Digital mine management method and management platform based on twinborn model

Abstract

The invention provides a digital mine management method and management platform based on a twinborn model, and belongs to the technical field of data processing, and the method specifically comprises the steps: obtaining the data size of associated collection data when different variation sub-models carry out model updating processing, and combining the model variation frequency coefficients of the different variation sub-models, determining change data of different change sub-models in different unit durations on the basis of change conditions of associated acquisition data of different change sub-models in different unit durations when it is determined that the digital twin model cannot adopt a preset updating strategy; according to the method, the reference period of model updating of the digital twin model is determined by using the variation data, and in the reference period, the updating processing strategy of the digital twin model is determined according to the analysis result of the associated acquisition data of different variation sub-models, so that the matching degree of the digital twin model and a mine is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of digital twins, and in particular relates to a digital mine management method and management platform based on a twin model. Background Art

[0002] The mine covers a large area and has a large number of mining equipment, making the management of the mine difficult. Specifically, in order to achieve the management of the mine, the invention patent application CN202410605769.X "A smart mine safety detection method and system based on digital twins" builds a digital twin system of the mine, which can realize visual display and warning workers, thereby solving the problem of backward safety detection in mining in the prior art. However, there are the following technical problems: In the process of constructing the digital twin model of a digital mine, as the mining data changes, the mine data will also change accordingly. Therefore, if a fixed digital twin model is used, it is often impossible to accurately reflect the actual mine status, and thus it is impossible to ensure the matching of the digital twin model with the mine.

[0003] In response to the above technical problems, the present application specifically provides a digital mine management method and management platform based on a twin model. Summary of the invention

[0004] To achieve the purpose of the present invention, the present invention adopts the following technical solutions: According to one aspect of the present invention, a digital mine management method based on a twin model is provided.

[0005] A digital mine management method based on a twin model, specifically comprising: S1 obtains the sub-models in the digital twin model corresponding to the digital mine, and determines the model change frequency coefficients and the changed sub-models of the different sub-models based on the analysis results of the associated collected data of the different sub-models; S2 obtains the amount of data associated with the collected data of different variable sub-models when performing model update processing, and combines the model change frequency coefficients of different variable sub-models to determine that the digital twin model cannot adopt the preset update strategy, and then proceeds to the next step; S3 determines the change data of different change sub-models within different unit time lengths based on the change of associated collected data of different change sub-models within different unit time lengths, and uses the change data to determine the reference period for model update of the digital twin model; S4: When within the reference period, the update processing strategy of the digital twin model is determined based on the analysis results of the associated collected data of different variable sub-models.

[0006] The beneficial effects of the present invention are: By utilizing the change data of different change sub-models within different unit time lengths to determine the benchmark period for model update of the digital twin model, it not only avoids the emergence of technical problems caused by the high complexity of update processing due to frequent update processing of the digital twin model, but also further combines the change data of different change sub-models within different unit time lengths to achieve the determination of the benchmark period based on the unit time length with a higher probability of change, thereby improving the reliability of the model update processing.

[0007] The update processing strategy of the digital twin model is determined based on the analysis results of the associated collected data of different variable sub-models, which realizes the determination of the update processing strategy based on the changes in the key collected data of different variable sub-models. This not only ensures the matching degree between the digital twin model and the real mine, but also avoids the emergence of technical problems such as the difficulty of update processing caused by frequent update processing of the digital twin model.

[0008] A further technical solution is that the sub-model includes environmental models of a mining area, a processing area and a mineral storage area.

[0009] A further technical solution is that the associated collected data is determined according to the data type of the environmental monitoring data of the mining area corresponding to the sub-model.

[0010] A further technical solution is that the method for determining the model change frequency coefficient of the sub-model is: Determine the change of the associated collected data of the sub-model on different dates based on the analysis result of the associated collected data corresponding to the sub-model; Determine the date on which the model needs to be updated according to the change and the preset change threshold, and use it as the model change date; The model change frequency coefficient of the sub-model is determined by the proportion of the model change dates in the dates.

[0011] A further technical solution is that the variable sub-model is a sub-model whose model variable frequency coefficient is greater than a preset frequency coefficient threshold.

[0012] A further technical solution is that the method for determining the update processing strategy of the digital twin model is: The analysis results of the associated collected data of different variable sub-models are combined with the preset change amount threshold to determine the variable sub-model that needs to be updated, and the variable sub-model that needs to be updated is used as the matching deviation sub-model, and the model matching deviation coefficient of the digital twin model is determined by the proportion of the number of matching deviation sub-models; Determine the variation deviation coefficient of the associated collected data of different variation sub-models by the deviation amount of the variation amount of the associated collected data of different variation sub-models from the preset variation threshold and the ratio of the variation amount to the preset variation threshold, and determine the variation deviation coefficient average value by using the average value of the variation deviation coefficients; A model update requirement coefficient is determined according to the ratio of the model matching deviation coefficient to the average value of the variation deviation coefficient of the digital twin model, and an update processing strategy of the digital twin model is determined using the model update requirement coefficient.

[0013] A further technical solution is to use the model update requirement coefficient to determine the update processing strategy of the digital twin model, specifically including: When the model update requirement coefficient is greater than a preset update requirement coefficient threshold, the update processing strategy of the digital twin model is determined to be a full update processing; When the model update requirement coefficient is not greater than a preset update requirement coefficient threshold, the update processing strategy of the digital twin model is determined to update the matching deviation sub-model.

[0014] In a second aspect, the present invention provides a management platform, which adopts the above-mentioned digital mine management method based on the twin model, and specifically includes: Data acquisition module, digital twin model update module; The data acquisition module is responsible for collecting and processing the associated collected data of different sub-models in the digital twin model; The digital twin model update module is responsible for updating the digital twin model according to the update processing strategy.

[0015] Other features and advantages will be described in the following description. The objects and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0016] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and other features and advantages of the present invention will become more apparent by describing in detail example embodiments thereof with reference to the accompanying drawings; Figure 1 It is a flow chart of a digital mine management method based on a twin model; Figure 2 is a flow chart of a method for determining a model change frequency coefficient of a sub-model; Figure 3 It is a flow chart to determine that the digital twin model cannot adopt the preset update strategy; Figure 4 It is a flow chart of a method for determining a reference period for model updating of a digital twin model; Figure 5 It is a framework diagram of a management platform. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0019] In the process of constructing the digital twin model of the digital mine, as the mining data changes, different indicators in the mine's environmental data will also change accordingly. Therefore, if a fixed digital twin model is used, it is often impossible to accurately reflect the actual mine status, and thus it is impossible to guarantee the matching of the digital twin model with the mine, and thus it is impossible to guarantee the reliability of mine management.

[0020] Model change frequency coefficient of the sub-model: determine the duration that the model needs to be updated on different dates based on the changes in the associated collected data of the sub-model on different dates and the preset change threshold, and use the ratio of the duration that the model needs to be updated on different dates to the preset duration to determine the model change frequency on different dates, and determine the model change frequency coefficient of the sub-model by taking the average of the model change frequencies on different dates, where when the model change frequency coefficient is greater than 0.6, the sub-model is determined to be a variable sub-model.

[0021] Determine that the digital twin model cannot adopt the preset update strategy: based on the model change frequency coefficient of the changing sub-model, determine the changing sub-model with the largest model change frequency coefficient, and use it as the benchmark sub-model, and determine the benchmark update period of the digital twin model corresponding to the model change frequency coefficient based on the model change frequency coefficient of the benchmark sub-model, determine the total amount of data processing within the unit time length based on the benchmark update period and the total amount of updated data, and use the total amount of data processing within the unit time length to determine whether the digital twin model can adopt the preset update strategy.

[0022] When the total amount of data processed within a unit time is not within the preset data volume range, it is determined that the digital twin model cannot adopt the preset update strategy.

[0023] Benchmark period: determine the change data of different change sub-models in different unit time periods on different dates based on the change data of different change sub-models in different unit time periods; determine the number of change sub-models that need to be updated in different unit time periods on different dates based on the change data of different change sub-models in different unit time periods; determine the average number of updated models in different unit time periods by taking the average number of change sub-models that need to be updated in different unit time periods on different dates.

[0024] The benchmark period for model updates of the digital twin model is the shortest unit time length in which the average number of updated models is greater than the preset threshold number of updated models.

[0025] Update processing strategy for the digital twin model: Based on the analysis results of the associated collected data of different variable sub-models and combined with the preset change threshold, the variable sub-model that needs to be updated is determined, and the variable sub-model that needs to be updated is used as the matching deviation sub-model. The model matching deviation coefficient of the digital twin model is determined by the proportion of the number of matching deviation sub-models. The update processing strategy of the digital twin model is determined according to the model matching deviation coefficient of the digital twin model. When there is a mismatch, the update processing strategy of the digital twin model is determined to update all of them. When there is a match, the update processing strategy of the digital twin model is to update the matching deviation sub-model. Example

[0026] To solve the above problems, according to one aspect of the present invention, Figure 1 As shown, a first aspect is provided. The present invention provides a digital mine management method based on a twin model, specifically comprising: S1 obtains the sub-models in the digital twin model corresponding to the digital mine, and determines the model change frequency coefficients and the changed sub-models of the different sub-models based on the analysis results of the associated collected data of the different sub-models; Furthermore, the sub-models include environmental models of the mining area, the processing area and the mineral storage area.

[0027] Specifically, the associated collected data is determined according to the data type of the environmental monitoring data of the mining area corresponding to the sub-model.

[0028] It is understandable that if Figure 2 As shown, the method for determining the model change frequency coefficient of the sub-model is: Determine the change of the associated collected data of the sub-model on different dates based on the analysis result of the associated collected data corresponding to the sub-model; Determine the date on which the model needs to be updated according to the change and the preset change threshold, and use it as the model change date; The model change frequency coefficient of the sub-model is determined by the proportion of the model change dates in the dates.

[0029] Furthermore, the variable sub-model is a sub-model whose model variable frequency coefficient is greater than a preset frequency coefficient threshold.

[0030] In another embodiment, the method for determining the model change frequency coefficient of the sub-model is: Determine the change of the associated collected data of the sub-model on different dates based on the analysis result of the associated collected data corresponding to the sub-model; Determine the duration of the model update process on different dates based on the change and a preset change threshold, and determine the model change frequency on different dates based on the ratio of the duration of the model update process on different dates to the preset duration; The model change frequency coefficient of the sub-model is determined by the average value of the model change frequencies on different dates.

[0031] It should be noted that the preset duration is 24 hours.

[0032] Optionally, the method for determining the model change frequency coefficient of the sub-model is: S11 determines the change of the associated collected data of the sub-model on different dates based on the analysis result of the associated collected data corresponding to the sub-model, determines the date on which the model needs to be updated according to the change and a preset change threshold, and uses it as the model change date; Optionally, the above step S11 includes the following contents: S111 determines the change of the associated collected data of the sub-model on different dates based on the analysis result of the associated collected data corresponding to the sub-model. If it is determined that there is no date for the sub-model to be updated according to the change and a preset change threshold, the sub-model is determined not to be a changed sub-model. If there is a date for the sub-model to be updated, the date is used as the model change date, and the process goes to step S112. S112: obtaining the number of model change dates. When the number of model change dates is greater than a preset change date number threshold, determining that the submodel belongs to a change submodel. When the number of model change dates is not greater than the preset change date number threshold, proceeding to step S113. S113 determines the number ratio of the change date in different divided time periods according to the number ratio of the model change date in different divided time periods. When the number ratio of the change date in different divided time periods is within the preset number ratio interval, it is determined that the sub-model does not belong to the change sub-model. When there is a divided time period in which the number ratio of the change date is not within the preset number ratio interval, the process proceeds to step S114. S114 When the number of divided time periods whose proportion of the number of changed dates is not within the preset proportion interval is greater than the preset number of divided time periods, it is determined that the sub-model belongs to the variable sub-model; when the number of divided time periods whose proportion of the number of changed dates is not within the preset proportion interval is not greater than the preset number of divided time periods, proceed to step S12.

[0033] S12 determines the model change frequency of different model change dates according to the number of update processes required on different model change dates and the update duration of different update processes; Optionally, the above step S12 includes the following contents: S121 determines the total number of times the sub-model needs to be updated by the number of times the update process needs to be performed on different model change dates, and uses it as the total number of model updates. When the total number of model updates is not greater than the preset update number threshold, the process proceeds to step S122; when the total number of model updates is greater than the preset update number threshold, the process proceeds to step S123; S122: when the number of times that the update process needs to be performed on different model change dates is within the preset update number interval, it is determined that the sub-model does not belong to the changed sub-model; when there is a model change date where the number of times that the update process needs to be performed is not within the preset update number interval, the process proceeds to step S123; S123 determines the model change frequency of different model change dates by the number of times the update process needs to be performed on different model change dates and the update duration of different update processes. When there is a model change date with a model change frequency greater than a preset frequency threshold, the process proceeds to step S124. When there is no model change date with a model change frequency greater than the preset frequency threshold, the process proceeds to step S13. S124 When the number of model change dates whose model change frequency is greater than the preset frequency threshold is greater than the preset change date number threshold, it is determined that the sub-model belongs to a changing sub-model; when the number of model change dates whose model change frequency is greater than the preset frequency threshold is not greater than the preset change date number threshold, proceed to step S13.

[0034] S13 determines the model change frequency coefficient of the sub-model based on the number ratio of the model change dates and the model change frequency of different model change dates.

[0035] Furthermore, the method for determining the model change frequency of the model change date is: Determine update weight coefficients for different numbers of update processes according to update durations for different numbers of update processes; The model change frequency of the model change date is determined by the sum of update weight coefficients of different numbers of update processes.

[0036] It should be noted that the model change frequency coefficient of the sub-model is determined according to the product of the average value of the model change frequency of different model change dates and the number ratio of the model change dates.

[0037] S2 obtains the amount of data associated with the collected data of different variable sub-models when performing model update processing, and combines the model change frequency coefficients of different variable sub-models to determine that the digital twin model cannot adopt the preset update strategy, and then proceeds to the next step; Specifically, Figure 3 As shown, it is determined that the digital twin model cannot adopt the preset update strategy, specifically including: Based on the model change frequency coefficient of the change sub-model, determine the change sub-model with the largest model change frequency coefficient, and use it as the benchmark sub-model; According to the difference between the model change frequency coefficients of different change sub-models and the model change frequency coefficient of the benchmark sub-model, determine the change sub-model whose difference is greater than a preset difference threshold, and use it as the unchanged sub-model; The total amount of updated data is determined by the amount of collected data associated with different changed sub-models during model update processing, and whether the digital twin model can adopt a preset update strategy is determined in combination with the proportion of the unchanged sub-models.

[0038] Furthermore, whether the digital twin model can adopt a preset update strategy is determined in combination with the proportion of the number of unchanged sub-models, specifically including: The percentage of the number of unchanged sub-models is used to determine the update data volume threshold corresponding to the percentage, and the update data volume threshold and the total amount of update data are used to determine whether the digital twin model can adopt a preset update strategy.

[0039] In another embodiment, determining that the digital twin model cannot adopt a preset update strategy specifically includes: Based on the model change frequency coefficient of the change sub-model, determine the change sub-model with the largest model change frequency coefficient, and use it as the benchmark sub-model; Determining a benchmark update period of the digital twin model based on a model change frequency coefficient of the benchmark sub-model; The total amount of updated data is determined by associating the amount of collected data with different variable sub-models during model update processing, and whether the digital twin model can adopt a preset update strategy is determined in combination with the benchmark update cycle.

[0040] Furthermore, determining whether the update processing complexity of the digital twin model meets the requirements in combination with the benchmark update cycle specifically includes: The total amount of data processing within a unit time is determined based on the benchmark update cycle and the total amount of updated data, and the total amount of data processing within the unit time is used to determine whether the digital twin model can adopt a preset update strategy.

[0041] It should be noted that the preset update strategy is to update the digital twin model as a whole when there is a sub-model that needs to be updated.

[0042] Optionally, determining that the digital twin model cannot adopt a preset update strategy specifically includes: S21 determines the total amount of updated data based on the amount of data collected by different variable sub-models when performing model update processing, and determines the variable sub-model with the largest model change frequency coefficient based on the model change frequency coefficient of the variable sub-model, and uses it as the benchmark sub-model; S22: determining update processing difficulty coefficients of different change sub-models according to the difference between the model change frequency coefficients of different change sub-models and the model change frequency coefficients of the benchmark sub-model, and in combination with the amount of data of the associated collected data when the different change sub-models are performing model update processing; S23 determines the comprehensive processing difficulty coefficient based on the update processing difficulty coefficients of different variable sub-models, and determines whether the digital twin model can adopt a preset update strategy based on the comprehensive processing difficulty coefficient.

[0043] Furthermore, the update processing difficulty coefficient of the variable sub-model is determined based on the difference and a preset difficulty coefficient corresponding to the amount of collected data associated with the variable sub-model when performing model update processing.

[0044] Specifically, the comprehensive processing difficulty coefficient is determined according to the weighted sum of the update processing difficulty coefficients of different variable sub-models.

[0045] S3 determines the change data of different change sub-models within different unit time lengths based on the change of associated collected data of different change sub-models within different unit time lengths, and uses the change data to determine the reference period for model update of the digital twin model; Specifically, Figure 4As shown, the method for determining the reference period for model update of the digital twin model is: Determine the change data of different change sub-models within different unit time lengths on different dates using the change data of different change sub-models within different unit time lengths; Based on the change data of different change sub-models in different unit time lengths, determine the number of change sub-models that need to be updated in different unit time lengths on different dates; By averaging the number of changing sub-models that need to be updated within different unit time periods on different dates, the average number of updated models within different unit time periods is determined, and the benchmark period for model update of the digital twin model is determined using the average number of updated models.

[0046] Furthermore, the benchmark period for model updating of the digital twin model is the shortest unit time length in which the average number of updated models is greater than a preset threshold value for the number of updated models.

[0047] It should be noted that the unit duration includes multiple durations ranging from 1 hour to one day, and specifically, 1 hour is used to cut and divide different unit durations.

[0048] In another embodiment, the method for determining the reference period for updating the model of the digital twin model is: Determine the change data of different change sub-models in the unit time lengths on different dates using the change data of different change sub-models in different unit time lengths; determine the change sub-models that need to be updated in the unit time lengths on different dates based on the change data of different change sub-models in the unit time lengths, and use them as update sub-models; When the number of dates for updating the sub-model within the unit time length is less than the preset number of dates, it is determined that the unit time length does not belong to the benchmark period for model updating of the digital twin model; When the number of dates for updating the sub-model within the unit time is not less than the preset number of dates: When it is determined that there is no date on which the number of updated sub-models is greater than a preset sub-model number threshold based on the number of updated sub-models on different dates within the unit time, it is determined that the unit time does not belong to the benchmark period for model update of the digital twin model; When there is a date when the number of updated sub-models is greater than the preset sub-model number threshold: The date when the number of updated sub-models is greater than the preset sub-model number threshold is used as the screening change date. When the proportion of the number of dates of the screening change date is less than the proportion of the preset number of dates, it is determined that the unit time does not belong to the benchmark period of the model update of the digital twin model; When the percentage of the number of dates in the filter change date is not less than the percentage of the number of preset dates: The model update frequency coefficient within the unit time length is determined based on the number of updated sub-models within the unit time length on different dates, and the model update frequency coefficient is used to determine the benchmark period for model update of the digital twin model.

[0049] S4: When within the reference period, the update processing strategy of the digital twin model is determined based on the analysis results of the associated collected data of different variable sub-models.

[0050] Specifically, the method for determining the update processing strategy of the digital twin model is: The analysis results of the associated collected data of different variable sub-models are combined with the preset change amount threshold to determine the variable sub-model that needs to be updated, and the variable sub-model that needs to be updated is used as the matching deviation sub-model, and the model matching deviation coefficient of the digital twin model is determined by the proportion of the number of matching deviation sub-models; Determine the variation deviation coefficient of the associated collected data of different variation sub-models by the deviation amount of the variation amount of the associated collected data of different variation sub-models from the preset variation threshold and the ratio of the variation amount to the preset variation threshold, and determine the variation deviation coefficient average value by using the average value of the variation deviation coefficients; A model update requirement coefficient is determined according to the ratio of the model matching deviation coefficient to the average value of the variation deviation coefficient of the digital twin model, and an update processing strategy of the digital twin model is determined using the model update requirement coefficient.

[0051] Furthermore, the update processing strategy of the digital twin model is determined by using the model update requirement coefficient, which specifically includes: When the model update requirement coefficient is greater than a preset update requirement coefficient threshold, the update processing strategy of the digital twin model is determined to be a full update processing; When the model update requirement coefficient is not greater than a preset update requirement coefficient threshold, the update processing strategy of the digital twin model is determined to update the matching deviation sub-model. Example

[0052] Second, as Figure 5 As shown, the present invention provides a management platform, which adopts the above-mentioned digital mine management method based on twin model, specifically including: Data acquisition module, digital twin model update module; The data acquisition module is responsible for collecting and processing the associated collected data of different sub-models in the digital twin model; The digital twin model update module is responsible for updating the digital twin model according to the update processing strategy.

[0053] Optionally, the above step S21 includes the following contents: S211 determines the total amount of updated data by associating the amount of collected data with different variable sub-models when performing model update processing. When the total amount of updated data is greater than the preset total amount, it is determined that the digital twin model cannot adopt the preset update strategy. When the total amount of updated data is not greater than the preset total amount of data, proceed to step S212. S212 determines a preset frequent coefficient threshold value by using the total amount of update data and a preset mapping function, and determines that there is no changing sub-model whose model change frequent coefficient is greater than the preset frequent coefficient threshold value based on the model change frequent coefficients of different changing sub-models, then determines that the digital twin model can adopt a preset update strategy, and when there is a changing sub-model whose model change frequent coefficient is greater than the preset frequent coefficient threshold value, proceeds to step S213; S213 uses the variable sub-model whose model frequency coefficient is greater than the preset frequency coefficient threshold as the screened variable sub-model. When the number of the screened variable sub-models does not meet the requirement, it is determined that the digital twin model can adopt the preset update strategy. When the number of the screened variable sub-models meets the requirement, it proceeds to step S214. S214: When there is a screening change sub-model whose deviation amount between the model frequent coefficient and the preset frequent coefficient threshold is not within the preset deviation range, it is determined that the digital twin model cannot adopt the preset update strategy; when there is no screening change sub-model whose deviation amount between the model frequent coefficient and the preset frequent coefficient threshold is not within the preset deviation range, the process proceeds to step S22; Optionally, the above step S22 includes the following contents: S221 determines whether there is a changing sub-model whose difference is not within a preset difference interval according to the difference between the model change frequency coefficients of different changing sub-models and the model change frequency coefficient of the benchmark sub-model. If so, proceed to the next step. If not, determine whether the digital twin model can adopt a preset update strategy. S222: The variable sub-model whose difference is not within the preset difference interval is used as the frequent coefficient deviation sub-model. When the number of the frequent coefficient deviation sub-model does not meet the requirement, it is determined. When the number of the frequent coefficient deviation sub-model meets the requirement, it is transferred to step S223. S223 determines the total amount of data processed within the unit time length based on the benchmark update cycle and the total amount of updated data. When the total amount of data processed within the unit time length is greater than the preset data amount threshold, the process proceeds to step S224. When the total amount of data processed within the unit time length is not greater than the preset data amount threshold, it is determined that the digital twin model can adopt the preset update strategy. S224 determines the update processing difficulty coefficients of different variable sub-models by using the difference between the model change frequency coefficients of different variable sub-models and the model change frequency coefficients of the benchmark sub-model, and the amount of associated collected data when performing model update processing. When the number of variable sub-models whose update processing difficulty coefficients do not meet the requirements is greater than the preset number of sub-models, it is determined that the digital twin model cannot adopt the preset update strategy. When the number of variable sub-models whose update processing difficulty coefficients do not meet the requirements is not greater than the preset number of sub-models, proceed to step S23.

[0054] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0055] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0056] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A digital mine management method based on a twin model, characterized in that: Specifically include: Obtain the sub-models in the digital twin model corresponding to the digital mine, and determine the model change frequency coefficients and the changed sub-models of different sub-models based on the analysis results of the associated collected data of different sub-models; Obtain the amount of data associated with the collected data when different variable sub-models are performing model update processing, and combine the model change frequency coefficients of different variable sub-models to determine that the digital twin model cannot adopt the preset update strategy, and then proceed to the next step; Based on the changes in the associated collected data of different changing sub-models within different unit time lengths, the change data of different changing sub-models within different unit time lengths are determined, and the reference period for model update of the digital twin model is determined by using the change data; When within the reference period, the update processing strategy of the digital twin model is determined based on the analysis results of the associated collected data of different variable sub-models.

2. The digital mine management method based on the twin model according to claim 1, characterized in that: The sub-models include environmental models of mining areas, processing areas and mineral storage areas.

3. The digital mine management method based on twin model according to claim 1, characterized in that: The associated collected data is determined according to the data type of the environmental monitoring data of the mining area corresponding to the sub-model.

4. The digital mine management method based on twin model according to claim 1, characterized in that: The method for determining the model change frequency coefficient of the sub-model is: Determine the change of the associated collected data of the sub-model on different dates based on the analysis result of the associated collected data corresponding to the sub-model; Determine the date on which the model needs to be updated according to the change and the preset change threshold, and use it as the model change date; The model change frequency coefficient of the sub-model is determined by the proportion of the model change dates in the dates.

5. The digital mine management method based on the twin model as claimed in claim 4, characterized in that: The variable sub-model is a sub-model whose model variable frequency coefficient is greater than a preset frequency coefficient threshold.

6. The digital mine management method based on twin model according to claim 1, characterized in that: Determining that the digital twin model cannot adopt a preset update strategy includes: Based on the model change frequency coefficient of the change sub-model, determine the change sub-model with the largest model change frequency coefficient, and use it as the benchmark sub-model; According to the difference between the model change frequency coefficients of different change sub-models and the model change frequency coefficient of the benchmark sub-model, determine the change sub-model whose difference is greater than a preset difference threshold, and use it as the unchanged sub-model; The total amount of updated data is determined by the amount of collected data associated with different changed sub-models during model update processing, and whether the digital twin model can adopt a preset update strategy is determined in combination with the proportion of the unchanged sub-models.

7. The digital mine management method based on twin model as claimed in claim 6, characterized in that: Determining whether the digital twin model can adopt a preset update strategy based on the proportion of the unchanged sub-models includes: The percentage of the number of unchanged sub-models is used to determine the update data volume threshold corresponding to the percentage, and the update data volume threshold and the total amount of update data are used to determine whether the digital twin model can adopt a preset update strategy.

8. The digital mine management method based on twin model according to claim 1, characterized in that: The method for determining the update processing strategy of the digital twin model is: The analysis results of the associated collected data of different variable sub-models are combined with the preset change amount threshold to determine the variable sub-model that needs to be updated, and the variable sub-model that needs to be updated is used as the matching deviation sub-model, and the model matching deviation coefficient of the digital twin model is determined by the proportion of the number of matching deviation sub-models; Determine the variation deviation coefficient of the associated collected data of different variation sub-models by the deviation amount of the variation amount of the associated collected data of different variation sub-models from the preset variation threshold and the ratio of the variation amount to the preset variation threshold, and determine the variation deviation coefficient average value by using the average value of the variation deviation coefficients; A model update requirement coefficient is determined according to the ratio of the model matching deviation coefficient to the average value of the variation deviation coefficient of the digital twin model, and an update processing strategy of the digital twin model is determined using the model update requirement coefficient.

9. The digital mine management method based on twin model as claimed in claim 8, characterized in that: The update processing strategy of the digital twin model is determined by using the model update requirement coefficient, specifically including: When the model update requirement coefficient is greater than a preset update requirement coefficient threshold, the update processing strategy of the digital twin model is determined to be a full update processing; When the model update requirement coefficient is not greater than a preset update requirement coefficient threshold, the update processing strategy of the digital twin model is determined to update the matching deviation sub-model.

10. A management platform, using a digital mine management method based on a twin model as claimed in any one of claims 1 to 9, characterized in that: Specifically include: Data acquisition module, digital twin model update module; The data acquisition module is responsible for collecting and processing the associated collected data of different sub-models in the digital twin model; The digital twin model update module is responsible for updating the digital twin model according to the update processing strategy.

Images