Garbage disposal knowledge management method and system combined with knowledge graph

Abstract

The invention provides a garbage disposal knowledge management method and system combined with a knowledge graph, and the method comprises the steps: firstly obtaining garbage disposal knowledge units and scene response features thereof, building an association set, and covering the knowledge units of garbage classification, disposal process, recovery flow and the like, and application trigger conditions and effect feedback features in different scenes; then, constructing a knowledge unit dynamic association path, and matching a trigger condition and an association factor to form association logic capable of changing along with a scene; and then scene adaptability evolution processing is carried out on the association path set, and the path is adjusted in combination with actual scene characteristic parameters. And generating an application scheme containing a knowledge unit calling sequence, a scene triggering rule and application connection logic based on the evolved path. Finally, the scheme is subjected to closed-loop adaptation with an actual scene, the scheme is adjusted according to feedback, a scene adaptation execution instruction is generated and used for guiding actual garbage disposal operation, and effective management and efficient application of garbage disposal knowledge are achieved.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence, and more specifically, to a waste management knowledge management method and system that incorporates knowledge graphs. Background Technology

[0002] In the field of waste management, with the increasing volume and complexity of waste generation, effective management of waste management knowledge has become crucial for improving efficiency and quality. Currently, traditional waste management knowledge management relies primarily on manual experience summaries and paper-based records, which have several drawbacks. Firstly, knowledge acquisition and organization are inefficient, making it difficult to quickly respond to the needs of different waste management scenarios. Secondly, the connections between different pieces of knowledge are not clearly presented, hindering the ability to flexibly adjust knowledge application plans according to changing scenarios. Furthermore, traditional methods lack real-time feedback and dynamic optimization mechanisms for the effectiveness of knowledge application, making it difficult for waste management knowledge to evolve and improve with changes in actual scenarios. Therefore, there is an urgent need for a management method that can efficiently integrate waste management knowledge, dynamically adapt to different scenario needs, and achieve iterative knowledge optimization. Summary of the Invention

[0003] In view of the aforementioned problems, and in conjunction with the first aspect of the present invention, embodiments of the present invention provide a waste management knowledge management method incorporating knowledge graphs, the method comprising: Obtain waste treatment knowledge units and corresponding scenario response features for each knowledge unit, establish the association between knowledge units and scenario response features, and obtain a knowledge unit scenario response feature association set. The waste treatment knowledge units include waste classification knowledge units, waste treatment process knowledge units, and waste recycling process knowledge units. The scenario response features include the application trigger conditions and application effect feedback features of the knowledge units in different waste treatment scenarios. Based on the association set of scene response features of knowledge units, a dynamic association path of knowledge units is constructed. By matching the triggering conditions and association factors in the scene response features of each knowledge unit, an association logic that can be adjusted with scene changes is formed, resulting in a set of dynamic association paths of knowledge units. The dynamic association path set of knowledge units is subjected to scenario-adaptive evolution processing. The logical nodes and connection relationships of the association paths are adjusted in combination with the characteristic parameters of the actual waste disposal scenario to obtain the evolved dynamic association path set of knowledge units. A waste management knowledge application solution is generated based on the dynamically associated path set of the evolved knowledge units. The solution includes the calling order of knowledge units, scenario triggering rules, and application connection logic. The waste treatment knowledge application scheme is adapted in a closed loop to the actual waste treatment scenario. The order of knowledge unit calls and triggering rules in the scheme are adjusted according to the scenario application feedback, and waste treatment knowledge scenario adaptation execution instructions are generated. These waste treatment knowledge scenario adaptation execution instructions are used to guide the knowledge application operation in the actual waste treatment scenario.

[0004] In another aspect, embodiments of the present invention also provide a waste management knowledge management system that incorporates a knowledge graph, including a processor and a machine-readable storage medium connected to the processor. The machine-readable storage medium is used to store programs, instructions, or code, and the processor is used to execute the programs, instructions, or code in the machine-readable storage medium to implement the above-described method.

[0005] Based on the above, this embodiment of the invention integrates knowledge from various aspects such as waste classification, treatment processes, and recycling procedures by constructing an association set of knowledge units and scenario response features, and clarifies the application triggering conditions and effect feedback characteristics of each knowledge unit in different scenarios. The dynamic association path constructed based on this association set can flexibly adjust the association logic according to changes in the scenario, making knowledge application more targeted and adaptable. Scenario-adaptive evolution processing is performed on the dynamic association path, and the path is optimized in combination with actual scenario feature parameters, further improving the accuracy of knowledge application. The generated waste treatment knowledge application scheme specifies in detail the knowledge unit calling order, scenario triggering rules, and application connection logic, ensuring the orderliness and coherence of knowledge application. Through closed-loop adaptation with actual scenarios, and continuous adjustment of the scheme based on feedback, the final generated scenario-adaptive execution instructions can effectively guide actual waste treatment operations, effectively improving waste treatment efficiency and quality, and realizing intelligent and dynamic management of waste treatment knowledge. Attached Figure Description

[0006] Figure 1 This is a schematic diagram of the execution flow of the waste management knowledge management method combining knowledge graphs provided in an embodiment of the present invention.

[0007] Figure 2 This is a schematic diagram of exemplary hardware and software components of a waste management knowledge management system that incorporates a knowledge graph, as provided in an embodiment of the present invention. Detailed Implementation

[0008] The present invention will now be described in detail with reference to the accompanying drawings. Figure 1 This is a flowchart illustrating a waste management knowledge method incorporating knowledge graphs according to an embodiment of the present invention. The following is a detailed description of this waste management knowledge method incorporating knowledge graphs.

[0009] Step S110: Obtain waste treatment knowledge units and corresponding scenario response features for each knowledge unit, establish the association between knowledge units and scenario response features, and obtain a knowledge unit scenario response feature association set. The waste treatment knowledge units include waste classification knowledge units, waste treatment process knowledge units, and waste recycling process knowledge units. The scenario response features include the application triggering conditions and application effect feedback features of the knowledge units in different waste treatment scenarios.

[0010] In this embodiment, the first step is to acquire waste management knowledge units and their corresponding scenario response features. Waste management knowledge units specifically include three categories: waste sorting knowledge units, waste management process knowledge units, and waste recycling process knowledge units. Waste sorting knowledge units cover the classification standards, identification features, and classification operation specifications for recyclables, kitchen waste, hazardous waste, and other waste. Waste management process knowledge units include the technical parameters, operation procedures, and applicable conditions of different processes such as landfill, incineration, and composting. Waste recycling process knowledge units involve information such as recycling site setup, transportation route planning, and resource reuse channels. Scenario response features refer to the triggering conditions for each knowledge unit to be applied in different waste management scenarios and the feedback on its application. For example, the triggering condition for a waste sorting knowledge unit in a community waste disposal point scenario might be the identification result of the type of waste disposed of, and the feedback on its application effect might be data such as sorting accuracy and resident cooperation. After acquiring these knowledge units and scenario response features, a one-to-one correspondence is established to bind each knowledge unit to its corresponding scenario response feature, thereby obtaining a knowledge unit scenario response feature association set.

[0011] Step S120: Construct dynamic association paths for knowledge units based on the association set of scene response features of knowledge units. By matching the triggering conditions and association factors in the scene response features of each knowledge unit, an association logic that can be adjusted according to scene changes is formed, resulting in a set of dynamic association paths for knowledge units.

[0012] In this embodiment, after obtaining the knowledge unit scenario response feature association set, the next step is to construct the dynamic association path of the knowledge units. First, the application triggering conditions of each knowledge unit scenario response feature in the knowledge unit scenario response feature association set are analyzed. Scenario parameters and feature thresholds in the triggering conditions are extracted to form a scenario triggering condition parameter set. The scenario parameters include the processing scale characteristics, processing environment characteristics, and processing target characteristics of the waste disposal scenario. Then, the association triggering factors of each knowledge unit are extracted. These association triggering factors include logical dependency factors between knowledge units, application order association factors, and scenario requirement matching factors. Finally, the scenario parameters in the scenario triggering condition parameter set are matched with the association triggering factors of the knowledge units to determine the association triggering factor combinations corresponding to the scenario parameters, forming scenario-factor matching combinations. An initial association path for knowledge units is constructed by matching and combining scenarios and factors. The initial association path includes the connection order and connection logic of the knowledge units, and the connection logic is determined by the association relationship in the matching and combination of scenarios and factors. Historical scenario change parameters of the waste disposal scenario are obtained, and the connection logic of the initial association path is adjusted based on the historical scenario change parameters so that the association path can be dynamically adjusted with the scenario change parameters. The node information and connection logic change rules of the adjusted association path are recorded to form a set of dynamic association paths for knowledge units. The node information includes the knowledge unit identifier and the corresponding scenario response feature identifier, and the connection logic change rules include the correspondence between the scenario change parameters and the path adjustment method.

[0013] Step S121: Analyze the application triggering conditions of each knowledge unit scene response feature in the knowledge unit scene response feature association set, extract the scene parameters and feature thresholds in the triggering conditions, and form a scene triggering condition parameter set. The scene parameters include the processing scale features, processing environment features, and processing target features of the waste disposal scene.

[0014] In this embodiment, when constructing the dynamic association path, the application triggering conditions are first parsed. For each knowledge unit in the knowledge unit scenario response feature association set, the application triggering conditions in its scenario response features are analyzed in detail. For example, the application triggering condition for a certain waste incineration process knowledge unit might be "when the processing scale reaches A tons of waste per hour, the processing environment temperature is between B and C degrees Celsius, and the processing target is a waste reduction rate of D%, the application of this knowledge unit is triggered." Scenario parameters are extracted from this, such as processing scale characteristics (A tons of waste per hour), processing environment characteristics (temperature between B and C degrees Celsius), processing target characteristics (reduction rate of D%), and feature thresholds, such as specific values ​​like A, B, C, and D. These scenario parameters and feature thresholds for all knowledge units are collected to form a scenario triggering condition parameter set.

[0015] Step S122: Extract the association triggering factors of each knowledge unit, wherein the association triggering factors include logical dependency factors between knowledge units, application order association factors, and scenario requirement matching factors.

[0016] In this embodiment, after extracting the set of scenario triggering condition parameters, the next step is to extract associated triggering factors. Logical dependency factors refer to the logical dependencies between knowledge units. For example, the application of the waste incineration process knowledge unit depends on the accurate classification of waste by the waste sorting knowledge unit. Only when the proportion of combustible components in the waste meets the requirements can the application of the incineration process knowledge unit be triggered. Application order factors refer to the sequential relationship between knowledge units in the actual application process. For example, in the waste treatment process, waste sorting is usually performed first, followed by the selection of waste treatment processes, and finally the waste recycling process. Therefore, the application order of the waste sorting knowledge unit precedes that of the waste treatment process knowledge unit and the waste recycling process knowledge unit. Scenario demand matching factors refer to the degree of matching between the application scenario of the knowledge unit and the actual waste treatment scenario. For example, in densely populated urban community scenarios, the efficient waste incineration process knowledge unit is more suitable, while in rural areas, the composting process knowledge unit may be more suitable. These factors are extracted from each knowledge unit.

[0017] Step S1221: Extract attribute information from the waste management knowledge unit. The attribute information includes the application prerequisites, application output results, and application associated objects of the knowledge unit.

[0018] In this embodiment, the step of extracting associated triggering factors first involves extracting attribute information. Application prerequisites refer to the conditions that a knowledge unit must meet to be applied; for example, the application prerequisite for a waste incineration process knowledge unit is that the calorific value of the waste reaches a certain standard. Application output results refer to the results produced after the knowledge unit is applied, such as ash and exhaust gas. Application associated objects refer to other objects related to the application of the knowledge unit; for example, the application associated objects of the waste incineration process knowledge unit include the waste incinerator and operators. This attribute information is then extracted from each knowledge unit.

[0019] Step S1222: Determine the logical dependency factors between knowledge units based on the application prerequisites and application outputs. If the application output of the first knowledge unit is consistent with the application prerequisites of the second knowledge unit, then the correspondence is taken as the logical dependency factor between the first knowledge unit and the second knowledge unit, and the description of the prerequisites and the description of the outputs corresponding to the logical dependency factor are recorded.

[0020] In this embodiment, after extracting the attribute information, the next step is to determine the logical dependency factor. For any two knowledge units, the application output of the first knowledge unit and the application prerequisites of the second knowledge unit are compared. If the application output of the first knowledge unit is consistent with the application prerequisites of the second knowledge unit, it indicates that the application of the second knowledge unit depends on the application output of the first knowledge unit. Therefore, this correspondence is used as the logical dependency factor between the first and second knowledge units, and the corresponding prerequisite description and output description are recorded.

[0021] Step S1223: Determine the application order correlation factor based on the application sequence of knowledge units in the actual waste treatment process. Collect application time series data of each knowledge unit in the historical waste treatment process, count the application frequency of different knowledge units in the same process, and take the order of application of knowledge units that exceeds the preset frequency standard as the application order correlation factor of the corresponding knowledge units.

[0022] In this embodiment, after determining the logical dependency factor, a sub-step to determine the application order association factor is executed. By collecting application time-series data of each knowledge unit in the historical waste disposal process, the application order of the knowledge units in different processes is recorded. Then, the application frequency of different knowledge units in the same process is counted, that is, the number of times a certain knowledge unit is applied before another knowledge unit. The order in which the frequency exceeds a preset frequency standard is determined as the application order association factor of the corresponding knowledge unit.

[0023] Step S12231: Extract process samples containing knowledge unit application records from historical waste disposal process data. The process samples contain application timestamps and application order records of all knowledge units in the historical waste disposal process.

[0024] In this embodiment, the first step in determining the application sequence association factor is to extract process samples. Process data containing knowledge unit application records is filtered from the historical waste disposal process database; this data constitutes the process samples. The process samples record the specific timestamps of each knowledge unit applied in the historical waste disposal processes, as well as the order in which they were applied.

[0025] Step S12232: Decompose the application order of knowledge units in the process sample to obtain knowledge unit application order pairs. Each knowledge unit application order pair contains two knowledge units and the order in which the two knowledge units are applied in the sample.

[0026] In this embodiment, after extracting the process sample, the application order of the knowledge units in the sample is broken down. Two consecutively applied knowledge units in the process sample are grouped into a knowledge unit application order pair, which includes the two knowledge units and their application order in the sample. For example, if knowledge unit A is applied before knowledge unit B, the resulting order pair is (A, B).

[0027] Step S12233: Count the total number of times knowledge unit application order pairs appear in all process samples to obtain the frequency statistics of knowledge unit application order pairs.

[0028] In this embodiment, after the knowledge unit application sequence pairs are decomposed, the sequence pairs in all process samples are statistically analyzed, the total number of times each knowledge unit application sequence pair appears is calculated, and the frequency statistics result is obtained.

[0029] Step S12234: Set the frequency standard. The frequency standard is determined based on the total number of process samples and the preset ratio. The frequency standard is the total number of process samples multiplied by the preset ratio coefficient.

[0030] In this embodiment, after obtaining the frequency statistics results, a frequency standard is set. The frequency standard is calculated by multiplying the total number of process samples by a preset proportional coefficient. The proportional coefficient is determined based on actual conditions and experience, for example, it can be set to 0.6.

[0031] Step S12235: Compare the frequency statistics of knowledge unit application order pairs with the frequency standard. If the number of occurrences of a knowledge unit application order pair exceeds the frequency standard, then the knowledge unit application order pair is used as the application order association factor of the corresponding knowledge unit.

[0032] In this embodiment, after setting the frequency standard, the frequency statistics of each knowledge unit application order pair are compared with the frequency standard. If the number of occurrences of a certain knowledge unit application order pair exceeds the frequency standard, it indicates that the order pair appears frequently in the historical waste disposal process and has a certain regularity. Therefore, it is used as the application order correlation factor of the corresponding knowledge unit.

[0033] Step S12236: Record the application time series data corresponding to the application sequence correlation factor, and at the same time record the number of occurrences, the total number of process samples, and the preset proportion coefficient in the frequency statistics results to form the supporting explanatory data for the application sequence correlation factor.

[0034] In this embodiment, after determining the application sequence association factor, the application time series data corresponding to the factor, as well as the number of occurrences, the total number of process samples, and the preset proportion coefficient in the frequency statistics results are recorded. These data serve as supporting explanatory data for the application sequence association factor.

[0035] Step S1224: Determine the scenario requirement matching factor based on the application scenario requirement description and scenario response characteristics of the knowledge unit, extract the scenario parameter requirements from the scenario response characteristics of the knowledge unit, and use the correspondence between the application scenario requirement description and scenario parameter requirements of the knowledge unit as the scenario requirement matching factor.

[0036] In this embodiment, after determining the application sequence association factor, the sub-step of determining the scenario requirement matching factor is executed. The application scenario requirement description of the knowledge unit refers to the scenario type and conditions to which the knowledge unit is applicable, and the scenario parameter requirements in the scenario response characteristics refer to the specific parameter conditions under which the knowledge unit is applied in different scenarios. The mapping between the application scenario requirement description of the knowledge unit and the scenario parameter requirements is the scenario requirement matching factor.

[0037] Step S1225: Add factor identifiers and corresponding knowledge unit identifiers to the logical dependency factors, application order association factors, and scenario requirement matching factors respectively to form a set of knowledge unit association triggering factors. Each factor in the set corresponds to a unique combination of factor identifier and knowledge unit identifier.

[0038] In this embodiment, after determining all associated triggering factors, a unique factor identifier and a corresponding knowledge unit identifier are added to each factor. The factor identifier is used to distinguish different associated triggering factors, and the knowledge unit identifier is used to indicate the knowledge unit to which the factor belongs. The factors with added identifiers are combined together to form a set of knowledge unit associated triggering factors.

[0039] Step S123: Match the scene parameters in the scene trigger condition parameter set with the associated trigger factors of the knowledge unit to determine the associated trigger factor combination corresponding to the scene parameter, and form a scene and factor matching combination.

[0040] In this embodiment, after extracting the associated triggering factors, a matching operation between the scene parameters and the associated triggering factors is performed. Each scene parameter in the set of scene triggering condition parameters, such as processing scale, processing environment, and processing target, is compared one by one with the associated triggering factors of each knowledge unit. For example, when the processing scale in the scene parameter is A tons of waste per hour, the logical dependency factor, application order association factor, and scene requirement matching factor that match the processing scale are searched among the associated triggering factors. If the logical dependency factor of a certain waste incineration process knowledge unit requires a processing scale of more than A tons of waste per hour, the application order association factor requires it to be after the waste sorting knowledge unit, and the scene requirement matching factor requires the processing environment temperature to be between B and C degrees Celsius, and the current scene parameter has a processing scale of A tons of waste per hour, a processing environment temperature between B and C degrees Celsius, and the waste sorting knowledge unit has already been triggered, then these associated triggering factors are combined to form the scene and factor matching combination corresponding to the scene parameter.

[0041] Step S124: Construct the initial association path of knowledge units based on the combination of scenario and factor matching. The initial association path includes the connection order and connection logic of knowledge units. The connection logic is determined by the association relationship in the combination of scenario and factor matching.

[0042] In this embodiment, after obtaining the scene and factor matching combination, the initial association path of knowledge units is then constructed. Based on the association relationships in the scene and factor matching combination, the connection order and connection logic between knowledge units are determined. For example, based on the scene and factor matching combination, the waste sorting knowledge unit is connected to the waste incineration process knowledge unit, and the waste incineration process knowledge unit is connected to the waste recycling process knowledge unit. Regarding the connection logic, when the application triggering condition of the waste sorting knowledge unit is met, and the scene parameters match the associated triggering factors, the application of the waste incineration process knowledge unit is triggered. Similarly, when the application triggering condition of the waste incineration process knowledge unit is met, the application of the waste recycling process knowledge unit is triggered. These knowledge units are connected according to the determined connection order and connection logic to form the initial association path.

[0043] Step S125: Obtain historical scene change parameters of the waste disposal scenario, and adjust the connection logic of the initial associated path based on the historical scene change parameters so that the associated path can be dynamically adjusted with the scene change parameters.

[0044] In this embodiment, after constructing the initial association path, the step of adjusting the connection logic of the initial association path is executed. First, historical scenario change parameters of the waste treatment scenario are obtained. These parameters include changes in the processing scale over a past period, fluctuation data of the processing environment, and adjustment records of the processing target. For example, historical scenario change parameters show that during a certain period, the processing scale increased from processing A tons of waste per hour to processing B tons of waste per hour, and the processing environment temperature decreased from B degrees Celsius to A degrees Celsius. Based on these historical scenario change parameters, it is analyzed whether the connection logic of the initial association path can adapt to the changes in the scenario. If the application trigger condition of the waste incineration process knowledge unit in the initial association path is a processing scale of A tons of waste per hour or more, and the historical scenario change parameters show a processing scale reaching B tons of waste per hour, then the connection logic needs to be adjusted to raise the processing scale threshold in the trigger condition to B tons of waste per hour to adapt to the scenario change. Through this adjustment, the connection logic of the initial association path can be dynamically adjusted according to the scenario change parameters.

[0045] Step S126: Record the node information and connection logic change rules of the adjusted associated paths to form a dynamic associated path set of knowledge units. The node information includes the knowledge unit identifier and the corresponding scene response feature identifier. The connection logic change rules include the correspondence between scene change parameters and path adjustment methods.

[0046] In this embodiment, after adjusting the initial association path connection logic, the steps of recording node information and connection logic change rules are executed. Node information includes the identifier of each knowledge unit and its corresponding scenario response feature identifier. For example, the identifier of the waste sorting knowledge unit is K1, and its corresponding scenario response feature identifier is S1; the identifier of the waste incineration process knowledge unit is K2, and its corresponding scenario response feature identifier is S2, etc. Connection logic change rules refer to the correspondence between scenario change parameters and path adjustment methods. For example, when the processing scale increases to B tons of waste per hour, the trigger condition threshold of the waste incineration process knowledge unit is adjusted; when the processing environment temperature drops to A degrees Celsius, it is switched to another more suitable waste treatment process knowledge unit, etc. These node information and connection logic change rules are recorded to form a dynamic association path set for knowledge units.

[0047] Step S130: Perform scenario-adaptive evolution processing on the dynamic association path set of knowledge units, and adjust the logical nodes and connection relationships of the association paths in combination with the characteristic parameters of the actual waste disposal scenario to obtain the evolved dynamic association path set of knowledge units.

[0048] In this embodiment, after obtaining the dynamic association path set of knowledge units, the next step is to perform scenario adaptation evolution processing. First, real-time scenario feature data of the actual waste disposal scenario is collected. This real-time scenario feature data includes the processing object attributes, processing equipment status, processing progress, and environmental influencing factors of the current scenario. The node structure and connection logic of each association path in the dynamic association path set of knowledge units are analyzed, and scenario adaptation parameters for each path are extracted. These scenario adaptation parameters include the applicable processing object attribute range, processing equipment status requirements, and processing progress nodes. The real-time scenario feature data is compared with the scenario adaptation parameters of each association path, and the differences between the two are extracted. Based on these differences, the adaptability of each association path to the current real-time scenario is calculated. The adaptability calculation process includes weight allocation and quantification of the difference degree of the differences. The weight allocation is determined based on the degree of influence of the differences on the knowledge application effect. Based on the adaptability calculation results, association paths whose adaptability meets the scenario requirements are selected as paths to be evolved, while association paths whose adaptability does not meet the scenario requirements are... The process involves: extracting the core differences between the path and real-time scene feature data; adjusting the node composition and connection logic of the path to be evolved based on these core differences, including adding knowledge unit nodes, deleting redundant knowledge unit nodes, and modifying the connection order between nodes; referencing the application triggering conditions and association factors in the knowledge unit scene response feature association set during the adjustment process; applying the adjusted association path to a simulated waste disposal scenario and collecting effect feedback data during the simulated application process, including knowledge unit call accuracy, application process coherence, and the degree to which scene requirements are met; verifying the scene adaptability of the adjusted association path based on the effect feedback data; if the effect feedback data meets the preset application effect standards, the adjusted association path is used as the evolved association path; if it does not meet the standards, the core differences are re-identified and the adjustment steps are repeated until the effect feedback data meets the application effect standards, ultimately forming the evolved knowledge unit dynamic association path set.

[0049] Step S131: Collect real-time scene feature data of the actual waste treatment scenario. The real-time scene feature data includes the attributes of the processing object, the status of the processing equipment, the progress of the processing process, and environmental influencing factors in the current scenario.

[0050] In this embodiment, the first step in performing scene adaptation evolution processing is to collect real-time scene feature data. The attributes of the processed object include information such as the type, composition ratio, humidity, and weight of the waste; the status of the processing equipment covers the operating parameters, fault conditions, and maintenance records of the waste processing equipment; the processing progress refers to the current stage in the waste processing process, such as the waste sorting stage, the waste processing technology implementation stage, and the waste recycling stage; environmental impact factors include the impact of noise, exhaust gas, and wastewater generated during waste processing on the surrounding environment. This data is acquired in real time by installing sensors and data acquisition devices in the actual waste processing scenario.

[0051] Step S132: Analyze the node composition and connection logic of each associated path in the dynamic association path set of knowledge units, and extract the scenario adaptation parameters of each path. The scenario adaptation parameters include the range of processing object attributes applicable to the path, the status requirements of the processing device, and the progress nodes of the processing process.

[0052] In this embodiment, after collecting real-time scene feature data, the next step is to parse the associated paths and extract scene adaptation parameters. For each associated path in the dynamic associated path set of knowledge units, its node composition is analyzed, that is, which knowledge unit nodes are included in the associated path, and the connection logic between the nodes, that is, the triggering conditions and sequential relationships between knowledge units. Then, scene adaptation parameters are extracted. For example, the applicable processing object attribute range for a certain associated path may be that the proportion of recyclables in the waste is within a certain range and the humidity is below a certain threshold; the processing equipment status requirements may be that the operating temperature of the waste incinerator is within a certain range and the equipment is fault-free; the processing process progress node may be that the associated path is applicable to the waste treatment process implementation stage.

[0053] Step S133: Compare the real-time scene feature data with the scene adaptation parameters of each associated path, extract the difference features between the two, and calculate the adaptation degree between each associated path and the current real-time scene based on the difference features. The adaptation degree calculation process includes the weight allocation of difference features and the quantification of the degree of difference. The weight allocation is determined according to the degree of influence of difference features on the knowledge application effect.

[0054] In this embodiment, after extracting the scene adaptation parameters, a comparison operation is performed between the real-time scene feature data and the scene adaptation parameters. The processing object attributes, processing equipment status, processing progress, and environmental influencing factors in the collected real-time scene feature data are compared with the scene adaptation parameters of each associated path to identify the features that differ from each other. For example, the humidity of the waste in the real-time scene may be higher than the humidity threshold in the scene adaptation parameters of a certain associated path, or the operating temperature of the waste incinerator in the processing equipment may be lower than the requirement in the scene adaptation parameters. Then, the differing features are weighted according to their impact on the knowledge application effect; the greater the impact, the higher the weight. For example, the difference in the processing equipment status has a greater impact on the knowledge application effect, so its weight is higher; while the difference in environmental influencing factors has a relatively smaller impact, so its weight is lower. Finally, the degree of difference of the differing features is quantified, and the magnitude of the difference is expressed numerically. Finally, the fit degree of each associated path with the current real-time scene is calculated based on the weight and the difference degree quantification value. The fit degree can be calculated by multiplying the weight of each difference feature with the difference degree quantification value and summing the results, and then converting them into a fit degree value according to certain rules.

[0055] Step S1331: Classify the difference features to obtain the difference features of processing scale, processing environment, and processing target.

[0056] In this embodiment, before assigning weights and quantifying the degree of difference, the difference features are first classified. Processing scale difference features refer to the difference between the waste processing scale in the real-time scenario and the processing scale range in the related path scenario adaptation parameters; processing environment difference features refer to the difference between the processing environment in the real-time scenario and the processing environment requirements in the related path scenario adaptation parameters; processing target difference features refer to the difference between the processing target in the real-time scenario and the processing target in the related path scenario adaptation parameters. The difference features are classified into these three categories.

[0057] Step S1332: Collect data on the impact of different differential features on the knowledge application effect in historical waste disposal scenarios. The impact data includes the magnitude of change in the knowledge application effect when the differential features exist.

[0058] In this embodiment, after classifying the differential characteristics, the next step is to collect impact data. By reviewing historical records of waste disposal scenarios, the changes in the effectiveness of knowledge application under different differential characteristics are collected. For example, when there are differential characteristics in the processing scale, the extent to which waste disposal efficiency decreases in the effectiveness of knowledge application; when there are differential characteristics in the processing environment, the extent to which the degree of environmental impact increases in the effectiveness of knowledge application, etc.

[0059] Step S1333: Determine the weight of each differential feature based on the impact data. For differential features with significant changes in the impact data, the weight allocation is increased accordingly. The weight values ​​of each differential feature are adjusted to the preset weight range through normalization processing.

[0060] In this embodiment, after collecting the impact data, the weights of each difference feature are determined based on the magnitude of change in the knowledge application effect of the difference features in the impact data. Difference features with significant changes indicate that they have a greater impact on the knowledge application effect, and therefore are assigned higher weights; difference features with smaller changes have lower weights. Then, the determined weights are normalized to adjust the weight values ​​to a preset weight range, such as between 0 and 1, to ensure the rationality and comparability of the weights.

[0061] Step S1334: Quantify the degree of difference of the difference features, and convert the difference content of the difference features into quantitative values. If the difference feature is the difference in processing scale, the ratio of the difference between the processing scale of the real-time scene and the processing scale of the associated path to the processing scale of the associated path is used as the quantitative value of the degree of difference. If the difference feature is the difference in processing environment, the quantitative value corresponding to the degree of deviation between the processing environment parameters of the real-time scene and the processing environment requirements of the associated path is used as the quantitative value of the degree of difference. If the difference feature is the difference in processing target, the difference in the degree of completion between the processing target of the real-time scene and the processing target standard of the associated path is used as the quantitative value of the degree of difference.

[0062] In this embodiment, after determining the weights, the degree of difference is quantified for the difference features. For the processing scale difference feature, the difference between the real-time scene processing scale and the range of associated path processing scales is calculated, and then this difference is divided by the range of associated path processing scales; the resulting ratio is the quantified value of the degree of difference. For the processing environment difference feature, levels are assigned based on the degree of deviation between the real-time scene processing environment parameters and the associated path processing environment requirements. Each level corresponds to a quantified value; for example, a smaller deviation corresponds to a lower quantified value, and a larger deviation corresponds to a higher quantified value. For the processing target difference feature, the difference between the completion degree of the real-time scene processing target and the completion degree of the associated path processing target standard is calculated; this difference is the quantified value of the degree of difference.

[0063] Step S13341: Extract the processing environment requirements from the scene adaptation parameters of the associated path, and determine the environmental parameter items included in the processing environment requirements. The environmental parameter items include temperature parameters, humidity parameters, pollutant concentration parameters, and equipment operating status parameters in the waste treatment scenario.

[0064] In this embodiment, in the sub-step of quantifying the degree of difference in the characteristics of the processing environment, the operation of extracting the processing environment requirements is first performed. The processing environment requirements are extracted from the scene adaptation parameters of the associated path, and the environmental parameter items included therein are determined, such as temperature parameters, humidity parameters, pollutant concentration parameters, equipment operating status parameters, etc.

[0065] Step S13342: For the environmental parameter items, determine the parameter range in the associated path processing environment requirements to form the standard range of the environmental parameter items.

[0066] In this embodiment, after determining the environmental parameter items, for each environmental parameter item, its parameter range is determined from the processing environment requirements of the associated path. For example, the standard range of the temperature parameter is a certain temperature range, the standard range of the humidity parameter is a certain humidity range, etc., thus forming the standard range of the environmental parameter item.

[0067] Step S13343: Collect the real-time values ​​of the corresponding environmental parameter items in the real-time scene processing environment parameters, and compare the real-time values ​​with the standard range of the corresponding environmental parameter items.

[0068] In this embodiment, after determining the standard range of environmental parameter items, real-time values ​​of the corresponding environmental parameter items in the real-time scene processing environmental parameters are collected, such as real-time temperature and real-time humidity, and these real-time values ​​are compared with the corresponding standard range.

[0069] Step S13344: Set the deviation level, which includes no deviation level, slight deviation level, moderate deviation level, and severe deviation level.

[0070] In this embodiment, after comparing the real-time value with the standard range, a deviation level is set. Based on the deviation between the real-time value and the standard range, the deviation level is divided into four levels: no deviation, slight deviation, moderate deviation, and severe deviation.

[0071] Step S13345: If the real-time value is within the standard range, it is determined to be at the no-deviation level, and the corresponding quantization value is the preset no-deviation quantization value; if the real-time value exceeds the standard range but the deviation is less than the preset slight deviation, it is determined to be at the slight deviation level, and the corresponding quantization value is the preset slight deviation quantization value; if the real-time value exceeds the standard range and the deviation is between the preset slight deviation and the preset moderate deviation, it is determined to be at the moderate deviation level, and the corresponding quantization value is the preset moderate deviation quantization value; if the real-time value exceeds the standard range and the deviation exceeds the preset moderate deviation, it is determined to be at the severe deviation level, and the corresponding quantization value is the preset severe deviation quantization value.

[0072] In this embodiment, after setting the deviation level, the deviation degree of each environmental parameter is determined based on the comparison between the real-time value and the standard range, and a corresponding quantification value is assigned. The preset no deviation quantification value, preset slight deviation quantification value, preset moderate deviation quantification value, and preset severe deviation quantification value are preset values ​​based on actual conditions and experience, used to represent the quantification degree of different deviation levels.

[0073] Step S13346: Weighted summation of the quantitative values ​​corresponding to the deviation levels of environmental parameter items, with the weight being the importance coefficient of the environmental parameter item in the treatment environment requirements, to obtain the quantitative value of the degree of difference in the treatment environment difference characteristics.

[0074] In this embodiment, after determining the degree of deviation and assigning a quantified value to each environmental parameter, the quantified value of each environmental parameter is weighted according to its importance coefficient in the treatment environment requirements. The importance coefficient is determined based on the degree of influence of the environmental parameter on the treatment environment; the greater the influence, the higher the coefficient. The weighted quantified values ​​are then summed to obtain the quantified value of the degree of difference in the treatment environment's differential characteristics.

[0075] Step S1335: Multiply the quantified value of the difference degree of the difference feature by the corresponding weight to obtain the weighted difference value of each difference feature. Sum the weighted difference values ​​of all difference features and take the reciprocal to obtain the fit between the associated path and the current real-time scene.

[0076] In this embodiment, after quantifying the degree of difference, the quantified value of the degree of difference for each difference feature is multiplied by its corresponding weight to obtain the weighted difference value for each difference feature. Then, the weighted difference values ​​of all difference features are summed, and the reciprocal of the sum is taken. The resulting value is the fit between the association path and the current real-time scene. The larger the fit value, the higher the degree of matching between the association path and the current real-time scene.

[0077] Step S134: Based on the adaptation calculation results, select the associated paths whose adaptation meets the scene requirements as the paths to be evolved. For the associated paths whose adaptation does not meet the scene requirements, extract their core differences from the real-time scene feature data.

[0078] In this embodiment, after calculating the fit of each associated path, associated paths that meet the fit requirements are selected as paths to be evolved based on preset scenario requirements. For associated paths whose fit does not meet the scenario requirements, the differences between them and real-time scenario feature data are further analyzed to identify the core differences that have the greatest impact on fit. For example, if the fit of a certain associated path is substandard, analysis reveals that the core difference causing the low fit is that the operating temperature of the waste incinerator in the processing equipment is much lower than the requirements in the scenario fit parameters.

[0079] Step S135: Adjust the node composition and connection logic of the path to be evolved for the core differences. The adjustment methods include adding knowledge unit nodes, deleting redundant knowledge unit nodes, and modifying the connection order between nodes. During the adjustment process, refer to the application trigger conditions and association factors in the knowledge unit scenario response feature association set.

[0080] In this embodiment, after identifying the core discrepancies, adjustments are made to them. If the core discrepancy is that the processing equipment status does not meet requirements, it may be necessary to add a new equipment maintenance knowledge unit node to guide the maintenance of the waste incinerator and ensure its operating temperature reaches the required level. If there are redundant knowledge unit nodes in the association path, meaning that the application of the knowledge unit node has no practical effect on the current scenario, it can be deleted. If the connection order between nodes is unreasonable, for example, if the application of subsequent knowledge units is triggered when the processing equipment does not meet the required state, the connection order between nodes can be modified to ensure that subsequent knowledge units are triggered only after the equipment status meets the requirements. During the adjustment process, the application triggering conditions and association factors in the knowledge unit scenario response feature association set are referenced to ensure that the adjusted association path conforms to the application logic of the knowledge unit.

[0081] Step S136: Apply the adjusted association path to the simulated waste disposal scenario, and collect effect feedback data during the simulated application process. The effect feedback data includes the accuracy of knowledge unit invocation, the consistency of the application process, and the degree to which scenario requirements are met.

[0082] In this embodiment, after adjusting the associated paths, the adjusted paths are applied to a simulated waste disposal scenario. The simulated waste disposal scenario is a virtual scenario built based on the characteristics of actual waste disposal scenarios, capable of simulating various situations in real-world scenarios. During the simulation application, feedback data is collected. Knowledge unit call accuracy refers to the ratio of the number of times a knowledge unit is correctly called within the associated path to the total number of calls; application flow continuity refers to whether the triggering and switching between knowledge units are smooth, without any stuttering or interruptions; and scenario requirement satisfaction refers to whether the application of the associated paths meets the requirements of the simulated waste disposal scenario, such as waste disposal efficiency and processing effectiveness.

[0083] Step S137: Verify the scenario adaptability of the adjusted association path based on the effect feedback data. If the effect feedback data meets the preset application effect standard, the adjusted association path will be used as the evolved association path. If it does not meet the standard, the core differences will be re-identified and the adjustment steps will be repeated until the effect feedback data meets the application effect standard, and finally the evolved knowledge unit dynamic association path set will be formed.

[0084] In this embodiment, after collecting the effect feedback data, the scenario adaptability of the adjusted association path is verified. Preset application effect standards include a certain percentage of knowledge unit call accuracy, a certain level of application process coherence, and a certain level of scenario requirement fulfillment. The collected effect feedback data is compared with the preset standards. If it meets the standards, the adjusted association path is used as the evolved association path; if it does not meet the standards, the effect feedback data is re-analyzed to identify new core differences, and the steps of adjustment, simulated application, and verification are repeated until the effect feedback data meets the application effect standards, ultimately forming the evolved set of dynamic association paths for knowledge units.

[0085] Step S140: Generate a waste management knowledge application scheme based on the dynamically associated path set of the evolved knowledge units. The scheme includes the calling order of knowledge units, scenario triggering rules, and application connection logic.

[0086] In this embodiment, after obtaining the evolved set of dynamic association paths for knowledge units, the next step is to generate a waste management knowledge application scheme. Based on the evolved set of association paths, the calling order of knowledge units is determined, i.e., knowledge units are called according to the connection order of knowledge unit nodes in the association paths. Scenario triggering rules refer to the scenario conditions under which the application of a corresponding knowledge unit is triggered; these rules are determined based on scenario adaptation parameters and connection logic in the association paths. Application connection logic refers to the connection method between knowledge units during the application process, including the transmission of triggering conditions and data interaction. These elements are integrated to form the waste management knowledge application scheme.

[0087] Step S150: Adapt the waste treatment knowledge application scheme to the actual waste treatment scenario in a closed loop. Adjust the order of knowledge unit calls and triggering rules in the scheme according to the scenario application feedback, and generate waste treatment knowledge scenario adaptation execution instructions. The waste treatment knowledge scenario adaptation execution instructions are used to guide the knowledge application operation in the actual waste treatment scenario.

[0088] In this embodiment, after generating the waste management knowledge application scheme, the final step is closed-loop adaptation. First, the knowledge unit calling order and triggering rules in the waste management knowledge application scheme are converted into an executable application process script. This application process script includes the time nodes for knowledge unit calls, triggering condition judgment logic, and exception handling logic. The application process script is then deployed to the knowledge application system of the actual waste management scenario. The script execution is initiated, and real-time application data is collected during the script execution process. This real-time application data includes the knowledge unit call time, triggering condition fulfillment status, and application operation execution results. Based on the real-time application data, a scenario application feedback report is generated. This feedback report includes the knowledge unit call accuracy, triggering rule compliance, and application process smoothness. The abnormal feedback items in the scenario application feedback report are analyzed. These abnormal feedback items include knowledge units whose call accuracy does not meet the preset standard, triggering conditions whose triggering rule compliance does not meet the standard, and application operation intervals whose smoothness does not meet the requirements. The waste management system is then adjusted according to the abnormal feedback items. The process involves adjusting the knowledge unit calling order and triggering rules in the knowledge application scheme. When adjusting the calling order, the node connection logic in the evolved dynamic association path set of knowledge units is referenced. When adjusting the triggering rules, the application triggering conditions in the scenario response characteristics of knowledge units are referenced. The adjusted waste disposal knowledge application scheme is then converted back into an application process script and redeployed to the knowledge application system in the actual waste disposal scenario for verification. Real-time application data is collected during the verification process, and a secondary feedback report is generated. If all feedback items in the secondary feedback report meet the preset standards, a waste disposal knowledge scenario adaptation execution instruction is generated based on the adjusted waste disposal knowledge application scheme. The execution instruction includes the adjusted knowledge unit calling order, triggering rules, and application process connection requirements. If there are still abnormal feedback items in the secondary feedback report, the adjustment and verification steps are repeated until all feedback items meet the preset standards, at which point a waste disposal knowledge scenario adaptation execution instruction is generated.

[0089] Step S151: Convert the knowledge unit calling order and triggering rules in the waste disposal knowledge application scheme into an executable application process script. The application process script includes the time node for knowledge unit calling, triggering condition judgment logic, and exception handling logic.

[0090] In this embodiment, during closed-loop adaptation, the first step is to convert the knowledge application scheme into an application flow script. The time node for knowledge unit invocation refers to the specific time point at which the corresponding knowledge unit is invoked; the trigger condition judgment logic refers to the logical statements that determine whether the trigger conditions for knowledge unit application are met; and the exception handling logic refers to the handling methods when exceptions occur during knowledge application, such as measures to address situations like knowledge unit invocation failure or failure to meet trigger conditions. These elements are then written into an executable application flow script using a scripting language.

[0091] Step S152: Deploy the application process script to the knowledge application system of the actual waste disposal scenario, start the script execution and collect real-time application data during the script execution process. The real-time application data includes the knowledge unit call time, the trigger condition satisfaction status, and the application operation execution result.

[0092] In this embodiment, after the application process script is written, it is deployed to the knowledge application system in a real-world waste management scenario. The knowledge application system is a hardware and software system used to execute knowledge application schemes. It can receive application process scripts and execute corresponding operations according to the script content. After the script execution is started, data is collected in real time during the script execution process, including the specific time when knowledge units are invoked, whether triggering conditions are met, and the execution results of application operations.

[0093] Step S153: Generate a scenario application feedback report based on real-time application data. The feedback report includes the accuracy of knowledge unit invocation, the compliance of triggering rules, and the smoothness of application process connection.

[0094] In this embodiment, after collecting real-time application data, the data is analyzed and processed to generate a scenario application feedback report. Knowledge unit invocation accuracy refers to the ratio of the number of times a knowledge unit is correctly invoked to the total number of invocations; trigger rule compliance refers to the degree to which the actual application of the knowledge unit conforms to the trigger rules; application process smoothness refers to whether the invocation and switching between knowledge units are smooth, without delays or interruptions. These indicators are calculated and written into the feedback report.

[0095] Step S154: Analyze the abnormal feedback items in the scenario application feedback report. The abnormal feedback items include knowledge units whose call accuracy does not meet the preset standard, trigger conditions whose trigger rule compliance does not meet the standard, and application operation intervals whose connection smoothness does not meet the requirements.

[0096] In this embodiment, after generating the scenario application feedback report, the content of the report is parsed to identify abnormal feedback items. Knowledge units whose accuracy rate does not meet the preset standard refer to those whose correct calls account for a lower percentage of total calls than the preset standard value; trigger conditions whose trigger rule compliance does not meet the standard refer to those whose actual triggering situation does not conform to the trigger rule to a lower degree than the preset standard; and application operation intervals whose smoothness does not meet the requirements refer to the interval between calls between knowledge units exceeding a preset reasonable range, resulting in an unsmooth application process.

[0097] Step S155: Adjust the knowledge unit calling order and triggering rules in the waste management knowledge application scheme for abnormal feedback items. When adjusting the calling order, refer to the node connection logic in the evolved knowledge unit dynamic association path set. When adjusting the triggering rules, refer to the application triggering conditions in the knowledge unit scenario response characteristics.

[0098] In this embodiment, after identifying the abnormal feedback item, the order of knowledge unit calls and the triggering rules in the waste management knowledge application scheme are adjusted. When adjusting the call order, the node connection logic in the evolved dynamic association path set of knowledge units is referenced to ensure that the call order of knowledge units conforms to the requirements of the association path; when adjusting the triggering rules, the application triggering conditions in the scenario response characteristics of knowledge units are referenced to make the triggering rules more accurate and reasonable.

[0099] Step S1551: For knowledge units whose call accuracy does not meet the preset standard, query the node connection logic corresponding to the knowledge unit in the evolved knowledge unit dynamic association path set, and determine the preceding and following node knowledge units of the knowledge unit in the path.

[0100] In this embodiment, in the sub-step of adjusting the knowledge application scheme for abnormal feedback items, the knowledge units whose invocation accuracy does not meet the preset standard are processed first. The evolved set of dynamic association paths for each knowledge unit is queried to find the node connection logic corresponding to that knowledge unit, thereby determining its preceding and following node knowledge units in the path. A preceding node knowledge unit refers to a knowledge unit invoked before the preceding knowledge unit, and a following node knowledge unit refers to a knowledge unit invoked after the preceding knowledge unit.

[0101] Step S1552: Check the calling status of the preceding node knowledge unit. If the calling of the preceding node knowledge unit is abnormal and the accuracy of the calling of the knowledge unit does not meet the preset standard, adjust the calling order of the preceding node knowledge unit to within the preset time interval before the calling of the knowledge unit.

[0102] In this embodiment, after determining the preceding node knowledge unit, its invocation status is checked. If there are anomalies in the invocation of the preceding node knowledge unit, such as invocation time delay or invocation failure, resulting in the invocation accuracy of the current knowledge unit not meeting the preset standard, then the invocation order of the preceding node knowledge units is adjusted, and their invocation time is adjusted to within the preset time interval before the current knowledge unit is invoked, so as to ensure that the application results of the preceding node knowledge unit can be transmitted to the current knowledge unit in a timely manner, thereby improving its invocation accuracy.

[0103] Step S1553: If the preceding node knowledge unit is called normally, check the connection logic between the knowledge unit and the following node knowledge unit. If the trigger condition setting in the connection logic is unreasonable, refer to the application trigger condition in the knowledge unit scenario response characteristics and adjust the trigger condition parameter of the knowledge unit.

[0104] In this embodiment, after confirming that the preceding node knowledge unit is being called normally, the connection logic between the current knowledge unit and the following node knowledge unit is checked. If the triggering conditions in the connection logic are not set reasonably, for example, if the triggering conditions are too strict or too lenient, causing the calling accuracy of the current knowledge unit to fall short of the standard, then the triggering condition parameters of the current knowledge unit are adjusted by referring to the application triggering conditions in the knowledge unit scenario response characteristics to make them more reasonable.

[0105] Step S1554: For triggering conditions where the compliance of the triggering rule does not meet the standard, extract the scene parameter requirements corresponding to the triggering condition from the scene response features of the knowledge unit, compare the difference between the real-time scene data and the scene parameter requirements, and adjust the parameter threshold in the triggering condition.

[0106] In this embodiment, after processing knowledge units whose invocation accuracy does not meet the standard, the next step is to process trigger conditions whose trigger rule compliance does not meet the standard. The scene parameter requirements corresponding to the trigger condition are extracted from the scene response features of the knowledge unit. Real-time scene data is compared with these parameter requirements to identify discrepancies. Based on these discrepancies, the parameter thresholds in the trigger conditions are adjusted to better align with the needs of the actual scenario.

[0107] Step S1555: If the trigger rule does not meet the standard, it is because the judgment logic of the trigger condition is unreasonable. Reconstruct the judgment logic of the trigger condition and refer to the scenario requirement matching factor in the knowledge unit associated trigger factor.

[0108] In this embodiment, if the compliance rate of the triggering rule still fails to meet the standard after adjusting the threshold of the triggering condition parameters, and the reason is that the judgment logic of the triggering condition is unreasonable, then the judgment logic of the triggering condition is reconstructed. During the reconstruction process, the scenario requirement matching factor in the knowledge unit associated triggering factor is referenced to ensure that the judgment logic matches the scenario requirements.

[0109] Step S1556: For application operation intervals where the smoothness of connection does not meet the requirements, query the connection logic of adjacent knowledge units in the dynamically associated path set of the evolved knowledge units, extract the time interval requirements in the connection logic, compare the difference between the real-time application operation interval and the time interval requirements, and adjust the calling time nodes of adjacent knowledge units.

[0110] In this embodiment, after handling cases where the trigger rule compliance does not meet the standard, the application operation interval that fails to meet the smoothness requirements is addressed. The evolved set of dynamic association paths for knowledge units is queried to find the connection logic of adjacent knowledge units, and the time interval requirements are extracted. The real-time application operation interval is compared with the time interval requirements to identify discrepancies. Based on these discrepancies, the call time nodes of adjacent knowledge units are adjusted to ensure the application operation interval meets the requirements, thereby improving smoothness.

[0111] Step S1557: If the smoothness of the connection does not meet the requirements due to the lack of intermediate transition operations, add a transitional knowledge unit in the calling order of adjacent knowledge units. The selection of the transitional knowledge unit refers to the logical dependency factor in the knowledge unit association trigger factor.

[0112] In this embodiment, if the smoothness of the connection still does not meet the requirements after adjusting the call time node, and the reason is the lack of intermediate transition operations, then a transitional knowledge unit is added to the call order of adjacent knowledge units. The selection of the transitional knowledge unit refers to the logical dependency factor in the knowledge unit association trigger factor to ensure that the application of the transitional knowledge unit can connect with the application of adjacent knowledge units, making the application process smoother.

[0113] For example, step S15571: Query the logical dependency factors of the preceding knowledge unit and the logical dependency factors of the following knowledge unit in the set of triggering factors associated with the knowledge unit, and extract the application output result description of the preceding knowledge unit and the application prerequisite description of the following knowledge unit.

[0114] In this embodiment, in the sub-step of adding transitional knowledge units, the set of triggering factors associated with knowledge units is first queried to find the logical dependency factors between the preceding and following knowledge units. From these factors, the application output description of the preceding knowledge unit and the application prerequisite description of the following knowledge unit are extracted.

[0115] Step S15572: Analyze the differences between the application output description of the preceding knowledge unit and the application prerequisite description of the subsequent knowledge unit, and determine the supplementary operation content required for the connection.

[0116] In this embodiment, after extracting the application output description and the application prerequisite description, the two are analyzed to identify any discrepancies. Based on these discrepancies, the necessary supplementary operations for connecting the preceding and following knowledge units are determined; these operations constitute the functions that the transitional knowledge unit needs to implement.

[0117] Step S15573: Select knowledge units that can implement supplementary operation content from the waste management knowledge units as candidate transitional knowledge units.

[0118] In this embodiment, after determining the supplementary operation content, knowledge units that can implement these operation contents are selected from the waste management knowledge units and used as candidate transitional knowledge units.

[0119] Step S15574: Query the associated triggering factors of the candidate transitional knowledge unit, and check the logical dependency factors between the candidate transitional knowledge unit and the previous knowledge unit, and the logical dependency factors between the candidate transitional knowledge unit and the subsequent knowledge unit.

[0120] In this embodiment, after screening out candidate transitional knowledge units, their associated triggering factors are queried, and the logical dependency factors between the candidate transitional knowledge units and the preceding knowledge units, as well as the logical dependency factors between the candidate transitional knowledge units and the following knowledge units, are checked to ensure that the candidate transitional knowledge units can form reasonable logical dependencies with the preceding and following knowledge units.

[0121] Step S15575: If the application prerequisites of the candidate transitional knowledge unit are consistent with the application output of the previous knowledge unit, and the application output of the candidate transitional knowledge unit is consistent with the application prerequisites of the subsequent knowledge unit, then the candidate transitional knowledge unit shall be used as the final transitional knowledge unit.

[0122] In this embodiment, after checking the logical dependency factors of the candidate transitional knowledge unit, if the application preconditions of the candidate transitional knowledge unit are consistent with the application output of the previous knowledge unit, and its application output is consistent with the application preconditions of the subsequent knowledge unit, it indicates that the candidate transitional knowledge unit can well connect the previous knowledge unit and the subsequent knowledge unit, and therefore it is used as the final transitional knowledge unit.

[0123] Step S15576: If there are multiple candidate transitional knowledge units that meet the conditions, collect the application effect data of the candidate transitional knowledge units in the historical waste disposal process, and count the operation success rate and operation time in the application effect data. Select the candidate transitional knowledge units whose operation success rate exceeds the preset success rate standard and whose operation time does not exceed the preset time standard as the final transitional knowledge units.

[0124] In this embodiment, when multiple candidate transitional knowledge units meet the criteria, their application effect data in historical waste disposal processes are collected. The statistical data includes the operation success rate and operation time. The operation success rate is the ratio of the number of successful applications of a candidate transitional knowledge unit to the total number of applications, and the operation time is the time required for the application of a candidate transitional knowledge unit. Candidate transitional knowledge units whose operation success rate exceeds a preset success rate standard and whose operation time does not exceed a preset time standard are selected as the final transitional knowledge units.

[0125] Step S15577: Insert the transitional knowledge unit between the calling order of the preceding knowledge unit and the following knowledge unit, and determine the calling time node of the transitional knowledge unit.

[0126] In this embodiment, after determining the final transitional knowledge unit, it is inserted between the calling order of the preceding and following knowledge units. Based on the calling time of the preceding and following knowledge units, the calling time node of the transitional knowledge unit is determined, ensuring that the application of the transitional knowledge unit can seamlessly connect with the application of the preceding and following knowledge units at an appropriate time.

[0127] Step S15578: Record the identifier, calling time node, and logical dependency relationship with the preceding and following knowledge units of the transitional knowledge unit, and update the knowledge unit calling order in the waste disposal knowledge application scheme.

[0128] In this embodiment, after determining the insertion and invocation time points of the transitional knowledge units, the identifier, invocation time point, and logical dependencies between the transitional knowledge units and the preceding and following knowledge units are recorded. Then, the knowledge unit invocation order in the waste management knowledge application scheme is updated, and the transitional knowledge units are added to their corresponding positions.

[0129] Step S1558: After the adjustment is completed, record the adjusted knowledge unit calling order, trigger rule parameters, judgment logic, and time node information to form the initial draft of the adjusted waste disposal knowledge application scheme.

[0130] In this embodiment, after all adjustment operations are completed, the adjusted knowledge unit calling order, trigger rule parameters, judgment logic, and time node information are recorded. This information is then integrated to form a draft of the adjusted waste management knowledge application scheme.

[0131] Step S156: Convert the adjusted waste management knowledge application scheme back into an application process script, redeploy it to the knowledge application system in the actual waste management scenario for verification, collect real-time application data during the verification process, and generate a secondary feedback report.

[0132] In this embodiment, after adjusting the knowledge application scheme, the adjusted scheme is re-converted into an application process script and redeployed to the knowledge application system in a real-world waste management scenario for verification. During the verification process, application data is collected in real time, and a secondary feedback report is generated.

[0133] Step S157: If all feedback items in the secondary feedback report meet the preset standards, then generate a waste treatment knowledge scenario adaptation execution instruction based on the adjusted waste treatment knowledge application scheme. The execution instruction includes the adjusted knowledge unit calling order, triggering rules, and application connection logic. If there are still abnormal feedback items in the secondary feedback report, repeat the adjustment and verification steps until all feedback items meet the preset standards and then generate the waste treatment knowledge scenario adaptation execution instruction.

[0134] In this embodiment, after generating the secondary feedback report, the feedback items in the report are checked. If all feedback items meet the preset standards, it means that the adjusted knowledge application scheme can adapt to the needs of the actual waste disposal scenario. At this time, a waste disposal knowledge scenario adaptation execution instruction is generated based on the adjusted scheme. This instruction includes the adjusted knowledge unit calling order, triggering rules, and application connection logic, which is used to guide the knowledge application operation in the actual waste disposal scenario. If there are still abnormal feedback items in the secondary feedback report, the steps of adjusting the knowledge application scheme, converting it into an application process script, deploying and verifying it, and generating a feedback report are repeated until all feedback items meet the preset standards, and then the execution instruction is generated.

[0135] Figure 2 The illustration shows exemplary hardware and software components of a knowledge graph-integrated waste management system 100 that can implement the ideas of this application, according to some embodiments of this application. For example, a processor 120 may be used in the knowledge graph-integrated waste management system 100 and to perform the functions described in this application.

[0136] The waste management knowledge management system 100 incorporating knowledge graphs can be a general-purpose server or a special-purpose server; both can be used to implement the waste management knowledge management method incorporating knowledge graphs of this application. Although only one server is shown in this application, for convenience, the functions described in this application can be implemented in a distributed manner on multiple similar platforms to balance the processing load.

[0137] For example, a waste management system 100 incorporating a knowledge graph may include a network port 110 connected to a network, one or more processors 120 for executing program instructions, a communication bus 130, and various forms of storage media 140, such as a disk, ROM, or RAM, or any combination thereof. Exemplarily, the waste management system 100 incorporating a knowledge graph may also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. The methods of this application can be implemented according to these program instructions. The waste management system 100 incorporating a knowledge graph also includes an I / O interface 150 between the computer and other input / output devices.

[0138] For ease of explanation, only one processor is described in the knowledge graph-integrated waste management system 100. However, it should be noted that the knowledge graph-integrated waste management system 100 of this application may also include multiple processors, and therefore the steps performed by one processor described in this application may also be performed jointly or individually by multiple processors. For example, if the processor of the knowledge graph-integrated waste management system 100 performs steps A and B, it should be understood that steps A and B may also be performed jointly by two different processors or individually by one processor. For example, the first processor performs step A, the second processor performs step B, or the first processor and the second processor jointly perform steps A and B.

[0139] Furthermore, this embodiment of the invention also provides a readable storage medium, wherein computer-executable instructions are preset in the readable storage medium, and when the processor executes the computer-executable instructions, the above-mentioned waste management knowledge management method combining knowledge graphs is implemented.

[0140] It should be noted that, in order to simplify the description of the present invention and thus help to understand one or more embodiments of the invention, multiple features may sometimes be grouped into one embodiment, drawing or description thereof in the foregoing description of the embodiments of the present invention.

Claims

1. A waste management knowledge management method combining knowledge graphs, characterized in that, The method includes: Obtain waste treatment knowledge units and corresponding scenario response features for each knowledge unit, establish the association between knowledge units and scenario response features, and obtain a knowledge unit scenario response feature association set. The waste treatment knowledge units include waste classification knowledge units, waste treatment process knowledge units, and waste recycling process knowledge units. The scenario response features include the application triggering conditions and application effect feedback features of the knowledge units in different waste treatment scenarios. Based on the association set of scene response features of knowledge units, a dynamic association path of knowledge units is constructed. By matching the triggering conditions and association factors in the scene response features of each knowledge unit, an association logic that can be adjusted with scene changes is formed, resulting in a set of dynamic association paths of knowledge units. The dynamic association path set of knowledge units is subjected to scenario-adaptive evolution processing. The logical nodes and connection relationships of the association paths are adjusted in combination with the characteristic parameters of the actual waste disposal scenario to obtain the evolved dynamic association path set of knowledge units. A waste management knowledge application solution is generated based on the dynamically associated path set of the evolved knowledge units. The solution includes the calling order of knowledge units, scenario triggering rules, and application connection logic. The waste treatment knowledge application scheme is adapted in a closed loop to the actual waste treatment scenario. The order of knowledge unit calls and triggering rules in the scheme are adjusted according to the scenario application feedback, and waste treatment knowledge scenario adaptation execution instructions are generated. These waste treatment knowledge scenario adaptation execution instructions are used to guide the knowledge application operation in the actual waste treatment scenario.

2. The waste management knowledge management method combining knowledge graphs according to claim 1, characterized in that, The process of constructing dynamic association paths for knowledge units based on the association set of scene response features of knowledge units yields a set of dynamic association paths for knowledge units, including: The application triggering conditions of each knowledge unit scene response feature in the association set of knowledge unit scene response features are analyzed, and the scene parameters and feature thresholds in the triggering conditions are extracted to form a scene triggering condition parameter set. The scene parameters include the processing scale features, processing environment features, and processing target features of the waste disposal scene. Extract the association triggering factors of each knowledge unit, which include logical dependency factors between knowledge units, application order association factors, and scenario requirement matching factors; Match the scene parameters in the scene trigger condition parameter set with the associated trigger factors of the knowledge unit to determine the associated trigger factor combination corresponding to the scene parameter, and form a scene and factor matching combination; The initial association path of knowledge units is constructed based on the combination of scenario and factor matching. The initial association path includes the connection order and connection logic of knowledge units. The connection logic is determined by the association relationship in the combination of scenario and factor matching. Obtain historical scene change parameters for waste disposal scenarios, and adjust the connection logic of the initial associated paths based on these parameters, so that the associated paths can be dynamically adjusted according to the scene change parameters. Record the node information and connection logic change rules of the adjusted associated paths to form a dynamic associated path set of knowledge units. The node information includes the knowledge unit identifier and the corresponding scene response feature identifier. The connection logic change rules include the correspondence between scene change parameters and path adjustment methods.

3. The waste management knowledge management method combining knowledge graphs according to claim 1, characterized in that, The process of performing scenario-adaptive evolution processing on the dynamic association path set of knowledge units to obtain the evolved dynamic association path set of knowledge units includes: Collect real-time scene feature data of actual waste treatment scenarios. The real-time scene feature data includes the attributes of the objects being treated in the current scenario, the status of the treatment equipment, the progress of the treatment process, and environmental influencing factors. The node structure and connection logic of each associated path in the dynamic association path set of knowledge units are analyzed, and the scenario adaptation parameters of each path are extracted. The scenario adaptation parameters include the range of processing object attributes applicable to the path, the status requirements of processing equipment, and the progress nodes of the processing process. The real-time scene feature data is compared with the scene adaptation parameters of each associated path, and the difference features between the two are extracted. Based on the difference features, the adaptation degree between each associated path and the current real-time scene is calculated. The adaptation degree calculation process includes the weight allocation of difference features and the quantification of the degree of difference. The weight allocation is determined according to the degree of influence of difference features on the knowledge application effect. Based on the adaptation calculation results, the associated paths that meet the scene requirements are selected as the paths to be evolved. For the associated paths that do not meet the scene requirements, the core differences between them and the real-time scene feature data are extracted. Adjust the node composition and connection logic of the path to be evolved based on the core differences. The adjustment methods include adding knowledge unit nodes, deleting redundant knowledge unit nodes, and modifying the connection order between nodes. During the adjustment process, refer to the application trigger conditions and association factors in the knowledge unit scenario response feature association set. The adjusted association path is applied to a simulated waste disposal scenario, and effect feedback data is collected during the simulated application process. The effect feedback data includes the accuracy of knowledge unit invocation, the coherence of the application process, and the degree to which scenario requirements are met. The scenario adaptability of the adjusted association path is verified based on the effect feedback data. If the effect feedback data meets the preset application effect standard, the adjusted association path is used as the evolved association path; if it does not meet the standard, the core differences are re-identified and the adjustment steps are repeated until the effect feedback data meets the application effect standard, and finally the evolved knowledge unit dynamic association path set is formed.

4. The waste management knowledge management method combining knowledge graphs according to claim 1, characterized in that, The process of adapting the waste management knowledge application scheme to actual waste management scenarios in a closed loop, adjusting the knowledge unit calling order and triggering rules in the scheme based on scenario application feedback, and generating waste management knowledge scenario adaptation execution instructions includes: The knowledge unit calling order and triggering rules in the waste disposal knowledge application scheme are transformed into an executable application process script. The application process script includes the time node for knowledge unit calling, trigger condition judgment logic, and exception handling logic. The application process script is deployed to the knowledge application system in the actual waste disposal scenario. The script is started to execute and real-time application data is collected during the script execution process. The real-time application data includes the knowledge unit call time, the status of trigger conditions, and the application operation execution results. Based on real-time application data, a scenario application feedback report is generated. The feedback report includes the accuracy of knowledge unit invocation, the compliance of triggering rules, and the smoothness of application process connection. The abnormal feedback items in the scenario application feedback report are analyzed. The abnormal feedback items include knowledge units whose call accuracy does not meet the preset standard, trigger conditions whose trigger rule compliance does not meet the standard, and application operation intervals whose smoothness does not meet the requirements. For abnormal feedback items, adjust the knowledge unit calling order and triggering rules in the waste management knowledge application scheme. When adjusting the calling order, refer to the node connection logic in the evolved knowledge unit dynamic association path set. When adjusting the triggering rules, refer to the application triggering conditions in the knowledge unit scenario response characteristics. The revised waste management knowledge application scheme was transformed back into an application process script and redeployed to the knowledge application system in the actual waste management scenario for verification. Real-time application data was collected during the verification process and a secondary feedback report was generated. If all feedback items in the secondary feedback report meet the preset standards, then a waste treatment knowledge scenario adaptation execution instruction is generated based on the adjusted waste treatment knowledge application scheme. The execution instruction includes the adjusted knowledge unit calling order, triggering rules, and application process connection requirements. If there are still abnormal feedback items in the secondary feedback report, the adjustment and verification steps are repeated until all feedback items meet the preset standards, and then a waste treatment knowledge scenario adaptation execution instruction is generated.

5. The waste management knowledge management method combining knowledge graphs according to claim 2, characterized in that, The step of extracting the association triggering factors for each knowledge unit includes logical dependency factors between knowledge units, application order association factors, and scenario requirement matching factors, including: Extract attribute information from waste management knowledge units, the attribute information including the application prerequisites, application output results, and application associated objects of the knowledge units; The logical dependency factors between knowledge units are determined based on the application prerequisites and application outputs. If the application output of the first knowledge unit is consistent with the application prerequisites of the second knowledge unit, then the correspondence is taken as the logical dependency factor between the first knowledge unit and the second knowledge unit, and the description of the prerequisites and the description of the outputs corresponding to the logical dependency factor are recorded. The application sequence correlation factor is determined based on the order of application of knowledge units in the actual waste treatment process. The application time series data of each knowledge unit in the historical waste treatment process are collected, and the application frequency of different knowledge units in the same process is counted. The order of application of knowledge units with frequencies exceeding the preset frequency standard is used as the application sequence correlation factor of the corresponding knowledge units. Based on the application scenario requirement description and scenario response characteristics of knowledge units, the scenario requirement matching factor is determined, the scenario parameter requirements in the scenario response characteristics of knowledge units are extracted, and the correspondence between the application scenario requirement description and scenario parameter requirements of knowledge units is used as the scenario requirement matching factor. Add factor identifiers and corresponding knowledge unit identifiers to logical dependency factors, application sequence association factors, and scenario requirement matching factors respectively to form a set of knowledge unit association trigger factors. Each factor in the set corresponds to a unique combination of factor identifier and knowledge unit identifier.

6. The waste management knowledge management method combining knowledge graphs according to claim 3, characterized in that, The process of calculating the fit between each associated path and the current real-time scenario based on difference features includes weight allocation and quantification of the degree of difference. The weight allocation is determined based on the degree of influence of the difference features on the knowledge application effect, including: The differences are classified into three categories: differences in processing scale, differences in processing environment, and differences in processing target. Data on the impact of different differences in historical waste disposal scenarios on the effectiveness of knowledge application is collected, and the impact data includes the magnitude of change in the effectiveness of knowledge application when the differences exist. The weights of each differential feature are determined based on the impact data. For differential features with significant changes in the impact data, the weights are increased accordingly. The weights of each differential feature are adjusted to the preset weight range through normalization. The degree of difference is quantified for the difference features by converting the difference content of the difference features into quantitative values. If the difference feature is a difference in processing scale, the ratio of the difference between the processing scale of the real-time scene and the processing scale of the associated path to the processing scale of the associated path is used as the quantitative value of the degree of difference. If the difference feature is a difference in processing environment, the quantitative value corresponding to the degree of deviation between the processing environment parameters of the real-time scene and the processing environment requirements of the associated path is used as the quantitative value of the degree of difference. If the difference feature is a difference in processing target, the difference in the degree of completion between the processing target of the real-time scene and the processing target standard of the associated path is used as the quantitative value of the degree of difference. Multiply the quantified value of the difference degree of the difference feature by the corresponding weight to obtain the weighted difference value of each difference feature. Sum the weighted difference values ​​of all difference features and take the reciprocal to obtain the fit degree between the association path and the current real-time scene.

7. The waste management knowledge management method combining knowledge graphs according to claim 4, characterized in that, The adjustment of the knowledge unit calling order and triggering rules in the waste management knowledge application scheme for abnormal feedback items, when adjusting the calling order, refers to the node connection logic in the evolved dynamic association path set of knowledge units, and when adjusting the triggering rules, refers to the application triggering conditions in the scenario response characteristics of knowledge units, including: For knowledge units whose invocation accuracy does not meet the preset standard, query the node connection logic corresponding to the knowledge unit in the dynamically associated path set of the evolved knowledge unit to determine the preceding and following node knowledge units in the path. Check the calling status of the knowledge unit of the preceding node. If the calling of the knowledge unit of the preceding node is abnormal and the calling accuracy of the knowledge unit does not meet the preset standard, adjust the calling order of the knowledge unit of the preceding node to within the preset time interval before the calling of the knowledge unit. If the preceding node knowledge unit is called normally, check the connection logic between the knowledge unit and the following node knowledge unit. If the trigger condition setting in the connection logic is unreasonable, refer to the application trigger condition in the knowledge unit scenario response characteristics and adjust the trigger condition parameter of the knowledge unit. For triggering conditions where the compliance of the triggering rule does not meet the standard, extract the scene parameter requirements corresponding to the triggering condition from the scene response features of the knowledge unit, compare the difference between the real-time scene data and the scene parameter requirements, and adjust the parameter threshold in the triggering condition. If the trigger rule does not meet the standard, it is because the judgment logic of the trigger condition is unreasonable. Reconstruct the judgment logic of the trigger condition and refer to the scenario requirement matching factor in the knowledge unit associated trigger factor. For application operation intervals that do not meet the requirements for smoothness, query the connection logic of adjacent knowledge units in the dynamically associated path set of the evolved knowledge units, extract the time interval requirements in the connection logic, compare the difference between the real-time application operation interval and the time interval requirements, and adjust the calling time nodes of adjacent knowledge units. If the smoothness of the connection does not meet the requirements due to the lack of intermediate transition operations, add transitional knowledge units in the calling order of adjacent knowledge units. The selection of transitional knowledge units should refer to the logical dependency factors in the knowledge unit association trigger factors. After the adjustment is completed, record the adjusted knowledge unit calling order, trigger rule parameters, judgment logic, and time node information to form the initial draft of the adjusted waste management knowledge application plan.

8. The waste management knowledge management method combining knowledge graphs according to claim 5, characterized in that, The method involves statistically analyzing the frequency of application of different knowledge units within the same process, and using the order in which the frequency exceeds a preset frequency standard as the application order correlation factor for the corresponding knowledge units, including: Extract process samples containing knowledge unit application records from historical waste disposal process data. The process samples contain application timestamps and application order records of all knowledge units in the historical waste disposal process. The application order of knowledge units in the process sample is broken down to obtain knowledge unit application order pairs. Each knowledge unit application order pair contains two knowledge units and the order in which the two knowledge units are applied in the sample. The total number of times knowledge unit application order pairs appear in all process samples is counted to obtain the frequency statistics of knowledge unit application order pairs; Set a frequency standard, which is determined based on the total number of process samples and a preset ratio. The frequency standard is the total number of process samples multiplied by the preset ratio coefficient. The frequency statistics of knowledge unit application order pairs are compared with the frequency standard. If the number of occurrences of a knowledge unit application order pair exceeds the frequency standard, then the knowledge unit application order pair is used as the application order association factor of the corresponding knowledge unit. Record the application time series data corresponding to the application sequence correlation factor, and at the same time record the number of occurrences, the total number of process samples, and the preset proportion coefficient in the frequency statistics results to form supporting explanatory data for the application sequence correlation factor.

9. The waste management knowledge management method combining knowledge graphs according to claim 6, characterized in that, If the difference characteristic is a difference in the processing environment, the quantitative value corresponding to the degree of deviation between the real-time scene processing environment parameters and the requirements of the associated path processing environment is used as the quantitative value of the degree of difference, including: Extract the processing environment requirements from the scene adaptation parameters of the associated path, and determine the environmental parameter items included in the processing environment requirements. The environmental parameter items include temperature parameters, humidity parameters, pollutant concentration parameters, and equipment operating status parameters in the waste treatment scenario. For environmental parameter items, determine the parameter range in the associated path processing environment requirements to form a standard range for environmental parameter items; Collect real-time values ​​of corresponding environmental parameter items in the real-time scene processing environment parameters, and compare the real-time values ​​with the standard range of the corresponding environmental parameter items; Set the deviation level, which includes no deviation level, slight deviation level, moderate deviation level, and severe deviation level; If the real-time value is within the standard range, it is determined to be at the no-deviation level, and the corresponding quantization value is the preset no-deviation quantization value; If the real-time value exceeds the standard range but the extent of the exceedance does not reach the preset slight deviation level, it is judged as a slight deviation level, and the corresponding quantization value is the preset slight deviation quantization value. If the real-time value exceeds the standard range and the excess is between the preset slight and preset moderate range, it is judged as a moderate deviation level, and the corresponding quantization value is the preset moderate deviation quantization value. If the real-time value exceeds the standard range and the magnitude of the deviation exceeds the preset moderate range, it is judged as a serious deviation level, and the corresponding quantization value is the preset serious deviation quantization value. The quantitative values ​​corresponding to the deviation levels of environmental parameter items are weighted and summed, with the weights being the importance coefficients of the environmental parameter items in the treatment environment requirements, to obtain the quantitative values ​​of the degree of difference in the treatment environment difference characteristics.

10. A waste management knowledge management system incorporating knowledge graphs, characterized in that, The waste management knowledge management system incorporating knowledge graphs includes a processor and a memory, the memory and the processor being connected. The memory is used to store programs, instructions, or code, and the processor is used to execute the programs, instructions, or code in the memory to implement the waste management knowledge management method incorporating knowledge graphs as described in any one of claims 1-9.

Images