A mobile shopping cart collaborative distribution method and system based on the Internet of Things

Abstract

This invention relates to the field of IoT mobile delivery technology, and in particular to an IoT-based mobile shopping cart collaborative delivery method and system. The method includes: collecting shopping cart status, delivery tasks, and regional environmental data through IoT terminals; extracting delivery scenario feature factors through edge computing preprocessing; and associating these factors to form a single set of delivery data. Cross-device interaction is achieved using an IoT gateway. Multiple sets of data are classified using a K-means clustering algorithm and combined with historical best solutions to generate a first collaborative delivery strategy. During delivery, dynamic interference factors are monitored through an IoT sensing network. After anomaly index evaluation, the strategy is corrected using a Kalman filter algorithm to obtain a second collaborative delivery strategy. This strategy is then distributed to the execution terminal based on a distributed decision-making algorithm on an IoT cloud platform, realizing multi-shopping cart route planning, task allocation, and capacity coordination. This effectively solves the problems of poor adaptability, low intelligence, and low delivery efficiency in existing technologies.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) mobile delivery technology, and in particular to a collaborative delivery method and system for mobile shopping carts based on IoT. Background Technology

[0002] As IoT technology penetrates deeper into the logistics field, mobile shopping carts, as a key carrier for last-mile delivery, are increasingly becoming a core direction for improving delivery efficiency through collaborative delivery models. Currently, mobile shopping cart delivery scheduling largely relies on centralized management systems. These systems collect basic data such as shopping cart location and task information, and then use simple path planning algorithms to allocate delivery tasks. Some solutions introduce IoT terminals to achieve data collection and instruction issuance, thus establishing a basic architecture for collaborative delivery. For example, GPS positioning modules can be used to obtain the real-time location of shopping carts, combined with regional delivery task lists for simple capacity allocation, or wireless communication modules can be used to achieve basic information exchange among multiple shopping carts to meet the needs of small-scale delivery scenarios.

[0003] However, existing technologies still have problems: On the one hand, data processing and decision-making efficiency is insufficient. Under the traditional centralized architecture, the collection and analysis of regional environmental data and shopping cart status data are delayed, and precise feature extraction is not performed on multi-dimensional data, resulting in a lack of scientific data support for the generation of collaborative strategies, making it difficult to adapt to the dynamic changes in complex delivery scenarios. On the other hand, the intelligence and anti-interference capabilities of collaborative scheduling are weak. Existing solutions have not effectively integrated IoT distributed algorithms, and lack real-time monitoring and rapid correction mechanisms for dynamic interference factors such as sudden congestion and equipment failure during the delivery process, leading to frequent problems such as delivery route conflicts and unreasonable task allocation, which seriously affect delivery efficiency and service quality. In addition, some technologies have not achieved edge deployment of data preprocessing and strategy decision-making, resulting in excessive computing power load on the cloud platform, further reducing the real-time response speed of collaborative delivery. Summary of the Invention

[0004] The purpose of this invention is to provide a mobile shopping cart collaborative delivery method and system based on the Internet of Things, which solves the problems of poor adaptability, low level of intelligence and low delivery efficiency in the existing technology.

[0005] To achieve the above objectives, the present invention provides a mobile shopping cart collaborative delivery method based on the Internet of Things, comprising the following steps: S1. Collect historical shopping cart status data, delivery task information and regional environmental data through IoT terminals, preprocess the regional environmental data using edge computing algorithms, extract delivery scenario feature factors, and determine the shopping cart status data, delivery task information and delivery scenario feature factors that are related to the same delivery task as a single set of delivery data. S2. Based on the Internet of Things gateway, realize cross-device interaction of single-set delivery data, use K-means clustering algorithm to classify multiple sets of delivery data, and combine historical optimal delivery solutions to generate the first collaborative delivery strategy; S3. Delivery is carried out based on the first collaborative delivery strategy, and dynamic interference factors in the delivery process are monitored in real time through the Internet of Things sensing network. Anomaly index is evaluated based on the dynamic interference factors, and the first collaborative delivery strategy with anomalies is corrected by the Kalman filter algorithm to obtain the second collaborative delivery strategy. S4. Based on the distributed decision-making algorithm of the Internet of Things cloud platform, the second collaborative delivery strategy is sent to the execution terminal of the corresponding mobile shopping cart to realize the path planning, task allocation and transportation capacity coordination of multiple shopping carts and complete the delivery task.

[0006] In some embodiments of this application, in S1, collecting historical shopping cart status data, delivery task information, and regional environmental data through an IoT terminal includes: Historical shopping cart status data, delivery task information, and regional environmental data are collected through positioning sensors, load sensors, temperature and humidity sensors, and road condition monitoring sensors in IoT terminals. Shopping cart status data includes real-time location, remaining weight, battery life, and temperature and humidity status of the goods. Delivery task information includes goods type, delivery time, and distance to the recipient address; Regional environmental data includes traffic flow, road congestion index, and weather conditions.

[0007] In some embodiments of this application, in S1, the preprocessing of regional environmental data using edge computing algorithms to extract delivery scenario feature factors includes: Real-time computing models deployed at edge nodes are used to perform time-series analysis and weight allocation on traffic flow, road congestion index, and weather data. The collected regional environmental data of traffic flow, road congestion index, and weather conditions undergo multi-dimensional preprocessing. For traffic flow data, a sliding window algorithm with a fixed duration of 5 minutes is used. The average value of the data within the window is used as the benchmark to remove instantaneous peak data that exceed the preset threshold and retain the average number of vehicles passing through the road per unit time. Gradient smoothing is performed on the road congestion index data. The gradient change rate is calculated by the difference between adjacent data points, and abrupt data with a gradient absolute value greater than a preset gradient threshold is removed. Quantitative coding of weather data is performed to convert qualitative indicators such as rainfall and strong winds into environmental impact values ​​within a set range; Transformation weights are configured for the preprocessed data in each dimension, and the regional traffic efficiency coefficient is calculated based on a weighted summation method. A risk assessment model is constructed based on the logistic regression algorithm and a historical environmental interference event database. The preprocessed data in each dimension is then input into the risk assessment model to obtain the interference risk value output by the risk assessment model. The interference risk value is then correlated with the regional traffic efficiency coefficient at the delivery task time node to obtain the delivery scenario characteristic factor.

[0008] In some embodiments of this application, in S2, the K-means clustering algorithm is used to classify multiple sets of delivery data, and combined with historical optimal delivery solutions to generate a first collaborative delivery strategy, including: Based on the analytic hierarchy process, credibility weights are assigned to shopping cart status data, delivery task information, and delivery scenario characteristic factors in a single set of delivery data. The credibility score of each set of delivery data is calculated based on weighted summation. The K-means clustering algorithm was used to perform unsupervised classification of the credibility scores of multiple sets of delivery data, resulting in three data clusters: high credibility, medium credibility, and low credibility. The optimal solution set for delivery tasks of the same type and region is retrieved from the historical delivery database of the IoT cloud platform. The cosine similarity algorithm is used to calculate the matching degree for the three types of data clusters and the optimal solution set respectively. Based on the matching degree calculation results, the delivery path priority and capacity allocation coefficient are configured for the three types of data clusters respectively to obtain the first collaborative delivery strategy.

[0009] In some embodiments of this application, in step S3, the dynamic interference factors in the delivery process are monitored in real time through an IoT sensing network, and an anomaly index assessment is performed based on the dynamic interference factors, including: The dynamic interference factors detected in the delivery process are normalized, and the influence weight of each dynamic interference factor is determined based on the analytic hierarchy process. An anomaly index is evaluated using a weighted synthesis algorithm. Dynamic interference factors include the probability of sudden congestion, the probability of shopping cart malfunction, and the stability of the goods' status.

[0010] In some embodiments of this application, in step S3, the expression for evaluating the anomaly index is: ; in, This is an abnormal index. The congestion impact weight is configured. For the configured fault impact weight, The weighting of the configured cargo status For the probability of sudden congestion, For the probability of shopping cart failure, For cargo condition stability.

[0011] In some embodiments of this application, in step S4, the distributed decision-making algorithm based on the IoT cloud platform sends the second collaborative delivery strategy to the execution terminal of the corresponding mobile shopping cart, including: The system acquires the real-time location and network signal strength of the mobile shopping cart execution terminal, dynamically selects the target distribution link based on the real-time location and network signal strength of the mobile shopping cart execution terminal, and uses the MQTT protocol to transmit strategy data packets.

[0012] In some embodiments of this application, an IoT-based mobile shopping cart collaborative delivery system is also disclosed, comprising: The acquisition module is used to collect historical shopping cart status data, delivery task information and regional environmental data through IoT terminals, preprocess the regional environmental data using edge computing algorithms, extract delivery scenario feature factors, and determine the shopping cart status data, delivery task information and delivery scenario feature factors that are related to the same delivery task as a single set of delivery data. The classification module is used to realize cross-device interaction of a single set of delivery data based on the Internet of Things gateway. It uses the K-means clustering algorithm to classify multiple sets of delivery data and combines the best historical delivery solutions to generate the first collaborative delivery strategy. The evaluation and correction module is used to carry out delivery based on the first collaborative delivery strategy, and to monitor dynamic interference factors in the delivery process in real time through the Internet of Things sensing network. Based on the dynamic interference factors, an anomaly index is evaluated, and the Kalman filter algorithm is used to correct the first collaborative delivery strategy that has been identified as abnormal, so as to obtain the second collaborative delivery strategy. The transmission and delivery module is used to distribute the second collaborative delivery strategy to the execution terminal of the corresponding mobile shopping cart based on the distributed decision algorithm of the Internet of Things cloud platform, so as to realize the path planning, task allocation and transportation capacity coordination of multiple shopping carts and complete the delivery task.

[0013] The advantages and beneficial effects of this invention compared to the prior art are: 1. This invention comprehensively collects multi-dimensional data on shopping cart status, delivery tasks, and regional environment through IoT terminals, preprocesses and extracts core feature factors using edge computing algorithms, classifies and adapts the data using K-means clustering, and corrects deviations caused by dynamic interference factors in real time using Kalman filtering algorithms. This enables the collaborative delivery strategy to accurately match different delivery scenarios, task types, and environmental changes, effectively solving the problem of insufficient adaptability of traditional solutions.

[0014] 2. This invention realizes intelligent decision-making throughout the entire process from data collection, feature extraction, strategy generation to dynamic correction, replacing the traditional mode that relies on manual scheduling or simple algorithms; through deep fusion analysis of historical and real-time data, it autonomously generates the optimal collaborative strategy and dynamically adjusts it, improving the autonomy and accuracy of delivery scheduling, and enhancing the intelligence and unmanned nature of delivery.

[0015] 3. This invention enables efficient cross-device data interaction based on an IoT gateway, ensures rapid policy distribution and execution through a distributed decision-making algorithm, and dynamically optimizes the path planning, task allocation, and transportation capacity coordination of multiple shopping carts, effectively reducing path conflicts, task overlaps, and waiting time. At the same time, the real-time monitoring and policy correction mechanism for dynamic interference factors avoids ineffective consumption during the delivery process, significantly increases the delivery volume per unit time, and reduces delivery costs and time loss.

[0016] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0017] Figure 1 This is a flowchart of a mobile shopping cart collaborative delivery method based on the Internet of Things in an embodiment of the present invention; Figure 2 This is a structural diagram of a mobile shopping cart collaborative delivery system based on the Internet of Things, according to an embodiment of the present invention. Detailed Implementation

[0018] In the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product is in use. They are used only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," and "connect" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0019] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0020] like Figure 1 As shown, this invention provides a mobile shopping cart collaborative delivery method based on the Internet of Things, including the following steps: S1. Collect historical shopping cart status data, delivery task information, and regional environmental data through IoT terminals. Use edge computing algorithms to preprocess the regional environmental data, extract delivery scenario feature factors, and determine the shopping cart status data, delivery task information, and delivery scenario feature factors that are related to the same delivery task as a single set of delivery data.

[0021] S2. Based on the IoT gateway, realize cross-device interaction of single-set delivery data, use K-means clustering algorithm to classify multiple sets of delivery data, and combine the historical best delivery solution to generate the first collaborative delivery strategy.

[0022] S3. Based on the first collaborative delivery strategy, deliveries are carried out, and dynamic interference factors in the delivery process are monitored in real time through the Internet of Things sensing network. Anomaly index is evaluated based on the dynamic interference factors, and the first collaborative delivery strategy with anomalies is corrected by using the Kalman filter algorithm to obtain the second collaborative delivery strategy.

[0023] S4. Based on the distributed decision-making algorithm of the Internet of Things cloud platform, the second collaborative delivery strategy is sent to the execution terminal of the corresponding mobile shopping cart to realize the path planning, task allocation and transportation capacity coordination of multiple shopping carts and complete the delivery task.

[0024] This invention enables intelligent decision-making throughout the entire process, from data collection, feature extraction, strategy generation to dynamic correction, replacing the traditional model that relies on manual scheduling or simple algorithms. Through deep fusion analysis of historical and real-time data, it autonomously generates the optimal collaborative strategy and dynamically adjusts it, thereby improving the autonomy and accuracy of delivery scheduling and enhancing the intelligence and unmanned nature of delivery.

[0025] In some embodiments of this application, in S1, collecting historical shopping cart status data, delivery task information, and regional environmental data through an IoT terminal includes: Historical shopping cart status data, delivery task information, and regional environmental data are collected through positioning sensors, load sensors, temperature and humidity sensors, and road condition monitoring sensors in IoT terminals. The shopping cart status data is a set of parameters describing the real-time operating status of the shopping cart, including real-time location, remaining weight, battery life, and temperature and humidity status data of the goods. Delivery task information describes the metadata of the delivery request, including the type of goods, delivery time, and distance to the recipient address; Regional environmental data includes external environmental parameters that affect delivery efficiency, such as traffic flow, road congestion index, and weather conditions.

[0026] In some embodiments of this application, in S1, the preprocessing of regional environmental data using edge computing algorithms to extract delivery scenario feature factors includes: Real-time computing models deployed at edge nodes are used to perform time-series analysis and weight allocation on traffic flow, road congestion index, and weather data. The collected regional environmental data of traffic flow, road congestion index, and weather conditions undergo multi-dimensional preprocessing. For traffic flow data, a sliding window algorithm with a fixed duration of 5 minutes is used. The average value of the data within the window is used as the benchmark to remove instantaneous peak data that exceed the preset threshold and retain the average number of vehicles passing through the road per unit time. Gradient smoothing is performed on the road congestion index data. The gradient change rate is calculated by the difference between adjacent data points, and abrupt data with a gradient absolute value greater than a preset gradient threshold is removed. Quantitative coding of weather data is performed to convert qualitative indicators such as rainfall and strong winds into environmental impact values ​​within a set range; Transformation weights are configured for the preprocessed data in each dimension, and the regional traffic efficiency coefficient is calculated based on a weighted summation method. A risk assessment model is constructed based on the logistic regression algorithm and a historical environmental interference event database. The preprocessed data in each dimension is then input into the risk assessment model to obtain the interference risk value output by the risk assessment model. The interference risk value is then correlated with the regional traffic efficiency coefficient at the delivery task time node to obtain the delivery scenario characteristic factor.

[0027] It is important to understand that the fusion features extracted by edge computing from the characteristic factors of the delivery scenario are composed of the regional traffic efficiency coefficient (reflecting road traffic capacity) and the interference risk value (environmental risk assessed based on historical data) correlated at a time node, and are used to quantify the delivery difficulty under specific spatiotemporal conditions.

[0028] In some embodiments of this application, in S2, the K-means clustering algorithm is used to classify multiple sets of delivery data, and combined with historical optimal delivery solutions to generate a first collaborative delivery strategy, including: Based on the analytic hierarchy process, credibility weights are assigned to shopping cart status data, delivery task information, and delivery scenario characteristic factors in a single set of delivery data. The credibility score of each set of delivery data is calculated based on weighted summation. The K-means clustering algorithm was used to perform unsupervised classification of the credibility scores of multiple sets of delivery data, resulting in three data clusters: high credibility, medium credibility, and low credibility. The optimal solution set for delivery tasks of the same type and region is retrieved from the historical delivery database of the IoT cloud platform. The cosine similarity algorithm is used to calculate the matching degree for the three types of data clusters and the optimal solution set respectively. Based on the matching degree calculation results, the delivery path priority and capacity allocation coefficient are configured for the three types of data clusters respectively to obtain the first collaborative delivery strategy.

[0029] It is important to understand that the first collaborative delivery strategy is based on a baseline scheme generated from initial data, which includes: delivery route priority (high-reliability clusters are given priority in allocating main roads) and capacity allocation coefficient (which determines the proportion of tasks each vehicle can carry).

[0030] In some embodiments of this application, in step S3, the dynamic interference factors in the delivery process are monitored in real time through an IoT sensing network, and an anomaly index assessment is performed based on the dynamic interference factors, including: The dynamic interference factors detected in the delivery process are normalized, and the influence weight of each dynamic interference factor is determined based on the analytic hierarchy process. An anomaly index is evaluated using a weighted synthesis algorithm. Dynamic disturbance factors are used to represent sudden variables that occur during the delivery process. In one embodiment, these include the probability of sudden congestion, the probability of shopping cart malfunction, and the stability of the goods' status.

[0031] This invention comprehensively collects multi-dimensional data on shopping cart status, delivery tasks, and regional environment through IoT terminals. It uses edge computing algorithms to preprocess and extract core feature factors, combines K-means clustering to classify and adapt the data, and uses Kalman filtering algorithm to correct deviations caused by dynamic interference factors in real time. This enables the collaborative delivery strategy to accurately match different delivery scenarios, task types, and environmental changes, effectively solving the problem of insufficient adaptability of traditional solutions.

[0032] In some embodiments of this application, in step S3, the expression for evaluating the anomaly index is: ; in, This is an abnormal index. The congestion impact weight is configured. For the configured fault impact weight, The weighting of the configured cargo status For the probability of sudden congestion, For the probability of shopping cart failure, For cargo condition stability.

[0033] In some embodiments of this application, in step S4, the distributed decision-making algorithm based on the IoT cloud platform sends the second collaborative delivery strategy to the execution terminal of the corresponding mobile shopping cart, including: The system acquires the real-time location and network signal strength of the mobile shopping cart execution terminal, dynamically selects the target distribution link based on the real-time location and network signal strength of the mobile shopping cart execution terminal, and uses the MQTT protocol to transmit strategy data packets.

[0034] The working principle of this invention is as follows: real-time collection of multi-dimensional data on shopping cart status, delivery tasks, and regional environment through IoT terminals; time-series analysis and feature extraction of regional environmental data using edge computing algorithms; construction of delivery scenario feature factors and association to form a single set of delivery data; and cross-device data interaction based on IoT gateways. Subsequently, K-means clustering algorithm is used to classify the credibility of multiple sets of delivery data, and the first collaborative delivery strategy is generated by combining the historical best solution.

[0035] During the delivery execution phase, the system uses an IoT sensing network to monitor dynamic interference factors such as sudden congestion, equipment failure, and cargo status in real time. It evaluates anomalies based on the analytic hierarchy process (AHP) and uses a Kalman filter algorithm to dynamically correct anomaly strategies to generate a second collaborative delivery strategy. Finally, based on the distributed decision-making algorithm of the IoT cloud platform, the system dynamically selects the delivery link by combining the real-time location and network status of each shopping cart, and accurately delivers the optimized strategy to the execution terminal. This enables route planning, task allocation, and capacity coordination for multiple shopping carts, completing an efficient and adaptive collaborative delivery task.

[0036] In some embodiments of this application, such as Figure 2 As shown, a mobile shopping cart collaborative delivery system based on the Internet of Things is also disclosed, including: The acquisition module is used to collect historical shopping cart status data, delivery task information, and regional environmental data through IoT terminals. It uses edge computing algorithms to preprocess the regional environmental data, extract delivery scenario feature factors, and determine the shopping cart status data, delivery task information, and delivery scenario feature factors that are related to the same delivery task as a single set of delivery data.

[0037] The classification module is used to enable cross-device interaction of single-set delivery data based on the IoT gateway. It uses the K-means clustering algorithm to classify multiple sets of delivery data and combines the best historical delivery solutions to generate the first collaborative delivery strategy.

[0038] The evaluation and correction module is used to carry out delivery based on the first collaborative delivery strategy, and to monitor dynamic interference factors in the delivery process in real time through the Internet of Things sensing network. Based on the dynamic interference factors, an anomaly index is evaluated, and the first collaborative delivery strategy that is determined to be abnormal is corrected using the Kalman filter algorithm to obtain the second collaborative delivery strategy.

[0039] The transmission and delivery module is used to distribute the second collaborative delivery strategy to the execution terminal of the corresponding mobile shopping cart based on the distributed decision algorithm of the Internet of Things cloud platform, so as to realize the path planning, task allocation and transportation capacity coordination of multiple shopping carts and complete the delivery task.

[0040] This system adopts a layered architecture that integrates cloud, edge, and terminal. The acquisition module deploys a multi-sensor array and edge computing nodes at the terminal layer to achieve localized preprocessing of regional environmental data and extraction of delivery scenario feature factors. The data is then aggregated across devices via an IoT gateway. The classification module performs credibility clustering analysis on multiple sets of delivery data in the cloud, combines the historical solution library to generate an initial collaborative strategy, and maps it to execution parameters.

[0041] During the delivery process, the evaluation and correction module relies on a distributed IoT sensing network to build a closed-loop monitoring mechanism, capture dynamic interference factors in real time and perform anomaly index quantification evaluation, and use the Kalman filter algorithm to compensate and correct the policy execution deviation in real time. The transmission and delivery module dynamically selects the optimal communication link based on a distributed decision algorithm, and accurately sends the corrected policy instructions to each shopping cart execution terminal, forming an organic feedback system of "perception-decision-execution-feedback" to realize adaptive collaborative delivery of multiple shopping carts.

[0042] In this application, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. In case of any inconsistency, the meaning set forth in this specification or derived from the content described herein shall prevail. Furthermore, the terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit the scope of this application.

[0043] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A mobile shopping cart collaborative delivery method based on the Internet of Things, characterized in that, Includes the following steps: S1. Collect historical shopping cart status data, delivery task information and regional environmental data through IoT terminals, preprocess the regional environmental data using edge computing algorithms, extract delivery scenario feature factors, and determine the shopping cart status data, delivery task information and delivery scenario feature factors that are related to the same delivery task as a single set of delivery data. S2. Based on the Internet of Things gateway, realize cross-device interaction of single-set delivery data, use K-means clustering algorithm to classify multiple sets of delivery data, and combine historical optimal delivery solutions to generate the first collaborative delivery strategy; S3. Delivery is carried out based on the first collaborative delivery strategy, and dynamic interference factors in the delivery process are monitored in real time through the Internet of Things sensing network. Anomaly index is evaluated based on the dynamic interference factors, and the first collaborative delivery strategy with anomalies is corrected by the Kalman filter algorithm to obtain the second collaborative delivery strategy. S4. Based on the distributed decision-making algorithm of the Internet of Things cloud platform, the second collaborative delivery strategy is sent to the execution terminal of the corresponding mobile shopping cart to realize the path planning, task allocation and transportation capacity coordination of multiple shopping carts and complete the delivery task.

2. The mobile shopping cart collaborative delivery method based on the Internet of Things according to claim 1, characterized in that, In step S1, the collection of historical shopping cart status data, delivery task information, and regional environmental data through the Internet of Things terminal includes: Historical shopping cart status data, delivery task information, and regional environmental data are collected through positioning sensors, load sensors, temperature and humidity sensors, and road condition monitoring sensors in IoT terminals. The shopping cart status data includes real-time location, remaining weight, battery life, and temperature and humidity status data of the goods. The delivery task information includes the type of goods, delivery time, and distance to the recipient address; The regional environmental data includes traffic flow, road congestion index, and weather conditions.

3. The mobile shopping cart collaborative delivery method based on the Internet of Things according to claim 2, characterized in that, In step S1, edge computing algorithms are used to preprocess regional environmental data and extract feature factors for the delivery scenario, including: Real-time computing models deployed at edge nodes are used to perform time-series analysis and weight allocation on traffic flow, road congestion index, and weather data. The collected regional environmental data of traffic flow, road congestion index, and weather conditions undergo multi-dimensional preprocessing. For traffic flow data, a sliding window algorithm with a fixed duration of 5 minutes is used. The average value of the data within the window is used as the benchmark to remove instantaneous peak data that exceed the preset threshold and retain the average number of vehicles passing through the road per unit time. Gradient smoothing is performed on the road congestion index data. The gradient change rate is calculated by the difference between adjacent data points, and abrupt data with a gradient absolute value greater than a preset gradient threshold is removed. Quantitative coding of weather data is performed to convert qualitative indicators such as rainfall and strong winds into environmental impact values ​​within a set range; Transformation weights are configured for the preprocessed data in each dimension, and the regional traffic efficiency coefficient is calculated based on a weighted summation method. A risk assessment model is constructed based on the logistic regression algorithm and a historical environmental interference event database. The preprocessed data in each dimension is then input into the risk assessment model to obtain the interference risk value output by the risk assessment model. The interference risk value is then correlated with the regional traffic efficiency coefficient at the delivery task time node to obtain the delivery scenario characteristic factor.

4. The mobile shopping cart collaborative delivery method based on the Internet of Things according to claim 3, characterized in that, In step S2, the K-means clustering algorithm is used to classify multiple sets of delivery data, and combined with the historical optimal delivery solution, the first collaborative delivery strategy is generated, including: Based on the analytic hierarchy process, credibility weights are assigned to shopping cart status data, delivery task information, and delivery scenario characteristic factors in a single set of delivery data. The credibility score of each set of delivery data is calculated based on weighted summation. The K-means clustering algorithm was used to perform unsupervised classification of the credibility scores of multiple sets of delivery data, resulting in three data clusters: high credibility, medium credibility, and low credibility. The optimal solution set for delivery tasks of the same type and region is retrieved from the historical delivery database of the IoT cloud platform. The cosine similarity algorithm is used to calculate the matching degree for the three types of data clusters and the optimal solution set respectively. Based on the matching degree calculation results, the delivery path priority and capacity allocation coefficient are configured for the three types of data clusters respectively to obtain the first collaborative delivery strategy.

5. The mobile shopping cart collaborative delivery method based on the Internet of Things according to claim 4, characterized in that, In step S3, the dynamic interference factors during the delivery process are monitored in real time through an IoT sensing network, and the anomaly index assessment based on these dynamic interference factors includes: The dynamic interference factors detected in the delivery process are normalized, and the influence weight of each dynamic interference factor is determined based on the analytic hierarchy process. An anomaly index is evaluated using a weighted synthesis algorithm. The dynamic interference factors include the probability of sudden congestion, the probability of shopping cart malfunction, and the stability of the goods status.

6. The mobile shopping cart collaborative delivery method based on the Internet of Things according to claim 5, characterized in that, In S3, the expression for evaluating the anomaly index is: ； in, This is an abnormal index. The congestion impact weight is configured. For the configured fault impact weight, The weighting of the configured cargo status For the probability of sudden congestion, For the probability of shopping cart failure, For cargo condition stability.

7. A mobile shopping cart collaborative delivery method based on the Internet of Things according to claim 6, characterized in that, In step S4, the distributed decision-making algorithm based on the IoT cloud platform sends the second collaborative delivery strategy to the execution terminal of the corresponding mobile shopping cart, including: The system acquires the real-time location and network signal strength of the mobile shopping cart execution terminal, dynamically selects the target distribution link based on the real-time location and network signal strength of the mobile shopping cart execution terminal, and uses the MQTT protocol to transmit strategy data packets.

8. A mobile shopping cart collaborative delivery system based on the Internet of Things, characterized in that, include: The acquisition module is used to collect historical shopping cart status data, delivery task information and regional environmental data through IoT terminals, preprocess the regional environmental data using edge computing algorithms, extract delivery scenario feature factors, and determine the shopping cart status data, delivery task information and delivery scenario feature factors that are related to the same delivery task as a single set of delivery data. The classification module is used to realize cross-device interaction of a single set of delivery data based on the Internet of Things gateway. It uses the K-means clustering algorithm to classify multiple sets of delivery data and combines the best historical delivery solutions to generate the first collaborative delivery strategy. The evaluation and correction module is used to carry out delivery based on the first collaborative delivery strategy, and to monitor dynamic interference factors in the delivery process in real time through the Internet of Things sensing network. Based on the dynamic interference factors, an anomaly index is evaluated, and the Kalman filter algorithm is used to correct the first collaborative delivery strategy that has been identified as abnormal, so as to obtain the second collaborative delivery strategy. The transmission and delivery module is used to distribute the second collaborative delivery strategy to the execution terminal of the corresponding mobile shopping cart based on the distributed decision algorithm of the Internet of Things cloud platform, so as to realize the path planning, task allocation and transportation capacity coordination of multiple shopping carts and complete the delivery task.

Images