Multi-target collaborative solid waste cyclic utilization intelligent decision-making method based on layered framework

Through a multi-objective collaborative solid waste recycling smart decision-making method based on a layered framework, combined with deep learning technology, the uncertainty problem of solid waste treatment decisions is solved, and the accurate and efficient decision-making of solid waste recycling schemes is achieved, and super-large cities are supported. Intelligent management of the group.

CN119066502AInactive Publication Date: 2024-12-03CHINESE RES ACAD OF ENVIRONMENTAL SCI
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411115712.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-14
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing solid waste treatment decision-making methods rely on expert experience, resulting in uncertainty and subjectivity of decision-making results, making it difficult to achieve accurate and efficient solid waste recycling solutions.

Method used

Using a multi-objective collaborative solid waste recycling intelligent decision-making method based on a layered framework, by obtaining the environmental goals, economic goals and social goals input by users, combining the data on solid waste industry lines, processing characteristics, circulation paths and real-life scene park situations, Use deep learning technology to perform semantic understanding and feature association fusion analysis to generate intelligent decision-making results.

Benefits of technology

It improves the accuracy and objectivity of solid waste recycling solutions, provides scientific, efficient and intelligent decision-making support for megacities, and achieves efficient utilization of solid waste resources and reduces environmental pollution.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066502A_ABST
    Figure CN119066502A_ABST
Patent Text Reader

Abstract

The invention relates to a multi-target collaborative solid waste cyclic utilization intelligent decision-making method based on a layered framework. The method comprises the following steps: on the basis of solid waste recycling related data such as a solid waste industrial line, solid waste treatment characteristics, a circulation path and a real scene park condition, building a multi-target collaborative decision framework by considering collaborative constraints in multiple aspects of an environment target, an economic target and a social target; meanwhile, an artificial intelligence technology based on deep learning is adopted to carry out semantic understanding on solid waste recycling related data and multi-target constraint information, and then fine-grained feature association reinforcement fusion analysis is carried out on the solid waste recycling related data and the multi-target constraint information, so that intelligent decision-making of a solid waste recycling scheme is realized. Therefore, the accuracy and objectivity of making a solid waste cyclic utilization scheme can be effectively improved, and scientific, efficient and intelligent decision support is provided for solid waste cyclic utilization of oversized urban groups.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of solid waste recycling, and specifically, to a multi-objective collaborative solid waste recycling intelligent decision-making method based on a hierarchical framework. Background Art

[0002] With the acceleration of urbanization and the in-depth development of industrialization, the amount of solid waste (SW) generated has increased dramatically, bringing tremendous pressure to the environment. Against the backdrop of increasingly severe global climate change and environmental problems, solid waste recycling has become an important way to achieve sustainable development, reduce environmental pollution, and improve resource utilization efficiency.

[0003] Solid waste treatment usually includes collection, classification, transportation, treatment and final disposal, involving the collaboration of multiple departments and fields. At present, due to the complex types and large composition uncertainty of solid waste in mega-city agglomerations, the decision-making process of solid waste recycling faces many challenges.

[0004] Traditional solid waste treatment decision-making methods mainly rely on expert experience. However, this approach is easily influenced by personal experience and preferences, resulting in uncertainty and subjectivity in decision-making results, making the formulation of recycling plans inaccurate and inefficient.

[0005] In recent years, with the development of big data and artificial intelligence technology, in-depth processing and intelligent decision-making of solid waste recycling related data have become possible. Therefore, a multi-objective collaborative solid waste recycling intelligent decision-making method based on a hierarchical framework is expected. Summary of the invention

[0006] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0007] In a first aspect, the present application provides a multi-objective collaborative solid waste recycling intelligent decision-making method based on a hierarchical framework, the method comprising:

[0008] Obtain environmental goals, economic goals, and social goals input by users;

[0009] Acquire the solid waste recycling related data input by the user, wherein the solid waste recycling related data includes the solid waste industry line, solid waste treatment characteristics, recycling path, and real scene park conditions;

[0010] Embedding and encoding the environmental goal, the economic goal and the social goal to obtain a multi-objective embedding constraint representation vector;

[0011] Performing global semantic association coding on the solid waste recycling related data to obtain a global semantic representation vector of the solid waste recycling related data;

[0012] Based on the eigenvalue granularity association fusion features of the global semantic representation vector of the solid waste recycling related data and the multi-objective embedded constraint representation vector, a decision result is generated, and the decision result is used to represent the type label of the solid waste recycling plan.

[0013] Optionally, the environmental goal, the economic goal and the social goal are embedded and encoded to obtain a multi-objective embedding constraint representation vector, including: using a target fully connected embedding matrix to embed the environmental goal, the economic goal and the social goal to obtain the multi-objective embedding constraint representation vector.

[0014] Optionally, the solid waste recycling related data is globally semantically associated encoded to obtain a global semantic representation vector of the solid waste recycling related data, including: segmenting the solid waste recycling related data into data items, and semantically encoding each data item in the solid waste recycling related data to obtain a set of semantic encoding feature vectors of solid waste recycling related data items; and context-associated encoding the set of semantic encoding feature vectors of the solid waste recycling related data items to obtain a global semantic representation vector of the solid waste recycling related data.

[0015] Optionally, the solid waste recycling related data are segmented into data items, and each data item in the solid waste recycling related data is semantically encoded to obtain a set of semantic encoding feature vectors of the solid waste recycling related data items, including: inputting each data item in the solid waste recycling related data into a semantic encoder based on the Bert model to obtain a set of semantic encoding feature vectors of the solid waste recycling related data items.

[0016] Optionally, the set of semantically encoded feature vectors of the solid waste recycling related data items are context-associated encoded to obtain a global semantic representation vector of the solid waste recycling related data, including: inputting the set of semantically encoded feature vectors of the solid waste recycling related data items into a context-associated encoder based on a Transformer structure to obtain a global semantic representation vector of the solid waste recycling related data.

[0017] Optionally, based on the eigenvalue granularity association fusion features of the global semantic representation vector of the solid waste recycling related data and the multi-objective embedding constraint representation vector, a decision result is generated, and the decision result is used to represent the type label of the solid waste recycling scheme, including: inputting the global semantic representation vector of the solid waste recycling related data and the multi-objective embedding constraint representation vector into a eigenvalue granularity association mask distinguishable attention fusion module to obtain a target-solid waste recycling related data association fusion representation vector; inputting the target-solid waste recycling related data association fusion representation vector into a classifier-based decision module to obtain the decision result, and the decision result is used to represent the type label of the solid waste recycling scheme.

[0018] Optionally, the global semantic representation vector of the solid waste recycling related data and the multi-objective embedding constraint representation vector are input into the eigenvalue granularity association mask distinguishable attention fusion module to obtain the target-solid waste recycling related data association fusion representation vector, including: calculating the global eigenvalue association matrix between the global semantic representation vector of the solid waste recycling related data and the multi-objective embedding constraint representation vector; inputting the global eigenvalue association matrix into a learnable gating function to obtain a correlation distinguishable weight matrix; using the correlation distinguishable weight matrix as a fusion mask matrix, respectively calculating the matrix product between the global semantic representation vector of the solid waste recycling related data, the multi-objective embedding constraint representation vector and the fusion mask matrix to obtain a distinguished and enhanced global semantic representation vector of the solid waste recycling related data and a distinguished and enhanced multi-objective embedding constraint representation vector; fusing the distinguished and enhanced global semantic representation vector of the solid waste recycling related data and the distinguished and enhanced multi-objective embedding constraint representation vector to obtain the target-solid waste recycling related data association fusion representation vector.

[0019] Optionally, the target-solid waste recycling related data associated fusion representation vector is input into a classifier-based decision module to obtain the decision result, and the decision result is used to represent the type label of the solid waste recycling scheme, including: using multiple fully connected layers of the classifier-based decision module to fully connect encode the target-solid waste recycling related data associated fusion representation vector to obtain an encoded classification feature vector; passing the encoded classification feature vector through the Softmax classification function of the classifier-based decision module to obtain the decision result.

[0020] The above technical solution is adopted, based on the solid waste recycling data such as solid waste industrial lines, solid waste treatment characteristics, recycling paths, and real-life park conditions, and considering the coordinated constraints of environmental goals, economic goals, and social goals, a multi-objective collaborative decision-making framework is constructed. At the same time, artificial intelligence technology based on deep learning is used to semantically understand the solid waste recycling data and multi-objective constraint information, and then the fine-grained feature correlation and enhanced fusion analysis of the two is performed to achieve intelligent decision-making of solid waste recycling solutions. In this way, the accuracy and objectivity of solid waste recycling solutions can be effectively improved, and scientific, efficient, and intelligent decision-making support can be provided for solid waste recycling in mega-city agglomerations.

[0021] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:

[0023] Figure 1 It is a schematic diagram of a regional solid waste recycling intelligent decision-making system with coordinated multi-objectives of technical feasibility, economic rationality and environmental friendliness according to an exemplary embodiment.

[0024] Figure 2 It is a flow chart of a multi-objective collaborative solid waste recycling intelligent decision-making method based on a hierarchical framework according to an exemplary embodiment.

[0025] Figure 3 It is a block diagram of a multi-objective collaborative solid waste recycling intelligent decision-making system based on a hierarchical framework according to an exemplary embodiment.

[0026] Figure 4 It is a block diagram of an electronic device according to an exemplary embodiment.

[0027] Figure 5 It is an application scenario diagram of a multi-objective collaborative solid waste recycling intelligent decision-making method based on a hierarchical framework according to an exemplary embodiment. DETAILED DESCRIPTION

[0028] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0029] It should be understood that the various steps described in the method implementation of the present application can be performed in different orders and / or performed in parallel. In addition, the method implementation may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0030] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0031] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0032] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0033] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0034] In view of the technical difficulties faced by megacities in complex real-life scenarios, such as complex types of solid waste, great uncertainty in composition, and difficulty in dynamic adaptation of recycling technologies, this application intends to focus on the management of the entire life cycle of solid waste recycling, and integrate a multi-source comprehensive data set of solid waste characteristics and a technical library of solid waste recycling paths based on data compilation and aggregation technologies; adopt data splicing and coupling technologies to build a database linkage mechanism, and form an information-based framework for solid waste recycling decision-making under the coordination of multiple objectives (technical feasibility, environmental friendliness, and economic rationality), laying the foundation for the construction of a smart decision-making platform for solid waste recycling, helping to make intelligent decisions on the resource utilization of solid waste, forming a new model of smart urban solid waste management and control, and promoting the intelligent, information-based, and digital transformation of solid waste recycling management.

[0035] This application intends to address the impact of multiple factors on the intra-park coordination and regional scheduling mechanism for solid waste recycling in complex real-world scenarios in urban agglomerations, and to achieve multi-objective collaborative decision-making of technical feasibility, environmental friendliness, and economic rationality. Comprehensively consider the different technical solutions and process flows of the park, combined with the characteristics of solid waste resources and environmental impacts in the urban agglomeration where it is located, consider the cost input, market demand, economic benefits and other aspects of the city where it is located, fully weigh the solid waste treatment efficiency, resource recovery rate, economic costs and benefits, and establish a feasible and effective regional scheduling mechanism. Based on intra-park scheduling, inter-park scheduling and other methods, a low-cost, low-pollution, high-efficiency, and strong economic solid waste recycling treatment model is achieved to ensure the maximization of solid waste recycling benefits and coordinated development among regions.

[0036] This application intends to use a multi-layer collaborative decision-making algorithm, with the environmental characteristics of the solid waste itself, the characteristics of the circulation path, and the characteristics of the region as input, and multi-objective collaborative benefits as output, to select the best solid waste recycling model, and make intelligent decisions and optimizations on the entire process of multi-source solid waste generation, classification, treatment, and reuse. In order to achieve efficient utilization of solid waste resources, effectively reduce environmental pollution, and promote the development of a circular economy. This application establishes a multi-source solid waste recycling decision-making framework through the development of new algorithm models, the fusion processing of multi-source data, the construction and optimization of decision-making models, and other steps, laying a theoretical foundation for subsequent multi-objective coordinated decision-making on solid waste recycling.

[0037] This application reveals the inherent laws and potential value of solid waste by deeply analyzing the metabolic network of solid waste in the region, that is, the entire process of solid waste generation, flow, transformation and consumption. At the same time, based on big data analysis and mining, it realizes intelligent matching and optimization between various links in the solid waste recycling industry chain, including the optimization of the whole process management of waste collection, classification, transportation, treatment, and reuse. The research and development of this application can effectively improve the utilization rate of solid waste resources, promote the development of regional circular economy and industrial upgrading, promote the implementation of regional solid waste recycling decisions, and help regional sustainable development.

[0038] The specific implementation of the present application is described in detail below with reference to the accompanying drawings.

[0039] At present, a lot of research has been conducted on multi-objective coordination theory and methods, but they are rarely used in the field of solid waste. In practical applications, each production line is designed for each solid waste resource, focusing on single-objective optimization, and there is insufficient research on multi-objective coordination. Solid waste recycling decision-making technology for environmental-economic-technical multi-objective coordination is of vital importance to achieving sustainable development and effective utilization of regional solid waste resources, and is a difficult problem that needs to be solved urgently.

[0040] In this application, we intend to build a multi-objective collaborative decision-making framework for realistic and complex scenarios, with AI decision-making models as the core, integrating methods such as regional solid waste industry metabolism and full life cycle analysis, and establishing a technically feasible, economically reasonable, and environmentally friendly multi-objective collaborative regional solid waste recycling intelligent decision-making system. Figure 1 The specific process is as follows:

[0041] Based on data such as solid waste industry lines, solid waste treatment characteristics, recycling paths, and real-world park conditions;

[0042] Incorporate a multi-level analysis model: the bottom layer is the common factors of the industry line, and the upper layer is the characteristic differentiation factors;

[0043] Output measures: hierarchical decision-making. Level 1 is industrial line optimization; Level 2 is collaboration within the park; Level 3 is regional scheduling;

[0044] Make decisions based on complex real-world scenarios, serve regional scheduling, and lay the foundation for subsequent platform construction.

[0045] Under this framework, module development was carried out to lay the foundation for subsequent integration into the platform. The main functions of the modules are set as follows: (1) Submit regional characteristic industry and function data: such as the largest solid waste output in the region, the output with the greatest market benefits, policy support, etc.; (2) Collect information on the characteristic technology chain of the park: Consider the best strengths and relative weaknesses of a single park, and estimate the regional scheduling of solid waste based on transportation scheduling costs; (3) Calculate the park coordination degree: the mutual coupling of technologies in different parks, as well as the intersection and intermediate connection of the technology process itself. (4) Evaluate the regional recycling benefits: energy flow, material flow, information flow, cost, benefit, and technical complexity.

[0046] This application will realize the scheduling strategy and regional scheduling function of technology-economy-environmental multi-objective coordination for complex scenarios.

[0047] This application is of great significance to promoting the innovation of multi-source solid waste recycling model. With AI+big data-enabled solid waste recycling hierarchical decision-making framework as the core, it helps to promote large-scale, cross-industry multi-source solid waste recycling model, which helps to form a replicable and popularizable engineering model, and promotes the recycling of solid waste with information technology. It has significant social, economic and ecological benefits.

[0048] Figure 2 is a flowchart of a multi-objective collaborative solid waste recycling intelligent decision-making method based on a hierarchical framework according to an exemplary embodiment. Figure 2 As shown, the method includes:

[0049] Step S101, obtaining environmental goals, economic goals and social goals input by the user;

[0050] Step S102: acquiring solid waste recycling related data input by the user, wherein the solid waste recycling related data includes solid waste industrial lines, solid waste treatment characteristics, recycling paths, and real-world park conditions;

[0051] Step S103, embedding and encoding the environmental goal, the economic goal and the social goal to obtain a multi-goal embedding constraint representation vector;

[0052] Step S104, performing global semantic association coding on the solid waste recycling related data to obtain a global semantic representation vector of the solid waste recycling related data;

[0053] Step S105, generating a decision result based on the eigenvalue granularity association fusion features of the global semantic representation vector of the solid waste recycling related data and the multi-objective embedded constraint representation vector, wherein the decision result is used to represent the type label of the solid waste recycling solution.

[0054] In response to the above technical problems, the technical concept of this application is: based on the solid waste recycling-related data such as solid waste industrial lines, solid waste treatment characteristics, recycling paths, and real-life scenario park conditions, consider the collaborative constraints of environmental goals, economic goals, and social goals, and build a multi-objective collaborative decision-making framework. At the same time, artificial intelligence technology based on deep learning is used to semantically understand the solid waste recycling-related data and multi-objective constraint information, and then through fine-grained feature correlation and enhanced fusion analysis of the two, intelligent decision-making of solid waste recycling plans can be achieved. In this way, the accuracy and objectivity of the formulation of solid waste recycling plans can be effectively improved, and scientific, efficient, and intelligent decision-making support can be provided for the recycling of solid waste in super-large urban agglomerations.

[0055] Based on this, in the technical solution of the present application, first, the environmental goals, economic goals and social goals input by the user, as well as the solid waste recycling related data input by the user are obtained, wherein the solid waste recycling related data include solid waste industry lines, solid waste treatment characteristics, recycling paths, and real-life scene park conditions. It should be understood that the decision-making process of solid waste recycling often involves multiple interrelated and potentially conflicting goals, and environmental goals (such as reducing pollution and protecting the ecological environment), economic goals (such as reducing costs and improving economic benefits) and social goals (such as increasing employment opportunities and improving public health) are the three most critical aspects. The degree of realization of environmental goals, economic goals and social goals depends to a large extent on the specific circumstances and data of solid waste recycling. For example, environmental goals may require understanding of pollutant emissions during solid waste treatment; economic goals may require evaluation of the cost-effectiveness of different treatment processes; and social goals may require consideration of the impact of solid waste treatment on surrounding communities. Therefore, in order to fully consider the interests and needs of all parties and achieve comprehensive and reasonable solid waste recycling decisions, in the technical solution of the present application, based on the solid waste recycling related data, a multi-objective collaborative decision-making scheme is constructed in combination with the collaborative constraints of environmental goals, economic goals and social goals.

[0056] Next, in order to effectively extract the content semantics of multi-objective information so as to integrate it into the decision-making process, this application uses a target fully connected embedding matrix to embed and encode the environmental goals, the economic goals and the social goals, so as to map the target information to the same semantic feature space, and capture the intrinsic correlation and potential constraint relationship between different goals, generate a multi-objective embedded constraint representation vector, and provide effective input for subsequent decision analysis.

[0057] In one embodiment of the present application, the environmental goal, the economic goal and the social goal are embedded and encoded to obtain a multi-objective embedded constraint representation vector, including: using a target fully connected embedding matrix to embed the environmental goal, the economic goal and the social goal to obtain the multi-objective embedded constraint representation vector.

[0058] Secondly, for the solid waste recycling related data, a deep learning model is also used to semantically encode it. Taking into account the content diversity and complexity of the solid waste recycling related data, in the technical solution of the present application, the solid waste recycling related data is first segmented into data items, and then a semantic encoder based on the Bert model is used to extract semantic features of the segmented solid waste industrial line, the solid waste treatment characteristics, the circulation path, and the real scene park situation and other multi-dimensional information, so as to utilize the two-way semantic understanding ability of the Bert model to capture the deep semantics in each data item, so as to obtain a set of semantic encoding feature vectors of solid waste recycling related data items, and provide comprehensive data support for solid waste recycling decision-making.

[0059] In one embodiment of the present application, the solid waste recycling related data is globally semantically associated encoded to obtain a global semantic representation vector of the solid waste recycling related data, including: segmenting the solid waste recycling related data into data items, and semantically encoding each data item in the solid waste recycling related data to obtain a set of semantic encoding feature vectors of the solid waste recycling related data items; and context-associated encoding the set of semantic encoding feature vectors of the solid waste recycling related data items to obtain a global semantic representation vector of the solid waste recycling related data.

[0060] Furthermore, in one embodiment of the present application, the solid waste recycling related data are segmented into data items, and each data item in the solid waste recycling related data is semantically encoded to obtain a set of semantic encoding feature vectors of the solid waste recycling related data items, including: inputting each data item in the solid waste recycling related data into a semantic encoder based on the Bert model to obtain a set of semantic encoding feature vectors of the solid waste recycling related data items.

[0061] Then, in order to comprehensively consider the mutual influence and correlation between each data item in the solid waste recycling related data and realize the global semantic understanding of the solid waste recycling related data, the present application further adopts a context association encoder based on the Transformer structure to perform global context semantic association encoding on the set of semantic encoding feature vectors of the solid waste recycling related data items. Based on the self-attention mechanism of the Transformer structure, the long-distance semantic dependencies and potential associations between each data item are captured to generate a global semantic association feature vector of the solid waste recycling related data, so as to grasp the relevant situation of solid waste recycling as a whole.

[0062] In one embodiment of the present application, context-associated encoding is performed on the set of semantically encoded feature vectors of the solid waste recycling related data items to obtain a global semantic representation vector of the solid waste recycling related data, including: inputting the set of semantically encoded feature vectors of the solid waste recycling related data items into a context-associated encoder based on a Transformer structure to obtain a global semantic representation vector of the solid waste recycling related data.

[0063] Then, the global semantic representation vector of the solid waste recycling related data and the multi-objective embedded constraint representation vector are further feature fused to comprehensively understand the impact and constraints of the target information on the solid waste recycling process, so as to make a more scientific and reasonable decision. At the same time, in the feature fusion process, in order to further strengthen the correlation between the target information and the solid waste recycling data, in the technical solution of the present application, an eigenvalue granularity association mask distinguishable attention fusion module is introduced to fuse the global semantic representation vector of the solid waste recycling related data and the multi-objective embedded constraint representation vector. Specifically, the eigenvalue granularity association mask distinguishable attention fusion module calculates the global eigenvalue association matrix between the global semantic representation vector of the solid waste recycling related data and the multi-objective embedded constraint representation vector to establish a global association between the solid waste recycling data and the multi-objective constraint information. Then, the gating function is used to perform feature learning on the global correlation information between the two, and the correlation distinguishable weight matrix of the eigenvalue granularity is adaptively generated. Furthermore, the global semantic representation vector of the solid waste recycling related data and the multi-objective embedded constraint representation vector are respectively subjected to feature differentiation and enhancement processing using the correlation distinguishable weight matrix to improve the pertinence and effectiveness of feature fusion, and ensure that key information can be highlighted and irrelevant or secondary information can be weakened in the decision-making process. Finally, the differentiated and enhanced feature vectors are integrated through a cascade operation to obtain the target-solid waste recycling related data associated fusion representation vector. In this way, it can be ensured that during the fusion process, the target information can effectively guide and constrain the key features of the solid waste recycling data, thereby improving the accuracy and adaptability of the decision.

[0064] In one embodiment of the present application, a decision result is generated based on the eigenvalue granularity association fusion features of the global semantic representation vector of the solid waste recycling related data and the multi-objective embedding constraint representation vector, and the decision result is used to represent the type label of the solid waste recycling scheme, including: inputting the global semantic representation vector of the solid waste recycling related data and the multi-objective embedding constraint representation vector into the eigenvalue granularity association mask distinguishable attention fusion module to obtain the target-solid waste recycling related data association fusion representation vector; inputting the target-solid waste recycling related data association fusion representation vector into the classifier-based decision module to obtain the decision result, and the decision result is used to represent the type label of the solid waste recycling scheme.

[0065] Furthermore, in one embodiment of the present application, the global semantic representation vector of the solid waste recycling related data and the multi-objective embedding constraint representation vector are input into the eigenvalue granularity association mask distinguishable attention fusion module to obtain the target-solid waste recycling related data association fusion representation vector, including: calculating the global eigenvalue association matrix between the global semantic representation vector of the solid waste recycling related data and the multi-objective embedding constraint representation vector; inputting the global eigenvalue association matrix into a learnable gating function to obtain a correlation distinguishable weight matrix; using the correlation distinguishable weight matrix as a fusion mask matrix, respectively calculating the matrix product between the global semantic representation vector of the solid waste recycling related data, the multi-objective embedding constraint representation vector and the fusion mask matrix to obtain a distinguished and enhanced global semantic representation vector of the solid waste recycling related data and a distinguished and enhanced multi-objective embedding constraint representation vector; fusing the distinguished and enhanced global semantic representation vector of the solid waste recycling related data and the distinguished and enhanced multi-objective embedding constraint representation vector to obtain the target-solid waste recycling related data association fusion representation vector.

[0066] Specifically, the solid waste recycling related data global semantic representation vector and the multi-objective embedding constraint representation vector are processed by the following feature interaction response fusion formula to obtain the target-solid waste recycling related data association fusion representation vector, wherein the feature interaction response fusion formula is:

[0067] S=(v1) 1 v2

[0068]

[0069] S w =S*W

[0070]

[0071] Wherein, v1 represents the global semantic representation vector of the solid waste recycling related data, v2 represents the multi-objective embedding constraint representation vector, (·) T represents the transpose of the eigenvector, S represents the global eigenvalue association matrix, exp(·) represents an exponential function operation with e as the base, W represents the correlation distinguishable weight matrix, * represents a matrix multiplication operation, represents the global semantic representation vector of the data related to distinguishing and strengthening solid waste recycling, represents the differentiated enhanced multi-objective embedded constraint representation vector, [·,·] represents the cascade operation, and x represents the target-solid waste recycling related data association fusion representation vector.

[0072] Next, the target-solid waste recycling related data association fusion representation vector is input into the decision module based on the classifier to obtain a decision result, and the decision result is used to represent the type label of the solid waste recycling scheme. That is, the decision module of the solid waste recycling scheme is constructed using the classifier model, and the target-solid waste recycling related data association fusion representation vector is subjected to high-dimensional feature learning and abstraction through the multi-layer nonlinear transformation of the classifier to mine its inherent decision-making mode and law, and map it to the predefined type label space of the solid waste recycling scheme, thereby generating corresponding decision results, such as biological treatment, pyrolysis, incineration, landfill and comprehensive treatment.

[0073] In one embodiment of the present application, the target-solid waste recycling related data association fusion representation vector is input into a classifier-based decision module to obtain the decision result, and the decision result is used to represent the type label of the solid waste recycling scheme, including: using multiple fully connected layers of the classifier-based decision module to fully connect the target-solid waste recycling related data association fusion representation vector to obtain an encoded classification feature vector; passing the encoded classification feature vector through the Softmax classification function of the classifier-based decision module to obtain the decision result.

[0074] In a preferred example, the present application takes into account that the global semantic representation vector of solid waste recycling related data and the multi-objective embedding constraint representation vector respectively express environmental goals, economic goals and social goals as well as text semantic encoding features of solid waste recycling related data. In this way, when the global semantic representation vector of solid waste recycling related data and the multi-objective embedding constraint representation vector are input into the feature value granularity association mask distinguishable attention fusion module, the obtained target-solid waste recycling related data association fusion representation vector will also cause distribution regression mode deviation due to the difference in association distinguishable attention weights caused by the difference in text semantic distribution, resulting in overflow of the decision result obtained by the target-solid waste recycling related data association fusion representation vector input into the decision module based on the classifier, affecting its accuracy.

[0075] Based on this, the target-solid waste recycling related data association fusion representation vector is input into the decision module based on the classifier to obtain the decision result, which specifically includes:

[0076] Passing the target-solid waste recycling related data association fusion representation vector through a probabilistic activation function to obtain a probabilistic target-solid waste recycling related data association fusion representation vector;

[0077] Determine the target-solid waste recycling related data association fusion representation vector input based on the classifier decision module to obtain n label probability values ​​corresponding to the type labels of n solid waste recycling schemes, and calculate the square root of the sum of the squares of the n label probability values ​​to obtain a type distribution probability value;

[0078] After performing point subtraction on the unit feature vector and the probabilistic target-solid waste recycling related data associated fusion representation vector, the power function with the type distribution probability value as the base is calculated, and further multiplied with the probabilistic target-solid waste recycling related data associated fusion representation vector to obtain the probabilistic target-solid waste recycling related data associated fusion convergence limiting feature vector;

[0079] Taking the absolute value of each eigenvalue of the probabilistic target-solid waste recycling related data association fusion representation vector as the base, calculating a power function with the inverse of the type distribution probability value as the exponent, and summing all eigenvalues ​​of the probabilistic target-solid waste recycling related data association fusion representation vector to obtain a target-solid waste recycling related data association fusion convergence bias eigenvalue;

[0080] The optimized target-solid waste recycling related data association fusion representation vector is obtained by multiplying the probabilistic target-solid waste recycling related data association fusion convergence limiting feature vector and the target-solid waste recycling related data association fusion convergence bias feature value and the weight as a hyperparameter; and

[0081] The optimized target-solid waste recycling related data associated fusion representation vector is input into the classifier-based decision module to obtain the decision result.

[0082] Wherein, let the probabilistic target-solid waste recycling related data association fusion representation vector be recorded as V, then the optimized target-solid waste recycling related data association fusion representation vector V′ is expressed as:

[0083]

[0084] Among them, the n label probability values ​​are represented as p j(j=1-n), the type distribution probability value p is expressed as:

[0085]

[0086] Wherein, V represents the probabilistic target-solid waste recycling related data association fusion representation vector obtained after the target-solid waste recycling related data association fusion representation vector is activated by the probabilistic function, p j (j=1-n) represents the probability value of each label corresponding to the type label of each solid waste recycling scheme, p represents the type distribution probability value, I represents the unit feature vector, v i represents the i-th eigenvalue of the probabilistic target-solid waste recycling related data association fusion representation vector, Indicates point addition, represents point subtraction, ⊙ represents point multiplication, α represents the weight as a hyperparameter, and V′ represents the optimized target-solid waste recycling related data associated fusion representation vector.

[0087] That is, for the target-solid waste recycling related data associated fusion representation vector, based on the convergence limit of the Cauchy-Hadamard form power series probability distribution, the feature set of the target-solid waste recycling related data associated fusion representation vector is represented by a formal power series based on the convergence probability, and a set convergence bounded bias based on each eigenvalue of the target-solid waste recycling related data associated fusion representation vector as a convergence radius representation is added, so as to avoid the invalid overflow of the classification result caused by the deviation of the distribution pattern of the target-solid waste recycling related data associated fusion representation vector in the regression process of the decision module based on the classifier due to the gradient propagation of the model parameters based on the convergence probability under a unified probability convergence limit standard, thereby improving the accuracy of the decision result obtained by the decision module based on the classifier.

[0088] In summary, the above scheme is adopted, based on the solid waste recycling-related data such as solid waste industrial lines, solid waste treatment characteristics, recycling paths, and real-life scenario park conditions, and considering the coordinated constraints of environmental goals, economic goals, and social goals, a multi-objective collaborative decision-making framework is constructed. At the same time, artificial intelligence technology based on deep learning is used to semantically understand the solid waste recycling-related data and multi-objective constraint information, and then through fine-grained feature correlation and enhanced fusion analysis of the two, intelligent decision-making of solid waste recycling schemes is achieved. In this way, the accuracy and objectivity of solid waste recycling schemes can be effectively improved, and scientific, efficient, and intelligent decision-making support can be provided for solid waste recycling in mega-city agglomerations.

[0089] Figure 3is a block diagram of a multi-objective collaborative solid waste recycling intelligent decision-making system based on a hierarchical framework according to an exemplary embodiment. Figure 3 As shown, the system 200 includes:

[0090] A target acquisition module 201 is used to acquire environmental targets, economic targets and social targets input by a user;

[0091] The solid waste recycling related data acquisition module 202 is used to acquire the solid waste recycling related data input by the user, wherein the solid waste recycling related data includes the solid waste industry line, solid waste treatment characteristics, recycling path, and real scene park conditions;

[0092] An embedding coding module 203, used for embedding the environmental goal, the economic goal and the social goal to obtain a multi-objective embedding constraint representation vector;

[0093] A global semantic association coding module 204 is used to perform global semantic association coding on the solid waste recycling related data to obtain a global semantic representation vector of the solid waste recycling related data;

[0094] The decision result generation module 205 is used to generate a decision result based on the eigenvalue granularity association fusion features of the global semantic representation vector of the solid waste recycling related data and the multi-objective embedded constraint representation vector, and the decision result is used to represent the type label of the solid waste recycling plan.

[0095] Reference below Figure 4 , which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present application. The terminal device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0096] like Figure 4As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0097] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0098] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present application are executed.

[0099] It should be noted that the computer-readable medium mentioned above in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0100] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0101] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0102] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0103] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0104] The modules involved in the embodiments described in this application can be implemented by software or hardware. The name of the module does not limit the module itself in some cases. For example, the test parameter acquisition module can also be described as a "module for acquiring device test parameters corresponding to the target device".

[0105] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0106] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0107] Figure 5 is an application scenario diagram of a multi-objective collaborative solid waste recycling intelligent decision-making method based on a hierarchical framework according to an exemplary embodiment. Figure 5 As shown, in this application scenario, first, the environmental goals, economic goals and social goals (for example, Figure 5 C1 shown in FIG); and obtaining solid waste recycling related data input by a user (for example, Figure 5 Then, the obtained environmental goals, economic goals, social goals, and solid waste recycling related data are input into a server that is deployed with a solid waste recycling intelligent decision-making algorithm based on multi-objective collaboration under a hierarchical framework (for example, Figure 5 In S) shown in the figure, the server is able to process the environmental goals, economic goals, social goals, and solid waste recycling related data based on the solid waste recycling intelligent decision-making algorithm under multi-objective collaboration under a hierarchical framework to generate a decision result, and the decision result is used to represent the type label of the solid waste recycling plan.

[0108] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

[0109] In addition, although each operation is described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or to be performed in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the application. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0110] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely exemplary forms of implementation. With respect to the apparatus in the above-mentioned embodiments, the specific manner in which each module performs the operation has been described in detail in the embodiments related to the method, and will not be described in detail here.

Claims

1. A multi-objective collaborative solid waste recycling intelligent decision-making method based on a hierarchical framework, It is characterized in that include: Obtain environmental goals, economic goals, and social goals input by users; Acquire the solid waste recycling related data input by the user, wherein the solid waste recycling related data includes the solid waste industry line, solid waste treatment characteristics, recycling path, and real scene park conditions; Embedding and encoding the environmental goal, the economic goal and the social goal to obtain a multi-objective embedding constraint representation vector; Performing global semantic association coding on the solid waste recycling related data to obtain a global semantic representation vector of the solid waste recycling related data; Based on the eigenvalue granularity association fusion features of the global semantic representation vector of the solid waste recycling related data and the multi-objective embedded constraint representation vector, a decision result is generated, and the decision result is used to represent the type label of the solid waste recycling plan.

2. According to the multi-objective collaborative solid waste recycling intelligent decision-making method based on a hierarchical framework according to claim 1, It is characterized in that Embedding and encoding the environmental goal, the economic goal, and the social goal to obtain a multi-objective embedding constraint representation vector includes: The environmental goal, the economic goal and the social goal are embedded and encoded using a target fully connected embedding matrix to obtain the multi-target embedding constraint representation vector.

3. The multi-objective collaborative solid waste recycling intelligent decision-making method based on a hierarchical framework according to claim 2, It is characterized in that Performing global semantic association coding on the solid waste recycling related data to obtain a global semantic representation vector of the solid waste recycling related data, including: Segmenting the solid waste recycling related data into data items, and semantically encoding each data item in the solid waste recycling related data to obtain a set of semantically encoded feature vectors of the solid waste recycling related data items; The set of semantically encoded feature vectors of the solid waste recycling related data items is context-associatedly encoded to obtain a global semantic representation vector of the solid waste recycling related data.

4. The multi-objective collaborative solid waste recycling intelligent decision-making method based on a hierarchical framework according to claim 3, It is characterized in that The solid waste recycling related data is segmented into data items, and each data item in the solid waste recycling related data is semantically encoded to obtain a set of semantic encoding feature vectors of the solid waste recycling related data items, including: Each data item in the solid waste recycling related data is input into a semantic encoder based on the Bert model to obtain a set of semantic encoding feature vectors of the solid waste recycling related data items.

5. The multi-objective collaborative solid waste recycling intelligent decision-making method based on a hierarchical framework according to claim 4, It is characterized in that The set of semantically encoded feature vectors of the solid waste recycling related data items is subjected to context association encoding to obtain a global semantic representation vector of the solid waste recycling related data, including: The set of semantically encoded feature vectors of the solid waste recycling related data items is input into a context-associated encoder based on a Transformer structure to obtain a global semantic representation vector of the solid waste recycling related data.

6. The multi-objective collaborative solid waste recycling intelligent decision-making method based on a hierarchical framework according to claim 5, It is characterized in that Based on the eigenvalue granularity association fusion features of the global semantic representation vector of the solid waste recycling related data and the multi-objective embedding constraint representation vector, a decision result is generated, and the decision result is used to represent the type label of the solid waste recycling scheme, including: Inputting the solid waste recycling related data global semantic representation vector and the multi-objective embedding constraint representation vector into a feature value granularity association mask distinguishable attention fusion module to obtain an objective-solid waste recycling related data association fusion representation vector; The target-solid waste recycling related data association fusion representation vector is input into a classifier-based decision module to obtain the decision result, and the decision result is used to represent the type label of the solid waste recycling solution.

7. The multi-objective collaborative solid waste recycling intelligent decision-making method based on a hierarchical framework according to claim 6, It is characterized in that Inputting the solid waste recycling related data global semantic representation vector and the multi-objective embedding constraint representation vector into a feature value granularity association mask distinguishable attention fusion module to obtain a target-solid waste recycling related data association fusion representation vector, including: Calculating a global eigenvalue association matrix between the global semantic representation vector of the solid waste recycling related data and the multi-objective embedding constraint representation vector; Inputting the global eigenvalue association matrix into a learnable gating function to obtain a correlation distinguishable weight matrix; Using the correlation distinguishable weight matrix as a fusion mask matrix, respectively calculating the matrix product between the global semantic representation vector of the solid waste recycling related data, the multi-objective embedding constraint representation vector and the fusion mask matrix to obtain a distinguished and enhanced solid waste recycling related data global semantic representation vector and a distinguished and enhanced multi-objective embedding constraint representation vector; The global semantic representation vector of the differentiated and enhanced solid waste recycling related data and the differentiated and enhanced multi-objective embedded constraint representation vector are fused to obtain the target-solid waste recycling related data associated fusion representation vector.

8. The multi-objective collaborative solid waste recycling intelligent decision-making method based on a hierarchical framework according to claim 7, It is characterized in that The target-solid waste recycling related data association fusion representation vector is input into a decision module based on a classifier to obtain the decision result, which is used to represent the type label of the solid waste recycling scheme, including: Using multiple fully connected layers of the classifier-based decision module to perform fully connected encoding on the target-solid waste recycling related data association fusion representation vector to obtain an encoded classification feature vector; The encoded classification feature vector is passed through the Softmax classification function of the classifier-based decision module to obtain the decision result.