Logistics data monitoring and management system and method based on Internet of Things

Abstract

The invention belongs to the technical field of logistics management of the Internet of Things, and provides a logistics data monitoring and management system and method based on the Internet of Things, and the system comprises an event triggering module, a state abstract module, an event aggregation module and a situation early warning module. Setting an edge intelligent node integrated with a lightweight rule engine to judge whether an event judgment rule is triggered or not, if so, packaging an event data packet, if not, generating a state abstract for original state data in a set aggregation time window, and dynamically adjusting the window length of the aggregation time window based on resource quantitative evaluation; the method comprises the following steps: receiving event data packets and state abstracts at a cloud service platform side, respectively storing the event data packets and the state abstracts, setting and adopting an event aggregation analysis engine to analyze and aggregate the event data packets to generate a composite event, constructing and adopting a situation awareness engine, and performing real-time analysis and prediction based on a composite event stream. And generating a logistics situation prediction trajectory and carrying out graded early warning.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of logistics management of Internet of Things, and in particular to a logistics data monitoring and management system and method based on Internet of Things. BACKGROUND

[0002] With the deep integration of Internet of Things technology in the logistics field, how to efficiently monitor and manage the data of goods, vehicles and facilities distributed all over the world has become a core challenge of modern supply chain. The existing technical solutions usually rely on two mainstream architectures: one is the centralized cloud processing mode, that is, all sensor data is uploaded to the cloud platform without distinction; the other is the edge computing mode with simple filtering function. However, in the actual application process, we find that these existing technologies have a series of technical problems to be solved.

[0003] Firstly, the existing technology has the contradiction between data flood and resource bottleneck. The traditional centralized processing mode requires continuous uploading of massive raw data, which not only occupies valuable network bandwidth, but also brings huge storage and computing pressure to the cloud, resulting in high system response delay and high operating cost. The existing edge computing scheme mostly adopts fixed data uploading strategy, and when the edge intelligent node is short of resources, the rigid uploading mechanism may cause node overload, data loss, and even affect the stability of the core monitoring function. Secondly, in the aspect of event identification and processing, the existing technology lacks the ability to identify complex event patterns, lacks correlation analysis between discrete event alarms, and is difficult to understand the global operation failure or security risk. It also lacks the ability to quantitatively evaluate the overall operation situation of the logistics system and predict the future trend, and cannot know the potential efficiency bottleneck or security risk in advance, but can only respond passively, losing the opportunity to make decisions.

[0004] In view of the above problems, the present application provides a logistics data monitoring and management system and method based on Internet of Things. SUMMARY

[0005] In order to make up for the deficiencies of the prior art and solve at least one technical problem in the background art.

[0006] The technical solution adopted by the present application to solve the technical problem is: a logistics data monitoring and management system based on Internet of Things, comprising: An event triggering module: collecting original state data in the logistics network, setting an edge intelligent node integrated with a lightweight rule engine to judge whether an event judgment rule is triggered, and if triggered, packaging event data packets; A state summary module: if not triggered, generating a state summary of the original state data within a set aggregation time window, and dynamically adjusting the window length of the aggregation time window based on resource quantification evaluation; Event aggregation module: receive event data packet and state summary on the cloud service platform side and store them respectively, set and use event aggregation analysis engine to analyze event data packet, and aggregate to generate composite event; Situation early warning module: build and use situation awareness engine, conduct real-time analysis and prediction based on composite event stream, generate logistics situation prediction trajectory, and conduct hierarchical early warning; Further, the event data packet is obtained in the following manner: Set an edge intelligent node integrated with a lightweight rule engine, the edge intelligent node is internally provided with a local rule library, the local rule library is internally provided with event judgment rules defined based on business logic, including threshold judgment rules, pattern matching rules and sequence identification rules, the lightweight rule engine performs logical operation on the real-time inflow of original state data based on the pre-set event judgment rules, identifies whether the event judgment rules are triggered, and generates a structured event data packet if triggered; Further, the state summary is generated in the following manner: Set an aggregation time window and initialize the window length to a pre-set standard window length, if the event judgment rules are not triggered, at the end of the current aggregation time window, obtain the original state data in the current aggregation time window and integrate them into a state time sequence according to the time sequence, and generate a state summary by extracting features from the state time sequence, the state summary encapsulates the peak value, valley value, arithmetic mean value and standard deviation of various original state data in the state time sequence; Further, the window length of the aggregation time window is dynamically adjusted in the following manner: Embed the resource state quantitative evaluator and the time window dynamic adjuster set inside the edge intelligent node, after the state summary is encapsulated, the resource state quantitative evaluator calculates the resource stress index, the time window dynamic adjuster inputs the generated resource stress index and matches it with the low, medium and high intervals of the pre-set resource stress index, when the resource stress index is in the low or high interval, the window length of the aggregation time window is set to the corresponding pre-set lower limit value or upper limit value of the window length, when it enters the medium interval, the adaptive adjustment of the window length is triggered, a negative correlation function based on the resource stress index is set, and the window length of the aggregation time window is adjusted in a segmented linear manner between the pre-set lower limit value and upper limit value of the window length; Further, the resource stress index is calculated in the following manner: The resource state quantitative evaluator continuously monitors the performance indicators of the core hardware resources of the edge intelligent node, the resource state quantitative evaluator is internally provided with a weighted fusion algorithm based on entropy weight method and analytic hierarchy process, which is used to weight and fuse the de-dimensioned performance indicators and normalize them into scalar values between 0 and 1, which are marked as resource stress indexes; Further, the composite event is generated in the following manner: The event data packet is received and verified at the cloud service platform side, and is stored in an event library after verification. An event aggregation analysis engine is set up to analyze the continuously flowing event data packet in the event library. The event aggregation analysis engine is based on a space-time correlation calculation framework, and a sliding time window and a geographic grid are set up. The geographic grid divides the grid unit. For the event data packet in the current sliding time window, a co-occurrence probability evaluation model and a causal strength evaluation model are used to calculate the co-occurrence probability and the causal effect value between the event data packets. If the event data packets are in the same grid unit and the co-occurrence probability exceeds the preset co-occurrence probability standard, or the causal effect value between the event data packets is significantly non-zero, the event data packets are aggregated into a composite event. Further, the specific calculation method of the co-occurrence probability and the causal effect value is as follows: The co-occurrence probability evaluation model uses a co-occurrence probability algorithm to calculate the frequency of different event types in the event library co-occurring in the same sliding time window and the same grid unit. The co-occurrence probability between event types is evaluated by a conditional probability formula. The causal strength evaluation model is based on a causal discovery algorithm to analyze the time sequence dependence relationship of the event sequence in the event library, constructs a causal graph combined with domain knowledge, and calculates the causal effect value between the event data packets. Further, the generation method of the logistics situation prediction trajectory is as follows: A situation awareness engine is constructed. The situation awareness engine is built-in real-time analysis model and prediction model. An evaluation period is set. The real-time analysis model analyzes the composite event and state summary in the evaluation period at the end of the current evaluation period, quantitatively calculates the multi-dimensional situation index of the current evaluation period, sets a historical period, integrates the multi-dimensional situation index in the historical period into an index time sequence according to the time sequence, and the prediction model takes the index time sequence as the input, uses a space-time graph convolution network based on an attention mechanism, and deduces the multi-dimensional situation index prediction value of the future preset number of evaluation periods. Combined with the multi-dimensional situation index in the current evaluation period, a logistics situation prediction trajectory is formed. Further, the specific calculation method of the multi-dimensional situation index is as follows: The real-time analysis model includes a composite event classification sub-model and a multi-dimensional situation index sub-model. The composite event classification sub-model classifies the composite event into efficiency impact events and safety impact events. At the end of the current evaluation period, the multi-dimensional situation index sub-model intercepts the composite event and the state summary in the evaluation period, and integrates the composite event and the state summary into a composite event evaluation sequence and a state summary evaluation sequence according to the time sequence, respectively. The multi-dimensional situation index sub-model defines the multi-dimensional situation index, including efficiency index, safety index and stability index. The efficiency index and the safety index are calculated based on the proportion of the time length of the efficiency impact event and the safety impact event in the evaluation period in the composite event evaluation sequence, respectively. The stability index is calculated by analyzing the fluctuation characteristics and trend changes in the state summary evaluation sequence.

[0007] The logistics data monitoring and management method based on the Internet of Things comprises the following steps: Raw state data is collected in the logistics network, an edge intelligent node integrated with a lightweight rule engine is set to judge whether an event judgment rule is triggered, if triggered, an event data packet is encapsulated; If not triggered, a state digest is generated from the raw state data within a set aggregation time window, and the window length of the aggregation time window is dynamically adjusted based on resource quantification evaluation; The event data packet and the state digest are received and stored at the cloud service platform side, an event aggregation analysis engine is set and used to analyze the event data packet, and a composite event is aggregated; A situational awareness engine is constructed and used, real-time analysis and prediction are carried out based on the composite event stream, a logistics situational prediction trajectory is generated, and hierarchical early warning is carried out.

[0008] The beneficial effects of the present application are as follows: 1. The present application realizes efficient preprocessing and intelligent decision of data at the source by deploying an edge intelligent node integrated with a lightweight rule engine, directly executes rules such as threshold, pattern matching and sequence recognition at the edge side, can instantly identify key events and immediately encapsulate and report, greatly shortens the delay from data generation to alarm response, meets the stringent requirements of logistics monitoring on real-time, and secondly, for normal data of untriggered events, the system dynamically adjusts the aggregation time window through resource quantification evaluation, generates high-precision digest to retain details when resources are abundant, and prolongs the window length for macro statistics when resources are scarce, significantly reduces the network transmission load and cloud storage pressure, realizes intelligent and adaptive saving of edge computing resources and communication bandwidth, and guarantees long-term stable operation of the system under complex working conditions.

[0009] 2. The present application realizes the cognitive leap from discrete events to system-level situation by using the cloud service platform through the event aggregation analysis engine and the situational awareness engine, aggregates isolated alarm events into composite events with business significance, thereby revealing deep-seated associated risks, solving the problems of isolated alarm and shallow insight of traditional systems, constructing multi-dimensional situational indicators and carrying out accurate prediction based on the composite event stream and historical state data, generating a logistics situational prediction trajectory, realizing the fundamental change from passive alarm to active early warning, providing forward-looking decision support for managers, and comprehensively improving the operation resilience and intelligent management level of the logistics system. BRIEF DESCRIPTION OF DRAWINGS

[0010] The present application will be further described below in conjunction with the drawings.

[0011] Figure 1 is a module architecture diagram of the logistics data monitoring and management system based on the Internet of Things described in the embodiments of the present application; Figure 2A flow chart of steps of the logistics data monitoring and management method based on the Internet of Things according to the embodiment of the present application. DETAILED DESCRIPTION

[0012] In order to make the technical means, creative features, purposes and effects of the present application easy to understand, the present application will be further described below in conjunction with specific embodiments.

[0013] Embodiment 1 Please refer to Figure 1 As shown in the drawings, the logistics data monitoring and management system based on the Internet of Things according to the embodiment of the present application aims to solve the problems of edge resource pressure and transmission bottleneck caused by data flood in existing logistics monitoring, and the problem of insufficient management insight caused by event isolation and situation lag, by deploying edge intelligent nodes integrated with lightweight rule engines to perform real-time stream processing on original state data, encapsulating event data packets immediately when triggering event judgment rules, and generating state summaries within an aggregated time window when not triggering, and based on resource quantification evaluation, adaptively adjusting the window length to realize resource-sensitive data simplification, on the cloud platform side, correlating and analyzing event data packets through an event aggregation analysis engine, aggregating to generate composite events, and then, a situation awareness engine calculates multi-dimensional situation indexes based on composite event streams and state summaries, and predicts and generates logistics situation prediction trajectories using a spatiotemporal graph convolution network with an attention mechanism, finally realizing hierarchical early warning, thereby completing the closed-loop intelligent management from data to decision, specifically including the following modules: Event triggering module: collecting original state data in the logistics network, setting edge intelligent nodes integrated with lightweight rule engines to judge whether to trigger event judgment rules, and if so, encapsulating event data packets; Specifically, lightweight, low-power Internet of Things sensor nodes are planned and deployed at key physical objects and operation links in the logistics network to form an Internet of Things sensor node network, and real-time collection of original state data is performed; Among them, the key physical objects and operation links include cargo carriers, storage locations, handling equipment and channel gates, the Internet of Things sensor nodes integrate multiple types of micro sensor units, including temperature and humidity sensors, three-axis acceleration sensors, optical recognition modules and RFID readers, and are directly installed and embedded in the corresponding planned monitoring positions, for continuously collecting original state data of the physical world according to a predefined unified data model and collection frequency, the original state data including environmental temperature data, environmental humidity data, vibration data, attitude data, visual image data and electronic tag information; It should be noted that the unified data model specifies the type, unit, coding format and timestamp of the data, providing a consistent interface standard for subsequent processing; An edge intelligent node integrated with a lightweight rule engine is arranged, the edge intelligent node representing an embedded intelligent unit deployed at a logistics operation site, having data acquisition, real-time calculation and local decision-making capabilities, networking with Internet of Things sensor nodes through a near field communication link, and performing real-time stream processing on raw state data uploaded by the Internet of Things sensor nodes; Specifically, the edge intelligent node is internally provided with a local rule library, the local rule library is internally preset with event judgment rules defined based on business logic, including threshold judgment rules, pattern matching rules and sequence identification rules, and the lightweight rule engine performs logical operation on the raw state data flowing in real time based on the preset event judgment rules to identify whether an event judgment rule is triggered; For example, the threshold judgment rule includes a temperature overrun rule, when the environmental temperature data in the raw state data exceeds the temperature safety threshold set by the temperature overrun rule, it is determined that the temperature overrun rule is triggered; For example, the pattern matching rule includes a bearing fault feature identification rule, which performs matching degree calculation on vibration data and a pre-stored fault feature template, and when it is identified that the matching degree with the bearing wear template exceeds a threshold, it is determined that the bearing fault feature identification rule is triggered; For example, the sequence identification rule includes an outbound process compliance verification rule, which continuously monitors the event sequence of electronic tag information reading, visual identification and access control scanning, and when it is detected that the event sequence is reversed or a key link is overdue and does not respond, it is determined that the outbound process compliance verification rule is triggered; When the real-time stream processing identifies that the raw state data triggers an event judgment rule, a structured event data packet is immediately generated, the event data packet encapsulates event type, trigger source identifier, occurrence location, timestamp and associated data snapshot, and is reported in real time through a priority communication queue; Wherein, the event type is obtained based on the triggered event judgment rule, the trigger source identifier is a unique code of the corresponding Internet of Things sensor node, the occurrence location is obtained based on positioning of the Internet of Things sensor node corresponding to the trigger source identifier, the timestamp records the time of triggering the event judgment rule, and the associated data snapshot stores the time sequence of the raw state data within a specific time window before and after triggering the event judgment rule; It should be noted that this step is to deploy an edge intelligent node integrated with a lightweight rule engine on the edge side to perform real-time stream processing on raw state data, achieving instantaneous identification and response to events, greatly reducing the delay from data acquisition to decision-making, at the same time, the structured event data packet significantly reduces the transmission of invalid data, saves network bandwidth and cloud resources, embeds the event judgment rule into the edge intelligent node at the logistics site, realizes intelligent filtering and decision-making of data at the source, changes the traditional mode of relying on cloud centralized processing, and improves the real-time performance and autonomy of the system; The state summary module: if the event judgment rule is not triggered, a state summary is generated for the original state data within the set aggregation time window, and the window length of the aggregation time window is dynamically adjusted based on resource quantitative evaluation; Specifically, an aggregation time window is set and the window length is initialized as a preset standard window length, and the end point of the current aggregation time window is also the start point of the next aggregation time window. At the end point of the current aggregation time window, the original state data within the current aggregation time window is obtained and integrated according to time sequence to generate a state time sequence, and a state summary is generated by feature extraction of the state time sequence, which encapsulates the peak value, valley value, arithmetic mean value and standard deviation of each type of original state data in the state time sequence. After the state summary is encapsulated, the window length of the aggregation time window is adaptively adjusted based on resource quantitative evaluation. Specifically, a resource state quantitative evaluator and a time window dynamic adjuster are embedded and deployed inside the edge intelligent node. The resource state quantitative evaluator continuously monitors the performance indicators of the core hardware resources of the edge intelligent node, including CPU utilization, memory occupancy, network bandwidth instantaneous availability and data queue depth. The resource state quantitative evaluator has a weighted fusion algorithm based on entropy weight method and analytic hierarchy process, which is used to weight and fuse the performance indicators after dimensionless processing and normalize them to scalar values between 0 and 1, which are marked as resource stress indexes. It should be noted that the higher the resource stress index, the more stressed the computing, storage and communication resources of the edge intelligent node, and the heavier the burden of data transmission and processing. The input end of the time window dynamic adjuster is connected to the output end of the resource state quantitative evaluator, and the generated resource stress index is obtained and matched with the low, medium and high intervals of the preset resource stress index. When the resource stress index is in the low interval, it is determined that the resources are abundant, the window length of the aggregation time window is set to the lower limit of the preset window length, and a high-frequency and high-precision state summary is generated to maximize the details and timeliness of the original state data. When the resource stress index enters the medium interval, it is determined that the resources are becoming tight, and the adaptive adjustment of the window length is triggered. A negative correlation function based on the resource stress index is set to adjust the window length of the aggregation time window in a segmented linear manner, and the window length dynamically takes a value between the lower limit of the preset window length and the upper limit of the window length. When the resource stress index reaches the high interval, it is determined that the resources are stressed, the window length of the aggregation time window is set to the upper limit of the preset window length, and a low-frequency state summary with more macro statistical features is generated to significantly reduce the data generation and reporting frequency, thereby ensuring the stability of the node core function. It should be noted that the role of this step is to realize the effective compression and archiving of data for normal data of untriggered events by generating a state summary containing statistical characteristics within the aggregation time window, and to dynamically adjust the window length of the aggregation time window according to the resource tension index through the resource state quantitative evaluator and the time window dynamic adjuster, to reduce the data reporting frequency to ensure node stability when resources are tight, and to retain data details when resources are abundant, to realize intelligent balance of edge computing resources and communication load, and to effectively solve the resource bottleneck problem of edge intelligent nodes under variable load; The event aggregation module receives the event data packet and the state summary on the cloud service platform side and stores them respectively, sets and uses an event aggregation analysis engine to analyze the event data packet, and aggregates to generate a composite event; Specifically, on the cloud service platform side, a high-throughput data access gateway is set as a unified data aggregation entrance, the data access gateway adopts a distributed cluster architecture, receives and verifies the event data packet and the state summary reported from the global edge intelligent nodes, the data access gateway performs format compliance check, source identity authentication and data integrity check on the received event data packet and the state summary, and after verification, stores the event data packet and the state summary in different topic databases of a distributed storage system respectively, the topic databases include an event library and a state history library; An event aggregation analysis engine is set to analyze the event data packet continuously flowing into the event library; Specifically, the event aggregation analysis engine is based on a space-time correlation calculation framework, uses a co-occurrence probability evaluation model and a causal strength evaluation model, and jointly analyzes concurrent events by setting a sliding time window and a geographic grid, wherein the sliding time window is defined as a configurable time interval that is backtracked from the current time, used to intercept the time sequence of the event data packet, and the geographic grid divides the logistics monitoring area into uniform grid units, each grid unit is assigned a unique geographic code, used for spatial clustering of event occurrence positions; It should be noted that the time interval of the sliding time window is dynamically set according to business requirements, and the granularity of the geographic grid is adjusted based on monitoring accuracy; The co-occurrence probability evaluation model uses a co-occurrence probability algorithm to calculate the frequency of different event types in the event library co-occurring in the same sliding time window and the same grid unit, and evaluates the co-occurrence probability between event types through a conditional probability formula, and the causal strength evaluation model is based on a causal discovery algorithm to analyze the time sequence dependence relationship of the event sequence in the event library, constructs a causal graph combined with domain knowledge, and calculates the causal effect value between the event data packets; For the event data packets within the current sliding time window, if the event data packets are in the same grid cell and the co-occurrence probability exceeds the preset co-occurrence probability standard, or the causal effect value between the event data packets is significantly non-zero, the event aggregation analysis engine aggregates the discrete event data packets into a composite event; It should be noted that the role of this step is to aggregate the discrete event data packets into a composite event with more business significance on the cloud service platform side through the event aggregation analysis engine using the co-occurrence probability evaluation model and the causal strength evaluation model, thereby revealing the internal correlation and causal chain between isolated events and improving the system's deep insight into complex logistics risks. The event aggregation analysis engine integrates the time and space dimensions and causal analysis, goes beyond simple threshold alarms, can discover potential correlation patterns and root causes from concurrent event streams, and realizes the cognitive upgrade from point to plane; The situation early warning module: constructs and uses a situation awareness engine, performs real-time analysis and prediction based on the composite event stream, generates a logistics situation prediction trajectory, and performs hierarchical early warning; Specifically, a situation awareness engine is constructed on the cloud service platform side, and the situation awareness engine is built-in with a real-time analysis model and a prediction model; The real-time analysis model includes a composite event classification sub-model and a multi-dimensional situation index sub-model. The composite event classification sub-model classifies the received composite events into efficiency impact events and safety impact events, sets an evaluation period, and the multi-dimensional situation index sub-model extracts the composite events and state summaries within the corresponding evaluation period from the composite event stream and the state history library at the end of each evaluation period. According to the time sequence, the composite event evaluation sequence and the state summary evaluation sequence within the evaluation period are obtained, respectively; The multi-dimensional situation index sub-model defines a set of multi-dimensional situation indexes reflecting the overall operation state of the logistics network. The multi-dimensional situation indexes include efficiency indexes, safety indexes, and stability indexes. The efficiency indexes and safety indexes are calculated based on the proportion of the time length of the efficiency impact events and safety impact events in the composite event evaluation sequence within the evaluation period, respectively. The stability index is calculated by analyzing the fluctuation characteristics and trend changes in the state summary evaluation sequence; At the end of the current evaluation period, the real-time analysis model performs analysis within the current evaluation period, and quantitatively calculates the multi-dimensional situation indexes of the current evaluation period; A historical period ending at the current time is set, and the historical period includes a preset number of evaluation periods. The multi-dimensional situation indexes within the historical period are integrated according to the time sequence to obtain an index time sequence; The prediction model takes the index time sequence as input, uses a spatio-temporal graph convolution network based on an attention mechanism to capture the long-term dependence and periodicity of the multi-dimensional situation indexes in the time dimension, and outputs the predicted values of the multi-dimensional situation indexes of the future preset number of evaluation periods through the prediction model; Integrate the multi-dimensional situation indicators in the current evaluation period with the predicted values of the multi-dimensional situation indicators to form a logistics situation prediction track; Preset the early warning threshold system for each multi-dimensional situation indicator, including the intervals of each multi-dimensional situation indicator corresponding to multiple early warning levels, the early warning levels include normal, attention, warning and serious, match the multi-dimensional situation indicators in the logistics situation prediction track with the early warning threshold system, take the highest early warning level in each multi-dimensional situation indicator as the current matching early warning level, encapsulate the early warning information, including the logistics situation prediction track and the early warning level, and send it to the logistics management terminal through the notification service of the cloud service platform, realize the monitoring and management of logistics data; It should be noted that the role of this step is to build a situation awareness engine, convert the composite event and state summary into quantifiable multi-dimensional situation indicators, and use a spatiotemporal graph convolution network based on attention mechanism for prediction to generate a logistics situation prediction track, and finally realize hierarchical warning through the early warning threshold system, so that the management changes from post-response to pre-prediction, provides forward-looking decision support, and forms a closed-loop intelligent management; The technical scheme of the embodiment of the present application is: collecting original state data in the logistics network, setting an edge intelligent node integrated with a lightweight rule engine to judge whether an event judgment rule is triggered, if triggered, encapsulating an event data packet, if the event judgment rule is not triggered, generating a state summary for the original state data within a set aggregation time window, and dynamically adjusting the window length of the aggregation time window based on resource quantification evaluation, receiving the event data packet and the state summary on the cloud service platform side and storing them respectively, setting and using an event aggregation analysis engine to analyze the event data packet, aggregating to generate a composite event, constructing and using a situation awareness engine, performing real-time analysis and prediction based on the composite event stream, generating a logistics situation prediction track and performing hierarchical warning.

[0014] Embodiment 2 As shown in Figure 2 The logistics data monitoring and management method based on the Internet of Things according to the embodiment of the present application comprises the following steps: Collecting original state data in the logistics network, setting an edge intelligent node integrated with a lightweight rule engine to judge whether an event judgment rule is triggered, if triggered, encapsulating an event data packet; If the event judgment rule is not triggered, generating a state summary for the original state data within a set aggregation time window, and dynamically adjusting the window length of the aggregation time window based on resource quantification evaluation; Receiving the event data packet and the state summary on the cloud service platform side and storing them respectively, setting and using an event aggregation analysis engine to analyze the event data packet, aggregating to generate a composite event; A situation awareness engine is constructed and used to perform real-time analysis and prediction based on complex event streams, to generate a logistics situation prediction track and perform hierarchical early warning.

[0015] The above shows and describes the basic principles, main features and advantages of the present application. Those skilled in the art should understand that the present application is not limited to the above-mentioned embodiments, and the above-mentioned embodiments and descriptions in the specification are only to illustrate the principles of the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. The logistics data monitoring and management system based on the Internet of Things, characterized in that: Comprise: Event trigger module: collect original state data in the logistics network, set up edge intelligent nodes integrated with lightweight rule engine to judge whether to trigger event judgment rules, if triggered, encapsulate event data packets; State summary module: if not triggered, generate state summary on original state data within the set aggregation time window, and dynamically adjust the window length of the aggregation time window based on resource quantitative evaluation; Event aggregation module: receive event data packets and state summaries on the cloud service platform side and store them respectively, set up and use event aggregation analysis engine to analyze event data packets, and aggregate to generate composite events; Situation early warning module: build and use situation awareness engine, conduct real-time analysis and prediction based on composite event stream, generate logistics situation prediction trajectory and conduct hierarchical early warning. 2.The logistics data monitoring and management system based on Internet of Things according to claim 1, characterized in that: The acquisition method of event data packet is: Set up edge intelligent nodes integrated with lightweight rule engine, the edge intelligent nodes have built-in local rule library, the local rule library has pre-set event judgment rules based on business logic definition, including threshold judgment rules, pattern matching rules and sequence recognition rules, the lightweight rule engine performs logical operation on real-time incoming original state data based on the pre-set event judgment rules, identifies whether to trigger event judgment rules, and generates structured event data packets if triggered. 3.The logistics data monitoring and management system based on Internet of Things according to claim 1, characterized in that: The generation method of state summary is: Set the aggregation time window and initialize the window length to the pre-set standard window length, if the event judgment rule is not triggered, at the end of the current aggregation time window, obtain the original state data within the current aggregation time window and integrate them into state time sequence according to time sequence, extract features from the state time sequence to generate state summary, and the state summary encapsulates the peak value, valley value, arithmetic mean value and standard deviation of each type of original state data in the state time sequence. 4.The logistics data monitoring and management system based on Internet of Things according to claim 3, characterized in that: The dynamic adjustment method of the window length of the aggregation time window is: Embed the set resource state quantitative evaluator and time window dynamic adjuster in the edge intelligent node, after the state summary is encapsulated, the resource state quantitative evaluator calculates the resource shortage index, the time window dynamic adjuster inputs the generated resource shortage index, and matches it with the pre-set low, medium and high intervals of the resource shortage index, when the resource shortage index is in the low or high interval, the window length of the aggregation time window is set to the corresponding pre-set lower limit or upper limit of the window length, when entering the medium interval, the adaptive adjustment of the window length is triggered, a negative correlation function based on the resource shortage index is set, and the window length of the aggregation time window is adjusted in a piecewise linear manner between the pre-set lower limit and upper limit of the window length. 5.The logistics data monitoring and management system based on Internet of Things according to claim 4, characterized in that: The specific calculation method of the resource shortage index is: The resource state quantitative evaluator continuously monitors the performance indicators of the core hardware resources of the edge intelligent node, the resource state quantitative evaluator has built-in weighted fusion algorithm based on entropy weight method and analytic hierarchy process, which is used to weight and fuse the performance indicators after de-dimensioning, and normalize them into scalar values between 0 and 1, which are marked as resource shortage indexes. 6.The logistics data monitoring and management system based on Internet of Things according to claim 1, characterized in that: The generation method of composite event is: The event data packet is received and verified at the cloud service platform side, and is stored in an event library after verification. An event aggregation analysis engine is set up to analyze the continuously flowing event data packet in the event library. The event aggregation analysis engine is based on a time-space correlation calculation framework, and a sliding time window and a geographic grid are set up. The geographic grid divides the grid unit. For the event data packet in the current sliding time window, a co-occurrence probability evaluation model and a causal strength evaluation model are used to calculate the co-occurrence probability and the causal effect value between the event data packets. If the event data packets are in the same grid unit and the co-occurrence probability exceeds the preset co-occurrence probability standard, or the causal effect value between the event data packets is significantly non-zero, the event data packets are aggregated into a composite event. 7.The logistics data monitoring and management system based on Internet of Things according to claim 6, characterized in that: The specific calculation method of the co-occurrence probability and the causal effect value is as follows: The co-occurrence probability evaluation model uses a co-occurrence probability algorithm to calculate the frequency of different event types in the event library co-occurring in the same sliding time window and the same grid unit. The co-occurrence probability between event types is evaluated by a conditional probability formula. The causal strength evaluation model is based on a causal discovery algorithm to analyze the time sequence dependence relationship of the event sequence in the event library, and constructs a causal graph combined with domain knowledge to calculate the causal effect value between the event data packets. 8.The logistics data monitoring and management system based on Internet of Things according to claim 1, characterized in that: The generation method of the logistics situation prediction trajectory is as follows: A situation awareness engine is constructed, which is built-in with a real-time analysis model and a prediction model. An evaluation period is set. The real-time analysis model analyzes the composite event and the state summary in the evaluation period at the end of the current evaluation period, and quantitatively calculates the multi-dimensional situation index of the current evaluation period. A historical period is set. The multi-dimensional situation index in the historical period is integrated into an index time sequence according to the time sequence. The prediction model takes the index time sequence as input, uses a spatio-temporal graph convolution network based on an attention mechanism, and deduces the multi-dimensional situation index prediction value of a preset number of evaluation periods in the future. Combined with the multi-dimensional situation index in the current evaluation period, the logistics situation prediction trajectory is formed. 9.The logistics data monitoring and management system based on Internet of Things according to claim 8, characterized in that: The specific calculation method of the multi-dimensional situation index is as follows: The real-time analysis model includes a composite event classification sub-model and a multi-dimensional situation index sub-model. The composite event classification sub-model classifies the composite event into efficiency impact events and safety impact events. At the end of the current evaluation period, the multi-dimensional situation index sub-model intercepts the composite event and the state summary in the evaluation period, and integrates the composite event and the state summary into a composite event evaluation sequence and a state summary evaluation sequence according to the time sequence, respectively. The multi-dimensional situation index sub-model defines the multi-dimensional situation index, including efficiency index, safety index and stability index. The efficiency index and the safety index are calculated based on the proportion of the time length of the efficiency impact events and the safety impact events in the composite event evaluation sequence in the evaluation period, respectively. The stability index is calculated by analyzing the fluctuation characteristics and trend changes in the state summary evaluation sequence.

10. The logistics data monitoring and management method based on the Internet of Things, characterized in that: The following steps are included: Original state data is collected in the logistics network. An edge intelligent node integrated with a lightweight rule engine is set up to determine whether an event judgment rule is triggered. If it is triggered, an event data packet is encapsulated. If it is not triggered, a state summary is generated for the original state data within the set aggregation time window, and the window length of the aggregation time window is dynamically adjusted based on resource quantification evaluation. The event data packet and the state digest are received at the cloud service platform side and are stored respectively, an event aggregation analysis engine is set and used to analyze the event data packet, and a composite event is generated by aggregation; A situation awareness engine is constructed and used, real-time analysis and prediction are carried out based on the composite event stream, a logistics situation prediction track is generated, and hierarchical early warning is carried out.

Images