Intelligent fresh food delivery system and method based on Internet of Things

Abstract

The invention belongs to the technical field of fresh food delivery, and particularly relates to an intelligent fresh food delivery system and method based on the Internet of Things, and the method comprises the following steps: step 1, collection of a fresh food delivery technology, step 2, construction of a delivery model, step 3, edge AI quality detection, step 4, group intelligent crowdsourcing delivery, and step 5, interaction and feedback. And step 6, system optimization and a feedback mechanism. Through the Internet of Things technology and the digital twinborn model, a large amount of data is collected and analyzed in real time, data-driven decision support is provided for enterprises, future delivery requirements are predicted according to historical order data and market trends, inventory management and resource allocation are optimized, the quality of fresh food is detected in real time through edge AI equipment, and the quality of the fresh food is improved. By combining the dynamic optimization function of the digital twin model, potential problems can be found and processed in time, the loss rate of fresh products in the distribution process is remarkably reduced, and social resources are efficiently utilized through a swarm intelligence algorithm and a crowdsourcing distribution network.

Description

Technical Field

[0001] The present invention belongs to the technical field of fresh food distribution, and specifically relates to an intelligent fresh food distribution system and method based on the Internet of Things. Background Art

[0002] With the rapid development of e-commerce, the online sales scale of fresh products has been expanding year by year. Fresh products are perishable, have a short shelf life, and have high requirements for storage and transportation conditions. Therefore, freshness preservation and timeliness during the distribution process have become key challenges. Traditional fresh food distribution models usually rely on manual scheduling and simple cold chain transportation.

[0003] Currently, current fresh food distribution systems generally face problems such as incomplete data collection and lagging response. Traditional solutions rely on manual experience for inventory management and route planning, and it is difficult to perceive changes in the transportation environment in real time, such as temperature and humidity fluctuations and traffic anomalies, resulting in a relatively high loss rate of goods. In addition, existing warning mechanisms mostly use single-sensor threshold alarms, lack the ability of multi-dimensional anomaly correlation analysis, and have insufficient ability to automatically generate emergency handling solutions.

[0004] Therefore, in view of the above problems, an intelligent fresh food distribution system and method based on the Internet of Things are proposed. Summary of the Invention

[0005] The purpose of the present invention is to address the deficiencies of the prior art by providing an intelligent fresh food distribution system and method based on the Internet of Things, thereby solving the technical problems raised in the background art.

[0006] For the above technical problems, the following technical solutions are adopted: An intelligent fresh food distribution system and method based on the Internet of Things, including the following steps;

[0007] Step 1: Collect fresh food distribution technology;

[0008] Step 2: Construct a distribution model;

[0009] Step 3: Edge AI quality inspection;

[0010] Step 4: Swarm intelligence crowdsourcing distribution;

[0011] Step 5: For interaction and feedback;

[0012] Step 6: System optimization and feedback mechanism.

[0013] Preferably, in step 1, sensor and RFID technologies are used to collect the environmental information, location information, and status information of fresh products.

[0014] Preferably, in step 2, a digital twin model of the entire process of fresh food distribution is constructed to map the state of the physical world in real time;

[0015] The digital twin model data includes:

[0016] Warehouse status: Specifically, fresh food inventory, fresh food temperature, and fresh food humidity;

[0017] Vehicle status: Specifically, fresh food location and fresh food route;

[0018] Fresh food product status: Specifically, fresh food quality and fresh food location;

[0019] Environmental status: Specifically, weather and traffic;

[0020] The physical world includes: warehouses, vehicles, fresh food products, and the environment.

[0021] Preferably, in step three, an AI device is deployed in the delivery vehicle or delivery box to detect the appearance, color, and odor characteristics of fresh food products in real time, and the detected results are uploaded to the digital twin model to dynamically update the status of fresh food products.

[0022] Preferably, in step four, a swarm intelligence algorithm is used to integrate social idle resources, dynamically optimize the distribution network, and dynamically adjust the distribution priority and route according to the digital twin model and the edge AI detection results. The social idle resources include food delivery riders, private cars, and community distribution points.

[0023] Preferably, in step five, it is used to view the status and delivery progress of fresh food products in real time through the mobile terminal or the Web terminal;

[0024] It is used to evaluate and feedback on the delivery service, and the system optimizes the delivery strategy according to the feedback.

[0025] Preferably, in step six, user evaluations, delivery efficiency data, and fresh food loss rate feedback information are collected to optimize the digital twin model, the edge AI detection model, and the swarm intelligence scheduling algorithm;

[0026] Dynamically adjust the delivery strategy, provide personalized services, and implement exception handling and early warning.

[0027] Preferably, the swarm intelligence algorithm is the ant colony algorithm.

[0028] Preferably, an intelligent fresh food delivery system based on the Internet of Things, the delivery system includes:

[0029] Temperature sensors, humidity sensors, and RFID for data collection;

[0030] 5G and NB-IOT for real-time collection of environmental information, location information, and status information of fresh food products and uploading the data to the cloud platform;

[0031] Delivery vehicle for fresh food delivery.

[0032] Advantages of the present invention:

[0033] (1) Through the Internet of Things technology and digital twin models, the system can collect and analyze a large amount of data in real time, providing data-driven decision-making support for enterprises. It can predict future delivery demands based on historical order data and market trends, and optimize inventory management and resource allocation.

[0034] (2) The system monitors abnormal situations in the delivery process in real time. When encountering traffic congestion, equipment failures, or a decline in the quality of fresh food, it triggers an early warning mechanism and automatically generates an emergency response plan. Specifically, it replaces the delivery vehicle, adjusts the delivery route, or notifies the customer to ensure the stability and reliability of the delivery process. Moreover, based on real-time data and user feedback, the system can dynamically adjust the delivery strategy to adapt to different market demands and environmental changes.

[0035] (3) By using edge AI devices to detect the quality of fresh food in real time and combining with the dynamic optimization function of the digital twin model, potential problems can be discovered and addressed in a timely manner, significantly reducing the loss rate of fresh food products during the delivery process. Through swarm intelligence algorithms and crowdsourcing delivery networks, the system can efficiently utilize social resources, reduce the investment in fixed delivery vehicles and personnel, and lower operating costs. Description of the Drawings

[0036] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0037] In the accompanying drawings:

[0038] Figure 1 is the fresh food delivery system and method flow of the present invention Figure 1 ;

[0039] Figure 2 is the fresh food delivery system and method flow of the present invention Figure 2 ;

[0040] Figure 3 is the fresh food delivery system and method flow of the present invention Figure 3 . Detailed Embodiments

[0041] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention.

[0042] Specific embodiments are given below.

[0043] Embodiment

[0044] Please refer to Figures 1 - 3 , the present invention provides an intelligent fresh food distribution system and method based on the Internet of Things, including the following steps;

[0045] Step 1: Collect fresh food distribution technologies;

[0046] In the said Step 1, use sensors and RFID technology to collect the environmental information, location information, and status information of fresh food products. Specifically, the collected data is as follows:

[0047] Environmental information: temperature T, humidity H, light L;

[0048] Location information: the precision of the fresh food product is the coordinate (x, y);

[0049] Status information: fresh food quality Q, maturity M.

[0050] The data collection frequency is Δt, and the collected data set is:

[0051] D = {(T i , H i , L i , x i , y i , Q i , M i )|i = 1, 2,......, n}

[0052] Step 2: Construct a distribution model;

[0053] In the said Step 2, construct a digital twin model of the entire fresh food distribution process to map the physical world state in real time;

[0054] The data of the digital twin model includes:

[0055] Warehouse status: Specifically, fresh food inventory, fresh food temperature, and fresh food humidity;

[0056] Vehicle status: Specifically, fresh food location and fresh food route;

[0057] Fresh food product status: Specifically, fresh food quality and fresh food location;

[0058] Environmental status: Specifically, weather and traffic;

[0059] The physical world includes: warehouses, vehicles, fresh food products, and the environment.

[0060] In this step, for the digital twin model of the whole process of fresh food distribution, the state update formula of the data twin model is:

[0061] S(t) = f(S(t - 1), D(t))

[0062] Where S(t) represents the state of the digital twin model at time t;

[0063] D(t) represents the data collected at time t;

[0064] f is the state update function, which is used to map the data in the physical world into the digital twin model.

[0065] The specific states of the digital twin model include:

[0066] Warehouse state: inventory I, temperature Tω, and humidity Hω.

[0067] Vehicle state: position (x ν , y ν ) and route R.

[0068] Fresh product state: quality Q p and position (x p , y p ).

[0069] Environmental state; weather W and traffic condition C.

[0070] Step Three: Edge AI Quality Detection;

[0071] In Step Three, an AI device is deployed in the delivery vehicle or delivery box to detect the appearance, color, and odor characteristics of fresh products in real time, and upload the detection results to the digital twin model to dynamically update the state of fresh products.

[0072] In Step Three, the edge AI device detects the appearance, color, and odor characteristics of fresh products in real time, and the detection results are used to calculate the fresh product quality score through the following formula:

[0073] Q P = ω1·A + ω2·C + ω3·S

[0074] Where: Q P is the fresh product quality score.

[0075] A is the appearance score.

[0076] C is the color score.

[0077] S is the odor score.

[0078] ω1, ω2, ω3 are weight coefficients, satisfying:

[0079] ω1 + ω2 + ω3 = 1。

[0080] The detection results are uploaded to the digital twin model to update the status of fresh products:

[0081] Q P (t) = Q P (t - 1) + ΔQ P 。

[0082] Step Four: Swarm intelligence crowdsourcing distribution;

[0083] In the said Step Four, using swarm intelligence algorithms, integrating social idle resources, dynamically optimizing the distribution network, and dynamically adjusting the distribution priority and path according to the digital twin model and the edge AI detection results. The social idle resources include food delivery riders, private cars, and community distribution points.

[0084] In this step, the ant colony algorithm is used to optimize the distribution path. The core formula of the ant colony algorithm is as follows:

[0085] Pheromone update formula: T ij (t + 1) = (1 - ρ)·T ij (t) + ΔT ij , where:

[0086] T ij (t) is the pheromone concentration of path (i, j) at time t.

[0087] ρ is the pheromone evaporation coefficient.

[0088] ΔTij is the pheromone increment released by the ant on path (i, j).

[0089] The path selection probability formula is as follows:

[0090]

[0091] where:

[0092] is the probability that ant κ selects path (i, j) at time t.

[0093] η ij is the heuristic information of path (i, j), more specifically, the reciprocal of the distance.

[0094] α and β are parameters that control the weights of pheromone and heuristic information.

[0095] Step Five: For interaction and feedback;

[0096] In the said Step Five, the status and distribution progress of fresh products are viewed in real time through the mobile terminal or the Web terminal

[0097] Based on the evaluation and feedback of the delivery service, the system optimizes the delivery strategy according to the feedback.

[0098] In this step, the user views the status and delivery progress of fresh products through the mobile or Web terminal. The feedback scoring formula is as follows:

[0099]

[0100] Where:

[0101] F is the comprehensive score of user feedback.

[0102] f i is the score of the i-th user.

[0103] N is the number of users.

[0104] Step Six: System Optimization and Feedback Mechanism;

[0105] In Step Six, collect user evaluations, delivery efficiency data, and feedback information on the fresh product loss rate, and optimize the digital twin model, edge AI detection model, and swarm intelligence scheduling algorithm;

[0106] Dynamically adjust the delivery strategy, provide personalized services, and implement exception handling and early warning.

[0107] In this step, the system optimizes the model based on user feedback and delivery data. The optimization objective function is as follows:

[0108] M inimize Z = ω1·L + ω2·D + ω3·C;

[0109] Where:

[0110] L is the fresh product loss rate.

[0111] D is the delivery time.

[0112] C is the delivery cost.

[0113] ω1, ω2, ω3 are weight coefficients, satisfying ω1 + ω2 + ω3 = 1.

[0114] Furthermore, an intelligent fresh product delivery system based on the Internet of Things, the delivery system includes:

[0115] Temperature sensors, humidity sensors, and RFID for data collection;

[0116] 5G and NB-IOT for real-time collection of environmental information, location information, and status information of fresh products, and uploading the data to the cloud platform;

[0117] Delivery vehicles for the delivery of fresh products;

[0118] An edge AI device for real-time detection of the appearance, color, and smell of fresh products, and for judging the freshness and quality of the produced products.

[0119] In summary, through the Internet of Things technology and the digital twin model, the system can collect and analyze a large amount of data in real time, provide data-driven decision support for enterprises, realize predicting future distribution demands according to historical order data and market trends, and optimize inventory management and resource allocation.

[0120] The system monitors abnormal situations in the distribution process in real time. When encountering traffic congestion, equipment failures, or a decline in the quality of fresh products, it triggers an early warning mechanism and automatically generates an emergency response plan. Specifically, it replaces the distribution vehicle, adjusts the distribution route, or notifies the customer to ensure the stability and reliability of the distribution process. Moreover, based on real-time data and user feedback, the system can dynamically adjust the distribution strategy to adapt to different market demands and environmental changes.

[0121] By using the edge AI device to detect the quality of fresh products in real time and combining with the dynamic optimization function of the digital twin model, potential problems can be discovered and processed in a timely manner, significantly reducing the loss rate of fresh products during the distribution process. Through swarm intelligence algorithms and crowdsourcing distribution networks, the system can efficiently utilize social resources, reduce the investment in fixed distribution vehicles and personnel, and lower the operating costs.

[0122] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by terms such as "front and back", "left and right", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or component referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation of the present invention.

[0123] Of course, in this technical solution, those skilled in the art should understand that the term "one" should be understood as "at least one" or "one or more". That is, in one embodiment, the number of an element can be one, while in other embodiments, the number of this element can be multiple. The term "one" should not be construed as a limitation on the quantity.

[0124] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art under the technical guidance of the present invention should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. An intelligent fresh food distribution method based on the Internet of Things, characterized by: The steps include: Step 1: Collect fresh food delivery technology; Step 2: Component distribution model; Step 3: Edge AI quality detection; Step 4: Group intelligent crowdsourcing delivery; Step 5: Used for interaction and feedback; Step 6: System optimization and feedback mechanism.

2. According to claim 1, an intelligent fresh food distribution method based on the Internet of Things is characterized by: In step one, sensors and RFID technology are used to collect environmental information, location information and status information of fresh products.

3. The intelligent fresh food distribution method based on the Internet of Things according to claim 1 is characterized by: In step 2, a digital twin model of the entire fresh food delivery process is constructed to map the state of the physical world in real time; The digital twin model data includes: Warehouse status: specifically, fresh food inventory, fresh food temperature, and fresh food humidity; Vehicle status: specifically, fresh food location and fresh food route; Fresh product status: specifically, fresh product quality and fresh product location; Environmental conditions: specifically, weather and traffic; The physical world includes: warehouses, vehicles, fresh products and the environment.

4. The intelligent fresh food distribution method based on the Internet of Things according to claim 1 is characterized by: In step three, AI equipment is deployed in the delivery vehicle or delivery box to detect the appearance, color and smell characteristics of the fresh products in real time, and the detection results are uploaded to the digital twin model to dynamically update the status of the fresh products.

5. The intelligent fresh food distribution method based on the Internet of Things according to claim 1 is characterized by: In step four, a swarm intelligence algorithm is used to integrate idle social resources, dynamically optimize the distribution network, and dynamically adjust the distribution priority and path based on the digital twin model and edge AI detection results. The idle social resources include food delivery riders, private cars, and community distribution points.

6. The intelligent fresh food distribution method based on the Internet of Things according to claim 1, characterized in that: In step 5, the status and delivery progress of fresh products are checked in real time through a mobile terminal or a web terminal; Based on the evaluation and feedback of the delivery service, the system optimizes the delivery strategy according to the feedback.

7. The intelligent fresh food distribution method based on the Internet of Things according to claim 1 is characterized by: In step six, user evaluations, delivery efficiency data, and fresh food loss rate feedback information are collected to optimize the digital twin model, edge AI detection model, and swarm intelligence scheduling algorithm; Dynamically adjust distribution strategies, provide personalized services, and implement exception handling and early warning.

8. The intelligent fresh food distribution method based on the Internet of Things according to claim 5 is characterized by: The swarm intelligence algorithm is an ant colony algorithm.

9. The method for intelligent fresh food distribution based on the Internet of Things according to claims 1-8 is applied to an intelligent fresh food distribution system based on the Internet of Things, characterized in that: The delivery system comprises: Temperature sensors, humidity sensors and RFID for data collection; 5G and NB-IOT are used to collect environmental information, location information, and status information of fresh products in real time, and upload the data to the cloud platform; Delivery vehicles, used for fresh food delivery; Edge AI devices are used to detect the appearance, color, and smell of fresh products in real time, and to judge the freshness and quality of production products.

Images