Intelligent storage supervision system based on Internet of Things comprehensive data analysis

Abstract

The invention discloses an intelligent warehousing supervision system based on Internet of Things comprehensive data analysis, and belongs to the field of warehousing supervision systems, and the system comprises a self-service weighing subsystem which is used for carrying out the automatic weighing of warehousing target waste materials, obtaining, encrypting and storing gross weight data and tare weight data, and capturing an initial state image set of the waste materials; the central control server is in communication connection with the self-service weighing subsystem and comprises a state comparison module which is used for calling a warehousing state image set of the target waste when the target waste is delivered out of a warehouse and carrying out multi-dimensional similarity matching on the warehousing state image set and a warehouse-out state image set collected in real time; the abnormity tracing engine is activated when the weight deviation ratio exceeds a preset threshold value or the image similarity is lower than a set standard; and calling the continuous monitoring video stream in the target waste storage period to carry out abnormal event identification. According to the invention, the warehouse-in and warehouse-out stage of the waste materials can be monitored more comprehensively, and the abnormity can be found and remedied in time when the abnormity occurs.

Description

Technical Field

[0001] The present invention relates to the field of warehouse supervision systems, and in particular to an intelligent warehouse supervision system based on comprehensive data analysis of the Internet of Things. Background Art

[0002] Waste recycling refers to the process of converting waste into usable resources through sorting, collection, processing, and disposal. It is essentially the recycling of "resources" rather than simply discarding or landfilling / incineration. The objects of recycling are very wide, including:

[0003] Common recyclables: waste paper (newspapers, cardboard boxes, office paper, etc.), waste plastic (beverage bottles, packaging film, containers, etc.), waste metal (cans, iron sheets, copper wire, etc.), waste glass (wine bottles, window glass, etc.), waste textiles (clothes, cloth).

[0004] Special waste: used electronic products (computers, mobile phones, home appliances, electronic waste), used batteries, used motor vehicles, construction waste (partially recyclable), waste grease (can be converted into biodiesel), agricultural waste (such as straw can be reused).

[0005] After the waste is recycled, it needs to be stored in the warehouse and wait for retrieval. In order to monitor the status of the waste in real time, a corresponding intelligent warehouse supervision system needs to be configured in the warehouse. The existing patent 202311635228.3 is an intelligent warehouse supervision system and method based on intelligent digital data analysis, including: a warehouse item supervision module, a supervision information collection module, a data management center, a target equipment screening module and an equipment adjustment management module. The warehouse item supervision module is used to monitor the flow status of goods in the warehouse in real time and conduct information sharing and interaction. The supervision information collection module is used to collect equipment information and historical supervision information used for goods supervision. The data management center stores and manages all collected data. The target equipment screening module is used to analyze the reasonable installation coefficients of different equipment and screen out the equipment to be adjusted. The equipment to be adjusted is replaced by the equipment adjustment management module, and the improperly selected reading equipment is promptly replaced with equipment with suitable working frequency, while ensuring the maximum coverage and capture of goods information and warehouse supervision efficiency while reducing unnecessary supervision costs.

[0006] The existing technology suffers from the following problems: Anomalies are most likely to occur during the inbound and outbound stages of waste storage, but existing warehouse supervision systems are incomplete in oversight of this stage, failing to promptly detect and remedy anomalies. Therefore, those skilled in the art have provided an intelligent warehouse supervision system based on comprehensive IoT data analysis to address the issues raised in the background art. Summary of the Invention

[0007] The purpose of the present invention is to provide an intelligent warehousing supervision system based on comprehensive data analysis of the Internet of Things, which can more comprehensively supervise the entry and exit stages of waste materials, and promptly detect and remedy abnormalities when they occur, so as to solve the problems raised in the above background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] An intelligent warehousing supervision system based on comprehensive data analysis of the Internet of Things, including:

[0010] The self-service weighing subsystem is used to automatically weigh incoming waste, obtain and encrypt gross weight and tare weight data, and capture an image set of the waste's initial state.

[0011] The central control server is communicatively connected to the self-service weighing subsystem and includes: a state comparison module for retrieving a set of images of the target waste in storage when the target waste is shipped out of the warehouse, and performing multi-dimensional similarity matching with a set of images of the target waste in storage collected in real time; an abnormality tracing engine for activating when the weight deviation rate exceeds a preset threshold or the image similarity falls below a set standard; a video analysis module for responsive to an abnormality tracing engine activation instruction to retrieve a continuous monitoring video stream during the storage period of the target waste to identify abnormal events;

[0012] The points management subsystem is used to calculate warehouse management personnel's contribution points based on the value, storage duration, and condition of incoming waste; dynamically allocate supervision authority for high-value waste to personnel with the highest points; and provide a points redemption interface to redeem stored waste at cost price.

[0013] The abnormal response subsystem includes: a multi-source sensing unit for real-time monitoring of waste state changes; a real-time abnormality detector for marking waste with sudden changes in state to the abnormal list during entry and exit, where sudden changes in state refer to waste state changes exceeding a preset value; and a priority calculation engine for generating a remediation order for the waste on the abnormal list, where the remediation order is sorted from large to small based on the remediation weight.

[0014] As a further solution of the present invention: the self-service weighing subsystem includes:

[0015] Tamper-proof weighing unit with built-in blockchain storage unit to achieve distributed storage of weight data;

[0016] Anomaly weight detector, which triggers equipment self-check when continuous weighing fluctuations exceed the limit;

[0017] Multispectral camera unit that simultaneously captures visible light images and infrared thermal images and generates surface deformation depth maps.

[0018] As a further solution of the present invention: the state comparison module performs:

[0019] Extract contour features, texture features, and material distribution features of incoming and outgoing images;

[0020] Calculate composite similarity: obtained by weighted fusion of contour similarity, texture matrix difference and material distribution divergence;

[0021] When the composite similarity is less than 85 percent (i.e., the image similarity is lower than the set standard), it is marked as morphological abnormality.

[0022] As a further solution of the present invention: the anomaly tracing engine includes:

[0023] The three-level causal analysis unit performs the following steps: (1) Environmental violation judgment: detecting whether the storage environment has caused deterioration based on temperature and humidity data; (2) Behavior violation detection: identifying the behavior of passing off inferior goods as good ones through video re-identification technology; (3) Theft suspicion analysis: matching access control logs with weight mutation timestamps;

[0024] The remediation knowledge base stores historical cases and optimization solutions and outputs targeted suggestions.

[0025] As a further solution of the present invention: the video analysis module adopts:

[0026] The spatial stream branch extracts key area features of a single frame;

[0027] The temporal flow branch analyzes the optical flow changes between consecutive frames;

[0028] Generates a theft alarm when abnormal movement is detected and there is no record of legitimate operation.

[0029] As a further solution of the present invention: the formula for calculating the contribution points of the points management subsystem is:

[0030] ;

[0031] Among them, P is the contribution points of the warehouse staff, k is the value coefficient preset according to the waste category, V in is the assessed value of the waste materials entering the warehouse, T store is the actual storage duration (days), Q out Score the outgoing condition (0-100), Q crit is the critical integrity threshold, and b is the basic supervision integral constant.

[0032] As a further solution of the present invention: the points management subsystem further performs:

[0033] Dynamic authority allocation: When high-value waste is stored, the top five contributors are selected to form a supervisory team.

[0034] Points redemption calculation: The cost price is dynamically generated based on the condition score and market valuation. The cost price is reduced by a preset ratio for every 10% increase in condition.

[0035] As a further solution of the present invention: the multi-source sensing unit includes:

[0036] a vibration sensor array to monitor changes in stack stability;

[0037] Gas composition analyzer, used to detect the concentration of leaked pollutants in real time;

[0038] Temperature and humidity sensor group, used to collect temperature and humidity environmental parameter changes;

[0039] Positioning tag reader / writer, used to track the location offset of waste.

[0040] As a further solution of the present invention: the formula for determining the remediation weight by the priority calculation engine is:

[0041] ;

[0042] Among them, S is the remediation weight value, is the degree of deviation of the status from the baseline value (percentage), To affect the amount of other waste within the radius, The estimated value of waste materials. is the pollutant concentration index, is the area affected by the leakage (square meters), is the pollution diffusion rate (percentage per minute), w1, w2, w3, w4 and w5 are dynamically adjusted weight coefficients.

[0043] As a further solution of the present invention: it also includes:

[0044] A decision-making support unit is used to match historical similar case libraries to obtain the best remediation plan and pre-dispatch remediation support equipment to high-risk areas on standby;

[0045] Improve the feedback device to extract the characteristics of the current operation defects and generate suggestions for updating the warehousing procedures; and optimize the weight coefficient assignment strategy based on the remediation effect.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] The present invention realizes the tamper-proof collection of the weight and morphological data of waste entering the warehouse through the self-service weighing subsystem and dual-spectral imaging technology, and eliminates the risk of manual tampering from the source by combining blockchain evidence storage; uses a multi-dimensional image feature comparison algorithm and a three-level traceability mechanism (environmental monitoring, behavior analysis, and theft identification) to accurately locate the cause of weight deviation or abnormal state, significantly improving the transparency of waste supervision; the contribution score formula set The storage quality is linked to personal benefits, and the enthusiasm of personnel is stimulated by dynamically allocating the supervision authority of high-value waste; with the help of multi-source sensor units, the state mutation during the storage and out-of-stock period is captured in real time, and the remedial weight formula is used. Quantify five-dimensional risks such as pollution leakage and value loss, intelligently generate emergency repair sequences, and prioritize resources for high-risk waste treatment; ultimately form a closed-loop management of "data collection-abnormal diagnosis-incentive optimization-emergency decision-making", reduce regulatory costs, and significantly reduce the accident rate of hazardous waste leakage, while promoting the recycling of storage resources through a points redemption mechanism. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a structural diagram of an intelligent warehousing supervision system based on comprehensive data analysis of the Internet of Things. DETAILED DESCRIPTION

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0050] As mentioned in the background technology of this application, research has found that anomalies are most likely to occur during the storage and retrieval stages of waste materials, but the existing warehouse supervision system is not comprehensive enough for this stage, and is unable to detect anomalies and remedy them in a timely manner, and has certain defects.

[0051] In order to address the above-mentioned defects, the present application discloses an intelligent warehousing supervision system based on comprehensive data analysis of the Internet of Things, which can more comprehensively supervise the entry and exit stages of waste materials, promptly detect abnormalities and take remedial measures when they occur. At the same time, it uses a multi-dimensional image feature comparison algorithm and a three-level traceability mechanism (environmental monitoring, behavior analysis, and theft identification) to accurately locate the causes of weight deviations or abnormal status, significantly improving the transparency of waste supervision.

[0052] The following will describe in detail how the solution of this application solves the above technical problems with reference to the accompanying drawings.

[0053] See also Figure 1In an embodiment of the present invention, an intelligent warehousing supervision system based on comprehensive data analysis of the Internet of Things includes: a self-service weighing subsystem for automatically weighing incoming target waste, obtaining and encrypting and storing gross weight data and tare weight data, and capturing an initial state image set of the waste; a central control server, which is communicatively connected to the self-service weighing subsystem and includes: a state comparison module for retrieving its incoming state image set when the target waste is out of the warehouse, and performing multi-dimensional similarity matching with the outgoing state image set collected in real time; an abnormality tracing engine, which is activated when the weight deviation rate exceeds a preset threshold or the image similarity is lower than a set standard; a video analysis module, which, in response to an abnormality tracing engine activation instruction, retrieves the target waste storage state image set. Continuous monitoring video streams during the storage cycle are used to identify abnormal events; the points management subsystem is used to: calculate the contribution points of warehouse personnel based on the value, storage time and intact state of incoming waste; dynamically allocate the supervision authority of high-value waste to the person with the highest points; provide a points exchange interface to exchange warehoused waste at cost price; the abnormal response subsystem includes: a multi-source sensor unit for real-time monitoring of waste status changes; a real-time anomaly detector for marking waste with sudden changes in status to the abnormal list during entry and exit, where a sudden change in status refers to a change in the status of a waste that exceeds a preset value; a priority calculation engine for generating a remedial order for the waste in the abnormal list, where the remedial order is sorted from large to small by the remedial weight. This application constructs an intelligent supervision closed loop driven by the Internet of Things, and implements tamper-proof storage data through self-service weighing and image acquisition to solve the problem of manual record fraud; uses multi-dimensional status comparison and video traceability to achieve automatic diagnosis of anomalies and reduce blind spots in supervision; the points mechanism binds personnel performance to the value of goods to enhance supervision responsibility; the multi-source sensor unit captures sudden changes in status in real time to block the spread of risks in advance.

[0054] In this embodiment, the self-service weighing subsystem includes a tamper-resistant weighing unit with a built-in blockchain storage unit for distributed weight data storage; a weight anomaly detector that triggers a self-check when continuous weight fluctuations exceed a certain limit (for example, if the weight anomaly detector detects that the difference between adjacent weights exceeds ±2% of the calibrated weight value in three consecutive weighings, it initiates a self-check of the tamper-resistant weighing unit); and a multispectral camera unit that simultaneously captures visible light images and infrared thermal images and generates a surface deformation depth map. This setup establishes a trusted record of weighing and depth status. Blockchain storage ensures that weight data cannot be tampered with (resolving the issue of human modification of tare / gross weight). Multispectral imaging simultaneously records surface deformation and thermodynamic characteristics, providing multi-dimensional evidence for later state comparison. A multispectral camera is an optical imaging device that can simultaneously capture images in multiple specific wavelength bands and serves as a core state perception function in the waste storage and supervision system.

[0055] In this embodiment, the state comparison module extracts the contour, texture, and material distribution features of incoming and outgoing images; calculates composite similarity by weightedly fusing contour similarity, texture matrix difference, and material distribution divergence; and flags an image as morphologically abnormal if the composite similarity falls below 85 percent (i.e., image similarity falls below a set threshold). This setup verifies physical state consistency across time periods, integrating contour, texture, and material distribution features to identify instances of substandard goods (e.g., replacing high-value components). An 85% similarity threshold accurately identifies morphological anomalies, avoiding subjective judgment errors. Contour similarity refers to the degree of matching of the edges of the waste object's shape (e.g., whether it is deformed or damaged); texture matrix difference quantifies differences in surface texture features (e.g., rust and stain distribution); and material distribution divergence measures the spatial distribution of internal material components (through multispectral imaging analysis).

[0056] In this embodiment, the anomaly tracing engine includes a three-level causal analysis unit, which sequentially performs the following: (1) environmental violation judgment: detecting whether the storage environment has caused deterioration based on temperature and humidity data; (2) behavioral violation detection: identifying the behavior of passing off inferior goods as good goods through video re-identification technology; (3) theft suspicion analysis: matching access control logs with weight mutation timestamps; and a remediation knowledge base that stores historical cases and optimization solutions and outputs targeted suggestions. This setup uses a three-level progressive root cause analysis, in which environmental violation judgment → resolving improper storage conditions; behavioral violation detection → identifying cheating by swapping goods; theft suspicion analysis → locating insider theft incidents; and the knowledge base outputs optimization suggestions to prevent the recurrence of similar anomalies.

[0057] In this embodiment, the video analysis module uses a spatial flow branch to extract key region features within a single frame, and a temporal flow branch to analyze optical flow variations between consecutive frames. A theft alarm is generated when abnormal movement is detected and no legitimate operation is recorded. This setup employs a combined spatiotemporal and temporal approach to identify abnormal behavior. Optical flow variation analysis captures unauthorized movement (e.g., the movement of goods during theft), while spatial feature comparison identifies partial replacements (e.g., the removal of some discarded items).

[0058] In this embodiment, the formula for calculating contribution points by the points management subsystem is:

[0059] ; Among them, P is the contribution points of the warehouse staff, k is the value coefficient preset according to the waste category, V in is the assessed value of the waste materials entering the warehouse, T store is the actual storage duration (days), Q out Score the outgoing condition (0-100), Q crit is the critical integrity threshold, and b is the basic regulatory credit constant. This setting provides an incentive algorithm that quantifies regulatory contributions, resolving the pain point of the mismatch between traditional warehousing responsibilities and benefits.

[0060] In this embodiment, the points management subsystem also implements: dynamic authority allocation: When high-value scrap arrives, the top five contributors by points are selected to form a supervisory queue; and point redemption calculation: a cost price is dynamically generated based on the condition score and market valuation, with the cost price decreasing by a preset percentage for every 10% increase in condition. This setup provides dynamic authority and redemption control, where the top five supervisors of high-value scrap form an elite supervisory team; and increased condition reduces redemption costs, incentivizing proactive maintenance of the goods.

[0061] In this embodiment, the multi-source sensing unit includes a vibration sensor array for monitoring stack stability changes; a gas composition analyzer for real-time detection of leaked pollutant concentrations; a temperature and humidity sensor array for collecting temperature and humidity parameter changes; and a positioning tag reader for tracking waste displacement. In this setup, the vibration sensor array provides early warning of stack collapse risks; the gas composition analyzer monitors toxic leaks in real time; and the positioning tag reader tracks illegal displacement.

[0062] In this embodiment, the priority calculation engine determines the remediation weight using the following formula:

[0063] ;

[0064] Among them, S is the remediation weight value, is the degree of deviation of the status from the baseline value (percentage), To affect the amount of other waste within the radius, The estimated value of waste materials. is the pollutant concentration index, is the area affected by the leakage (square meters), is the pollution diffusion rate (percentage per minute), and w1, w2, w3, w4, and w5 are dynamically adjusted weight coefficients. This application establishes a multi-factor weighted emergency decision-making process, prioritizing remediation of high-value, high-pollution projects according to a pre-set procedure, addressing the inefficiency and delays of traditional manual inspections.

[0065] This embodiment also includes: a decision-making support unit that matches a library of historical similar cases to determine the optimal remediation plan; pre-dispatches remediation support equipment to high-risk areas for standby; an improved feedback controller that extracts the characteristics of the current operational defect and generates recommended updates to warehousing procedures; and optimizes the weight coefficient assignment strategy based on the remediation results. This setup provides a self-learning improvement mechanism, where historical case matching reduces decision-making time by 90%, weight coefficient optimization continuously improves the accuracy of remediation strategies, and equipment pre-dispatching achieves a golden 5-minute emergency response.

[0066] The present invention realizes the tamper-proof collection of the weight and morphological data of waste entering the warehouse through the self-service weighing subsystem and dual-spectral imaging technology, and eliminates the risk of manual tampering from the source by combining blockchain evidence storage; uses a multi-dimensional image feature comparison algorithm and a three-level traceability mechanism (environmental monitoring, behavior analysis, and theft identification) to accurately locate the cause of weight deviation or abnormal state, significantly improving the transparency of waste supervision; the contribution score formula set The storage quality is linked to personal benefits, and the enthusiasm of personnel is stimulated by dynamically allocating the supervision authority of high-value waste; with the help of multi-source sensor units, the state mutation during the storage and out-of-stock period is captured in real time, and the remedial weight formula is used. Quantify five-dimensional risks such as pollution leakage and value loss, intelligently generate emergency repair sequences, and prioritize resources for high-risk waste treatment; ultimately form a closed-loop management of "data collection-abnormal diagnosis-incentive optimization-emergency decision-making", reduce regulatory costs, and significantly reduce the accident rate of hazardous waste leakage, while promoting the recycling of storage resources through a points redemption mechanism.

[0067] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

[0068] The above is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solutions and inventive concepts of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. An intelligent warehousing supervision system based on comprehensive data analysis of the Internet of Things, characterized by: include: The self-service weighing subsystem is used to automatically weigh incoming waste, obtain and encrypt and store gross weight and tare weight data, and capture an image set of the waste's initial state; The central control server is communicatively connected to the self-service weighing subsystem and includes: a state comparison module for retrieving the incoming state image set of the target waste when it is out of the warehouse, and performing multi-dimensional similarity matching with the outgoing state image set collected in real time; an abnormality tracing engine, which is activated when the weight deviation rate exceeds a preset threshold or the image similarity is lower than a set standard; The video analysis module, in response to the abnormal tracing engine activation instruction, retrieves the continuous monitoring video stream during the target waste storage period to identify abnormal events; The points management subsystem is used to calculate the warehouse management staff's contribution points based on the value, storage time and intact condition of the incoming waste; and dynamically allocate the supervision authority of high-value waste to the person with the highest points; Provide a points exchange interface to exchange storage waste at cost price; The abnormal response subsystem includes: a multi-source sensing unit for real-time monitoring of waste state changes; a real-time abnormality detector for marking waste with sudden changes in state to an abnormal list during storage and outbound transportation. A sudden change in state refers to a waste state change value exceeding a preset value. The priority calculation engine is used to generate a remediation order for the wastes in the exception list, wherein the remediation order is sorted from large to small according to the remediation weight.

2. The intelligent warehousing supervision system based on comprehensive data analysis of the Internet of Things according to claim 1 is characterized in that: The self-service weighing subsystem includes: Tamper-proof weighing unit with built-in blockchain storage unit to achieve distributed storage of weight data; Anomaly weight detector, which triggers equipment self-check when continuous weighing fluctuations exceed the limit; Multispectral camera unit that simultaneously captures visible light images and infrared thermal images and generates surface deformation depth maps.

3. The intelligent warehousing supervision system based on comprehensive data analysis of the Internet of Things according to claim 2 is characterized in that: The state comparison module performs: Extract contour features, texture features, and material distribution features of incoming and outgoing images; Calculate composite similarity: obtained by weighted fusion of contour similarity, texture matrix difference and material distribution divergence; When the composite similarity is less than 85 percent, it is marked as morphological abnormality.

4. The intelligent warehousing supervision system based on comprehensive data analysis of the Internet of Things according to claim 3 is characterized in that: The exception tracing engine includes: The three-level causal analysis unit performs the following steps: (1) Environmental violation judgment: detecting whether the storage environment has caused deterioration based on temperature and humidity data; (2) Behavior violation detection: identifying the behavior of passing off inferior goods as good ones through video re-identification technology; (3) Theft suspicion analysis: matching access control logs with weight mutation timestamps; The remediation knowledge base stores historical cases and optimization solutions and outputs targeted suggestions.

5. The intelligent warehousing supervision system based on comprehensive data analysis of the Internet of Things according to claim 4 is characterized in that: The video analysis module uses: The spatial stream branch extracts key area features of a single frame; The temporal flow branch analyzes the optical flow changes between consecutive frames; Generates a theft alarm when abnormal movement is detected and there is no record of legitimate operation.

6. The intelligent warehousing supervision system based on comprehensive data analysis of the Internet of Things according to claim 5 is characterized in that: The formula for calculating contribution points in the points management subsystem is: ； Among them, P is the contribution points of the warehouse staff, k is the value coefficient preset according to the waste category, V in is the assessed value of the incoming waste, T store is the actual storage duration, Q out Score the good condition of the warehouse, Q crit is the critical integrity threshold, and b is the basic supervision integral constant.

7. The intelligent warehousing supervision system based on comprehensive data analysis of the Internet of Things according to claim 6 is characterized in that: The points management subsystem also performs: Dynamic authority allocation: When high-value waste enters the warehouse, the top five contributors are selected to form a supervisory queue; Points redemption calculation: The cost price is dynamically generated based on the condition score and market valuation. The cost price is reduced by a preset ratio for every 10% increase in condition.

8. The intelligent warehousing supervision system based on comprehensive data analysis of the Internet of Things according to claim 7 is characterized in that: The multi-source sensing unit comprises: a vibration sensor array to monitor changes in stack stability; Gas composition analyzer, used to detect the concentration of leaked pollutants in real time; Temperature and humidity sensor group, used to collect temperature and humidity environmental parameter changes; Positioning tag reader / writer, used to track waste location deviation.

9. The intelligent warehousing supervision system based on comprehensive data analysis of the Internet of Things according to claim 8 is characterized in that: The formula used by the priority calculation engine to determine the remediation weight is: ； Among them, S is the remediation weight value, The degree to which the state deviates from the reference value, To affect the amount of other waste within the radius, For waste value assessment, is the pollutant concentration index, is the leakage affected area, is the pollution diffusion rate, w1, w2, w3, w4 and w5 are dynamically adjusted weight coefficients.

10. The intelligent warehousing supervision system based on comprehensive data analysis of the Internet of Things according to claim 9 is characterized in that: Also includes: A decision-making support unit, used to match historical similar case libraries to obtain the best remediation plan; And pre-dispatch remedial auxiliary equipment to high-risk areas on standby; Improve the feedback device to extract the characteristics of the current operation defects and generate suggestions for updating the warehousing procedures; And optimize the weight coefficient assignment strategy according to the remediation effect.

Images