps of extracting features of the identified risk peak area, obtaining positions, risk levels, risk types and dynamic evolution trends of the risk peak area, taking the features as input parameters of scheduling decisions, comprehensively evaluating each executor through the multi-objective optimization scheduling algorithm based on the input parameters, calculating a sub-term index, carrying out weighted calculation on a plurality of the sub-term indexes of each executor, determining an optimal executor under the current situation, and generating scheduling instructions for the optimal executor, wherein the scheduling instructions comprise intervention positions, risk type summaries and recommended response levels.
3. The intelligent personnel scheduling management method based on the Internet of things is characterized in that the item indexes comprise an intervention time index, a skill matching degree index and a task interruption cost index, wherein the intervention time index is determined based on the current real-time position of an operator and the position of a risk peak area, the shortest estimated transit time of a reachable path is calculated by adopting a path planning algorithm, the skill matching degree index is determined by comparing and quantifying the preset requirement skills corresponding to the risk types of the risk peak area with skill items and skill levels pre-stored in a skill profile of the operator, and the task interruption cost index is a cost quantification value comprehensively assessed according to the preset priority of the task currently being executed by the operator and the attribute of whether the task can be safely interrupted.
4. The intelligent personnel scheduling management method based on the Internet of things is characterized in that the personnel relationship knowledge graph is generated through a social network analysis method, and concretely comprises the steps of continuously recording close contact events of n personnel in a monitoring area within a preset distance threshold value based on the real-time position data, storing contact duration and identity information, carrying out association analysis on the close contact events related to the event before and after a time point of occurrence of the event when a risk peak area appears on the aggregate risk topological graph and/or a security event report input from the outside is received, carrying out quantitative update on relationship attributes among the personnel related to the close contact events according to the result of the association analysis, and storing the updated relationship attributes into a relationship database for the situation association risk assessment model to be called when calculating individual risk scores.
5. The intelligent personnel scheduling management system based on the Internet of things is characterized by comprising a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module acquires multi-source data of each personnel in a monitoring area in real time, and the multi-source data comprises real-time position data, physiological data and behavior data of each personnel; the risk assessment module dynamically calculates a current individual risk score for each person based on a situation-related risk assessment model, calculates the individual risk score, fuses multi-source data acquired by the person, real-time multi-source data of other persons in a surrounding area and a dynamically updated person relationship knowledge graph, wherein the situation-related risk assessment model comprises a data input and preprocessing unit, an individual state assessment unit, a social situation analysis unit and a risk fusion decision unit, the data input and preprocessing unit is used for receiving the multi-source data, cleaning, normalizing and extracting features of the multi-source data to generate a standardized input data stream, the individual state assessment unit is used for calculating a basic risk level of a target person in an isolated state based on the standardized input data stream of the target person, the social situation analysis unit is used for inquiring nodes and relationships of the target person and the surrounding person in the person relationship knowledge, analyzing and quantifying potential risk influence of the current social environment through graph calculation and reasoning to generate a situation risk correction factor, the fusion risk state assessment unit is used for outputting the basic risk level of the target person in an isolated state by the individual state assessment unit through a weighted risk calculation algorithm, the method comprises the steps of outputting individual risk scores of target personnel, a topological graph generating module, a scheduling decision module, a factor type and dynamic evolution trend judging module, wherein the factor type and the dynamic evolution trend judging module are used for constructing a risk distribution function representing the influence range and the intensity of individual risks of each personnel in a space by taking the current real-time position of each personnel in a monitoring area as a center and taking the individual risk score as an amplitude value, traversing each grid point in the digital grid, calculating and accumulating function values of the risk distribution function of all personnel on the grid point to obtain an accumulated aggregate risk value on the grid point, rendering all grid points and corresponding aggregate risk values thereof to generate an aggregate risk topological graph, and visually presenting different aggregate risk values through different color gradients.

Description

Personnel intelligent scheduling management method and system based on Internet of things Technical Field The invention relates to the technical field of the Internet of things, in particular to an intelligent personnel scheduling management method and system based on the Internet of things. Background The operation management of specific places is extremely complex, and the dynamic scheduling and risk management and control of human resources are strictly required. The introduction of advanced data processing methods to improve management efficiency and decision quality is a key requirement. The existing personnel management system mostly adopts a scheduling method based on static rules or fixed periods, so that resource allocation is stiff, and sudden human demand changes and complex task assignment are difficult to deal with. The decision process relies on the personal experience of the manager, lacks data-driven risk assessment and dynamic optimization capabilities, results in inefficient operation and potential management of risk. Therefore, the existing management method needs to solve how to integrate multidimensional operation data, and realize resource scheduling from static scheduling to dynamic, intelligent and risk perception. Therefore, the intelligent personnel scheduling management method and system based on the Internet of things are provided. Disclosure of Invention The invention aims to provide a personnel intelligent scheduling management method and system based on the Internet of things, and aims to solve the problems of risk identification hysteresis, situation awareness splitting and low scheduling response efficiency existing in specific place management by constructing a multi-layer intelligent awareness and decision framework integrating individual physiology/behaviors, social situations and space dimensions. In order to achieve the above purpose, the present invention provides the following technical solutions: A personnel intelligent scheduling management method based on the Internet of things comprises the following steps: Acquiring multi-source data of each person in a monitoring area in real time, wherein the multi-source data comprises real-time position data, physiological data and behavior data of each person; dynamically calculating a current individual risk score for each person based on the context-associated risk assessment model; the calculation of the individual risk score integrates the multisource data acquired by the personnel, the real-time multisource data of other personnel in the surrounding area and a dynamically updated personnel relationship knowledge graph; the situation-associated risk assessment model comprises a data input and preprocessing unit, an individual state assessment unit, a social situation analysis unit and a risk fusion decision unit, wherein the data input and preprocessing unit is used for receiving multi-source data, cleaning, normalizing and extracting characteristics of the multi-source data to generate a standardized input data stream, the individual state assessment unit is used for calculating a basic risk grade of a target person in an isolated state based on the standardized input data stream of the target person, the social situation analysis unit is used for inquiring nodes and relations of the target person and surrounding persons in the person relation knowledge graph according to the real-time position of the target person, analyzing and quantifying potential risk influence of a current social environment through graph calculation and reasoning to generate a situation risk correction factor, and the risk fusion decision unit is used for fusing the basic risk grade output by the individual state assessment unit and the situation risk correction factor output by the social situation analysis unit, calculating through a weighting algorithm and outputting an individual risk score of the target person; The method comprises the steps of discretizing a physical space of a monitoring area into a two-dimensional and/or three-dimensional digital grid formed by a plurality of grid points, carrying out zero setting treatment on initial risk values of all the grid points, taking the current real-time position of each person in the monitoring area as a center, taking the individual risk score of each person as an amplitude, applying a preset kernel function to construct a risk distribution function representing the influence range and the intensity of the individual risk of the person in space, traversing each grid point in the digital grid, calculating and accumulating function values of the risk distribution function of all the person on the grid point to obtain an accumulated aggregate risk value of all the grid points, rendering all the grid points and the corresponding aggregate risk values to generate an aggregate risk topological graph, and carrying out visual presentation on different aggregate risk values through different color gra