Knowledge Graph-Based Decision-Making Method and System for Construction Waste Disposal

Abstract

This application discloses a knowledge graph-based decision-making method and system for construction waste treatment, relating to the field of construction waste technology. The disclosed method includes: obtaining current attribute information of the construction waste to be treated; obtaining a preset knowledge graph, the nodes of which include construction waste type nodes and construction waste attribute nodes, any type node in the preset knowledge graph being connected to at least two attribute nodes through edges, the relationship between edges in the preset knowledge graph representing the association between construction waste type and construction waste attributes; determining corresponding target type information in the preset knowledge graph based on the current attribute information; generating a target processing strategy based on the target type information, the target processing strategy including at least multiple target processing devices associated with the target type information and the processing order of each target processing device; and responding to the construction waste to be treated through the target processing strategy, effectively improving the decision-making accuracy of construction waste treatment.

Description

Technical Field

[0001] This application relates to the field of construction waste technology, and in particular to a construction waste treatment decision-making method and system based on knowledge graphs. Background Technology

[0002] Construction waste refers to the general term for slag, waste concrete, waste bricks and stones, and other waste generated during demolition, construction, decoration, and repair activities in the construction industry. With the acceleration of urbanization and the rapid development of the construction industry, the amount of construction waste generated is increasing year by year. Construction waste not only occupies a large amount of land resources but also causes serious environmental pollution. Therefore, how to efficiently identify and recycle construction waste has become one of the important issues in the field of environmental protection.

[0003] Currently, existing methods for handling construction waste mainly involve personnel identifying the type of construction waste and manually selecting appropriate processing equipment based on that type for recycling. However, this method relies on human experience for decision-making, is susceptible to subjective factors, and has low accuracy. Summary of the Invention

[0004] The main purpose of this application is to provide a knowledge graph-based decision-making method and system for construction waste disposal, aiming to solve the technical problems of existing technologies that rely on human experience for decision-making, are easily affected by subjective factors, and have low accuracy.

[0005] To achieve the above objectives, this application proposes a knowledge graph-based decision-making method for construction waste disposal, the method comprising:

[0006] Obtain the current attribute information of the construction waste to be processed;

[0007] Obtain a preset knowledge graph, wherein the nodes of the preset knowledge graph include type nodes of construction waste and attribute nodes of construction waste, and any type node in the preset knowledge graph is connected to at least two attribute nodes through an edge, and the relationship of the edges in the preset knowledge graph represents the association between the type of construction waste and the attributes of construction waste;

[0008] Query the preset knowledge graph to see if there is a target attribute node that matches the current attribute information;

[0009] If it exists, then obtain the type node associated with the target attribute node as the target type information corresponding to the current attribute information;

[0010] If it does not exist, then calculate the similarity between the current attribute information and each attribute node in the preset knowledge graph;

[0011] Select the type node corresponding to the attribute node with the maximum similarity as the target type information corresponding to the current attribute information;

[0012] A target processing strategy is generated based on the target type information. The target processing strategy includes at least a plurality of target processing devices associated with the target type information and the processing order of each target processing device.

[0013] The construction waste to be processed is responded to through a target processing strategy.

[0014] In one embodiment, before the step of obtaining the preset knowledge graph, the method further includes:

[0015] Obtain historical processing data for previously processed construction waste;

[0016] Extract the types and attributes of processed construction waste based on the historical processing data;

[0017] Determine the association between each type of processed construction waste and each attribute of processed construction waste, wherein any type of processed construction waste is associated with at least two attributes of processed construction waste in the association;

[0018] The processed construction waste type is used as a type node, and the processed construction waste attribute is used as an attribute node.

[0019] By connecting each type node with its corresponding attribute node through the aforementioned association relationships, a preset knowledge graph is generated.

[0020] In one embodiment, the step of generating a target processing strategy based on the target type information includes:

[0021] Obtain the first type of target processing device associated with the target type information;

[0022] Obtain the associated attribute information of the target type information in the preset knowledge graph;

[0023] In the first type of target processing device, obtain the second type of target processing device that matches the associated attribute information;

[0024] A target processing strategy is generated based on the second type of target processing device, and the target processing strategy includes at least each of the second type of target processing devices and the processing order of each of the second type of target processing devices.

[0025] In one embodiment, the step of generating a target processing strategy based on the second type of target processing device includes:

[0026] Randomly generate initial processing order information for each of the second type of target processing devices to obtain an initial processing strategy that includes each of the second type of target processing devices and the initial processing order of each of the second type of target processing devices;

[0027] The fitness between the initial treatment strategy and the construction waste to be treated is calculated using a preset fitness formula to obtain the initial fitness. The preset fitness formula is as follows:

[0028] ;

[0029] In the formula, For fitness, This is the weighting coefficient for resource recovery rate. For resource recycling rate, To handle cost weighting coefficients, To reduce processing costs, For environmental impact weighting coefficients, For environmental parameters;

[0030] The target processing strategy is generated based on the initial fitness and the initial processing order.

[0031] In one embodiment, the step of generating a target processing strategy based on the initial fitness and the initial processing order includes:

[0032] The order of any two target processing devices in the initial processing strategy is swapped to obtain the updated processing strategy.

[0033] Determine the post-update fitness value of the post-update processing strategy;

[0034] Determine whether the updated fitness value is greater than the initial fitness value;

[0035] If so, the updated post-processing strategy is used as the new initial processing strategy, and the step of swapping the order of any two target processing devices in the initial processing strategy to obtain the updated post-processing strategy is returned until the updated fitness value reaches the preset fitness threshold or the number of iterations reaches the preset number.

[0036] The post-update processing strategy that obtains the updated fitness value that reaches the preset fitness threshold or the number of iterations that reaches the preset number is taken as the target processing strategy.

[0037] In one embodiment, after the step of determining whether the updated fitness value is greater than the initial fitness value, the method further includes:

[0038] If not, the deviation between the updated fitness value and the initial fitness value is calculated to obtain the fitness difference.

[0039] The acceptance probability is calculated based on the fitness difference using a preset probability formula, which is:

[0040] ;

[0041] In the formula, To accept probability, For fitness difference, As the initial factor, The decreasing coefficient, This represents the current iteration number;

[0042] Generate random numbers;

[0043] Determine whether the random number is less than the acceptance probability;

[0044] When the random number is less than the acceptance probability, the updated post-processing strategy is used as the new initial processing strategy, and the step of swapping the order of any two target processing devices in the initial processing strategy to obtain the updated post-processing strategy is returned until the updated fitness value reaches the preset fitness threshold or the number of iterations reaches the preset number.

[0045] The post-update processing strategy that obtains the updated fitness value that reaches the preset fitness threshold or the number of iterations that reaches the preset number is taken as the target processing strategy.

[0046] Furthermore, to achieve the above objectives, this application also proposes a knowledge graph-based construction waste disposal decision-making system, which includes:

[0047] The data acquisition module is used to acquire the current attribute information of the construction waste to be processed;

[0048] The knowledge graph module is used to obtain a preset knowledge graph. The nodes of the preset knowledge graph include type nodes of construction waste and attribute nodes of construction waste. Any type node in the preset knowledge graph is connected to at least two attribute nodes through edges. The relationship of the edges in the preset knowledge graph represents the association between the type of construction waste and the attributes of construction waste.

[0049] The type identification module is used to query whether there is a target attribute node in the preset knowledge graph that is consistent with the current attribute information;

[0050] The type identification module is further configured to, if present, obtain the type node associated with the target attribute node as the target type information corresponding to the current attribute information;

[0051] The type recognition module is further configured to calculate the similarity between the current attribute information and each attribute node in the preset knowledge graph if the type does not exist.

[0052] The type recognition module is further configured to select the type node corresponding to the attribute node with the maximum similarity as the target type information corresponding to the current attribute information;

[0053] The strategy generation module is used to generate a target processing strategy based on the target type information. The target processing strategy includes at least a plurality of target processing devices associated with the target type information and the processing order of each target processing device.

[0054] The decision processing module is used to respond to the construction waste to be processed according to the target processing strategy.

[0055] Furthermore, to achieve the above objectives, this application also proposes a knowledge graph-based construction waste disposal decision-making device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the knowledge graph-based construction waste disposal decision-making method described above.

[0056] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the knowledge graph-based construction waste disposal decision-making method described above.

[0057] One or more technical solutions proposed in this application have at least the following technical effects:

[0058] This application obtains the current attribute information of the construction waste to be processed; obtains a preset knowledge graph, the nodes of which include construction waste type nodes and construction waste attribute nodes, and any type node in the preset knowledge graph is connected to at least two attribute nodes by an edge, the relationship of the edges in the preset knowledge graph representing the association between construction waste type and construction waste attribute; queries the preset knowledge graph to see if there is a target attribute node consistent with the current attribute information; if it exists, the type node associated with the target attribute node is obtained as the target type information corresponding to the current attribute information; if it does not exist, the similarity between the current attribute information and each attribute node in the preset knowledge graph is calculated; the type node corresponding to the attribute node with the maximum similarity is selected as the target type information corresponding to the current attribute information; a target processing strategy is generated based on the target type information, the target processing strategy including at least multiple target processing devices associated with the target type information and the processing order of each target processing device; and the construction waste to be processed is responded to through the target processing strategy. This application identifies the target type information of construction waste to be processed through a preset knowledge graph, and generates a target processing strategy based on the target type information, which includes at least multiple target processing devices associated with the target type information and the processing order of each target processing device, in response to the construction waste to be processed. Compared with the prior art that relies on human experience for decision-making, this application realizes automatic identification of the type of construction waste and automatic generation of target processing strategies based on a preset knowledge graph, avoiding interference from subjective factors and effectively improving the decision-making accuracy of construction waste. Attached Figure Description

[0059] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0060] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0061] Figure 1 This is a flowchart illustrating the first embodiment of the knowledge graph-based construction waste disposal decision-making method of this application;

[0062] Figure 2 This is a flowchart illustrating the second embodiment of the knowledge graph-based construction waste disposal decision-making method of this application;

[0063] Figure 3 This is a flowchart illustrating the third embodiment of the knowledge graph-based construction waste disposal decision-making method of this application;

[0064] Figure 4 This is a schematic diagram of the module structure of the knowledge graph-based construction waste disposal decision system of this application;

[0065] Figure 5 This is a schematic diagram of the knowledge graph-based construction waste treatment decision-making device of this application.

[0066] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0067] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0068] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0069] The main solution of this application embodiment is as follows: obtaining the current attribute information of the construction waste to be processed; obtaining a preset knowledge graph, the nodes of which include construction waste type nodes and construction waste attribute nodes, any type node in the preset knowledge graph is connected to at least two attribute nodes through edges, and the relationship of the edges in the preset knowledge graph represents the association between construction waste type and construction waste attribute; determining the corresponding target type information in the preset knowledge graph based on the current attribute information; generating a target processing strategy according to the target type information, the target processing strategy including at least multiple target processing devices associated with the target type information and the processing order of each target processing device; and responding to the construction waste to be processed through the target processing strategy.

[0070] Because existing technologies rely on human experience for decision-making, they are easily influenced by subjective factors and have low accuracy.

[0071] This application provides a solution that identifies the target type information of construction waste to be processed through a preset knowledge graph, and generates a target processing strategy based on the target type information, which includes at least multiple target processing devices associated with the target type information and the processing order of each target processing device, in response to the construction waste to be processed. Therefore, compared with the prior art that relies on human experience for decision-making, this application realizes automatic identification of the type of construction waste and automatic generation of target processing strategies based on a preset knowledge graph, avoiding interference from subjective factors and effectively improving the decision-making accuracy of construction waste.

[0072] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, such as a knowledge graph-based construction waste disposal decision-making device. The following description uses a knowledge graph-based construction waste disposal decision-making device (hereinafter referred to as the decision-making device) as an example to illustrate this embodiment and the subsequent embodiments.

[0073] Based on this, embodiments of this application provide a knowledge graph-based decision-making method for construction waste disposal, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the knowledge graph-based construction waste disposal decision-making method of this application.

[0074] In this embodiment, the knowledge graph-based construction waste disposal decision-making method includes steps S10 to S50:

[0075] Step S10: Obtain the current attribute information of the construction waste to be processed.

[0076] It should be noted that construction waste attribute information can be information that characterizes construction waste and describes its specific characteristics and properties. Construction waste attributes include physical attributes (such as the content ratio of particles of different sizes in construction waste, the mass of construction waste per unit volume, and the shape of construction waste), chemical attributes (such as the chemical elements contained in construction waste and their content ratio, the acidity or alkalinity of construction waste, and the content of organic matter in construction waste), and other attributes (such as the amount or volume of construction waste generated, the specific time of construction waste generation, and the impurity content in construction waste).

[0077] In practical implementation, the construction waste to be processed can be identified or scanned to collect its current attribute information. For example, for physical attributes, the particle size distribution of the construction waste can be measured using sieving or laser particle size analyzers, and the density of the construction waste can be measured using a densitometer; for chemical attributes, the chemical elements and their content in the construction waste can be determined using X-ray fluorescence spectroscopy or energy-dispersive X-ray spectroscopy, and the organic composition and thermal stability of the construction waste can be evaluated using thermogravimetric analysis; and the source (such as demolition projects, new construction projects, etc.) and quantity of the construction waste to be processed can be recorded as other attribute information.

[0078] Step S20: Obtain the preset knowledge graph.

[0079] The nodes of the preset knowledge graph include type nodes of construction waste and attribute nodes of construction waste. Any type node in the preset knowledge graph is connected to at least two attribute nodes through edges. The relationship between the edges in the preset knowledge graph represents the association between the type of construction waste and the attributes of construction waste.

[0080] It should be noted that construction waste types can be classified based on the source, composition, and characteristics of construction waste. Construction waste types include concrete, bricks, wood, metal, etc. One type of construction waste can be associated with multiple construction waste attributes; for example, concrete can be associated with construction waste attributes such as hardness, density, particle size distribution, and calcium content.

[0081] In its implementation, the aforementioned decision-making device can pre-receive various types of construction waste and their corresponding attributes from user input. In a graph database (such as Neo4j), the construction waste types are designated as type nodes, and the construction waste attributes as attribute nodes. Based on the association between construction waste types and attributes, each type node is connected to its associated attribute node via edges, forming a pre-defined knowledge graph. After obtaining the current attribute information of the construction waste to be processed, the decision-making device can invoke this pre-defined knowledge graph to perform subsequent operations.

[0082] Step S30: In the preset knowledge graph, query whether there is a target attribute node that is consistent with the current attribute information.

[0083] Step S40: If it exists, obtain the type node associated with the target attribute node as the target type information corresponding to the current attribute information.

[0084] In its implementation, the aforementioned decision-making device can traverse each attribute node in the preset knowledge graph to determine whether there is a target attribute node that matches the current attribute information. If a target attribute node that matches the current attribute information exists, the type node associated with the target attribute node is taken as the target type information corresponding to the current attribute information.

[0085] Step S50: If it does not exist, calculate the similarity between the current attribute information and each attribute node in the preset knowledge graph.

[0086] Step S60: Select the type node corresponding to the attribute node with the maximum similarity as the target type information corresponding to the current attribute information.

[0087] In a specific implementation, when the decision-making device detects that there is no target attribute node that matches the current attribute information, it can calculate the similarity between the current attribute information and each attribute node in the preset knowledge graph, and select the type node corresponding to the attribute node with the maximum similarity as the target type information corresponding to the current attribute information.

[0088] The calculation methods for the similarity between the current attribute information and each attribute node in the preset knowledge graph include, but are not limited to, cosine similarity, Euclidean distance, and Manhattan distance.

[0089] It should be understood that by querying the preset knowledge graph to see if there is a target attribute node that is consistent with the current attribute information; if it exists, the type node associated with the target attribute node is obtained as the target type information corresponding to the current attribute information; if it does not exist, the similarity between the current attribute information and each attribute node in the preset knowledge graph is calculated; the type node corresponding to the attribute node with the maximum similarity is selected as the target type information corresponding to the current attribute information, thereby achieving accurate identification of the type of construction waste to be processed, and thus improving the accuracy of construction waste processing decisions.

[0090] Step S70: Generate a target processing strategy based on the target type information.

[0091] The target processing strategy includes at least multiple target processing devices associated with the target type information and the processing order of each target processing device.

[0092] In practical implementation, corresponding processing equipment can be pre-configured for different types of construction waste, forming an equipment mapping table. Multiple suitable processing devices can be configured for each type of construction waste. These devices can be used for recycling and processing construction waste, and the processing order of each device in each combination can be pre-set. After determining the target type information, the decision-making device can query the equipment mapping table for each target processing device associated with the target type information and generate a target processing strategy based on the combination of target processing devices and their processing order. For example, when the construction waste to be processed contains concrete blocks and bricks, the target processing strategy may include a combination of a crusher, a screening machine, an air separator, and a magnetic separator, as well as the processing order of the devices in the combination. The processing order could be: first, the construction waste to be processed is transported to the crusher; then, after processing by the crusher, it is transported to the screening machine; after processing by the screening machine, it is transported to the air separator; and after processing by the air separator, it is transported to the magnetic separator.

[0093] Step S80: Respond to the construction waste to be processed through the target processing strategy.

[0094] In practical implementation, after generating the target processing strategy, the decision-making device can respond to the construction waste to be processed through the target processing strategy. It can control the operation of each target processing device in the target processing strategy according to the processing order of the devices in the target processing strategy to process the construction waste to be processed.

[0095] For example, taking a target processing strategy consisting of a crusher, screening machine, air separator, and magnetic separator as an example, the operating time of each processing device (crusher, screening machine, air separator, and magnetic separator) can be preset or manually adjusted by the user. The aforementioned decision-making device can communicate with the crusher, screening machine, air separator, and magnetic separator. When the crusher detects that it has received the construction waste to be processed, it can send a crusher-ready-to-operate message carrying the crusher's identification information to the decision-making device. The decision-making device responds to the crusher-ready-to-operate message by outputting control commands to control the crusher's operation. During operation, the crusher can crush large pieces of construction waste into smaller particles and transport the processed construction waste to the screening machine. When the screening machine detects that it has received construction waste, it can send a screening-ready-to-operate message carrying the screening machine's identification information to the decision-making device. The decision-making device responds to the screening-ready-to-operate message by outputting control commands to control the screening machine's operation. During operation, the screening machine can classify the crushed construction waste according to particle size, separating materials of different specifications, and then process the waste. Construction waste is transported to an air separator. When the air separator detects the construction waste, it sends a message indicating that it is operational to a decision-making device. The decision-making device responds to this message by outputting control commands to operate the air separator. During operation, the air separator separates lightweight materials such as plastics, paper, and wood chips from the construction waste, improving its purity. The processed construction waste is then transported to a magnetic separator. When the magnetic separator detects the construction waste, it sends a message indicating that it is operational to the decision-making device. The decision-making device responds to this message by outputting control commands to operate the magnetic separator. During operation, the magnetic separator separates metallic materials such as steel bars, nails, and wire from the construction waste, enabling metal recycling. After processing by a crusher, screening machine, air separator, and magnetic separator, the recycling of construction waste is complete.

[0096] This application obtains the current attribute information of the construction waste to be processed; obtains a preset knowledge graph, the nodes of which include construction waste type nodes and construction waste attribute nodes, and any type node in the preset knowledge graph is connected to at least two attribute nodes by an edge, the relationship of the edges in the preset knowledge graph representing the association between construction waste type and construction waste attributes; determines the corresponding target type information in the preset knowledge graph based on the current attribute information; generates a target processing strategy based on the target type information, the target processing strategy including at least multiple target processing devices associated with the target type information and the processing order of each target processing device; and responds to the construction waste to be processed through the target processing strategy. This application identifies the target type information of the construction waste to be processed through a preset knowledge graph, and generates a target processing strategy based on the target type information, including at least multiple target processing devices associated with the target type information and the processing order of each target processing device, to respond to the construction waste to be processed. Compared with the prior art that relies on human experience for decision-making, this application realizes automatic identification of construction waste type and automatic generation of target processing strategy based on preset knowledge graph, avoiding the interference of subjective factors and effectively improving the decision-making accuracy of construction waste.

[0097] Based on the first embodiment of this application, a second embodiment of this application is proposed. In the second embodiment, content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the knowledge graph-based construction waste disposal decision-making method of this application.

[0098] In this embodiment, steps S21 to S25 are included before step S20:

[0099] Step S21: Obtain historical processing data of processed construction waste.

[0100] It should be noted that the aforementioned historical processing data can be data generated from processed construction waste, including the type, properties, processing equipment, and processing sequence of the construction waste.

[0101] Step S22: Extract the types and attributes of processed construction waste based on the historical processing data.

[0102] In practice, the aforementioned decision-making equipment can identify and extract the types and attributes of processed construction waste from historical processing data.

[0103] Step S23: Determine the association between each type of processed construction waste and each attribute of processed construction waste, wherein any type of processed construction waste is associated with at least two attributes of processed construction waste.

[0104] In its implementation, the aforementioned decision-making equipment can standardize the types and attributes of processed construction waste, converting them into numerical forms of the same scale. It then calculates the Pearson correlation coefficient between each type and attribute, and associates processed construction waste types with absolute Pearson correlation coefficients greater than a set threshold with their corresponding attributes, thus determining the association relationships between each type and attribute. In this association, any processed construction waste type is associated with at least two of the aforementioned processed construction waste attributes.

[0105] Step S24: The processed construction waste type is used as a type node, and the processed construction waste attribute is used as an attribute node.

[0106] Step S25: Connect each type node and its corresponding attribute node with edges through the association relationship to generate a preset knowledge graph.

[0107] In a specific implementation, the aforementioned decision-making device can use the processed construction waste type as the construction waste type node and the processed construction waste attribute as the construction waste attribute node in a graph database (such as Neo4j). Based on the association between the processed construction waste type and the processed construction waste attribute, the device can connect each type node with its associated attribute node through edges to form a preset knowledge graph.

[0108] In addition, users can regularly update the preset knowledge graph as needed to ensure the accuracy and completeness of the information.

[0109] This embodiment extracts the types and attributes of processed construction waste from historical processing data; determines the association between each type and attribute of processed construction waste; uses the types of processed construction waste as type nodes and the attributes as attribute nodes; and connects each type node and its corresponding attribute node with edges through the association to generate a preset knowledge graph, thereby achieving accurate construction of the preset knowledge graph and improving the accuracy of construction waste treatment decisions.

[0110] Based on the first and second embodiments of this application, a third embodiment of this application is proposed. In this third embodiment, content that is the same as or similar to the first and second embodiments described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 , Figure 3 This is a flowchart illustrating the third embodiment of the knowledge graph-based construction waste disposal decision-making method of this application.

[0111] In this embodiment, step S70 includes steps S701 to S704:

[0112] Step S701: Obtain the first type of target processing device associated with the target type information.

[0113] In a specific implementation, the aforementioned decision-making device can obtain a device mapping table, determine all processing devices associated with the target type information from the device mapping table, and the processing devices associated with the target type information can be classified as first-type target processing devices.

[0114] Step S702: Obtain the associated attribute information of the target type information in the preset knowledge graph.

[0115] In practical implementation, in addition to associating the target type information with the current attribute information of the construction waste to be processed, the aforementioned preset knowledge graph also associates with other attribute information. The aforementioned decision-making device can use each attribute node associated with the target type information as associated attribute information.

[0116] Step S703: Obtain the second type of target processing device that matches the associated attribute information in the first type of target processing device.

[0117] In practical implementation, corresponding processing equipment can be pre-configured for different construction waste attributes, and the association between construction waste attributes and processing equipment can be updated in the equipment mapping table. The decision-making equipment can query the equipment mapping table for candidate processing equipment that matches each associated attribute information, and then select the processing equipment that matches the candidate processing equipment from the first type of target processing equipment as the second type of target processing equipment. This allows the second type of target processing equipment to be associated with both target type information and associated attribute information, ensuring that the second type of target processing equipment can process the construction waste to be processed.

[0118] Step S704: Generate a target processing strategy based on the second type of target processing device.

[0119] The target processing strategy includes at least each of the second type of target processing devices and the processing order of each of the second type of target processing devices.

[0120] In a specific implementation, the aforementioned decision-making device can feed back each of the second-type target processing devices to the user, who can then manually input the processing order of each second-type target processing device to generate a target processing strategy. If the user-inputted processing order is not received after a set waiting period, the processing order of each second-type target processing device can be randomly generated to obtain the target processing strategy.

[0121] In one feasible implementation, to improve the generation accuracy of the target processing strategy, step S704 includes steps S7041 to S7043:

[0122] Step S7041: Randomly generate initial processing order information for each of the second type of target processing devices to obtain an initial processing strategy that includes each of the second type of target processing devices and the initial processing order of each of the second type of target processing devices.

[0123] Step S7042: Calculate the fitness between the initial treatment strategy and the construction waste to be treated using a preset fitness formula to obtain the initial fitness.

[0124] The preset fitness formula is:

[0125] ;

[0126] In the formula, For fitness, This is the weighting coefficient for resource recovery rate. For resource recycling rate, To handle cost weighting coefficients, To reduce processing costs, For environmental impact weighting coefficients, These are environmental parameters.

[0127] It should be noted that the resource recovery rate mentioned above refers to the proportion of usable resources recovered from construction waste (i.e., the amount of construction waste recycled) to the total amount of construction waste produced, reflecting the efficiency and degree of resource recovery and utilization in construction waste. The weighting coefficient of the resource recovery rate can characterize the importance of the resource recovery rate in the fitness calculation. The higher the resource recovery rate, the better the treatment strategy is in terms of resource utilization of construction waste.

[0128] Understandably, the aforementioned treatment costs can include all related expenses incurred during the construction waste treatment process, including equipment operating costs, equipment maintenance costs, and labor costs, and can be determined by summing up all costs incurred during construction waste treatment. The aforementioned treatment cost weighting coefficient can characterize the importance of treatment costs in the fitness calculation. The lower the treatment cost, the better the economic efficiency of the treatment strategy.

[0129] It should be noted that the environmental parameters mentioned above can refer to the environmental impact of construction waste disposal activities, and carbon emissions can be used as an environmental parameter. The environmental impact weighting coefficients mentioned above can characterize the importance of environmental impact in the fitness calculation. The smaller the environmental impact, the lower the negative impact of the treatment strategy on the environment.

[0130] In its implementation, the aforementioned decision-making device can randomly generate initial processing sequence information for each type of second-class target processing device, obtaining an initial processing strategy that includes each type of second-class target processing device and its initial processing sequence. Then, it determines the resource recovery rate, processing cost, and environmental parameters related to the construction waste to be processed for each type of second-class target processing device within the initial processing strategy (i.e., the sequence of each type of second-class target processing device corresponding to the initial processing sequence information). The resource recovery rate can be determined by the proportion of construction waste recycled by each type of second-class target processing device in its corresponding processing sequence to the total amount of construction waste produced. The processing cost can be determined by the expenses required by each type of second-class target processing device in its corresponding processing sequence. The environmental parameters can be determined by predicting carbon emissions from factors such as energy consumption and operating efficiency of each type of second-class target processing device in its corresponding processing sequence.

[0131] Step S7043: Generate a target processing strategy using the initial fitness and the initial processing order.

[0132] In a specific implementation, the aforementioned decision-making device can determine whether the initial fitness is less than a preset fitness threshold. If it is not less than the preset fitness threshold, the initial treatment strategy is deemed to meet the requirements, meaning that the initial treatment strategy performs better in treating the construction waste to be treated, and thus the initial treatment strategy is taken as the target treatment strategy. If it is less than the preset fitness threshold, the initial treatment order can be adjusted to obtain a new treatment strategy. Then, the fitness value between the new treatment strategy and the construction waste to be treated is calculated. The above process is repeated to determine whether the fitness of the new treatment strategy is less than the preset fitness threshold, until a target treatment strategy with a fitness value not less than the preset fitness threshold is obtained.

[0133] In one feasible implementation, step S7043 includes steps S70431 to S70435:

[0134] Step S70431: Swap the order of any two target processing devices in the initial processing strategy to obtain the updated processing strategy.

[0135] In practical implementation, the aforementioned decision-making device can swap the order of any two target processing devices in the initial processing strategy to obtain an updated processing strategy. For example, if the initial processing strategy includes a crusher, screening machine, air separator, and magnetic separator arranged in the initial processing order, swapping the positions of the crusher and screening machine results in an updated processing strategy that includes a screening machine, crusher, air separator, and magnetic separator arranged in the processing order.

[0136] Step S70432: Determine the post-update fitness value of the post-update processing strategy.

[0137] In practical implementation, the decision-making device can determine the resource recovery rate, processing cost, and environmental parameters related to the updated post-processing strategy and the construction waste to be processed, and calculate the updated post-fitness value of the updated post-processing strategy based on the preset fitness formula.

[0138] Step S70433: Determine whether the updated fitness value is greater than the initial fitness value.

[0139] In a specific implementation, the decision-making device can compare the updated fitness value with the initial fitness value to determine whether the updated fitness value is greater than the initial fitness value, that is, to determine whether the updated processing strategy is better than the initial processing strategy.

[0140] If so, in step S70434, the updated post-processing strategy is used as the new initial processing strategy, and the process of swapping the order of any two target processing devices in the initial processing strategy to obtain the updated post-processing strategy is repeated until the updated fitness value reaches the preset fitness threshold or the number of iterations reaches the preset number.

[0141] It should be noted that the aforementioned preset fitness threshold can be the optimal fitness value set in advance through testing. The aforementioned preset number of iterations can be a pre-set threshold to avoid excessive iterations.

[0142] Step S70435: Obtain the post-update processing strategy when the updated fitness value reaches the preset fitness threshold or the number of iterations reaches the preset number as the target processing strategy.

[0143] In a specific implementation, the decision-making device can, when the updated fitness value is greater than the initial fitness value, use the updated processing strategy as the new initial processing strategy, and return to the step of swapping the order of any two target processing devices in the initial processing strategy to obtain the updated processing strategy. That is, the above operation is repeated for iteration until the updated fitness value reaches a preset fitness threshold or the number of iterations reaches a preset number. That is, in each iteration, the processing order of devices with fitness values ​​greater than the previous fitness value can be selected. When the updated fitness value reaches the preset fitness threshold or the number of iterations reaches the preset number, the iteration is determined to be complete, and the updated processing strategy at this time is selected as the target processing strategy, thereby determining the optimal target processing strategy.

[0144] Step S70433 is followed by steps S704331 to S704336:

[0145] Step S704331: If not, calculate the deviation between the updated fitness value and the initial fitness value to obtain the fitness difference.

[0146] It should be noted that, based on the above description, during the iteration process, there is an operation that uses the updated post-processing strategy as the new initial processing strategy. Therefore, the above initial fitness value can be the fitness value of the initial processing strategy in the first iteration, or it can be the fitness value of the updated post-processing strategy in the previous iteration.

[0147] In specific implementation, when the updated fitness value of the decision-making device is not greater than the initial fitness value, that is, when the updated fitness value of the currently obtained updated processing strategy is not greater than the fitness value obtained last time, the deviation between the updated fitness value and the initial fitness value (i.e., the absolute value of the difference) can be calculated to obtain the fitness difference.

[0148] Step S704332: If the acceptance probability is calculated based on the fitness difference using a preset probability formula.

[0149] The preset probability formula is:

[0150] ;

[0151] In the formula, To accept probability, For fitness difference, As the initial factor, The decreasing coefficient, This represents the current iteration number.

[0152] In a specific implementation, the decision-making device can call the preset probability formula and substitute the fitness difference to obtain the acceptance probability of the updated fitness value during the current iteration, i.e., when the updated fitness value is not greater than the initial fitness value.

[0153] Step S704333: If a random number is generated.

[0154] Step S704334: Determine whether the random number is less than the acceptance probability.

[0155] Step S704335: If the random number is less than the acceptance probability, the updated post-processing strategy is used as the new initial processing strategy, and the process of swapping the order of any two target processing devices in the initial processing strategy is repeated until the updated fitness value reaches the preset fitness threshold or the number of iterations reaches the preset number.

[0156] Step S704336: If the updated fitness value reaches the preset fitness threshold or the number of iterations reaches the preset number, the updated processing strategy is taken as the target processing strategy.

[0157] In a specific implementation, after determining the acceptance probability of the updated fitness value, the decision-making device can randomly generate any random number and determine whether the random number is less than the acceptance probability. If the random number is less than the acceptance probability, the updated processing strategy is used as the new initial processing strategy. The process of exchanging the order of any two target processing devices in the initial processing strategy to obtain the updated processing strategy is repeated iteratively. When the updated fitness value reaches a preset fitness threshold or the number of iterations reaches a preset number, the iteration is considered complete, and the updated processing strategy at this time is selected as the target processing strategy, thereby determining the optimal target processing strategy.

[0158] It should be understood that when the updated fitness value is not greater than the initial fitness value, directly ignoring the processing strategy corresponding to the updated fitness value (i.e., only using the processing strategy where the updated fitness value is not greater than the initial fitness value) can easily lead to getting trapped in a local optimum. By comparing the random number and the acceptance probability, accepting a worse solution with a certain probability allows for the acceptance of some worse processing strategies, thereby avoiding getting trapped in a local optimum, increasing the probability of finding the globally optimal processing strategy, increasing the diversity of processing strategies participating in the iteration, and thus improving the accuracy of determining the target processing strategy.

[0159] In this embodiment, when generating a target processing strategy based on the second type of target processing equipment, the initial processing order information of each second type of target processing equipment is randomly generated to obtain an initial processing strategy including each second type of target processing equipment and its initial processing order. The fitness between the initial processing strategy and the construction waste to be processed is calculated using a preset fitness formula to obtain the initial fitness. The order of any two target processing equipment in the initial processing strategy is swapped to obtain an updated processing strategy. The updated fitness value of the updated processing strategy is determined. It is then determined whether the updated fitness value is greater than the initial fitness value. If so, the updated processing strategy is used as the new initial processing strategy, and the process of swapping the order of any two target processing equipment in the initial processing strategy to obtain the updated processing strategy is repeated until the updated fitness value reaches a preset fitness threshold or the number of iterations reaches a preset threshold. The process involves setting the number of iterations; if not, calculating the deviation between the updated fitness value and the initial fitness value to obtain the fitness difference; calculating the acceptance probability based on the fitness difference using a preset probability formula; generating a random number; determining whether the random number is less than the acceptance probability; if the random number is less than the acceptance probability, using the updated processing strategy as the new initial processing strategy, and returning to the step of swapping the order of any two target processing devices in the initial processing strategy to obtain the updated processing strategy, until the updated fitness value reaches a preset fitness threshold or the number of iterations reaches a preset number; obtaining the updated processing strategy whose updated fitness value reaches the preset fitness threshold or the number of iterations reaches the preset number of iterations as the target processing strategy, thereby realizing the determination of the target processing strategy by iterating the processing strategy based on the fitness value, effectively improving the determination accuracy of the target processing strategy, and thus improving the accuracy of construction waste processing.

[0160] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the knowledge graph-based construction waste disposal decision-making method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0161] This application also provides a knowledge graph-based construction waste disposal decision-making system; please refer to [reference needed]. Figure 4 , Figure 4 This is a schematic diagram of the module structure of the knowledge graph-based construction waste disposal decision system of this application.

[0162] The knowledge graph-based construction waste disposal decision system includes:

[0163] The data acquisition module 10 is used to acquire the current attribute information of the construction waste to be processed.

[0164] The knowledge graph module 20 is used to obtain a preset knowledge graph. The nodes of the preset knowledge graph include type nodes of construction waste and attribute nodes of construction waste. Any type node in the preset knowledge graph is connected to at least two attribute nodes through edges. The relationship of the edges in the preset knowledge graph represents the association between the type of construction waste and the attribute of construction waste.

[0165] The type identification module 30 is used to query whether there is a target attribute node in the preset knowledge graph that is consistent with the current attribute information.

[0166] The type identification module is further configured to, if present, obtain the type node associated with the target attribute node as the target type information corresponding to the current attribute information.

[0167] The type identification module is further configured to calculate the similarity between the current attribute information and each attribute node in the preset knowledge graph if the type does not exist.

[0168] The type recognition module is further configured to select the type node corresponding to the attribute node with the highest similarity as the target type information corresponding to the current attribute information.

[0169] The strategy generation module 40 is used to generate a target processing strategy based on the target type information. The target processing strategy includes at least a plurality of target processing devices associated with the target type information and the processing order of each target processing device.

[0170] The decision processing module 50 is used to respond to the construction waste to be processed through a target processing strategy.

[0171] The knowledge graph-based construction waste disposal decision-making system provided in this application, employing the knowledge graph-based construction waste disposal decision-making method described in the above embodiments, can solve the technical problems of existing technologies that rely on human experience for decision-making, are easily influenced by subjective factors, and have low accuracy. Compared with the prior art, the beneficial effects of the knowledge graph-based construction waste disposal decision-making system provided in this application are the same as those of the knowledge graph-based construction waste disposal decision-making method provided in the above embodiments, and other technical features of the knowledge graph-based construction waste disposal decision-making system are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0172] This application provides a knowledge graph-based construction waste disposal decision-making device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the knowledge graph-based construction waste disposal decision-making method in the first embodiment described above.

[0173] The following is for reference. Figure 5 , Figure 5 This is a schematic diagram of the knowledge graph-based construction waste disposal decision-making device of this application. The knowledge graph-based construction waste disposal decision-making device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), vehicle terminals (such as vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The knowledge graph-based construction waste management decision-making device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0174] like Figure 5As shown, a knowledge graph-based construction waste management decision-making device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the knowledge graph-based construction waste management decision-making device to communicate wirelessly or wiredly with other devices to exchange data. While the figure shows a knowledge graph-based construction waste management decision-making device with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0175] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0176] The knowledge graph-based construction waste disposal decision-making device provided in this application, employing the knowledge graph-based construction waste disposal decision-making method described in the above embodiments, can solve the technical problems of existing technologies that rely on human experience for decision-making, are easily influenced by subjective factors, and have low accuracy. Compared with the prior art, the beneficial effects of the knowledge graph-based construction waste disposal decision-making device provided in this application are the same as those of the knowledge graph-based construction waste disposal decision-making method provided in the above embodiments, and other technical features in this knowledge graph-based construction waste disposal decision-making device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0177] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0178] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0179] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the knowledge graph-based construction waste disposal decision-making method in the above embodiments.

[0180] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0181] The aforementioned computer-readable storage medium may be included in a knowledge graph-based construction waste treatment decision-making device; or it may exist independently and not be assembled into the knowledge graph-based construction waste treatment decision-making device.

[0182] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by a knowledge graph-based construction waste processing decision-making device, the knowledge graph-based construction waste processing decision-making device: acquires the current attribute information of the construction waste to be processed; acquires a preset knowledge graph, the nodes of which include construction waste type nodes and construction waste attribute nodes, any type node in the preset knowledge graph being connected to at least two attribute nodes via edges, the relationship between edges in the preset knowledge graph representing the association between construction waste type and construction waste attribute; determines the corresponding target type information in the preset knowledge graph based on the current attribute information; generates a target processing strategy based on the target type information, the target processing strategy including at least multiple target processing devices associated with the target type information and the processing order of each target processing device; and responds to the construction waste to be processed through the target processing strategy.

[0183] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0184] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0185] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0186] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described knowledge graph-based construction waste disposal decision-making method. This addresses the technical problem of existing technologies relying on human experience for decision-making, being susceptible to subjective interference, and having low accuracy. Compared to existing technologies, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the knowledge graph-based construction waste disposal decision-making method provided in the above embodiments, and will not be elaborated upon here.

[0187] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A knowledge graph-based decision-making method for construction waste disposal, characterized in that, The method includes: Obtain the current attribute information of the construction waste to be processed; Obtain a preset knowledge graph, wherein the nodes of the preset knowledge graph include type nodes of construction waste and attribute nodes of construction waste, and any type node in the preset knowledge graph is connected to at least two attribute nodes through an edge, and the relationship of the edges in the preset knowledge graph represents the association between the type of construction waste and the attributes of construction waste; Query the preset knowledge graph to see if there is a target attribute node that matches the current attribute information; If it exists, then obtain the type node associated with the target attribute node as the target type information corresponding to the current attribute information; If it does not exist, then calculate the similarity between the current attribute information and each attribute node in the preset knowledge graph; Select the type node corresponding to the attribute node with the maximum similarity as the target type information corresponding to the current attribute information; A target processing strategy is generated based on the target type information. The target processing strategy includes at least a plurality of target processing devices associated with the target type information and the processing order of each target processing device. The construction waste to be processed is responded to through a target processing strategy; Prior to the step of obtaining the preset knowledge graph, the method further includes: Obtain historical processing data for previously processed construction waste; Extract the types and attributes of processed construction waste based on the historical processing data; Determine the association between each type of processed construction waste and each attribute of processed construction waste, wherein any type of processed construction waste is associated with at least two attributes of processed construction waste in the association; The processed construction waste type is used as a type node, and the processed construction waste attribute is used as an attribute node. By connecting each type node with its corresponding attribute node through the aforementioned association relationships, a preset knowledge graph is generated. The step of generating a target processing strategy based on the target type information includes: Obtain the first type of target processing device associated with the target type information; Obtain the associated attribute information of the target type information in the preset knowledge graph; In the first type of target processing device, obtain the second type of target processing device that matches the associated attribute information; A target processing strategy is generated based on the second type of target processing device, and the target processing strategy includes at least each of the second type of target processing devices and the processing order of each of the second type of target processing devices; The step of generating a target processing strategy based on the second type of target processing device includes: Randomly generate initial processing order information for each of the second type of target processing devices to obtain an initial processing strategy that includes each of the second type of target processing devices and the initial processing order of each of the second type of target processing devices; The fitness between the initial treatment strategy and the construction waste to be treated is calculated using a preset fitness formula to obtain the initial fitness. The preset fitness formula is as follows: In the formula, For fitness, This is the weighting coefficient for resource recovery rate. For resource recycling rate, To handle cost weighting coefficients, To reduce processing costs, For environmental impact weighting coefficients, For environmental parameters; The target processing strategy is generated based on the initial fitness and the initial processing order.

2. The construction waste disposal decision-making method based on knowledge graphs as described in claim 1, characterized in that, The step of generating the target processing strategy based on the initial fitness and the initial processing order includes: The order of any two target processing devices in the initial processing strategy is swapped to obtain the updated processing strategy. Determine the post-update fitness value of the post-update processing strategy; Determine whether the updated fitness value is greater than the initial fitness value; If so, the updated post-processing strategy is used as the new initial processing strategy, and the step of swapping the order of any two target processing devices in the initial processing strategy to obtain the updated post-processing strategy is returned until the updated fitness value reaches the preset fitness threshold or the number of iterations reaches the preset number. The post-update processing strategy that obtains the updated fitness value that reaches the preset fitness threshold or the number of iterations that reaches the preset number is taken as the target processing strategy.

3. The knowledge graph-based construction waste disposal decision-making method as described in claim 2, characterized in that, After the step of determining whether the updated fitness value is greater than the initial fitness value, the method further includes: If not, the deviation between the updated fitness value and the initial fitness value is calculated to obtain the fitness difference. The acceptance probability is calculated based on the fitness difference using a preset probability formula, which is: In the formula, To accept probability, For fitness difference, As the initial factor, The decreasing coefficient, This represents the current iteration number; Generate random numbers; Determine whether the random number is less than the acceptance probability; When the random number is less than the acceptance probability, the updated post-processing strategy is used as the new initial processing strategy, and the step of swapping the order of any two target processing devices in the initial processing strategy to obtain the updated post-processing strategy is returned until the updated fitness value reaches the preset fitness threshold or the number of iterations reaches the preset number. The post-update processing strategy that obtains the updated fitness value that reaches the preset fitness threshold or the number of iterations that reaches the preset number is taken as the target processing strategy.

4. A knowledge graph-based decision-making system for construction waste disposal, characterized in that, The knowledge graph-based construction waste management decision system, as described in claim 1, comprises: The data acquisition module is used to acquire the current attribute information of the construction waste to be processed; The knowledge graph module is used to obtain a preset knowledge graph. The nodes of the preset knowledge graph include type nodes of construction waste and attribute nodes of construction waste. Any type node in the preset knowledge graph is connected to at least two attribute nodes through edges. The relationship of the edges in the preset knowledge graph represents the association between the type of construction waste and the attributes of construction waste. The type identification module is used to query whether there is a target attribute node in the preset knowledge graph that is consistent with the current attribute information; The type identification module is further configured to, if present, obtain the type node associated with the target attribute node as the target type information corresponding to the current attribute information; The type recognition module is further configured to calculate the similarity between the current attribute information and each attribute node in the preset knowledge graph if the type does not exist. The type recognition module is further configured to select the type node corresponding to the attribute node with the maximum similarity as the target type information corresponding to the current attribute information; The strategy generation module is used to generate a target processing strategy based on the target type information. The target processing strategy includes at least a plurality of target processing devices associated with the target type information and the processing order of each target processing device. The decision processing module is used to respond to the construction waste to be processed according to the target processing strategy.

5. A construction waste treatment decision-making device based on knowledge graphs, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the knowledge graph-based construction waste disposal decision-making method as described in any one of claims 1 to 3.

6. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the knowledge graph-based construction waste disposal decision-making method as described in any one of claims 1 to 3.

Images