Intelligent solid waste classification, valuation and recycling decision-making system
By using multi-dimensional data fusion algorithms and dynamic single-spectral irradiation parameters, accurate classification and valuation of solid waste have been achieved, solving the problems of low accuracy and inadequacy of existing systems and improving resource utilization efficiency and economy.
Patent Information
- Application Number
- CN202511380897.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-25
- Publication Date
- 2026-02-13
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing solid waste treatment systems suffer from low classification accuracy, inaccurate valuation, and lack of proactive reuse, leading to resource waste and increased treatment costs. Furthermore, these systems cannot adapt to market and policy changes in real time.
By employing multi-dimensional feature data and multi-model fusion algorithms, combined with individual user data and real-time correlated data, dynamic single-spectral illumination parameters are generated to achieve accurate classification, valuation, and proactive reuse decisions.
The classification accuracy was improved to 95%, the valuation error was reduced to 5%, the reuse efficiency was increased by 50%, and the system's adaptability and economy were significantly improved.
Smart Images
Figure CN121526575A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application belongs to the technical field of waste treatment, and particularly relates to an intelligent solid waste classification, valuation and recycling decision system. BACKGROUND
[0002] The classification and recycling of solid waste is a key link to achieve the "double carbon" goal and resource recycling, but the existing treatment system has the following core technical defects, which restrict the resource recycling efficiency and economy: such as: low classification accuracy, relying on manual and single dimension: the existing system mostly relies on manual sorting or single image recognition technology for classification, without fusing the physical properties (such as density, hardness) of waste, the composition (such as metal content, plastic type) and the pollution degree (such as harmful substance residue), resulting in a classification accuracy of less than 65%. For example, plastic containing metal impurities is classified as pure plastic, which needs to be sorted again during subsequent recycling, increasing the processing cost; low-pollution industrial solid waste is misjudged as hazardous waste, causing resource waste.
[0003] The valuation method is one-sided and disconnected from the market: the existing valuation is only based on the weight or basic category of waste (such as waste paper according to ton price, waste iron according to kilogram price), without considering the purity of waste (such as water content of waste paper, impurity content of waste metal), real-time market recycling price fluctuation, regional transportation cost and processing cost, resulting in a valuation deviation of more than 20%. For example, waste paper with high water content is valued at the standard dry paper price, and the actual profit of the recycling enterprise is insufficient; the transportation cost in remote areas is not taken into account, resulting in a valuation higher than the actual income, affecting the recycling enthusiasm.
[0004] Recycling decision is passive and information is asymmetric: the existing system can only provide basic classification information of waste, and manual contact is needed to connect with recycling enterprises to meet the recycling demand, which has the problem of "mismatch between waste supply and enterprise demand". For example, a large amount of waste plastic accumulates in a certain area, but the nearby recycling enterprises only recycle waste metal, resulting in long-term accumulation of waste; when the recycling enterprise has an urgent demand for waste electronic components, it cannot quickly locate the source of waste that meets the requirements, reducing the recycling efficiency.
[0005] Data update lags behind, poor adaptability: the classification standard and valuation parameters (such as price, cost) of the existing system are mostly fixed settings, without real-time updating of market dynamics (such as daily fluctuations in metal prices), policy requirements (such as newly added plastic-free categories) and recycling technology progress (such as waste types suitable for new plastic recycling processes). For example, a certain type of plastic has increased in value due to new recycling technology, but the system still values it at the old price, missing out on high-income opportunities; after the addition of new hazardous waste categories by policy, the system does not adjust the classification standard in time, resulting in illegal handling.
[0006] The above defects make it difficult for the existing system to achieve a closed loop of "accurate classification - reasonable valuation - efficient recycling", and an intelligent system that integrates multi-dimensional data, dynamically adapts and actively decides is urgently needed. SUMMARY
[0007] In view of the problems mentioned in the background art, the purpose of the present application is to provide an intelligent solid waste classification, valuation and recycling decision system to solve the problems mentioned in the background art.
[0008] The above technical purpose of the present application is achieved by the following technical solution: An intelligent solid waste classification, valuation and recycling decision system, comprising the following steps: Step one, collecting basic data: collecting individual basic data of the user, which reflects the inherent characteristics of the user's eyes and the basic state of myopia; Step two, collecting real-time associated data: collecting real-time associated data of the user, which reflects the dynamic progress of the user's myopia and the daily eye use scene; Step three, initial single spectrum irradiation parameter generation: based on the individual basic data and real-time associated data, generate the initial single spectrum irradiation parameter adapted to the user, which includes irradiation wavelength, irradiation intensity, single irradiation duration and irradiation period; Step four, collecting eye safety data: performing single spectrum irradiation according to the initial single spectrum irradiation parameter, and collecting real-time eye safety data of the user; Step five, safety risk judgment: judging whether there is a safety risk in the irradiation process based on the eye safety data, if there is a risk, adjusting the single spectrum irradiation parameter and continuing to execute; Step six, data update processing: regularly updating the individual basic data and real-time associated data of the user, and optimizing the single spectrum irradiation parameter based on the updated data.
[0009] Preferably, in step one, the individual basic data includes the user's age, axial length, diopter number, corneal curvature, and macular thickness of the fundus.
[0010] Preferably, in step two, the real-time associated data includes the user's eye axis growth rate every 3 months, daily near-distance eye use time, daily outdoor activity time, and sleep period.
[0011] Preferably, in step three, when generating the initial single spectrum irradiation parameter, the irradiation wavelength is determined according to the user's axial length, the irradiation wavelength is 640 to 650 nanometers when the axial length is less than 24 millimeters, and the irradiation wavelength is 650 to 660 nanometers when the axial length is greater than or equal to 24 millimeters.
[0012] Preferably, in the step three, when generating the initial single-spectrum irradiation parameter, the irradiation intensity is adjusted according to the diopter number of the user, and when the absolute value of the diopter number is less than or equal to 300 degrees, the irradiation intensity is 8 to 10 milliwatts per square centimeter, and when the absolute value of the diopter number is greater than 300 degrees, the irradiation intensity is 10 to 12 milliwatts per square centimeter.
[0013] Preferably, in the step four, the eye safety data includes the fundus temperature, the pupil diameter change amplitude, and the retinal light reflection intensity of the user, and when judging the safety risk, if the fundus temperature is greater than 37.5 degrees Celsius, the irradiation intensity is reduced, if the pupil diameter change amplitude is greater than 1 millimeter, the irradiation is suspended, and if the retinal light reflection intensity exceeds the preset threshold, the irradiation is stopped.
[0014] Preferably, the basic data collection application basic data collection module collects, and further includes an associated data collection module, a parameter generation module, an irradiation execution module, a safety monitoring module, and a parameter optimization module; the basic data collection module is used to collect individual basic data of the user, and the individual basic data reflects inherent characteristics and myopia basic state of the user's eyes; the associated data collection module is used to collect real-time associated data of the user, and the real-time associated data reflects myopia progression dynamics and daily eye use scenarios of the user; the parameter generation module is connected with the basic data collection module and the associated data collection module, respectively, and is used to generate initial single-spectrum irradiation parameters adapted to the user based on the individual basic data and the real-time associated data; the irradiation execution module is connected with the parameter generation module, and is used to output single-spectrum according to the initial single-spectrum irradiation parameters; the safety monitoring module is connected with the irradiation execution module and the parameter generation module, and is used to collect eye safety data of the user in real time and feed back to the parameter generation module; and the parameter optimization module is connected with the basic data collection module, the associated data collection module, and the parameter generation module, respectively, and is used to update the individual basic data and the real-time associated data periodically and optimize the single-spectrum irradiation parameters.
[0015] Preferably, the basic data collection module includes an optometry instrument, an eye axis measuring instrument, a corneal curvature instrument, and an ocular fundus thickness measuring instrument, the optometry instrument is used to collect the diopter number, the eye axis measuring instrument is used to collect the eye axis length, the corneal curvature instrument is used to collect the corneal curvature, and the ocular fundus thickness measuring instrument is used to collect the thickness of the macular region of the ocular fundus.
[0016] Preferably, the associated data collection module includes an eye use behavior sensor, an outdoor activity timer, and a sleep monitor, the eye use behavior sensor is used to collect the daily near-distance eye use time, the outdoor activity timer is used to collect the daily outdoor activity time, and the sleep monitor is used to collect the sleep period.
[0017] In summary, the present application has the following beneficial effects: the present application can improve classification accuracy and reduce secondary processing: through multi-dimensional feature data and multi-model fusion algorithm, the solid waste classification accuracy is improved to more than 95% (30% higher than the existing system), the identification error of subcategory is less than 5%, the secondary sorting cost caused by "misclassification and missed classification" is avoided, and the processing efficiency is improved by 40%.
[0018] The present application can realize dynamic accurate valuation and balance the interests of all parties: the dynamic valuation is calculated by combining market and cost data, the valuation deviation is reduced to within 5% (15% lower than the existing system), which not only ensures that the waste producer obtains reasonable income, but also avoids the loss of recycling enterprises due to overestimated valuation, and the participation of regional recycling enterprises is improved by 35%. BRIEF DESCRIPTION OF DRAWINGS
[0019] Figure 1 is a flowchart of the present application. DETAILED DESCRIPTION
[0020] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application. EMBODIMENT
[0021] REFERENCE Figure 1 An intelligent solid waste classification, valuation and reuse decision system, comprising the following steps: Step one, collecting basic data: collecting individual basic data of the user, the individual basic data reflecting the inherent characteristics of the user's eyes and the basic state of myopia; Step two, collecting real-time associated data: collecting real-time associated data of the user, the real-time associated data reflecting the dynamic progress of the user's myopia and the daily eye use scene; Step three, initial single spectrum irradiation parameter generation: based on the individual basic data and the real-time associated data, generating the initial single spectrum irradiation parameter adapted to the user, the initial single spectrum irradiation parameter including irradiation wavelength, irradiation intensity, single irradiation duration and irradiation period; Step four, collecting eye safety data: performing single spectrum irradiation according to the initial single spectrum irradiation parameter, and simultaneously collecting the user's eye safety data in real time; Step five, safety risk judgment: judging whether there is a safety risk in the irradiation process based on the eye safety data, if there is a risk, adjusting the single spectrum irradiation parameter and continuing to execute; Step six, data updating processing: regularly updating the individual basic data and the real-time associated data of the user, and optimizing the single spectrum irradiation parameter based on the updated data.
[0022] The individual basic data includes the age, the axial length, the diopter, the corneal curvature, and the macular thickness of the user.
[0023] The real-time associated data includes the axial length growth rate of the user every 3 months, the daily near-distance use time, the daily outdoor activity time, and the sleep period.
[0024] In the step three, when the initial monochromatic spectrum irradiation parameter is generated, the irradiation wavelength is determined according to the axial length of the user, the irradiation wavelength is 640-650 nm when the axial length is less than 24 mm, and the irradiation wavelength is 650-660 nm when the axial length is greater than or equal to 24 mm.
[0025] In the step three, when the initial monochromatic spectrum irradiation parameter is generated, the irradiation intensity is adjusted according to the diopter of the user, the irradiation intensity is 8-10 mW / cm2 when the absolute value of the diopter is less than or equal to 300 degrees, and the irradiation intensity is 10-12 mW / cm2 when the absolute value of the diopter is greater than 300 degrees.
[0026] In the step four, the eye safety data includes the fundus temperature, the pupil diameter change amplitude, and the retinal light reflection intensity of the user, when the safety risk is judged, the irradiation intensity is reduced if the fundus temperature is greater than 37.5 degrees Celsius, the irradiation is suspended if the pupil diameter change amplitude is greater than 1 mm, and the irradiation is stopped if the retinal light reflection intensity exceeds the preset threshold.
[0027] The basic data acquisition application basic data acquisition module collects, and further includes an associated data acquisition module, a parameter generation module, an irradiation execution module, a safety monitoring module, and a parameter optimization module; the basic data acquisition module is used to collect the individual basic data of the user, and the individual basic data reflects the inherent characteristics and basic state of myopia of the user; the associated data acquisition module is used to collect the real-time associated data of the user, and the real-time associated data reflects the dynamic progress and daily use scene of myopia of the user; the parameter generation module is connected with the basic data acquisition module and the associated data acquisition module, and is used to generate the initial monochromatic spectrum irradiation parameter suitable for the user based on the individual basic data and the real-time associated data; the irradiation execution module is connected with the parameter generation module, and is used to output the monochromatic spectrum according to the initial monochromatic spectrum irradiation parameter; the safety monitoring module is connected with the irradiation execution module and the parameter generation module, and is used to collect the eye safety data of the user in real time and feed back to the parameter generation module; the parameter optimization module is connected with the basic data acquisition module, the associated data acquisition module, and the parameter generation module, and is used to update the individual basic data and the real-time associated data regularly and optimize the monochromatic spectrum irradiation parameter.
[0028] The basic data collection module comprises an optometry instrument, an axial length measuring instrument, a corneal curvature instrument and an ocular fundus thickness measuring instrument, the optometry instrument is used for collecting diopter, the axial length measuring instrument is used for collecting eye axial length, the corneal curvature instrument is used for collecting corneal curvature, and the ocular fundus thickness measuring instrument is used for collecting ocular fundus macular thickness.
[0029] The correlation data collection module comprises an eye behavior sensor, an outdoor activity timer and a sleep monitor, the eye behavior sensor is used for collecting daily near distance eye use time, the outdoor activity timer is used for collecting daily outdoor activity time, and the sleep monitor is used for collecting sleep period.
[0030] The application can improve classification accuracy and reduce secondary processing: through multi-dimensional feature data and multi-model fusion algorithm, the solid waste classification accuracy is improved to more than 95% (30% higher than the existing system), the subdivision category recognition error is less than 5%, the secondary sorting cost caused by "wrong sorting and missing sorting" is avoided, and the processing efficiency is improved by 40%.
[0031] The application can realize dynamic accurate valuation and balance the interests of all parties: the dynamic valuation is calculated by fusing market and cost data, the valuation deviation is reduced to within 5% (15% lower than the existing system), reasonable income is obtained for waste producers, and loss of recycling enterprises due to high valuation is avoided, and the participation of regional recycling enterprises is improved by 35%.
[0032] The application can actively match the recycling demand and reduce the accumulation rate: through real-time matching of recycling enterprise demand, the waste and enterprise demand matching time is shortened from 24 hours to within 1 hour, the recycling efficiency is improved by 50%, the solid waste accumulation rate is reduced by 45%, and the pollution risk caused by long-term accumulation is avoided.
[0033] The application can adapt to dynamic changes in real time and improve economic efficiency: real-time update of market, policy and technical data ensures that the classification standard, valuation and decision-making scheme are synchronized with actual demand, for example, when the value of a certain type of plastic increases due to technological upgrading, the system adjusts the valuation within 2 hours, and the recycling enterprise's income increases by 20%; the classification standard is updated within 12 hours after policy adjustment, and the illegal processing rate is reduced to 0.
[0034] The application can form a data closed loop and support industry optimization: the system stores the whole process data (classification record, valuation change, decision result), can output regional waste distribution report and market demand trend analysis, provides data support for government to formulate recycling policy and enterprise to layout recycling point, and promotes the overall efficiency of the industry.
[0035] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.
Claims
1. An intelligent solid waste classification, valuation, and reuse decision-making system, characterized in that: Includes the following steps: Step 1: Collect multi-dimensional feature data: Collect multi-dimensional feature data of solid waste, which reflects the physical composition and pollution level of the waste; Step 2: Collect related data: Collect real-time related data, including market recycling prices, regional transportation costs, processing costs, and recycling company demand information; Step 3: Waste Classification: Based on multi-dimensional feature data, solid waste is classified using a multi-model fusion algorithm to determine the subcategories and reuse potential levels of the waste. Step 4: Calculate the valuation: Calculate the dynamic valuation of solid waste based on the classification results and real-time correlation data. The dynamic valuation includes the basic value purity adjustment value and the cost deduction value. Step 5: Decision-making scheme generation: Based on the recycling potential level of waste subcategories and dynamic valuation, matching recycling companies that meet the needs, generating recycling decision-making schemes; Step Six: Dynamically Adjust Decision-Making Scheme: Monitor the waste treatment status and related data changes in real time. If there are classification deviations, valuation fluctuations, or demand mismatches, dynamically adjust the classification result valuation and reuse decision-making scheme. Step 7: Dynamically adjust parameters: Regularly update the classification criteria of multi-dimensional feature data, real-time correlation data, and multi-model fusion algorithm parameters.
2. The intelligent solid waste classification, valuation, and reuse decision-making system according to claim 1, characterized in that, In step one, the multi-dimensional feature data includes the density, hardness, color, component content, moisture content, hazardous residue amount and size of the waste. The component content includes metal content, plastic content and paper content.
3. The intelligent solid waste classification, valuation, and reuse decision-making system according to claim 1, characterized in that, In step four, when calculating the dynamic valuation, the base value is the market recycling price of the waste sub-category multiplied by the weight of the waste. The purity adjustment value is the value added when the waste purity is higher than the standard purity or the value reduced when it is lower than the standard purity. The cost deduction value is the sum of regional transportation costs and processing costs.
4. The intelligent solid waste classification, valuation, and reuse decision-making system according to claim 1, characterized in that, In step five, when matching recycling companies, priority is given to recycling companies that are close to the location, have a high degree of demand matching, and whose quotations are close to the dynamic valuation, so as to generate at least two alternative reuse decision schemes.
5. The intelligent solid waste classification, valuation, and reuse decision-making system according to claim 1, characterized in that, In step six, the conditions for dynamically adjusting the classification results are that subsequent testing reveals a deviation of more than 10% between the waste composition and the classification results; the conditions for dynamically adjusting the valuation are that the daily fluctuation of the market recycling price exceeds 5%; and the conditions for dynamically adjusting the reuse decision-making scheme are that the recycling company cancels its demand or the waste exceeds the storage time limit.
6. The intelligent solid waste classification, valuation, and reuse decision-making system according to claim 1, characterized in that, The system comprises a feature data acquisition module, a correlation data acquisition module, a classification module, an valuation module, a decision-making module, a dynamic adjustment module, and a data update module. The feature data acquisition module collects multi-dimensional feature data of solid waste, reflecting its physical properties, composition, and pollution level. The correlation data acquisition module collects real-time correlation data, including market recycling prices, regional transportation costs, processing costs, and recycling company demand information. The classification module, connected to the feature data acquisition module, incorporates a multi-model fusion algorithm to classify solid waste and determine its reuse potential level. The valuation module, connected to both the classification and correlation data acquisition modules, calculates dynamic valuations based on classification results and real-time correlation data. The decision-making module, connected to both the classification and valuation modules, matches suitable recycling companies and generates reuse decision-making schemes. The dynamic adjustment module, connected to both the classification and valuation modules, monitors waste treatment status and data changes, adjusting classification results, valuations, and reuse decision-making schemes. The data update module, connected to both the feature data acquisition module, correlation data acquisition module, and classification module, periodically updates classification standard correlation data and algorithm parameters.
7. The intelligent solid waste classification, valuation, and reuse decision-making system according to claim 6, characterized in that: The feature data acquisition module includes an image scanner, a densitometer, a component analyzer, and a hazardous substance detector. The image scanner is used to collect the color and size of the waste, the densitometer is used to collect the density of the waste, the component analyzer is used to collect the component content of the waste, and the hazardous substance detector is used to collect the amount of hazardous substances remaining in the waste.
8. The intelligent solid waste classification, valuation, and reuse decision-making system according to claim 6, characterized in that: The associated data acquisition module includes a market price interface, a logistics cost system, and an enterprise demand platform. The market price interface is used to obtain market recycling prices, the logistics cost system is used to obtain regional transportation costs, and the enterprise demand platform is used to obtain recycling enterprise demand information.
9. The intelligent solid waste classification, valuation, and reuse decision-making system according to claim 6, characterized in that: The multi-model fusion algorithm built into the classification module includes weight allocation logic.