An intelligent decision support method, system, storage medium and electronic device for estimating carbon sinks of a power transmission channel and optimizing recovery potential

Abstract

The present application provides a kind of transmission channel carbon sink estimation and recovery potential optimization Intelligent decision support method, system, storage medium and electronic equipment, wherein the method comprises: respectively on transmission channel carbon sink estimation and recovery potential optimization, obtain carbon sink estimation result and recovery potential optimization result;Intelligent decision support is carried out to user based on carbon sink estimation result and recovery potential optimization result.The present application carries out carbon sink estimation and recovery potential optimization respectively on transmission channel, obtains carbon sink estimation result and recovery potential optimization result, and based on this, intelligent decision support is carried out to user, without user manual carbon sink estimation and recovery potential optimization decision, give user effective automatic intelligent decision support, greatly improve the decision efficiency, reduce the labor cost.

Description

Technical Field

[0001] This invention relates to the field of computer data processing technology, and in particular to an intelligent decision support method, system, storage medium, and electronic device for estimating carbon sinks and optimizing recovery potential in power transmission channels. Background Technology

[0002] As the global climate change problem becomes increasingly severe, carbon emission control has become a key measure in addressing climate change worldwide. As one of the major sources of carbon emissions, the power industry plays a vital role in mitigating climate change.

[0003] Currently, enhancing the carbon sequestration capacity and resilience of power transmission channels has become a crucial approach to reducing the carbon footprint of the power system. Power transmission channels are not only core infrastructure for electricity transmission but also contribute to mitigating climate change by absorbing carbon dioxide from the atmosphere and improving the surrounding ecological environment. Furthermore, optimizing the resilience of power transmission channels to ensure the continued stability of their electricity transmission and carbon sequestration functions is particularly important in the face of external shocks such as natural disasters and environmental degradation.

[0004] To enhance the carbon sequestration capacity and recovery potential of power transmission channels, it is necessary to estimate their carbon sequestration and optimize recovery potential decisions. However, traditional decision-making methods largely rely on manual operation and lack effective automated intelligent decision support, resulting in low decision-making efficiency and high labor costs. Summary of the Invention

[0005] One of the objectives of this invention is to provide an intelligent decision support method for carbon sink estimation and recovery potential optimization of power transmission channels. The method performs carbon sink estimation and recovery potential optimization on the power transmission channels to obtain carbon sink estimation results and recovery potential optimization results. Based on these results, intelligent decision support is provided to users, eliminating the need for users to manually perform carbon sink estimation and recovery potential optimization decisions. This provides users with effective automated intelligent decision support, greatly improving decision-making efficiency and reducing labor costs.

[0006] This invention provides an intelligent decision support method for estimating carbon sinks and optimizing the recovery potential of power transmission channels, comprising:

[0007] Carbon sink estimation and recovery potential optimization were performed on the power transmission channels to obtain carbon sink estimation results and recovery potential optimization results.

[0008] Based on carbon sink estimation results and recovery potential optimization results, intelligent decision support is provided to users.

[0009] Optionally, when estimating carbon sinks for transmission channels, the following steps may be performed:

[0010] To obtain the basis for carbon sink estimation of power transmission channels;

[0011] Based on the carbon sink estimation model, carbon sink estimation is performed on the transmission channel according to the carbon sink estimation criteria to obtain the carbon sink estimation results.

[0012] Optionally, when optimizing the recovery potential of transmission channels, the following steps may be performed:

[0013] Optimize the recovery potential of power transmission channels;

[0014] Based on the recovery potential optimization algorithm, the recovery potential of the transmission channel is optimized according to the recovery potential optimization criteria to obtain the recovery potential optimization results.

[0015] Optionally, the intelligent decision support for users based on carbon sink estimation results and recovery potential optimization results includes:

[0016] A visualization model was created based on the carbon sink estimation results and the recovery potential optimization results.

[0017] When a user views a visualization model, a decision-making trigger network is dynamically deployed within the visualization model.

[0018] Based on decision-making thought processes, a network is triggered to assist users in initiating decision-making processes;

[0019] Plan the timing and strategies for decision support based on user-triggered decision-making processes;

[0020] When a user enters a decision support phase, appropriate decision support is provided to the user based on the decision support strategy.

[0021] Optionally, the dynamic deployment of the decision-making triggering network within the visualization model includes:

[0022] Whenever the first target point is generated within the visualization model, multiple decision-making approaches are matched based on the feature distribution of the target range within the visualization model. Among these, the user's viewpoint center intermittently stays at the first target point during the most recent first time period, and the ratio of the total duration of intermittent stays to the first time period exceeds a ratio threshold. The target range is the maximum viewpoint range when the user's viewpoint center stays at the first target point during the most recent first time period.

[0023] Multiple related idea nodes are distributed within the visualization model; among them, the same related idea node distribution contains multiple supporting element nodes of the same decision-making idea knowledge within the visualization model.

[0024] The distribution of all related thought nodes is combined to form a decision-making trigger network.

[0025] Optionally, the decision-based triggering network, which assists the user in triggering decision-making strategies, includes:

[0026] Continuously acquire the movement trajectory formed by the user's viewpoint center moving when viewing the visualization model in any future second time period;

[0027] Plot the number of surrounding nodes versus time curves for each associated thought node distribution in the decision-making thought triggering network; where the vertical axis of the number of surrounding nodes versus time curves represents the total number of supporting element nodes in the same associated thought node distribution surrounded by the minimum enclosing sphere of the movement trajectory, and the horizontal axis represents the corresponding enclosing time.

[0028] When the number of surrounding nodes minus the time curve of at least two related thought node distributions both show a peak and the time difference between the peaks does not exceed the time difference threshold, stop acquiring the movement trajectory and acquire the minimum enclosing sphere of the movement trajectory at the enclosing moment of the maximum peak to enclose the enclosed supporting element nodes and unenclosed supporting element nodes in the related thought node distribution corresponding to the maximum peak.

[0029] Match multiple standard association relationships and corresponding relationship weights between unenclosed support element nodes and enclosed support element nodes;

[0030] When any unenclosed support element node appears in the user's field of view of the visualization model in any future third time period, the standard association relationship corresponding to the newly appeared unenclosed support element node will be used as the target standard association relationship.

[0031] Zoom in on the viewing angle until all enclosed support element nodes that have a target standard correlation with the newly appearing unenclosed support element nodes appear;

[0032] The relationships of each target standard are mapped into the magnified field of view in descending order of their respective relationship weights. Each time a target standard relationship is mapped, the next target standard relationship is mapped when the user selects the target standard relationship.

[0033] When all target criteria relationships are selected by the user, the decision-making process for the distribution of associated thought nodes corresponding to the largest peak is triggered.

[0034] Optionally, the decision support timing and decision support strategies for planning user-triggered decision-making processes include:

[0035] Planning decision support timing includes: when the latest decision content of the user in the visualization model does not match the triggered decision thinking, and the user's current thinking back ability is lower than the ability threshold;

[0036] The planning decision support strategy includes: displaying to the user the decision support content for the first part of the decision-making process that matches the latest decision content before the latest decision content, as well as the second part of the decision-making process within the scope of the triggered decision-making process.

[0037] The steps for determining the user's current thought process reversal capability are as follows:

[0038] If, during the fourth time period, the supporting element nodes of the differences in the distribution of related thought nodes corresponding to the first and second locally consistent ideas in the triggered decision ideas continue to exceed the threshold duration and do not enter the user's field of view of the visualization model, the user's current thought return capability is counted as being lower than the preset target value of the capability threshold.

[0039] This invention provides an intelligent decision support system for estimating carbon sinks and optimizing the recovery potential of power transmission channels, comprising:

[0040] The carbon sink estimation and recovery potential optimization module is used to perform carbon sink estimation and recovery potential optimization on the transmission channel to obtain carbon sink estimation results and recovery potential optimization results.

[0041] The user intelligent decision support module is used to provide intelligent decision support to users based on carbon sink estimation results and recovery potential optimization results.

[0042] The present invention provides a computer-readable storage medium storing a computer program, wherein a processor executes the computer program to implement the method described in any of the above embodiments.

[0043] An electronic device provided by an embodiment of the present invention includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described in any of the above embodiments.

[0044] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0045] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0046] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0047] Figure 1 This is a flowchart of an intelligent decision support method for estimating and optimizing the carbon sink potential of power transmission channels, as described in an embodiment of the present invention.

[0048] Figure 2 This is a schematic diagram of an intelligent decision support system for estimating and optimizing the carbon sink potential of power transmission channels, as described in an embodiment of the present invention. Detailed Implementation

[0049] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0050] Example 1:

[0051] This invention provides an intelligent decision support method for estimating carbon sinks and optimizing the recovery potential of power transmission channels, such as... Figure 1 As shown, it includes:

[0052] S1. Perform carbon sink estimation and recovery potential optimization on the power transmission channels respectively to obtain carbon sink estimation results and recovery potential optimization results;

[0053] In S1, carbon sink refers to the ability of vegetation, soil, and other ecosystem components in the area traversed by the power transmission channel (such as the strip area of ​​the power line, the forest, grassland, wetland, etc.) to absorb, store, and fix carbon dioxide through natural processes; recovery potential refers to the ability of the ecosystem in the area traversed by the power transmission channel to restore its carbon absorption, carbon storage, and other ecosystem service functions after being damaged or disturbed; the system performs carbon sink estimation and recovery potential optimization on the power transmission channel separately, and obtains the corresponding carbon sink estimation results and recovery potential optimization results respectively;

[0054] S2. Based on carbon sink estimation results and recovery potential optimization results, provide intelligent decision support to users.

[0055] In S2, the carbon sink estimation results and recovery potential optimization results can serve as the basis for decision support, providing intelligent decision support for users to improve the carbon sink capacity and recovery potential of transmission channels.

[0056] This application performs carbon sink estimation and recovery potential optimization on power transmission channels to obtain carbon sink estimation results and recovery potential optimization results. Based on these results, it provides intelligent decision support to users, eliminating the need for users to manually perform carbon sink estimation and recovery potential optimization decisions. This provides users with effective automated intelligent decision support, greatly improving decision-making efficiency and reducing labor costs.

[0057] Example 2:

[0058] In one embodiment, during step S1, when estimating the carbon sink of the transmission channel, the following steps are performed:

[0059] S111, Obtain the basis for carbon sink estimation of power transmission channels;

[0060] In S111, the carbon sink estimation is based on at least the following: land type, land cover type, soil characteristics, preparation data, climate data, and historical land use in different areas of the transmission channel;

[0061] S112. Based on the carbon sink estimation model, carbon sink estimation is performed on the transmission channel according to the carbon sink estimation criteria to obtain the carbon sink estimation results.

[0062] In S112, the carbon sink estimation model is an artificial intelligence model that is trained by machine learning using a large number of historical records and human experience of carbon sink estimation based on carbon sink estimation criteria. It can automatically estimate the carbon sink of the transmission channel based on the carbon sink estimation criteria. The obtained carbon sink estimation results include at least: carbon absorption and carbon storage.

[0063] In this embodiment of the invention, when estimating the carbon sink of a power transmission channel, a carbon sink estimation model is introduced. Based on the carbon sink estimation criteria obtained for the power transmission channel, the carbon sink of the power transmission channel is estimated, and the final carbon sink estimation result is obtained, thereby improving the accuracy and efficiency of carbon sink estimation for power transmission channels.

[0064] Example 3:

[0065] In one embodiment, during step S1, when optimizing the recovery potential of the transmission channel, the following steps are performed:

[0066] S121. Optimize the recovery potential of power transmission channels;

[0067] In S121, the restoration potential optimization criteria include at least: land degradation status, vegetation loss degree, vegetation type, soil health status, and ecological function in different areas of the transmission channel; S122, based on the restoration potential optimization algorithm, the restoration potential of the transmission channel is optimized according to the restoration potential optimization criteria to obtain the restoration potential optimization results.

[0068] In S122, the recovery potential optimization algorithm includes recovery potential optimization results corresponding to different recovery potential optimization criteria pre-divided based on historical experience of transmission channel recovery potential optimization. These results can be used to determine the recovery potential optimization results corresponding to the chosen criteria. The recovery potential optimization results include at least: current recovery potential, optimal recovery measures, and implementation recommendations. Alternatively, the recovery potential optimization algorithm can also be an artificial intelligence algorithm trained using machine learning based on a large amount of historical experience of transmission channel recovery potential optimization.

[0069] In this embodiment of the invention, when optimizing the recovery potential of a power transmission channel, a recovery potential optimization algorithm is introduced. Based on the obtained recovery potential optimization criteria of the power transmission channel, the algorithm optimizes the recovery potential of the power transmission channel and finally obtains the recovery potential optimization result, thereby improving the accuracy and efficiency of optimizing the recovery potential of the power transmission channel.

[0070] Example 4:

[0071] In the decision-making process of enhancing carbon sequestration capacity and recovery potential, users often encounter complex information and situations, leading to unclear decision-making approaches. (For example, when selecting carbon sequestration projects, users may consider economic benefits, environmental impact, and social acceptance simultaneously, but due to a lack of clear prioritization, they may not be able to determine which factor is more important, ultimately choosing a solution that does not maximize carbon benefits.) This ambiguous decision-making approach may lead to inefficient decision-making processes or even erroneous decisions, thereby affecting the carbon management effectiveness of power transmission channels.

[0072] Secondly, the timing of decision support is crucial to ensuring its effectiveness. Providing decision support at an inappropriate time may lead to excessive information interference or delayed decision-making, affecting the quality and efficiency of the decision (for example, providing decision support too early may disrupt the user's judgment, while providing it too late may cause the best decision-making opportunity to be missed).

[0073] Therefore, to address the aforementioned issues, in one embodiment, step S2, providing intelligent decision support to the user based on carbon sink estimation results and recovery potential optimization results, includes:

[0074] S21. Based on the carbon sink estimation results and the recovery potential optimization results, create a visualization model;

[0075] In S21, when creating a visualization model, the carbon sink estimation results and recovery potential optimization results can be set in the corresponding model area of ​​the three-dimensional map model of the transmission channel according to their related transmission channel areas. Finally, the three-dimensional map model with all settings is used as the visualization model.

[0076] S22. When a user views a visualization model, a decision-making trigger network is dynamically deployed within the visualization model.

[0077] S23. Based on the decision-making process triggering network, assist users in triggering decision-making processes;

[0078] In S22 to S23, users can use smart terminals (such as mobile phones, tablets, etc.) to view the visualization model. When viewing the visualization model, they will have a vague idea of ​​how to improve the carbon sequestration capacity and recovery potential of the power transmission channel. The dynamically deployed decision-making triggering network helps them trigger a clear decision-making idea to improve decision-making efficiency.

[0079] S24. Decision support timing and strategies for planning user-triggered decision-making processes;

[0080] S25. When a user enters a decision support opportunity, provide the user with corresponding decision support based on the decision support strategy.

[0081] In S24 to S25, the decision support timing refers to the time when a user makes a decision on how to improve the carbon sequestration capacity and recovery potential of the transmission channel according to the triggered decision-making idea. The decision support strategy is the strategy applicable to provide decision support to the user under this timing. Therefore, when the user enters the decision support timing, the user is given corresponding decision support based on the decision support strategy.

[0082] This invention constructs a visualization model based on carbon sink estimation results and recovery potential optimization results, enabling users to clearly view various information related to carbon sink capacity and recovery potential in an intuitive 3D map model. Simultaneously, by dynamically deploying a decision-making trigger network within this visualization model, when users browse the model, the system triggers a rapid transition from vague ideas to clear decision-making processes, effectively clarifying decision logic, improving decision-making efficiency, avoiding erroneous decisions, and ultimately enhancing the carbon management effectiveness of power transmission channels. Furthermore, by planning the timing and strategies for decision support based on user-triggered decision-making processes, the system can accurately grasp the optimal timing for decision support, avoiding the negative impact of being too early or too late, ensuring that appropriate decision support strategies are provided when users enter the decision support phase, thereby significantly improving decision quality and efficiency.

[0083] Example 5:

[0084] In one embodiment, step S22, dynamically deploying a decision-making trigger network within the visualization model, includes:

[0085] S221. Whenever the first target point is generated within the visualization model, multiple decision-making ideas are matched based on the feature distribution of the target range within the visualization model. Among them, the user's viewpoint center intermittently stays at the first target point when viewing the visualization model in the most recent first time period, and the ratio of the total duration of the intermittent stay to the first time period exceeds the ratio threshold; the target range is the maximum viewpoint range when the user's viewpoint center stays at the first target point when viewing the visualization model in the most recent first time period.

[0086] S222. Multiple related idea nodes are distributed within the visualization model; wherein, the same related idea node distribution contains multiple supporting element nodes of the same decision-making idea knowledge within the visualization model.

[0087] In S221 to S222, the most recent first time period can be the most recent 5 minutes; when users view the visualization model, they view it through the perspective of terminal operation, which has a view center; the view center intermittently stays at the first target point, which means that the view center intermittently coincides with the first target point within a certain period of time, and the corresponding total duration of intermittent stay refers to the total time of coincidence; the ratio threshold can be 1 / 2; when users decide how to improve the carbon sequestration capacity and recovery potential of the transmission channel, they will make regional decisions on the transmission channel. When making decisions for a region, users will have a global view of the region and maintain this view for a relatively long time, and they will also have a local view of different local areas within the region. At this time, a first target point will be generated in the visualization model. This first target point is the view center of the user's global view of the region, and the target range is the range of the region;

[0088] The feature distribution of the target area includes at least: the type of geographic information within the target area, the type of information related to carbon sequestration capacity and recovery potential, etc. The matching decision-making knowledge indication feature distribution reflects the clear thinking that users should have when facing the target area to decide how to improve carbon sequestration capacity and recovery potential. For example, if the feature distribution reflects that the target area involves a forest and wetland boundary area, the wetland has a high carbon storage, but the forest area has been degraded due to logging, resulting in a low carbon storage, and the assessment shows that the wetland has a large recovery potential, then the clear thinking is to prioritize the decision on how to protect the wetland area, and at the same time implement artificial planting and management decisions for the degraded forest to maximize carbon sequestration capacity. The decision-making thinking has supporting element nodes in the visualization model. The supporting element nodes are model elements that reflect the clear thinking indicated by the decision-making knowledge. For example, if the clear thinking is to prioritize the decision on how to protect the wetland area, then the corresponding supporting element nodes are the location of the wetland area, the geographic information of the wetland area, etc. Multiple supporting element nodes of the same decision-making knowledge in the visualization model are combined into a related thinking node distribution. The related thinking node distribution represents the clear thinking indicated by the matched decision-making knowledge, which can be used to assist users in triggering decision-making thinking.

[0089] S223. Combine the distribution of each related idea node to form a decision-making idea trigger network.

[0090] In S223, the nodes of each related idea are ultimately distributed and combined to form a decision-making idea triggering network.

[0091] This invention, in its embodiments, dynamically deploys a decision-making trigger network by matching multiple decision-making thought knowledge points based on the feature distribution of the target range whenever a first target point is generated within the visualization model. This process continuously and specifically assists users in triggering decision-making thoughts, improving efficiency and significantly enhancing the user experience. Furthermore, by combining the intermittent dwell time of the user's viewpoint on the visualization model over a recent period to determine the first target point and the target range, these represent the user's global perspective and decision range for a specific area, subtly revealing the user's ambiguous thought process and improving the accuracy of subsequent dynamic deployment of the decision-making trigger network.

[0092] Example 6:

[0093] In one embodiment, S23, which assists the user in triggering decision-making strategies based on a decision-making network, includes:

[0094] S231. Continuously acquire the movement trajectory formed by the user's viewpoint center moving when viewing the visualization model in any second time period in the future;

[0095] In S231, any second time period in the future can be any time period of 100 seconds after the decision-making network is deployed; when the center of view moves, its corresponding position in the visualization model will also move, and this position movement forms a movement trajectory.

[0096] S232. Draw the number of surrounding nodes versus time curve for each associated thought node distribution in the decision-making thought triggering network; where the vertical axis of the number of surrounding nodes versus time curve is the total number of supporting element nodes in the same associated thought node distribution surrounded by the minimum surrounding sphere of the movement trajectory, and the horizontal axis is the corresponding surrounding time.

[0097] In S232, as time changes, the movement trajectory also changes continuously, and the total number of supporting element nodes in the distribution of nodes of the same related idea that are surrounded by the minimum enclosing sphere will also change. The total number and the enclosing time of the corresponding minimum enclosing sphere are mapped into a curve coordinate system with the total number on the vertical axis and the enclosing time on the horizontal axis to obtain multiple coordinate points. Connecting these coordinate points forms the number of enclosing nodes-time curve.

[0098] S233. When the number of surrounding nodes-time curves of at least two related thought node distributions both show peaks and the time difference between the peaks does not exceed the time difference threshold, stop acquiring the movement trajectory and acquire the minimum enclosing sphere of the movement trajectory at the enclosing moment of the maximum peak to enclose the enclosed support element nodes and unenclosed support element nodes in the related thought node distribution corresponding to the maximum peak.

[0099] In S233, when the number of surrounding nodes in the distribution of nodes with the same related thought process increases on the time curve, it means that the user's thought process is getting closer and closer to the thought process of the distribution of nodes with the same related thought process when making decisions in the future. When it is closest, a peak will appear. The time difference threshold can be 10 seconds. When the number of surrounding nodes in the distribution of nodes with the time curve of at least two related thought process distributions both show peaks and the time difference between the peaks does not exceed the time difference threshold, it means that the user's thought process when making decisions in a short period of time is closest to the thought process of at least two related thought process distributions. At this time, it is urgent to help the user clarify the thought process that is closer to the current one in order to determine a clear decision-making thought process as soon as possible. Therefore, the acquisition of the movement trajectory is stopped. The situation of the smallest enclosing sphere of the movement trajectory surrounding the supporting element nodes in the distribution of nodes with the corresponding related thought process at the moment of the largest peak is the key basis for helping the user clarify the thought process that is closer to the current one. The enclosed supporting element nodes are the supporting element nodes of the smallest enclosing sphere at that moment. Correspondingly, the unenclosed supporting element nodes are the unenclosed supporting element nodes.

[0100] S234. Match multiple standard association relationships and corresponding relationship weights between unenclosed support element nodes and enclosed support element nodes;

[0101] In S234, the standard association relationship refers to the association relationship between two supporting element nodes that allows users to consider the surrounding supporting element node to the non-surrounded supporting element node. For example, if the surrounding supporting element node is a high-carbon emission device that has already received user attention, while the non-surrounded supporting element node is a device that has not yet received user attention but may have an impact on carbon emissions, then the standard association relationship is a carbon emission source association. The relationship weight represents the extent to which the standard association relationship allows users to consider the non-surrounded supporting element node from the surrounding supporting element node, and can be preset in advance by technical personnel based on the actual capability. In S235, when any non-surrounded supporting element node newly appears in the user's field of view of the visualization model in any future third time period, the standard association relationship corresponding to the newly appeared non-surrounded supporting element node is taken as the target standard association relationship.

[0102] S236. Zoom in on the viewing angle until all enclosed support element nodes that have a target standard correlation with the newly appearing unenclosed support element nodes appear.

[0103] S237. Map each target standard relationship into the magnified view range in descending order of its respective relationship weight. Each time the user selects a target standard relationship to be mapped, the next target standard relationship is mapped.

[0104] S238. When all target standard relationships are selected by the user, the decision-making process of the distribution of the associated thought nodes corresponding to the maximum peak is triggered.

[0105] In S235 to S238, any future third time period can be any 80-second period after the standard association relationship and corresponding relationship weight matching are completed. When any unenclosed support element node newly appears in the user's field of view of the visualization model during any future third time period, it indicates that the user needs to consider unenclosed support element nodes from the already enclosed support element nodes. Therefore, the relevant target standard association relationship is determined, and the field of view is magnified until all enclosed support element nodes with target standard association relationships with the newly appeared unenclosed support element node appear. Each target standard association relationship is mapped into the magnified field of view in descending order of their respective relationship weights. Mapping means setting them into this field for the user to view. The user will try to consider the unenclosed support element nodes by viewing the mapped target standard association relationships. If it is confirmed that they need to be considered in subsequent decisions, the target standard association relationship is confirmed. Finally, when all target standard association relationships are confirmed by the user, the decision-making approach of the association idea node distribution corresponding to the largest peak is the approach that helps the user clarify, and it is triggered.

[0106] This invention, based on the user's movement trajectory formed by the shift of the viewpoint center of the visualization model during any future second time period, plots the number of surrounding nodes versus time curves for each associated thought node distribution in the decision-making triggering network. Based on the curve's peak characteristics, it quickly determines the timing for assisting the user in developing rational thinking, and prepares to provide assistance in triggering decision-making at the most appropriate time, greatly improving the effectiveness of assisting users in triggering decision-making. Secondly, by combining the situation of supporting element nodes in the associated thought node distribution corresponding to the maximum peak surrounded by the minimum surrounding sphere of the movement trajectory at the moment of the maximum peak's encirclement, multiple standard association relationships and corresponding relationship weights are matched. This helps the user consider both surrounded and unencircled supporting element nodes, greatly improving the accuracy, efficiency, and comprehensiveness of assisting users in triggering decision-making.

[0107] Example 7:

[0108] In one embodiment, S24, the decision support timing and decision support strategy for planning user-triggered decision-making approaches, includes:

[0109] S241. Planning decision support timing, including: the latest decision content of the user in the visualization model does not match the triggered decision thinking, and the user's current thinking back ability is lower than the ability threshold.

[0110] In S241, when a user makes a decision according to the triggered decision-making line, decision content will be continuously generated. If the latest decision content is inconsistent with the triggered decision-making line and the user's current line reversal ability is lower than the ability threshold, it means that the user needs decision support the most at this time, and this is the time for decision support. Line reversal ability is the user's ability to return from the current thinking or decision direction to the thinking point that was inconsistent with the triggered decision-making line during the decision-making process.

[0111] S242. Planning decision support strategy, including: displaying to the user the decision support content of the first part of the decision-making process that matches the latest decision content before the latest decision content, and the second part of the decision-making process within the scope of the triggered decision-making process.

[0112] In S242, before the user makes the latest decision, a previously decided content is generated. In the triggered decision-making process, there is a first partially consistent thought process. The first partially consistent thought process and the second partially consistent thought process within its subsequent thought process range (such as within two thought process steps) each have decision-making assistance content. The decision-making assistance content is content for the user to refer to in order to return to the corresponding partially consistent thought process for subsequent decisions, such as relevant thought guidance information, etc. When the user sees the decision-making assistance content, he will automatically rewind his thinking.

[0113] In step S241, the steps for determining the user's current thought process reversal capability are as follows:

[0114] S2411. When the difference supporting element node in the distribution of related thought nodes corresponding to the triggered decision thought continues to exceed the threshold duration and does not enter the user's field of view of the visualization model during the fourth time period, the user's current thought return capability is counted as a preset target value that is lower than the capability threshold.

[0115] In S2411, both the first and second locally consistent ideas have corresponding supporting element nodes in the distribution of associated idea nodes. The different supporting element nodes among the supporting element nodes of the two are called differential supporting element nodes. The threshold duration can be 120 seconds. The fourth time period is within 300 seconds after the user enters the decision support time. The preset target value is a value lower than the capability threshold. When the differential supporting element node does not enter the user's field of view of the visualization model for a longer period of time, it means that the user has not been able to revert to the previous idea for a long time. In this case, the user's current idea reversion capability is counted as the preset target value lower than the capability threshold.

[0116] This invention, in its embodiments, plans the timing of decision support by combining the user's latest decision content with the triggered decision-making process and the user's ability to reconsider their thought processes. It also plans decision support strategies by combining the decision support content of the first partially consistent thought process and the second partially consistent thought process within the subsequent thought process range. This significantly improves the accuracy, comprehensiveness, and efficiency of the timing of decision support for the user's triggered decision-making process and the planning of decision support strategies, thereby enhancing the system's applicability. Furthermore, it determines the ability to reconsider thought processes by combining the duration for which different support element nodes remain outside the user's field of view of the visualization model, improving the accuracy of determining the ability to reconsider thought processes.

[0117] Example 8:

[0118] This invention provides an intelligent decision support system for estimating carbon sinks and optimizing the recovery potential of power transmission channels, such as... Figure 2 As shown, it includes:

[0119] Carbon sink estimation and recovery potential optimization module 1 is used to perform carbon sink estimation and recovery potential optimization on the transmission channel to obtain carbon sink estimation results and recovery potential optimization results.

[0120] User intelligent decision support module 2 is used to provide intelligent decision support to users based on carbon sink estimation results and recovery potential optimization results.

[0121] Example 9:

[0122] The present invention provides a computer-readable storage medium storing a computer program, wherein a processor executes the computer program to implement the method described in any of the above embodiments.

[0123] Example 10:

[0124] An electronic device provided by an embodiment of the present invention includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described in any of the above embodiments.

[0125] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An intelligent decision support method for estimating carbon sinks and optimizing the recovery potential of power transmission channels, characterized in that, include: Carbon sink estimation and recovery potential optimization were performed on the power transmission channels to obtain carbon sink estimation results and recovery potential optimization results. Based on carbon sink estimation results and recovery potential optimization results, intelligent decision support is provided to users; The intelligent decision support for users based on carbon sink estimation results and recovery potential optimization results includes: A visualization model was created based on the carbon sink estimation results and the recovery potential optimization results. When a user views a visualization model, a decision-making trigger network is dynamically deployed within the visualization model. Based on decision-making thought processes, a network is triggered to assist users in initiating decision-making processes; Plan the timing and strategies for decision support based on user-triggered decision-making processes; When a user enters a decision support situation, appropriate decision support is provided to the user based on the decision support strategy. The dynamic deployment of the decision-making trigger network within the visualization model includes: Whenever the first target point is generated within the visualization model, multiple decision-making approaches are matched based on the feature distribution of the target range within the visualization model. Among these, the user's viewpoint center intermittently stays at the first target point during the most recent first time period, and the ratio of the total duration of intermittent stays to the first time period exceeds a ratio threshold. The target range is the maximum viewpoint range when the user's viewpoint center stays at the first target point during the most recent first time period. Multiple related idea nodes are distributed within the visualization model; among them, the same related idea node distribution contains multiple supporting element nodes of the same decision-making idea knowledge within the visualization model. The distribution of all related idea nodes is combined to form a decision-making idea triggering network; The decision-making triggering network, which assists users in triggering decision-making processes, includes: Continuously acquire the movement trajectory formed by the user's viewpoint center moving when viewing the visualization model in any future second time period; Plot the number of surrounding nodes versus time curves for each associated thought node distribution in the decision-making thought triggering network; where the vertical axis of the number of surrounding nodes versus time curves represents the total number of supporting element nodes in the same associated thought node distribution surrounded by the minimum enclosing sphere of the movement trajectory, and the horizontal axis represents the corresponding enclosing time. When the number of surrounding nodes minus the time curve of at least two related thought node distributions both show a peak and the time difference between the peaks does not exceed the time difference threshold, stop acquiring the movement trajectory and acquire the minimum enclosing sphere of the movement trajectory at the enclosing moment of the maximum peak to enclose the enclosed supporting element nodes and unenclosed supporting element nodes in the related thought node distribution corresponding to the maximum peak. Match multiple standard association relationships and corresponding relationship weights between unenclosed support element nodes and enclosed support element nodes; When any unenclosed support element node appears in the user's field of view of the visualization model in any future third time period, the standard association relationship corresponding to the newly appeared unenclosed support element node will be used as the target standard association relationship. Zoom in on the viewing angle until all enclosed support element nodes that have a target standard correlation with the newly appearing unenclosed support element nodes appear; The relationships of each target standard are mapped into the magnified field of view in descending order of their respective relationship weights. Each time a target standard relationship is mapped, the next target standard relationship is mapped when the user selects the target standard relationship. When all target criteria relationships are selected by the user, the decision-making process for the distribution of associated thought nodes corresponding to the largest peak is triggered.

2. The intelligent decision support method for estimating and optimizing the carbon sink potential of power transmission channels as described in claim 1, characterized in that, When estimating carbon sequestration for power transmission channels, the following steps should be performed: To obtain the basis for carbon sink estimation of power transmission channels; Based on the carbon sink estimation model, carbon sink estimation is performed on the transmission channel according to the carbon sink estimation criteria to obtain the carbon sink estimation results.

3. The intelligent decision support method for estimating and optimizing the carbon sink potential of power transmission channels as described in claim 1, characterized in that, When optimizing the recovery potential of transmission channels, the following steps are performed: Optimize the recovery potential of power transmission channels; Based on the recovery potential optimization algorithm, the recovery potential of the transmission channel is optimized according to the recovery potential optimization criteria to obtain the recovery potential optimization results.

4. The intelligent decision support method for estimating and optimizing the carbon sink potential of power transmission channels as described in claim 1, characterized in that, The decision support timing and strategies for user-triggered decision-making processes include: Planning decision support timing includes: when the latest decision content of the user in the visualization model does not match the triggered decision thinking, and the user's current thinking back ability is lower than the ability threshold; The planning decision support strategy includes: displaying to the user the decision support content for the first part of the decision-making process that matches the latest decision content before the latest decision content, as well as the second part of the decision-making process within the scope of the triggered decision-making process. The steps for determining the user's current thought process reversal capability are as follows: If, during the fourth time period, the supporting element nodes of the differences in the distribution of related thought nodes corresponding to the first and second locally consistent ideas in the triggered decision ideas continue to exceed the threshold duration and do not enter the user's field of view of the visualization model, the user's current thought return capability is counted as being lower than the preset target value of the capability threshold.

5. An intelligent decision support system for estimating carbon sinks and optimizing the recovery potential of power transmission channels, characterized in that, include: The carbon sink estimation and recovery potential optimization module is used to perform carbon sink estimation and recovery potential optimization on the transmission channel to obtain carbon sink estimation results and recovery potential optimization results. The user intelligent decision support module is used to provide intelligent decision support to users based on carbon sink estimation results and recovery potential optimization results. The intelligent decision support for users based on carbon sink estimation results and recovery potential optimization results includes: A visualization model was created based on the carbon sink estimation results and the recovery potential optimization results. When a user views a visualization model, a decision-making trigger network is dynamically deployed within the visualization model. Based on decision-making thought processes, a network is triggered to assist users in initiating decision-making processes; Plan the timing and strategies for decision support based on user-triggered decision-making processes; When a user enters a decision support situation, appropriate decision support is provided to the user based on the decision support strategy. The dynamic deployment of the decision-making trigger network within the visualization model includes: Whenever the first target point is generated within the visualization model, multiple decision-making approaches are matched based on the feature distribution of the target range within the visualization model. Among these, the user's viewpoint center intermittently stays at the first target point during the most recent first time period, and the ratio of the total duration of intermittent stays to the first time period exceeds a ratio threshold. The target range is the maximum viewpoint range when the user's viewpoint center stays at the first target point during the most recent first time period. Multiple related idea nodes are distributed within the visualization model; among them, the same related idea node distribution contains multiple supporting element nodes of the same decision-making idea knowledge within the visualization model. The distribution of all related idea nodes is combined to form a decision-making idea triggering network; The decision-making triggering network, which assists users in triggering decision-making processes, includes: Continuously acquire the movement trajectory formed by the user's viewpoint center moving when viewing the visualization model in any future second time period; Plot the number of surrounding nodes versus time curves for each associated thought node distribution in the decision-making thought triggering network; where the vertical axis of the number of surrounding nodes versus time curves represents the total number of supporting element nodes in the same associated thought node distribution surrounded by the minimum enclosing sphere of the movement trajectory, and the horizontal axis represents the corresponding enclosing time. When the number of surrounding nodes minus the time curve of at least two related thought node distributions both show a peak and the time difference between the peaks does not exceed the time difference threshold, stop acquiring the movement trajectory and acquire the minimum enclosing sphere of the movement trajectory at the enclosing moment of the maximum peak to enclose the enclosed supporting element nodes and unenclosed supporting element nodes in the related thought node distribution corresponding to the maximum peak. Match multiple standard association relationships and corresponding relationship weights between unenclosed support element nodes and enclosed support element nodes; When any unenclosed support element node appears in the user's field of view of the visualization model in any future third time period, the standard association relationship corresponding to the newly appeared unenclosed support element node will be used as the target standard association relationship. Zoom in on the viewing angle until all enclosed support element nodes that have a target standard correlation with the newly appearing unenclosed support element nodes appear; The relationships of each target standard are mapped into the magnified field of view in descending order of their respective relationship weights. Each time a target standard relationship is mapped, the next target standard relationship is mapped when the user selects the target standard relationship. When all target criteria relationships are selected by the user, the decision-making process for the distribution of associated thought nodes corresponding to the largest peak is triggered.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and the processor executes the computer program to implement the method as described in any one of claims 1-4.

7. An electronic device, characterized in that, The electronic device includes a memory and a processor, wherein the memory stores a computer program and the processor executes the computer program to implement the method as described in any one of claims 1-4.

Images