Ecological restoration planning implementation monitoring evaluation method based on multi-source data fusion technology

Abstract

The invention relates to the technical field of ecological restoration, in particular to an ecological restoration planning implementation monitoring and evaluation method based on a multi-source data fusion technology, and the method comprises the steps: collecting restoration indexes associated with a plurality of to-be-fused data sources from an ecological restoration cloud platform; collecting health data associated with the plurality of to-be-fused data sources from the plurality of ecological restoration historical records; the restoration indexes associated with the multiple to-be-fused data sources and the health data associated with the multiple to-be-fused data sources are input into the simulated deep learning architecture, restoration plan data associated with the multiple to-be-fused data sources are generated, and the restoration plan data comprise a current restoration index and a reference interval of the restoration index; and according to the recovery plan data associated with the plurality of to-be-fused data sources, completing evaluation of the plurality of to-be-fused data sources in the ecological restoration data table. The method can effectively improve the monitoring and evaluation quality, credibility and accuracy of ecological restoration planning implementation, and reduces monitoring and evaluation errors.

Description

Technical Field

[0001] The present application relates to the field of ecological restoration technology, and in particular to an ecological restoration planning implementation monitoring and evaluation method based on multi-source data fusion technology. Background Art

[0002] Ecological restoration is a comprehensive method of repairing polluted environment under the guidance of ecological principles, based on biological restoration, combined with various physical restoration, chemical restoration and engineering technical measures, and optimized combination to achieve the best effect and lowest cost. The smooth implementation of ecological restoration projects requires not only strengthening the management of project progress, safety, funds and acceptance, but also full-process supervision of ecological protection and restoration projects, and real-time grasp of the progress and effectiveness of ecological restoration, so as to timely adjust the progress and restoration plan of ecological restoration projects.

[0003] In the prior art, ecological restoration data is monitored and evaluated by implementing artificial ecological restoration planning, that is, professionals manually input monitoring and evaluation information. This method has the problems of low labeling efficiency, difficulty in ensuring the quality of monitoring and evaluation, and is easily affected by human factors.

[0004] This shows that a more efficient and accurate planning implementation monitoring and evaluation method and system is needed to support the construction and application of ecological restoration. Summary of the invention

[0005] To achieve the above objectives, this application provides the following technical solutions:

[0006] According to the first aspect of the present invention, the present invention claims a method for monitoring and evaluating the implementation of ecological restoration planning based on multi-source data fusion technology, comprising:

[0007] Collect restoration indicators associated with each of the multiple data sources to be fused from the ecological restoration cloud platform, and collect health data associated with each of the multiple data sources to be fused from multiple ecological restoration historical records;

[0008] Inputting the restoration indexes associated with each of the plurality of data sources to be fused and the health data associated with each of the plurality of data sources to be fused into the simulated deep learning architecture, generating restoration plan data associated with each of the plurality of data sources to be fused, wherein the restoration plan data includes the current restoration index and a reference interval of the restoration index;

[0009] Based on the restoration plan data associated with each of the multiple data sources to be integrated, the multiple data sources to be integrated in the ecological restoration data table are evaluated.

[0010] Furthermore, the restoration indicators associated with each of the multiple data sources to be integrated are collected from the ecological restoration cloud platform, including:

[0011] Collect candidate restoration indicators associated with multiple data sources to be integrated from the ecological restoration cloud platform;

[0012] Preprocessing is performed on the candidate repair indicators, blank indicators in the candidate repair indicators are ignored, and invalid indicators in the candidate repair indicators are ignored; wherein the invalid indicators refer to data far away from the valid interval.

[0013] Furthermore, the health data associated with each of the multiple data sources to be integrated are collected from the multiple ecological restoration historical records, including:

[0014] Selecting at least one target historical record mapped to the ecological restoration cloud platform from the plurality of ecological restoration historical records;

[0015] Complete semantic detection on the at least one target historical record, and output health data associated with each of the multiple data sources to be fused.

[0016] Furthermore, the method further comprises:

[0017] Collecting a simulation log set and a test log set, wherein the simulation log set includes the repair indicators, health data, and actual recovery plan data associated with each of the multiple first data sources to be fused, and the test log set includes the repair indicators, health data, and actual recovery plan data associated with each of the multiple second data sources to be fused;

[0018] The candidate deep learning architecture is simulated according to the repair indicators, health data, and actual recovery plan data associated with each of the plurality of first data sources to be fused;

[0019] The confidence of the candidate deep learning architecture is determined by using the repair indicators, health data, and actual recovery plan data associated with each of the multiple second data sources to be fused. If the confidence is less than a preset threshold value, the candidate deep learning architecture is corrected until the confidence is not less than the preset threshold value, and the simulated deep learning architecture is output.

[0020] Furthermore, the collection of simulation log sets and test log sets includes:

[0021] For each first data source to be fused, the restoration indicators associated with the first data source to be fused are collected from the ecological restoration cloud platform, and the health data associated with the first data source to be fused are collected from multiple ecological restoration historical records, and the actual restoration plan data associated with the first data source to be fused are collected through manual evaluation, and the simulation log set is output;

[0022] For each second data source to be fused, the restoration indicators associated with the second data source to be fused are collected from the ecological restoration cloud platform, and the health data associated with the second data source to be fused are collected from multiple ecological restoration historical records, and the actual restoration plan data associated with the second data source to be fused are collected through manual evaluation, and the test log set is output.

[0023] Furthermore, the simulation of the candidate deep learning architecture is completed according to the repair indicators, health data, and actual recovery plan data associated with each of the plurality of first data sources to be fused, including:

[0024] Inputting the repair indicators and health data associated with each first data source to be fused into the candidate deep learning architecture, and outputting the evaluation recovery plan data of each first data source to be fused;

[0025] The candidate deep learning architecture is simulated according to the evaluated recovery plan data of each first data source to be fused and the actual recovery plan data of each first data source to be fused.

[0026] The present application relates to the field of ecological restoration technology, and in particular to an ecological restoration planning implementation monitoring and evaluation method based on multi-source data fusion technology, wherein the restoration indicators associated with each of the multiple data sources to be fused are collected from the ecological restoration cloud platform, and the health data associated with each of the multiple data sources to be fused are collected from multiple ecological restoration historical records; the restoration indicators associated with each of the multiple data sources to be fused and the health data associated with each of the multiple data sources to be fused are input into a simulated deep learning architecture, and restoration plan data associated with each of the multiple data sources to be fused are generated, wherein the restoration plan data includes the current restoration indicators and the reference interval of the restoration indicators; and the multiple data sources to be fused in the ecological restoration data table are evaluated based on the restoration plan data associated with each of the multiple data sources to be fused. The present invention can effectively improve the quality, credibility and accuracy of monitoring and evaluation of the implementation of ecological restoration planning, and reduce monitoring and evaluation errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram of an application scenario of the ecological restoration planning implementation monitoring and evaluation method based on multi-source data fusion technology claimed in the embodiment of the present application;

[0028] Figure 2 A workflow diagram of the ecological restoration planning implementation monitoring and evaluation method based on multi-source data fusion technology claimed in the embodiment of the present application;

[0029] Figure 3 A second workflow diagram of the ecological restoration planning implementation monitoring and evaluation method based on multi-source data fusion technology claimed in the embodiment of the present application;

[0030] Figure 4 This is a schematic diagram of the structure of the ecological restoration planning implementation monitoring and evaluation device based on multi-source data fusion technology that is requested to be protected in the embodiments of the present application. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. According to the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0032] The terms "first", "second" and "third" in this application are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first", "second" and "third" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of this application are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, cloud platform, product or data source to be fused that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or data sources to be fused.

[0033] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0034] Figure 1 Schematic diagram of the application scenario of the ecological restoration planning implementation monitoring and evaluation method based on multi-source data fusion technology provided in the embodiment of the present disclosure. Figure 1As shown, it can be applied to the scenario of completing data evaluation for multiple data sources to be fused in the ecological restoration data table. Data transmission between the display terminal 101 and the server 102 can be completed by wired or wireless means. Exemplarily, the display terminal 101 can send an ecological restoration planning implementation monitoring and evaluation request based on multi-source data fusion technology to the server 102. The server 102 receives the evaluation request, completes the evaluation of the ecological restoration data table through the ecological restoration planning implementation monitoring and evaluation method based on multi-source data fusion technology provided by the embodiment of the present disclosure, and outputs the evaluated ecological restoration data table. The server 102 returns the evaluated ecological restoration data table to the display terminal 101, and displays the ecological restoration data table through the display terminal 101, providing intelligent support and decision-making reference for industrial and mining production.

[0035] The following specific embodiments are combined with the accompanying drawings to describe the technical solution of the present application in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0036] Figure 2 The process of the ecological restoration planning implementation monitoring and evaluation method based on multi-source data fusion technology provided in the embodiment of the present disclosure Figure 1 The execution subject of the method in the embodiment of the present application can be a terminal or a server; the embodiment of the present application takes the execution subject as a server as an example to complete the description. Figure 2 As shown in the figure, the ecological restoration planning implementation monitoring and evaluation method based on multi-source data fusion technology includes:

[0037] S201. Collect restoration indicators associated with each of the multiple data sources to be integrated from the ecological restoration cloud platform, and collect health data associated with each of the multiple data sources to be integrated from multiple ecological restoration historical records.

[0038] In the disclosed embodiment, the ecological restoration cloud platform may be an industrial and mining production cloud platform. For example, a coal mine production cloud platform. The ecological restoration cloud platform includes multiple data sources to be fused. For example, transmission of data sources to be fused, classification of data sources to be fused, detection of data sources to be fused, etc. The restoration index of the data source to be fused may be any index of the power, voltage, rotation speed, temperature, etc. of the data source to be fused.

[0039] In some embodiments, the multiple ecological restoration historical records may be multiple historical records related to the ecological restoration cloud platform in an Internet database. Accordingly, collecting health data associated with each of the multiple data sources to be fused from the multiple ecological restoration historical records may include: selecting at least one target historical record mapped to the ecological restoration cloud platform from the multiple ecological restoration historical records; completing semantic detection on the at least one target historical record, and outputting health data associated with each of the multiple data sources to be fused.

[0040] It should be noted that after collecting the original data associated with multiple data sources to be fused, pre-processing operations such as cleaning and denoising can be performed on the original data to ensure the quality and integrity of the data.

[0041] In some embodiments, restoration indicators associated with each of multiple data sources to be fused are collected from the ecological restoration cloud platform, including: collecting candidate restoration indicators associated with each of multiple data sources to be fused from the ecological restoration cloud platform; preprocessing the candidate restoration indicators, ignoring blank indicators in the candidate restoration indicators, and ignoring invalid indicators in the candidate restoration indicators; wherein invalid indicators refer to data far away from the valid interval.

[0042] S202. Input the repair indicators associated with each of the multiple data sources to be fused and the health data associated with each of the multiple data sources to be fused into the simulated deep learning architecture to generate recovery plan data associated with each of the multiple data sources to be fused, wherein the recovery plan data includes the current repair indicator and the reference range of the repair indicator.

[0043] The deep learning architecture may be a machine learning architecture, a deep learning architecture, etc. The input feature information of the deep learning architecture includes: the repair index of the data source to be fused, and the health data of the data source to be fused. The output feature information includes: the current repair index and the reference interval of the repair index.

[0044] For example, for the transmission data source to be fused in the coal mine production cloud platform. The output feature information includes: the current power of the transmission data source to be fused is 2000 watts, the optimal performance power is 2500 watts, and the power of the transmission data source to be fused needs to be corrected. The current load capacity of the belt in the transmission data source to be fused is 400 kilograms, and the maximum belt load capacity is 500 watts, which has not exceeded the warning. The current speed of the motor in the transmission data source to be fused is 2000 revolutions per second, and the maximum speed is 3000 revolutions per second, which has not exceeded the warning.

[0045] S203. Based on the restoration plan data associated with each of the multiple data sources to be integrated, evaluate the multiple data sources to be integrated in the ecological restoration data table.

[0046] In some embodiments, the ecological restoration data table includes icons associated with multiple data sources to be fused. Completing the evaluation of multiple data sources to be fused in the ecological restoration data table includes: associating the icons of the data sources to be fused associated with each data source to be fused in the ecological restoration data table with the restoration plan data associated with each data source to be fused. The restoration plan data can be displayed at any position around the icons of the data sources to be fused.

[0047] Optionally, when the user clicks the icon of the data source to be fused, the restoration plan data of the data source to be fused can be displayed in the ecological restoration data table. For example, when the user clicks the belt icon in the data source to be fused, the restoration plan data is displayed on the upper side of the belt icon: the current load capacity is 400 kg, the maximum belt load capacity is 500 watts, and it has not exceeded the warning.

[0048] It should be noted that, based on the restoration plan data associated with each of the multiple data sources to be fused, the multiple data sources to be fused in the ecological restoration data table are evaluated, and the evaluated ecological restoration data table is output. At this point, Ha can complete a manual review of the ecological restoration data table to improve the accuracy of the ecological restoration data table. Furthermore, the deep learning architecture can be optimized based on the manual review results.

[0049] The present application provides a method for monitoring and evaluating the implementation of ecological restoration planning based on multi-source data fusion technology, including: collecting restoration indicators associated with each of multiple data sources to be fused from an ecological restoration cloud platform, and collecting health data associated with each of multiple data sources to be fused from multiple ecological restoration historical records; inputting the restoration indicators associated with each of multiple data sources to be fused and the health data associated with each of multiple data sources to be fused into a simulated deep learning architecture, generating restoration plan data associated with each of multiple data sources to be fused, wherein the restoration plan data includes the current restoration indicator and the reference interval of the restoration indicator; and completing the evaluation of multiple data sources to be fused in the ecological restoration data table based on the restoration plan data associated with each of multiple data sources to be fused. In an embodiment of the present application, since the restoration plan data associated with each of multiple data sources to be fused is automatically generated through a deep learning architecture, the automatic evaluation of the ecological restoration data table is realized, the evaluation quality of industrial and mining ecological restoration data is improved, and evaluation errors are reduced, thereby improving the credibility and accuracy of the evaluation of the data. At the same time, the present application can also speed up the construction of data tables, reduce labor costs and time costs, and improve the economic benefits of data table construction, which has obvious cost advantages for enterprises.

[0050] Figure 3 The process of the simulation method of the deep learning architecture provided in the embodiment of the present disclosure Figure 1 In the embodiment of the present disclosure, the simulation method of the deep learning architecture in step S202 is specifically described. Figure 3 As shown, the simulation method of the deep learning architecture includes:

[0051] S301. Collect a simulation log set and a test log set, wherein the simulation log set includes repair indicators, health data, and actual recovery plan data associated with each of the multiple first data sources to be fused, and the test log set includes repair indicators, health data, and actual recovery plan data associated with each of the multiple second data sources to be fused.

[0052] In some embodiments, a simulation log set and a test log set are collected, including: for each first data source to be fused, the restoration indicators associated with the first data source to be fused are collected from the ecological restoration cloud platform, and, health data associated with the first data source to be fused are collected from multiple ecological restoration historical records, and, actual recovery plan data associated with the first data source to be fused are collected through manual evaluation, and a simulation log set is output; for each second data source to be fused, the restoration indicators associated with the second data source to be fused are collected from the ecological restoration cloud platform, and, health data associated with the second data source to be fused are collected from multiple ecological restoration historical records, and, actual recovery plan data associated with the second data source to be fused are collected through manual evaluation, and a test log set is output.

[0053] S302. Complete simulation of the candidate deep learning architecture according to the repair indicators, health data, and actual recovery plan data associated with each of the multiple first data sources to be fused.

[0054] In some embodiments, a candidate deep learning architecture is simulated based on the repair indicators, health data, and actual recovery plan data associated with each of the multiple first data sources to be fused, including: inputting the repair indicators and health data associated with each of the first data sources to be fused into the candidate deep learning architecture, and outputting the evaluated recovery plan data of each first data source to be fused; and simulating the candidate deep learning architecture based on the evaluated recovery plan data of each first data source to be fused and the actual recovery plan data of each first data source to be fused.

[0055] It should be noted that when the repair indicators and health data associated with each first data source to be fused are input into the candidate deep learning architecture, the repair indicators and health data associated with each first data source to be fused can be converted into a form suitable for processing by the machine learning algorithm to improve the efficiency of the architecture simulation.

[0056] S303. Determine the confidence of the candidate deep learning architecture through the repair indicators, health data, and actual recovery plan data associated with each of the multiple second data sources to be fused. If the confidence is less than a preset threshold value, the candidate deep learning architecture is corrected until the confidence is not less than the preset threshold value, and the simulated deep learning architecture is output.

[0057] In the embodiment of the present disclosure, the value of the preset threshold value is not specifically limited, and can be set and modified as needed. Optionally, the preset threshold value can be 85%, 90%, 95%, etc.

[0058] It should be noted that this method can also be combined with an evaluation result fusion mechanism to merge the results of manual evaluation and automated evaluation, thereby improving the accuracy and credibility of the overall evaluation.

[0059] Figure 4 This is a schematic diagram of the structure of the ecological restoration planning implementation monitoring and evaluation device based on multi-source data fusion technology provided in the embodiment of the present application. Figure 4 As shown, the ecological restoration planning implementation monitoring and evaluation device based on multi-source data fusion technology includes: a collection module 401, a generation module 402 and an evaluation module 403.

[0060] The collection module 401 is used to collect restoration indicators associated with each of the multiple data sources to be fused from the ecological restoration cloud platform, and to collect health data associated with each of the multiple data sources to be fused from multiple ecological restoration historical records;

[0061] A generation module 402 is used to input the restoration indexes associated with each of the multiple data sources to be fused and the health data associated with each of the multiple data sources to be fused into the simulated deep learning architecture, and generate restoration plan data associated with each of the multiple data sources to be fused, wherein the restoration plan data includes the current restoration index and the reference interval of the restoration index;

[0062] The evaluation module 403 is used to evaluate the multiple data sources to be integrated in the ecological restoration data table according to the restoration plan data associated with each of the multiple data sources to be integrated.

[0063] In one possible implementation, the collection module 401 collects restoration indicators associated with each of the multiple data sources to be fused from the ecological restoration cloud platform, specifically including: collecting candidate restoration indicators associated with each of the multiple data sources to be fused from the ecological restoration cloud platform; completing preprocessing of the candidate restoration indicators, ignoring blank indicators in the candidate restoration indicators, and ignoring invalid indicators in the candidate restoration indicators; wherein the invalid indicators refer to data far away from the valid interval.

[0064] In one possible implementation, the collection module 401 collects health data associated with each of the multiple data sources to be fused from multiple ecological restoration historical records, specifically including: selecting at least one target historical record mapped to the ecological restoration cloud platform from the multiple ecological restoration historical records; completing semantic detection on the at least one target historical record, and outputting the health data associated with each of the multiple data sources to be fused.

[0065] In a possible implementation, the evaluation device also includes: a simulation module; the simulation module is used to collect a simulation log set and a test log set, wherein the simulation log set includes repair indicators, health data, and actual recovery plan data associated with each of the multiple first data sources to be fused, and the test log set includes repair indicators, health data, and actual recovery plan data associated with each of the multiple second data sources to be fused; according to the repair indicators, health data, and actual recovery plan data associated with each of the multiple first data sources to be fused, the candidate deep learning architecture is simulated; the confidence of the candidate deep learning architecture is determined by the repair indicators, health data, and actual recovery plan data associated with each of the multiple second data sources to be fused, and if the confidence is less than a preset threshold value, the candidate deep learning architecture is corrected until the confidence is not less than the preset threshold value, and the simulated deep learning architecture is output.

[0066] In one possible implementation, the simulation module collects a simulation log set and a test log set, specifically including: for each first data source to be fused, collecting the restoration indicators associated with the first data source to be fused from the ecological restoration cloud platform, and, collecting the health data associated with the first data source to be fused from multiple ecological restoration historical records, and, collecting the actual restoration plan data associated with the first data source to be fused through manual evaluation, and outputting the simulation log set; for each second data source to be fused, collecting the restoration indicators associated with the second data source to be fused from the ecological restoration cloud platform, and, collecting the health data associated with the second data source to be fused from multiple ecological restoration historical records, and, collecting the actual restoration plan data associated with the second data source to be fused through manual evaluation, and outputting the test log set.

[0067] In one possible implementation, the simulation module completes the simulation of the candidate deep learning architecture based on the repair indicators, health data, and actual recovery plan data associated with each of the multiple first data sources to be fused, specifically including: inputting the repair indicators and health data associated with each of the first data sources to be fused into the candidate deep learning architecture, and outputting the evaluated recovery plan data of each first data source to be fused; completing the simulation of the candidate deep learning architecture based on the evaluated recovery plan data of each first data source to be fused and the actual recovery plan data of each first data source to be fused.

[0068] The ecological restoration planning implementation monitoring and evaluation device based on multi-source data fusion technology provided in the embodiment of the present application can be used to execute the technical solution of the ecological restoration planning implementation monitoring and evaluation method based on multi-source data fusion technology in the above-mentioned embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0069] In the several embodiments provided in the present application, it should be understood that the disclosed cloud platform, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another cloud platform, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0070] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated units may be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application, and does not limit the patent range of the present application. Any equivalent structure or equivalent process transformation made using the contents of the specification and drawings of this application, or directly or indirectly used in other related technical fields, are also included in the patent protection range of the present application.

[0071] The above detailed description of the specific implementation of the invention is only used as an example, and the present application is not limited to the specific implementation described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the present application. Therefore, the equalization, modification, improvement, etc. made without departing from the spirit and principle of the present application should be included in the scope of the present application.

Claims

1. A monitoring and evaluation method for the implementation of ecological restoration planning based on multi-source data fusion technology, characterized in that: include: Collect restoration indicators associated with each of the multiple data sources to be fused from the ecological restoration cloud platform, and collect health data associated with each of the multiple data sources to be fused from multiple ecological restoration historical records; Inputting the restoration indexes associated with each of the plurality of data sources to be fused and the health data associated with each of the plurality of data sources to be fused into the simulated deep learning architecture, generating restoration plan data associated with each of the plurality of data sources to be fused, wherein the restoration plan data includes the current restoration index and a reference interval of the restoration index; Based on the restoration plan data associated with each of the multiple data sources to be integrated, the multiple data sources to be integrated in the ecological restoration data table are evaluated.

2. The method for monitoring and evaluating the implementation of ecological restoration planning based on multi-source data fusion technology as claimed in claim 1, characterized in that: The restoration indicators associated with each of the multiple data sources to be integrated are collected from the ecological restoration cloud platform, including: Collect candidate restoration indicators associated with multiple data sources to be integrated from the ecological restoration cloud platform; Preprocessing is performed on the candidate repair indicators, blank indicators in the candidate repair indicators are ignored, and invalid indicators in the candidate repair indicators are ignored; wherein the invalid indicators refer to data far away from the valid interval.

3. The method for monitoring and evaluating the implementation of ecological restoration planning based on multi-source data fusion technology as claimed in claim 1, characterized in that: The health data associated with each of the multiple data sources to be fused are collected from the multiple ecological restoration historical records, including: Selecting at least one target historical record mapped to the ecological restoration cloud platform from the plurality of ecological restoration historical records; Complete semantic detection on the at least one target historical record, and output health data associated with each of the multiple data sources to be fused.

4. The method for monitoring and evaluating the implementation of ecological restoration planning based on multi-source data fusion technology according to claim 1, characterized in that: Also includes: Collecting a simulation log set and a test log set, wherein the simulation log set includes the repair indicators, health data, and actual recovery plan data associated with each of the multiple first data sources to be fused, and the test log set includes the repair indicators, health data, and actual recovery plan data associated with each of the multiple second data sources to be fused; The candidate deep learning architecture is simulated according to the repair indicators, health data, and actual recovery plan data associated with each of the plurality of first data sources to be fused; The confidence of the candidate deep learning architecture is determined by using the repair indicators, health data, and actual recovery plan data associated with each of the multiple second data sources to be fused. If the confidence is less than a preset threshold value, the candidate deep learning architecture is corrected until the confidence is not less than the preset threshold value, and the simulated deep learning architecture is output.

5. The method for monitoring and evaluating the implementation of ecological restoration planning based on multi-source data fusion technology as claimed in claim 4, characterized in that: The collection of simulation log sets and test log sets includes: For each first data source to be fused, the restoration indicators associated with the first data source to be fused are collected from the ecological restoration cloud platform, and the health data associated with the first data source to be fused are collected from multiple ecological restoration historical records, and the actual restoration plan data associated with the first data source to be fused are collected through manual evaluation, and the simulation log set is output; For each second data source to be fused, the restoration indicators associated with the second data source to be fused are collected from the ecological restoration cloud platform, and the health data associated with the second data source to be fused are collected from multiple ecological restoration historical records, and the actual restoration plan data associated with the second data source to be fused are collected through manual evaluation, and the test log set is output.

6. The method for monitoring and evaluating the implementation of ecological restoration planning based on multi-source data fusion technology as claimed in claim 4, characterized in that: The method of completing the simulation of the candidate deep learning architecture according to the repair indicators, health data, and actual recovery plan data associated with each of the plurality of first data sources to be fused includes: Inputting the repair indicators and health data associated with each first data source to be fused into the candidate deep learning architecture, and outputting the evaluation recovery plan data of each first data source to be fused; The candidate deep learning architecture is simulated according to the evaluated recovery plan data of each first data source to be fused and the actual recovery plan data of each first data source to be fused.

Images