Intelligent evaluation system of power grid cash flow

Abstract

The invention relates to the technical field of power grid economic models, in particular to an intelligent evaluation system for power grid cash flow, which comprises an information acquisition module used for acquiring evaluation index information of data flow of a plurality of companies and power grid data flow characteristic information; the index selection module is used for determining general evaluation indexes based on the overlap ratio of the data flow evaluation indexes of the companies; the evaluation model construction module is used for constructing a power grid data flow evaluation model according to the sensitivity of each selected evaluation index to the change of the power grid data flow; the exception handling module is used for determining an exception handling method according to the influence degree of the abnormal power grid data stream data on the evaluation result; the adjusting module is used for determining whether to adjust the power grid data flow evaluation process parameters or not according to the fluctuation amplitude of the accuracy of the evaluation result of the power grid data flow evaluation model within the preset time, and the evaluation model with accurate evaluation is constructed by improving the accuracy of evaluation index selection.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid economic models, and in particular to an intelligent evaluation system for power grid cash flow. Background Art

[0002] Grid data flow is one of the important indicators of the power industry, which is directly related to the stability and profitability of grid operation. Accurate evaluation of grid data flow is crucial for formulating reasonable business strategies and investment decisions. The evaluation system of grid data flow in the existing technology has the problem of relying on manual analysis or simple rule engines. It is impossible to select accurate evaluation indicators, resulting in inaccurate evaluation of changing trends and anomalies of grid data flow.

[0003] Chinese patent application publication number: CN115841166A discloses a method and system for intelligent cash flow prediction of power grid enterprises, including the following steps: S1, using a prediction model; S2, using a strategy model; S3, using an evaluation model; optimizing the capital management of power grid enterprises, achieving cost reduction of enterprise financing, reducing the workload of financial management personnel, and improving work efficiency, facilitating top-down management guidance and bottom-up execution feedback within the power grid enterprise system, improving the scientificity and leanness of overall capital management, and promoting power grid enterprises to be more scientific and reasonable in terms of financing direction and capital utilization, and more in line with corporate operations and construction and the development of the entire society.

[0004] It can be seen that the existing technology has the problem that the evaluation indicators of power grid data flow are not selected accurately enough, resulting in inaccurate evaluation results of the constructed power grid data flow evaluation model. Summary of the invention

[0005] To this end, the present invention provides an intelligent evaluation system for power grid cash flow to overcome the problem in the prior art that the evaluation index selection for power grid data flow is not accurate enough, resulting in inaccurate evaluation results of the constructed power grid data flow evaluation model.

[0006] To achieve the above object, the present invention provides an intelligent evaluation system for power grid cash flow, comprising:

[0007] An information acquisition module, which is used to obtain evaluation index information of data flows of several companies and characteristic information of power grid data flows;

[0008] An indicator selection module, which is connected to the information acquisition module, and is used to determine the general evaluation indicators based on the overlap of the data flow evaluation indicators of several companies, and select the specific evaluation indicators based on the characteristics of the power grid data flow;

[0009] An evaluation model construction module, which is connected to the indicator selection module, and is used to determine the weight of each evaluation indicator according to the sensitivity of each selected evaluation indicator to the change of the power grid data flow, and to construct a power grid data flow evaluation model based on each evaluation indicator and the weight of each evaluation indicator, wherein each selected evaluation indicator includes a general evaluation indicator and a specific evaluation indicator;

[0010] An exception handling module, which is connected to the evaluation model building module, is used to determine an exception handling method for the abnormal power grid data flow data according to the degree of influence of the abnormal power grid data flow data on the evaluation result in the evaluation result of the power grid data flow evaluation model;

[0011] An adjustment module is connected to the abnormality processing module and is used to determine whether to adjust the parameters of the power grid data flow evaluation process according to the fluctuation range of the accuracy of the evaluation result of the power grid data flow evaluation model within a preset time.

[0012] Furthermore, the indicator selection module selects the general evaluation indicator based on the overlap of data flow evaluation indicators of several companies and determines the data flow evaluation indicator as the general evaluation indicator according to the comparison result that the overlap of several data flow evaluation indicators is greater than or equal to the preset overlap.

[0013] Furthermore, the overlap of the data flow evaluation indicators of the several companies is determined according to the ratio of the number of times a single data flow evaluation indicator is used to the number of the several companies.

[0014] Furthermore, the evaluation model construction module determines the weight of each evaluation indicator according to the sensitivity of each selected evaluation indicator to the change of the power grid data flow, including adjusting the numerical value of each evaluation indicator one by one to obtain the power grid data flow change value to determine the sensitivity, and calculating the corresponding weight based on the sensitivity of each evaluation indicator.

[0015] Furthermore, the evaluation model construction module constructs a power grid data flow evaluation model based on the various evaluation indicators and the weights of the various evaluation indicators, including weighted summing up the selected evaluation indicators and the corresponding weights to obtain the evaluation results, and inputting the above data into the neural network model for training to obtain the power grid data flow evaluation model.

[0016] Furthermore, the exception handling module determines the exception handling method for the abnormal power grid data flow data, including:

[0017] The abnormal processing module determines to perform data smoothing processing on the abnormal power grid data flow data according to a comparison result that the influence degree of the abnormal power grid data flow data on the evaluation result in the evaluation result of the power grid data flow evaluation model is less than a first preset influence degree;

[0018] The abnormal processing module determines to perform difference replacement processing on the abnormal power grid data flow data according to the comparison result that the influence degree of the abnormal power grid data flow data on the evaluation result in the evaluation result of the power grid data flow evaluation model is greater than or equal to the first preset influence degree and less than the second preset influence degree;

[0019] The exception processing module determines to delete the abnormal power grid data flow data according to the comparison result that the influence degree of the abnormal power grid data flow data on the evaluation result of the power grid data flow evaluation model is greater than or equal to the second preset influence degree.

[0020] Furthermore, the degree of influence of the abnormal power grid data flow data on the evaluation results is determined based on the difference value of the evaluation results before and after removing the abnormal values, the first preset degree of influence is determined based on one tenth of the maximum difference value of the evaluation results before and after removing the abnormal values ​​in the historical evaluation process, and the second preset degree of influence is determined based on one eighth of the maximum difference value of the evaluation results before and after removing the abnormal values ​​in the historical evaluation process.

[0021] Furthermore, the adjustment module determines whether to adjust the parameters of the power grid data flow evaluation process, including determining the need to adjust the parameters of the power grid data flow evaluation process based on a comparison result that the fluctuation range of the accuracy of the evaluation results of the power grid data flow evaluation model within a preset time is greater than or equal to a preset fluctuation range, wherein the power grid data flow evaluation process parameters include a preset overlap degree and a second preset influence degree.

[0022] Furthermore, the preset fluctuation range is determined according to an average value of the fluctuation range of the accuracy of the evaluation result of the power grid data flow evaluation model within a preset time during the historical evaluation process.

[0023] Furthermore, the adjustment amount of the preset overlap degree is positively correlated with the density of the accuracy fluctuation range of the evaluation results of the power grid data flow evaluation model within the preset time, and the adjustment amount of the second preset influence degree is negatively correlated with the density of the accuracy fluctuation range of the evaluation results of the power grid data flow evaluation model within the preset time.

[0024] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention selects data flow evaluation indicators with high overlap according to the comparison results of the overlap of several data flow evaluation indicators with the preset overlap through the indicator selection module, and the accuracy of the evaluation results can be improved by screening the general evaluation indicators for the comparison results of the overlap. The above method improves the accuracy of the selection of evaluation indicators for power grid data flow, so that the evaluation results of the constructed power grid data flow evaluation model are more accurate. The accuracy of power grid data flow evaluation is also improved by establishing an evaluation system by combining the indicators of ordinary companies and enterprises with the indicators unique to power companies.

[0025] Furthermore, the present invention can more accurately determine the degree of influence of each evaluation indicator on the power grid data flow by performing sensitivity analysis, thereby optimizing the weight of each indicator, identifying which evaluation indicators are most sensitive to changes in the power grid data flow, and helping management to better understand key risk factors. Determining the weight of each evaluation indicator can provide management with more powerful data support. By calculating the sensitivity of each evaluation indicator and determining the weight, it can better guide the allocation and utilization of resources and optimize the allocation of funds and human resources. The above method improves the accuracy of the selection of evaluation indicators for the power grid data flow, so that the evaluation results of the constructed power grid data flow evaluation model are more accurate.

[0026] Furthermore, the present invention can perform data cleaning on abnormal data with a low impact, that is, remove data points with obvious errors or abnormalities, which helps to improve data quality and the accuracy of evaluation results. For abnormal data with a medium impact, an interpolation method can be used or the average value of the surrounding data can be used to replace the abnormal value to smooth the data and reduce the impact of the abnormality on the results. For abnormal data with a high impact, it can be marked as an outlier, and special treatment can be considered during the analysis process to avoid the abnormal data from having a greater impact on the overall evaluation results. The above method improves the accuracy of the selection of evaluation indicators for power grid data flow, so that the evaluation results of the constructed power grid data flow evaluation model are more accurate.

[0027] Furthermore, the present invention determines whether to adjust the parameters of the power grid data flow evaluation process based on the comparison result of the fluctuation amplitude of the accuracy of the evaluation result of the power grid data flow evaluation model within the preset time and the preset fluctuation amplitude. If the fluctuation amplitude is greater than or equal to the preset fluctuation amplitude, it means that the evaluation result of the constructed power grid data flow evaluation model is inaccurate. At this time, it is necessary to adjust the parameters of the power grid data flow evaluation process. The above method improves the accuracy of the selection of evaluation indicators for the power grid data flow, so that the evaluation result of the constructed power grid data flow evaluation model is more accurate.

[0028] Furthermore, the present invention determines an adjustment method based on a comparison result of the density of the fluctuation amplitude of the accuracy of the evaluation results of the power grid data flow evaluation model within a preset time and a preset density. If the density is greater than or equal to the preset density, it means that the selected evaluation indicators or features are insufficient to capture the key features of the data due to inaccurate selected evaluation indicators, and the evaluation model cannot accurately evaluate the power grid data, resulting in a large error density. At this time, the first adjustment coefficient is used to increase the preset overlap and thereby improve the accuracy of the selection of evaluation indicators. If the density is less than the preset density, it means that when processing abnormal values, the abnormal values ​​with a large impact on the evaluation results are retained due to the large second preset influence degree. At this time, it is determined to reduce the second preset influence degree with the second adjustment coefficient. The above method improves the accuracy of the selection of evaluation indicators for the power grid data flow, so that the evaluation results of the constructed power grid data flow evaluation model are more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a structural schematic diagram of an intelligent evaluation system for power grid cash flow according to an embodiment of the present invention;

[0030] Figure 2 This is a working flow chart of an indicator selection module in the intelligent evaluation system of power grid cash flow according to an embodiment of the present invention;

[0031] Figure 3 The present invention is a flowchart of the adjustment module in the intelligent evaluation system of power grid cash flow according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0033] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0034] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0035] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0036] See also Figure 1 - Figure 3 As shown, Figure 1 It is a structural schematic diagram of an intelligent evaluation system for power grid cash flow according to an embodiment of the present invention; Figure 2 This is a working flow chart of an indicator selection module in the intelligent evaluation system of power grid cash flow according to an embodiment of the present invention; Figure 3 The present invention is a flowchart of the adjustment module in the intelligent evaluation system of power grid cash flow according to an embodiment of the present invention.

[0037] The intelligent evaluation system of power grid cash flow according to the embodiment of the present invention includes:

[0038] An information acquisition module, which is used to obtain evaluation index information of data flows of several companies and characteristic information of power grid data flows;

[0039] An indicator selection module, which is connected to the information acquisition module, and is used to determine the general evaluation indicators based on the overlap of the data flow evaluation indicators of several companies, and select the specific evaluation indicators based on the characteristics of the power grid data flow;

[0040] An evaluation model construction module, which is connected to the indicator selection module, and is used to determine the weight of each evaluation indicator according to the sensitivity of each selected evaluation indicator to the change of the power grid data flow, and to construct a power grid data flow evaluation model based on each evaluation indicator and the weight of each evaluation indicator, wherein each selected evaluation indicator includes a general evaluation indicator and a specific evaluation indicator;

[0041] An exception handling module, which is connected to the evaluation model building module, is used to determine an exception handling method for the abnormal power grid data flow data according to the degree of influence of the abnormal power grid data flow data on the evaluation result in the evaluation result of the power grid data flow evaluation model;

[0042] An adjustment module is connected to the abnormality processing module and is used to determine whether to adjust the parameters of the power grid data flow evaluation process according to the fluctuation range of the accuracy of the evaluation result of the power grid data flow evaluation model within a preset time.

[0043] The evaluation index information of the data streams of several companies described in the embodiment of the present invention includes but is not limited to "stability-related indicators, trend-related indicators and periodicity-related indicators". The selection of unique evaluation indicators based on the characteristics of the power grid data stream includes performing principal component analysis on all acquired indicator data. The principal component analysis can convert multiple related indicators into a few unrelated comprehensive indicators, namely, principal components. According to the characteristics of the power grid data stream, the unique distribution of the power grid cash flow data in the principal component space is analyzed, and those indicators that can highlight this uniqueness are found as unique evaluation indicators. If the power grid cash flow presents a distribution pattern different from that of other companies in the principal component space, such as a value on a certain principal component that is obviously higher or lower, the original indicator that causes this difference can be further analyzed and used as a unique evaluation indicator. The unique evaluation indicators include but are not limited to "policy and seasonal correlation-related indicators, regional correlation-related indicators, and user type correlation-related indicators".

[0044] Specifically, the indicator selection module determines the general evaluation indicator based on the comparison result of the overlap of several data flow evaluation indicators and the preset overlap under the condition that the general evaluation indicator is determined based on the overlap of several companies' data flow evaluation indicators;

[0045] If the overlap of the data flow evaluation index is greater than or equal to the preset overlap, the index selection module determines the data flow evaluation index as a general evaluation index;

[0046] If the overlap of the data flow evaluation index is less than the preset overlap, the index selection module determines that the data flow evaluation index is not used as a general evaluation index;

[0047] Among them, the value range of the preset overlap is set to 0.6-1, and the value of the preset overlap is preferably 0.75. The above value is not limited to this, and technical personnel in this field can also adjust the value according to actual needs.

[0048] The overlap of the data flow evaluation indicators of the several companies in the embodiment of the present invention is determined according to the ratio of the number of times a single data flow evaluation indicator is used to the number of the several companies.

[0049] The present invention selects data flow evaluation indicators with high overlap according to the comparison results of the overlap of several data flow evaluation indicators with preset overlap through an indicator selection module. The accuracy of the evaluation results can be improved by screening general evaluation indicators for the comparison results of the overlap. The accuracy of the selection of evaluation indicators for power grid data flow is improved through the above method, so that the evaluation results of the constructed power grid data flow evaluation model are more accurate. The accuracy of power grid data flow evaluation is also improved by establishing an evaluation system by combining the indicators of ordinary companies and enterprises with the indicators unique to power companies.

[0050] Specifically, the evaluation model construction module determines the weight of each evaluation indicator according to the sensitivity of each selected evaluation indicator to the change of power grid data flow, including adjusting the numerical value of each evaluation indicator one by one to obtain the power grid data flow change value to determine the sensitivity, and calculating the corresponding weight based on the sensitivity of each evaluation indicator.

[0051] In the embodiment of the present invention, the sensitivity is determined by the ratio of the adjustment amount of each evaluation indicator to the corresponding power grid data flow change value, and the corresponding weight is calculated based on the sensitivity of each evaluation indicator, including calculating the multiple relationship of the sensitivity of each evaluation indicator based on the sensitivity of each evaluation indicator, and calculating the weight of each evaluation indicator based on the multiple relationship with a total of 1.

[0052] By performing sensitivity analysis, the present invention can more accurately determine the degree of influence of each evaluation indicator on the power grid data flow, thereby optimizing the weight of each indicator, identifying which evaluation indicators are most sensitive to changes in the power grid data flow, and helping management to better understand key risk factors. Determining the weight of each evaluation indicator can provide more powerful data support for the management. By calculating the sensitivity of each evaluation indicator and determining the weight, it can better guide the allocation and utilization of resources and optimize the allocation of funds and human resources. The above method improves the accuracy of the selection of evaluation indicators for the power grid data flow, so that the evaluation results of the constructed power grid data flow evaluation model are more accurate.

[0053] Specifically, the evaluation model construction module constructs a power grid data flow evaluation model based on the various evaluation indicators and the weights of the various evaluation indicators, including weighted summing up the selected evaluation indicators and the corresponding weights to obtain the evaluation results, and inputting the above data into the neural network model for training to obtain the power grid data flow evaluation model.

[0054] The power grid data flow evaluation model described in the embodiment of the present invention determines the change trend of the power grid data flow based on the result of weighted summation calculation of evaluation indicators and corresponding weights and the previous evaluation result, and further determines whether there is an abnormality in the power grid data flow based on the comparison result of the calculation result and the threshold. If the calculation result is greater than the threshold, it means that there is an abnormality in the power grid data flow. The threshold can be determined based on the historical maximum value in the power grid data flow evaluation result.

[0055] Specifically, under the condition that the power grid data flow evaluation model determines that the power grid data flow has an abnormality, the abnormality processing module determines the abnormality processing method for the abnormal power grid data flow data according to the comparison result of the influence degree of the abnormal power grid data flow data on the evaluation result in the evaluation result of the power grid data flow evaluation model and the preset influence degree;

[0056] If the influence degree of the power grid data flow data on the evaluation result is less than the first preset influence degree, the abnormality processing module determines to perform data smoothing processing on the abnormal power grid data flow data;

[0057] If the influence degree of the power grid data flow data on the evaluation result is greater than or equal to the first preset influence degree and less than the second preset influence degree, the abnormal processing module determines to perform difference replacement processing on the abnormal power grid data flow data;

[0058] If the influence degree of the power grid data flow data on the evaluation result is greater than or equal to the second preset influence degree, the abnormal processing module determines to perform data deletion processing on the abnormal power grid data flow data;

[0059] Among them, the value of the first preset impact degree is one tenth of the maximum difference value of the evaluation results before and after removing the outliers in the historical evaluation process, and the value of the second preset impact degree is one eighth of the maximum difference value of the evaluation results before and after removing the outliers in the historical evaluation process. The above values ​​are not limited to this, and technical personnel in this field can also adjust the values ​​according to actual needs.

[0060] In the embodiment of the present invention, the influence degree of the abnormal power grid data flow data on the evaluation result is determined according to the difference value of the evaluation result before and after the abnormal value is removed, and the interpolation replacement processing includes using the mean or median to replace the abnormal value.

[0061] The present invention can perform data cleaning for abnormal data with low impact, that is, remove data points with obvious errors or abnormalities, which helps to improve data quality and the accuracy of evaluation results. For abnormal data with medium impact, an interpolation method can be used or the average value of surrounding data can be used to replace the abnormal value to smooth the data and reduce the impact of the abnormality on the result. For abnormal data with high impact, it can be marked as an abnormal value, and special treatment can be considered during the analysis process to avoid the abnormal data from having a greater impact on the overall evaluation result. The above method improves the accuracy of the selection of evaluation indicators for power grid data flow, so that the evaluation results of the constructed power grid data flow evaluation model are more accurate.

[0062] Specifically, the adjustment module determines whether to adjust the parameters of the power grid data flow evaluation process, including determining whether to adjust the parameters of the power grid data flow evaluation process according to a comparison result of the fluctuation range of the accuracy of the evaluation result of the power grid data flow evaluation model within a preset time and a preset fluctuation range;

[0063] If the fluctuation range of the accuracy of the evaluation result of the power grid data flow evaluation model is greater than or equal to the preset fluctuation range, the adjustment module determines that the parameters of the power grid data flow evaluation process need to be adjusted;

[0064] If the fluctuation range of the accuracy of the evaluation result of the power grid data flow evaluation model is less than the preset fluctuation range, the adjustment module determines that there is no need to adjust the parameters of the power grid data flow evaluation process;

[0065] Among them, the preset fluctuation amplitude value is the average fluctuation amplitude of the accuracy of the evaluation results of the power grid data flow evaluation model within a preset time in the historical evaluation process. The above value is not limited to this, and technical personnel in this field can also adjust the value according to actual needs.

[0066] In the embodiment of the present invention, the preset time is set to 5 days. The fluctuation range of the accuracy of the evaluation results of the power grid data flow evaluation model within the preset time is the ratio of the number of inaccurate evaluation results to the total number of evaluations. The power grid data flow evaluation process parameters include a preset overlap and a second preset influence degree.

[0067] The present invention determines whether to adjust the parameters of the power grid data flow evaluation process based on the comparison result of the fluctuation amplitude of the evaluation result accuracy of the power grid data flow evaluation model within a preset time and the preset fluctuation amplitude. If the fluctuation amplitude is greater than or equal to the preset fluctuation amplitude, it means that the evaluation result of the constructed power grid data flow evaluation model is inaccurate. At this time, it is necessary to adjust the parameters of the power grid data flow evaluation process. The above method improves the accuracy of the selection of evaluation indicators for the power grid data flow so that the evaluation result of the constructed power grid data flow evaluation model is more accurate.

[0068] Specifically, the adjustment module determines the adjustment method according to the comparison result of the intensity of the fluctuation range of the evaluation result accuracy of the power grid data flow evaluation model within a preset time and the preset intensity under the condition that it is determined that the parameters of the power grid data flow evaluation process need to be adjusted;

[0069] If the density is greater than or equal to the preset density, the adjustment module determines to adjust the preset overlap by a first adjustment coefficient;

[0070] If the density is less than the preset density, the adjustment module determines to adjust the second preset influence degree by a second adjustment coefficient;

[0071] The preset density value range is set to 0.5-1, and the preset density value is preferably 0.68. The above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0072] In the embodiment of the present invention, the value range of the first adjustment coefficient is set to 1-1.2, and the value range of the second adjustment coefficient is set to 0.85-1.

[0073] The density of the fluctuation amplitude described in the embodiment of the present invention is the number of adjacent evaluation errors in the evaluation results compared with the total number of evaluation errors. For example, if the total number of evaluation errors is 5 times, the number of evaluations is 10 times, and the numbers of evaluation errors are the first, second, third, fifth and seventh times respectively, then the number of adjacent evaluation errors is three, and the density of the fluctuation amplitude is 0.6; if the total number of evaluation errors is 7 times, the number of evaluations is 12 times, and the numbers of evaluation errors are the first, second, third, fifth, sixth, ninth and eleventh times respectively, then the number of adjacent evaluation errors is 5, and the density of the fluctuation amplitude is 0.71.

[0074] The present invention determines an adjustment method based on a comparison result of the density of the fluctuation amplitude of the accuracy of the evaluation result of the power grid data flow evaluation model within a preset time and a preset density. If the density is greater than or equal to the preset density, it means that the selected evaluation indicators or features are insufficient to capture the key features of the data due to inaccurate selected evaluation indicators, and the evaluation model cannot accurately evaluate the power grid data, resulting in a large error density. At this time, the first adjustment coefficient is used to increase the preset overlap and thus improve the accuracy of the selection of the evaluation indicators. If the density is less than the preset density, it means that when processing abnormal values, the abnormal values ​​with a large impact on the evaluation results are retained due to the large second preset influence degree. At this time, it is determined to reduce the second preset influence degree with the second adjustment coefficient. The above method improves the accuracy of the selection of evaluation indicators for the power grid data flow, so that the evaluation results of the constructed power grid data flow evaluation model are more accurate.

[0075] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0076] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent evaluation system for power grid cash flow, characterized in that: include: An information acquisition module, which is used to obtain evaluation index information of data flows of several companies and characteristic information of power grid data flows; An indicator selection module, which is connected to the information acquisition module, and is used to determine the general evaluation indicators based on the overlap of the data flow evaluation indicators of several companies, and select the specific evaluation indicators based on the characteristics of the power grid data flow; An evaluation model construction module, which is connected to the indicator selection module, and is used to determine the weight of each evaluation indicator according to the sensitivity of each selected evaluation indicator to the change of the power grid data flow, and to construct a power grid data flow evaluation model based on each evaluation indicator and the weight of each evaluation indicator, wherein each selected evaluation indicator includes a general evaluation indicator and a specific evaluation indicator; An exception handling module, which is connected to the evaluation model building module, is used to determine an exception handling method for the abnormal power grid data flow data according to the degree of influence of the abnormal power grid data flow data on the evaluation result in the evaluation result of the power grid data flow evaluation model; An adjustment module is connected to the abnormality processing module and is used to determine whether to adjust the parameters of the power grid data flow evaluation process according to the fluctuation range of the accuracy of the evaluation result of the power grid data flow evaluation model within a preset time.

2. The intelligent evaluation system for power grid cash flow according to claim 1 is characterized in that: The indicator selection module selects the general evaluation indicator based on the overlap of data flow evaluation indicators of several companies, and determines the data flow evaluation indicator as the general evaluation indicator according to the comparison result that the overlap of several data flow evaluation indicators is greater than or equal to the preset overlap.

3. The intelligent evaluation system for power grid cash flow according to claim 2 is characterized in that: The overlap of the data flow evaluation indicators of the several companies is determined according to the ratio of the number of times a single data flow evaluation indicator is used to the number of the several companies.

4. The intelligent evaluation system for power grid cash flow according to claim 3 is characterized in that: The evaluation model building module determines the weight of each evaluation indicator according to the sensitivity of each selected evaluation indicator to the change of power grid data flow, including adjusting the value of each evaluation indicator one by one to obtain the power grid data flow change value to determine the sensitivity, and calculating the corresponding weight based on the sensitivity of each evaluation indicator.

5. The intelligent evaluation system for power grid cash flow according to claim 4 is characterized in that: The evaluation model construction module constructs a power grid data flow evaluation model based on the various evaluation indicators and the weights of the various evaluation indicators, including weighted summing up the selected evaluation indicators and the corresponding weights to obtain the evaluation results, and inputting the above data into the neural network model for training to obtain the power grid data flow evaluation model.

6. The intelligent evaluation system for power grid cash flow according to claim 5 is characterized in that: The exception handling module determines the exception handling method for the abnormal power grid data flow data, including: The abnormal processing module determines to perform data smoothing processing on the abnormal power grid data flow data according to a comparison result that the influence degree of the abnormal power grid data flow data on the evaluation result in the evaluation result of the power grid data flow evaluation model is less than a first preset influence degree; The abnormal processing module determines to perform difference replacement processing on the abnormal power grid data flow data according to the comparison result that the influence degree of the abnormal power grid data flow data on the evaluation result in the evaluation result of the power grid data flow evaluation model is greater than or equal to the first preset influence degree and less than the second preset influence degree; The exception processing module determines to delete the abnormal power grid data flow data according to the comparison result that the influence degree of the abnormal power grid data flow data on the evaluation result of the power grid data flow evaluation model is greater than or equal to the second preset influence degree.

7. The intelligent evaluation system for power grid cash flow according to claim 6 is characterized in that: The degree of influence of the abnormal power grid data flow data on the evaluation results is determined based on the difference value of the evaluation results before and after the abnormal values ​​are removed, the first preset degree of influence is determined based on one tenth of the maximum difference value of the evaluation results before and after the abnormal values ​​are removed in the historical evaluation process, and the second preset degree of influence is determined based on one eighth of the maximum difference value of the evaluation results before and after the abnormal values ​​are removed in the historical evaluation process.

8. The intelligent evaluation system for power grid cash flow according to claim 7 is characterized in that: The adjustment module determines whether to adjust the parameters of the power grid data flow evaluation process, including determining the need to adjust the parameters of the power grid data flow evaluation process based on a comparison result that the fluctuation range of the accuracy of the evaluation results of the power grid data flow evaluation model within a preset time is greater than or equal to a preset fluctuation range, wherein the power grid data flow evaluation process parameters include a preset overlap degree and a second preset influence degree.

9. The intelligent evaluation system for power grid cash flow according to claim 8, characterized in that: The preset fluctuation range is determined according to the average fluctuation range of the accuracy of the evaluation result of the power grid data flow evaluation model within a preset time in the historical evaluation process.

10. The intelligent evaluation system for power grid cash flow according to claim 9, characterized in that: The adjustment amount of the preset overlap degree is positively correlated with the density of the fluctuation range of the accuracy of the evaluation results of the power grid data flow evaluation model within the preset time, and the adjustment amount of the second preset influence degree is negatively correlated with the density of the fluctuation range of the accuracy of the evaluation results of the power grid data flow evaluation model within the preset time.

Images