Performance evaluation method and device, nonvolatile storage medium and electronic equipment

Abstract

The invention discloses a performance evaluation method and device, a nonvolatile storage medium and electronic equipment. The method comprises the following steps: obtaining evaluation index data generated by a to-be-evaluated object in a previous detection period, the evaluation index data comprising power operation data and service quality data; determining an index type corresponding to each evaluation index data, and classifying all the evaluation index data into a plurality of data sets according to the index types; the multiple data sets are processed and analyzed through a performance evaluation model, a data processing result is obtained, the data processing result is used for indicating performance scores of the to-be-evaluated objects, and the performance evaluation model is obtained by training a neural network model with historical evaluation index data of multiple different to-be-evaluated objects as training data. The technical problem that the evaluation result is inaccurate due to the fact that performance evaluation is carried out by counting and analyzing data in a manual mode is solved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a performance evaluation method and device, a non-volatile storage medium, and an electronic device. Background Art

[0002] The traditional performance indicator evaluation system of power companies has a large number of data sources, which need to be reported step by step and then manually summarized and then the performance evaluation is carried out based on the summarized data. The risk of data being tampered in the process of reporting step by step, and the manual calculation method will lead to inaccurate performance evaluation results;

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a performance evaluation method and device, a non-volatile storage medium, and an electronic device to at least solve the technical problem of inaccurate evaluation results caused by using manual statistical analysis of data to perform performance evaluation.

[0005] According to one aspect of an embodiment of the present application, a performance evaluation method is provided, comprising: obtaining evaluation index data generated by an object to be evaluated in a previous detection cycle, wherein the evaluation index data comprises: power operation data and service quality data, the power operation data is used to indicate the operation status of a power grid, the service quality data is used to indicate the evaluation of the power grid on the user side, and the object to be evaluated is an object for managing the power grid; determining the indicator type corresponding to each evaluation index data, and classifying all the evaluation index data into multiple data sets according to the indicator type, wherein the indicator types comprise: a first type of indicator for indicating the operation result of the power grid, a second type of indicator for indicating the operation efficiency of the power grid, and a third type of indicator for performing risk assessment on the operation of the power grid; using a performance evaluation model to process and analyze multiple data sets to obtain data processing results, wherein the data processing results are used to indicate the performance score of the object to be evaluated, and the performance evaluation model is obtained by training a neural network model using historical evaluation index data of multiple different objects to be evaluated as training data.

[0006] Optionally, power operation data include: electricity sales, average power outage time for users, total profit, line loss rate, business expansion service time limit compliance rate, 10 kV line loss compliance rate, energy efficiency service index, the energy efficiency service index includes: energy consumption reduction rate, clean energy utilization rate; service quality data include: the number of violations, the number of power outages for more than 1,000 households due to a single fault, and the number of safety incidents, and safety incidents include: power equipment failure, personal injury incidents caused by power grid failure, and power equipment network failure; all evaluation indicator data are classified into multiple data sets according to the indicator type, including: electricity sales, average power outage time for users, total profit and energy efficiency service index are classified as data sets corresponding to the first category of indicators; line loss rate, business expansion service time limit compliance rate, and 10 kV line loss compliance rate are classified as data sets corresponding to the second category of indicators; the number of violations, the number of power outages for more than 1,000 households due to a single fault and the number of safety incidents are classified as data sets corresponding to the third category of indicators.

[0007] Optionally, a performance evaluation model is used to process and analyze the data set to obtain data processing results, including: using the performance evaluation model to process and analyze the first category of indicators, the second category of indicators, and the third category of indicators respectively to obtain multiple prediction values, wherein the prediction values ​​include: a first prediction value corresponding to the first category of indicators, a second prediction value corresponding to the second category of indicators, and a third prediction value corresponding to the third category of indicators, the first prediction value is used to indicate the operating results of the power grid in the next detection cycle, the second prediction value is used to indicate the operating efficiency of the power grid in the next detection cycle, and the third prediction value is used to indicate the risk events of the power grid in the next detection cycle; the data processing results are determined based on the multiple prediction values.

[0008] Optionally, determining the data processing result according to multiple predicted values ​​includes: obtaining identification information of the object to be evaluated, wherein the identification information is used to indicate the functional attributes of the object to be evaluated; determining a reference indicator value associated with the identification information, and obtaining multiple weight coefficients associated with the identification information, wherein the multiple weight coefficients correspond to multiple scoring dimensions, and the reference indicator value includes multiple reference values, and the multiple reference values ​​include: a first reference value corresponding to a first category of indicators, a second reference value corresponding to a second category of indicators, and a third reference value corresponding to a third category of indicators; jointly determining the data processing result according to the multiple predicted values, the multiple reference values, and the multiple weight coefficients.

[0009] Optionally, the data processing result is determined based on the multiple predicted values, multiple reference values, and multiple weight coefficients, including: for each indicator type, determining the predicted value and reference value corresponding to the indicator type, and determining the ratio of the predicted value to the reference value; determining the scoring factor corresponding to each scoring dimension, wherein the scoring factor includes: at least one ratio; for each scoring dimension, determining the product of the scoring factor and the weight coefficient to obtain multiple products; and determining the cumulative result of the multiple products as the data processing result.

[0010] Optionally, before obtaining the data processing result, it includes: determining a first ratio of the predicted value and the reference value corresponding to the first category of indicators, and issuing a first alarm message when the first ratio is less than a first threshold, wherein the first alarm message is used to indicate that the operation result of the power grid is abnormal, and the first threshold is the minimum value of the first ratio when the power grid is operating normally; determining a second ratio of the predicted value and the reference value corresponding to the second category of indicators, and issuing a second alarm message when the second ratio is less than a second threshold, wherein the second alarm message is used to indicate that the operation efficiency of the power grid is abnormal, and the second threshold is the minimum value of the second ratio when the power grid is operating normally.

[0011] Optionally, the performance evaluation method also includes: in each detection cycle, using the evaluation index data generated by the object to be evaluated in the previous detection cycle to test the performance evaluation model to obtain the prediction accuracy; when the prediction accuracy is less than the preset accuracy, retraining the performance evaluation model.

[0012] According to another aspect of an embodiment of the present application, a performance evaluation device is also provided, including: an acquisition module, used to acquire evaluation index data generated by an object to be evaluated in a previous detection cycle, wherein the evaluation index data include: power operation data and service quality data, the power operation data is used to indicate the operation status of the power grid, the service quality data is used to indicate the evaluation of the power grid on the user side, and the object to be evaluated is an object for managing the power grid; a determination module, used to determine the indicator type corresponding to each evaluation index data, and classify all the evaluation index data into multiple data sets according to the indicator type, wherein the indicator types include: a first type of indicator for indicating the operation result of the power grid, a second type of indicator for indicating the operation efficiency of the power grid, and a third type of indicator for performing risk assessment on the operation of the power grid; a processing module, used to process and analyze multiple data sets using a performance evaluation model to obtain a data processing result, wherein the data processing result is used to indicate the performance score of the object to be evaluated, and the performance evaluation model is obtained by training a neural network model using historical evaluation index data of multiple different objects to be evaluated as training data.

[0013] According to another aspect of an embodiment of the present application, a non-volatile storage medium is provided, in which a computer program is stored, wherein the above-mentioned performance evaluation method is executed by running the computer program on a device where the non-volatile storage medium is located.

[0014] According to another aspect of an embodiment of the present application, there is also provided an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above-mentioned performance evaluation method through the computer program.

[0015] According to another aspect of the embodiments of the present application, a computer program product is also provided, including computer instructions, which implement the steps of the above-mentioned performance evaluation method when executed by a processor.

[0016] In an embodiment of the present application, the evaluation index data generated by the object to be evaluated in the previous detection cycle is obtained, wherein the evaluation index data includes: power operation data and service quality data, the power operation data is used to indicate the operation status of the power grid, the service quality data is used to indicate the evaluation of the power grid on the user side, and the object to be evaluated is the object of managing the power grid; the indicator type corresponding to each evaluation index data is determined, and all the evaluation index data are classified into multiple data sets according to the indicator type, wherein the indicator type includes: a first type of indicator for indicating the operation result of the power grid, a second type of indicator for indicating the operation efficiency of the power grid, and a third type of indicator for risk assessment of the operation of the power grid; and a performance evaluation model is used to process multiple data sets. The method realizes automated performance evaluation by analyzing and obtaining data processing results, wherein the data processing results are used to indicate the performance score of the object to be evaluated, and the performance evaluation model is obtained by training the neural network model with historical evaluation index data of multiple different objects to be evaluated as training data; by classifying the data according to the indicator type represented by the data, a trained neural network model (i.e., the performance evaluation model) is used to perform performance evaluation on the object to be evaluated according to multiple data sets obtained according to the above classification, thereby achieving the purpose of avoiding manual participation in statistical calculations, thereby achieving the technical effect of improving the accuracy of the performance evaluation results, and further solving the technical problem of inaccurate evaluation results caused by using manual statistical analysis of data to perform performance evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 is a hardware structure block diagram of a computer terminal for implementing a performance evaluation method according to an embodiment of the present application;

[0019] Figure 2 is a flowchart of a method for performance evaluation according to an embodiment of the present application;

[0020] Figure 3 It is a structural diagram of a performance evaluation device according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings 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. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] In order to better understand the embodiments of the present application, the technical terms involved in the embodiments of the present application are explained as follows:

[0024] Line loss rate (line loss rate): the percentage of electric energy lost in the power network (line loss load) to the electric energy supplied to the power network (power supply load).

[0025] Business expansion services: Business related to adding new users of the power grid.

[0026] Business expansion service time limit compliance rate: the ratio of the number of business expansion services completed within the prescribed time limit to the total number of business expansion service applications.

[0027] Clean energy utilization rate: the proportion of clean energy (such as wind energy and solar energy) in total power generation.

[0028] In the related art, data is manually summarized and performance evaluation is performed on the subject to be evaluated based on the summarized data. Therefore, there is a problem of inaccurate performance evaluation results. In order to solve this problem, a relevant solution is provided in the embodiments of the present application, which is described in detail below.

[0029] According to an embodiment of the present application, a method embodiment of a performance evaluation method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing a performance evaluation method. Figure 1 As shown, the computer terminal 10 may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0031] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0032] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the () method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned () method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0033] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0034] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .

[0035] The embodiment of the present application provides a performance evaluation method that can be run in the above-mentioned operating environment. Figure 2 is a flowchart of the steps of the performance evaluation method provided in the embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0036] Step S202, obtaining the evaluation index data generated by the object to be evaluated in the previous detection cycle, wherein the evaluation index data includes: power operation data and service quality data, the power operation data is used to indicate the operation status of the power grid, and the service quality data is used to indicate the evaluation of the power grid on the user side, and the object to be evaluated is the object of managing the power grid.

[0037] The embodiment of the present application provides an automated performance evaluation method, which uses a trained neural network model to process and analyze the data (i.e., evaluation index data) generated by each object to be evaluated in each evaluation cycle (i.e., detection cycle) to manage the power grid and output the performance evaluation result of the object to be evaluated. In step S202, if the object to be evaluated is to be evaluated, it is necessary to first obtain the relevant data generated by the object to be evaluated in the evaluation cycle. For example, the relevant data generated by the object to be evaluated in the previous evaluation cycle (i.e., detection cycle) to manage the power grid can be obtained, and the relevant data can be processed and analyzed to obtain the performance evaluation result of the object to be evaluated in the previous evaluation cycle. The evaluation cycle of the object to be evaluated is the detection cycle for obtaining the relevant data of the power grid. The data generated by the object to be evaluated in the evaluation cycle includes: power operation data used to reflect the operation of the power grid, and service quality data used to reflect the evaluation of the power grid by the user side; in addition, in this embodiment, the management unit of the power grid referred to by the object to be evaluated is, for example, a power supply enterprise, power companies at all levels (such as provincial and county levels), and units with different functions in the power supply enterprise (such as business units and market units). The data of the evaluation indicators can be obtained through both online and offline channels. Acquisition through online channels refers to automatically accessing the power grid and the application programming interface (API) of the power grid management device that executes the method device / system provided in the embodiment of the present application to obtain the evaluation indicator data. Acquisition through offline channels refers to the user inputting the evaluation indicator data in the interactive interface of the method device / system that executes the embodiment of the present application.

[0038] Step S204, determine the indicator type corresponding to each evaluation indicator data, and classify all the evaluation indicator data into multiple data sets according to the indicator type, wherein the indicator type includes: a first type of indicator for indicating the operating results of the power grid, a second type of indicator for indicating the operating efficiency of the power grid, and a third type of indicator for performing risk assessment on the operation of the power grid.

[0039] In this embodiment, if the performance of the object to be evaluated in the last evaluation cycle is to be determined, then after the relevant data generated by the object to be evaluated in the last evaluation cycle to be evaluated is obtained in step S202, in step S204, the obtained evaluation index data is classified to use the classified data to determine the performance of the object to be evaluated under different evaluation dimensions. In this embodiment, the evaluation index data is classified according to the index type, wherein the index type is divided into index data for indicating the operation results of the power grid (i.e., the first type of index), index data for indicating the operation efficiency of the power grid (i.e., the second type of index) and index data for risk assessment of the operation of the power grid (i.e., the third type of index); the index data for indicating the operation results of the power grid is the relevant data generated by the actual operation of the power grid, such as power consumption; the index data for indicating the operation efficiency of the power grid is the data further calculated based on the relevant data generated by the actual operation of the power grid, such as the ratio of power consumption to power generation of the power grid in the same period; the index data for risk assessment of the operation of the power grid is the data related to the failure of the power grid, such as the number of failures and the type of failures of the power grid in a period of time.

[0040] Optionally, power operation data include: electricity sales, average power outage time for users, total profit, line loss rate, business expansion service time limit compliance rate, 10 kV line loss compliance rate, energy efficiency service index, the energy efficiency service index includes: energy consumption reduction rate, clean energy utilization rate; service quality data include: the number of violations, the number of power outages for more than 1,000 households due to a single fault, and the number of safety incidents, and safety incidents include: power equipment failure, personal injury incidents caused by power grid failure, and power equipment network failure; all evaluation indicator data are classified into multiple data sets according to the indicator type, including: electricity sales, average power outage time for users, total profit and energy efficiency service index are classified as data sets corresponding to the first category of indicators; line loss rate, business expansion service time limit compliance rate, and 10 kV line loss compliance rate are classified as data sets corresponding to the second category of indicators; the number of violations, the number of power outages for more than 1,000 households due to a single fault and the number of safety incidents are classified as data sets corresponding to the third category of indicators.

[0041] The evaluation index data obtained in step S202 include power operation data generated by power grid operation and service quality data related to the services of the power grid, wherein the power operation data include: the power generation of the power grid (i.e., power sales), the average power outage time of users within the detection period, the total profit generated within the detection period, the line loss rate of the power grid within the detection period, the compliance rate of the business expansion service time limit of the object to be evaluated within the detection period, the compliance rate of the line loss when the power grid power generation is 10 kilovolts, and the data used to illustrate the energy efficiency of the power grid (i.e., the energy efficiency service index) include: the reduction ratio of the energy consumption generated by the power grid in the detection period to be evaluated relative to the energy consumption generated by the power grid in the previous detection period of the detection period to be evaluated (i.e., the energy consumption reduction rate), and the clean energy utilization rate of the power grid in the inspection period to be evaluated. The service quality data include: the number of violations related to the power grid during the detection period, the number of single fault power outages exceeding one thousand households during the detection period, and the number of safety incidents that occurred during the detection period. The above-mentioned violations include: failure to operate the power equipment of the power grid in accordance with operating specifications or technical requirements; safety incidents include: power equipment failure (failure of the power equipment itself), personal injury caused by power grid failure (including injury to users of the power grid and injury to technicians operating the power grid), and network failure of power equipment. In this embodiment, when classifying the evaluation index data according to the index type in step S204, the electricity sales volume, average power outage time for users, total profit and energy efficiency service index in the above-mentioned power operation data and service quality data are classified into a data set, which is a set of index data (i.e., first-class indicators) used to indicate the operation results of the power grid; the line loss rate, the business expansion service time limit compliance rate, and the 10 kV line loss compliance rate are classified into another data set, which is a set of index data (i.e., second-class indicators) used to indicate the operation efficiency of the power grid; the number of violations, the number of power outages exceeding 1,000 households due to a single fault, and the number of safety incidents are classified into another data set, which is a set of index data (i.e., third-class indicators) used to conduct risk assessment on the operation of the power grid. When classifying the evaluation index data in step S204, the key indicator method (KPI), the management by objectives method (MBO) and the critical incident method (CIM) can be used. The evaluation index data that conforms to the key indicator method (KPI) is classified as the first category of indicators, the evaluation index data that conforms to the management by objectives method (MBO) is classified as the second category of indicators, and the evaluation index data that conforms to the critical incident method (CIM) is classified as the third category of indicators.

[0042] Step S206, using the performance evaluation model to process and analyze multiple data sets to obtain data processing results, wherein the data processing results are used to indicate the performance score of the object to be evaluated. The performance evaluation model is obtained by training a neural network model using historical evaluation indicator data of multiple different objects to be evaluated as training data.

[0043] After the acquired evaluation index data is classified according to the index type, in step S206, the performance evaluation model is used to process and analyze the classified evaluation index data to obtain the data processing result output by the performance evaluation model, wherein the data processing result is in the form of a numerical value, which is the performance evaluation result (i.e., performance score) of the object to be evaluated. In this embodiment, the performance evaluation model is used to complete the automated performance evaluation. The performance evaluation model used in step S206 is a trained neural network model. When training the neural network model, the relevant data (i.e., historical evaluation index data) generated by multiple different objects managing the power grid (i.e., multiple objects to be evaluated) in managing the power grid before the current moment is used as training data.

[0044] In step S206, the performance evaluation model may be loaded into the memory, for example, the raw data of the performance evaluation model may be loaded from the non-volatile memory into the volatile memory, so that the processor runs the performance evaluation model. The raw data of the performance evaluation model refers to unprocessed data, and generally includes parameters and structural data of the performance evaluation model. The structural data may be a calculation relationship based on the parameters, such as a forward propagation calculation relationship between intermediate layers and neurons. Specifically, the structural data may include code related to the structure of the performance evaluation model, such as code for executing related calculations between intermediate layers and neurons.

[0045] In one embodiment, an area for loading the performance evaluation model can be divided in the memory, which can include a structure data storage area and a parameter storage area. The structure data storage area is used to store structure-related codes, and the parameters referenced by it can point to the address of a specific parameter in the parameter storage area through a pointer. During the training process of the performance evaluation model, it may be necessary to frequently update the parameters, and the parameter values ​​in the parameter storage area can be updated.

[0046] According to an optional embodiment of the present application, a performance evaluation model is used to process and analyze a data set to obtain a data processing result, including: using the performance evaluation model to process and analyze a first category of indicators, a second category of indicators, and a third category of indicators respectively to obtain a plurality of prediction values, wherein the prediction values ​​include: a first prediction value corresponding to the first category of indicators, a second prediction value corresponding to the second category of indicators, and a third prediction value corresponding to the third category of indicators, the first prediction value is used to indicate the operating result of the power grid in the next detection cycle, the second prediction value is used to indicate the operating efficiency of the power grid in the next detection cycle, and the third prediction value is used to indicate the risk event of the power grid in the next detection cycle; the data processing result is determined based on the plurality of prediction values.

[0047] The performance evaluation model provided in the embodiment of the present application includes multiple neural networks, which can process data in parallel at the same time. In this embodiment, the performance evaluation model includes at least four neural networks, and these three neural networks can run in parallel. These three neural networks are used to process the data set corresponding to the first type of indicators, the data set corresponding to the second type of indicators, and the data set corresponding to the third type of indicators. A neural network of the performance evaluation model processes and analyzes the data set corresponding to the first type of indicators and outputs a numerical set (i.e., a first prediction value). The data in this numerical set (i.e., the first prediction value) is the predicted value of the operation result of the power grid in the next detection cycle. For example, the data set corresponding to the first type of indicators includes: power sales, average power outage time for users, total profit, and energy efficiency service index. The first prediction value includes: the predicted value of power sales in the next detection cycle, the predicted value of the average power outage time for users in the next detection cycle, the predicted value of the total profit in the next detection cycle, and multiple predicted values ​​of multiple energy efficiency service indexes in the next detection cycle. The neural network used to process and analyze the data set of the second type of indicators in the performance evaluation model outputs another data set (i.e., the second predicted value). The data in this numerical set (i.e., the second predicted value) is the predicted value of the operating efficiency of the power grid in the next detection cycle. For example, the data set corresponding to the second type of indicators includes: line loss rate, business expansion service time limit compliance rate, and 10 kV line loss compliance rate. The second predicted value includes: the predicted value of the line loss rate in the next detection cycle, the predicted value of the business expansion service time limit compliance rate in the next detection cycle, and the predicted value of the 10 kV line loss compliance rate in the next detection cycle. The data set corresponding to the third type of indicators is used to process and output another data set (i.e., the third predicted value). The data in this numerical set (i.e., the third predicted value) is the predicted value of the risk events of the power grid in the next detection cycle. For example, the data set corresponding to the third type of indicators includes: the number of violations, the number of power outages exceeding 1,000 households due to a single fault, and the number of safety events. The third predicted value includes: the predicted value of the number of violations in the next detection cycle, the predicted value of the number of power outages exceeding 1,000 households due to a single fault in the next detection cycle, and the predicted value of the number of safety events in the next detection cycle. The performance evaluation model further processes the predicted values ​​output by the above three neural networks in other neural networks different from the above three neural networks to obtain the performance score of the object to be evaluated (i.e., the data processing result).

[0048] Optionally, determining the data processing result according to multiple predicted values ​​includes: obtaining identification information of the object to be evaluated, wherein the identification information is used to indicate the functional attributes of the object to be evaluated; determining a reference indicator value associated with the identification information, and obtaining multiple weight coefficients associated with the identification information, wherein the multiple weight coefficients correspond to multiple scoring dimensions, and the reference indicator value includes multiple reference values, and the multiple reference values ​​include: a first reference value corresponding to a first category of indicators, a second reference value corresponding to a second category of indicators, and a third reference value corresponding to a third category of indicators; jointly determining the data processing result according to the multiple predicted values, the multiple reference values, and the multiple weight coefficients.

[0049] As mentioned in the above embodiment, the performance evaluation model jointly processes and analyzes different prediction values ​​corresponding to different indicator types in a neural network layer to obtain the performance score of the object to be evaluated (i.e., the data processing result); in this embodiment, when jointly processing and analyzing different prediction values ​​corresponding to different indicator types, firstly, the reference value of each indicator type is determined according to the identification information of the object to be evaluated, wherein the identification information records the functional attributes of the object to be evaluated, and these reference values ​​are the normal numerical ranges of different evaluation indicator data when the power grid operates normally and operates the power grid in accordance with the operating specifications; and, at the same time, multiple weight coefficients associated with the object to be evaluated are determined according to the identification information of the object to be evaluated; the weight coefficient is the basic weight coefficient under different dimensions, which is used to illustrate the influence of each scoring dimension on the performance score of the object to be evaluated. The larger the weight coefficient, the higher the influence of this evaluation dimension on the performance score of the object to be evaluated; for objects to be evaluated with different functional attributes, their basic weight coefficients under different scoring dimensions are different. For example, the objects to be evaluated are business units and market units in power supply enterprises, and the basic weight coefficients corresponding to the business units and market units under the same scoring dimension are different; the scoring dimension can include: safety and efficiency, business management, development planning, customer service, and scientific and technological innovation. In this embodiment, the reference value corresponding to each type of indicator is different. For example, for the first type of indicator, the corresponding data set includes electricity sales, average power outage time for users, total profit and multiple energy efficiency service indexes. The data set including the reference value of electricity sales, the reference value of average power outage time for users, the reference value of total profit and multiple reference values ​​corresponding to multiple energy efficiency service indexes is the first reference value; the data set corresponding to the second type of indicator includes line loss rate, business expansion service time limit compliance rate and 10 kV line loss compliance rate. The data set consisting of the reference value of line loss rate, the reference value of business expansion service time limit compliance rate and the reference value of 10 kV line loss compliance rate is classified as the second reference value; for the third type of indicator, it includes the number of violations, the number of power outages exceeding 1,000 households due to a single fault and the number of safety incidents. The reference value corresponding to the third type of indicator (i.e., the third reference value) includes: the reference value of the number of violations, the reference value of the number of power outages exceeding 1,000 households due to a single fault and the reference value of the number of safety incidents. Next, the performance score of the object to be evaluated (ie, the data processing result) is determined based on multiple predicted values ​​output by the neural network that processes the indicator data in the performance evaluation model, multiple reference values ​​associated with the object to be evaluated, and multiple weight coefficients.

[0050] According to another optional embodiment of the present application, a data processing result is determined based on multiple prediction values, multiple reference values, and multiple weight coefficients, including: for each indicator type, determining the prediction value and reference value corresponding to the indicator type, and determining the ratio of the prediction value to the reference value; determining a scoring factor corresponding to each scoring dimension, wherein the scoring factor includes: at least one ratio; for each scoring dimension, determining the product of the scoring factor and the weight coefficient to obtain multiple products; and determining the cumulative result of the multiple products as the data processing result.

[0051] In this embodiment, when the performance score (i.e., data processing result) of the object to be evaluated is determined based on multiple predicted values ​​output by the neural network that processes the indicator data in the performance evaluation model, multiple reference values ​​associated with the object to be evaluated, and multiple weight coefficients, the score value of the object to be evaluated in each scoring dimension is first determined. Specifically, different scoring factors are used to perform the performance score of the object to be evaluated in each scoring dimension. For example, the scoring factor of scoring dimension A is the qualified ratio of the first category of indicators, and the scoring factor of scoring dimension B is the qualified ratio of the first category of indicators and the qualified ratio of the second category of indicators. For example, the scoring factor of the scoring dimension of safety and efficiency is the qualified ratio of the third category of indicators. and the qualified ratio of the second type of indicators, the scoring factor of the scoring dimension of business management is the qualified ratio of the first type of indicators, the scoring factor of the scoring dimension of development planning is the qualified ratio of the second type of indicators and the qualified ratio of the third type of indicators, the scoring factor of the scoring dimension of customer service is the qualified ratio of the second type of indicators and the qualified ratio of the first type of indicators, and the scoring factor of the scoring dimension of scientific and technological innovation is the qualified ratio of the second type of indicators; the qualified ratio of each type of indicator mentioned above is the ratio of the predicted value of this type of indicator to the reference value of this type of indicator, which is used to indicate the probability that the data of this type of indicator will still be qualified in the next detection cycle when the object to be evaluated continues to manage the power grid in the current way in the detection cycle. When determining the score value of the object to be evaluated under each scoring dimension, the weight coefficient corresponding to the scoring dimension is multiplied by the multiple scoring factors under the scoring dimension, and the product obtained is the score value of the object to be evaluated under the scoring dimension; if there is only one scoring factor in the scoring dimension, the product of this scoring factor and the weight coefficient of the scoring dimension is used as the score value of the object to be evaluated in the scoring dimension; the sum of the score values ​​of the object to be evaluated in each scoring dimension is the performance score value of the object to be evaluated.

[0052] According to some optional embodiments of the present application, before obtaining the data processing result, it includes: determining a first ratio of the predicted value and the reference value corresponding to the first category of indicators, and issuing a first alarm message when the first ratio is less than a first threshold value, wherein the first alarm message is used to indicate that the operation result of the power grid is abnormal, and the first threshold value is the minimum value of the first ratio when the power grid is operating normally; determining a second ratio of the predicted value and the reference value corresponding to the second category of indicators, and issuing a second alarm message when the second ratio is less than a second threshold value, wherein the second alarm message is used to indicate that the operation efficiency of the power grid is abnormal, and the second threshold value is the minimum value of the second ratio when the power grid is operating normally.

[0053] The method provided in the embodiment of the present application can also realize the function of abnormal indicator warning. In this embodiment, before the object to be evaluated is comprehensively scored, it is separately detected whether there is a possibility of abnormality in the dimension of each type of indicator of the object to be evaluated, mainly to detect whether there is a possibility of abnormality in the operation of the power grid. For example, the ratio of the predicted value of the first type of indicator used to indicate the operation result of the power grid to the reference value (i.e., the first ratio) is compared with the threshold value corresponding to the first type of indicator (i.e., the first threshold value). In this embodiment, the threshold value corresponding to the first type of indicator (i.e., the first threshold value) is set to the minimum value of the ratio of the predicted value of the first type of indicator to the reference value (i.e., the first ratio) when the power grid operates normally. Therefore, when the first ratio is less than the first threshold, an alarm message indicating that the operation result of the power grid is abnormal (i.e., the first alarm message) is output. When the ratio of the predicted value of the second type of indicator used to indicate the operating efficiency of the power grid to the reference value (i.e., the second ratio) is compared with the threshold value corresponding to the second type of indicator (i.e., the second threshold), in this embodiment, the threshold value corresponding to the second type of indicator (i.e., the second threshold) is set to the minimum value of the ratio of the predicted value of the second type of indicator to the reference value (i.e., the second ratio) when the power grid operates normally. Therefore, when the second ratio is less than the second threshold, an alarm message indicating abnormal power grid operating efficiency (i.e., the second alarm message) is output.

[0054] According to an optional embodiment of the present application, the performance evaluation method also includes: in each detection cycle, using the evaluation index data generated by the object to be evaluated in the previous detection cycle to test the performance evaluation model to obtain the prediction accuracy; when the prediction accuracy is less than the preset accuracy, retraining the performance evaluation model.

[0055] In this embodiment, since the performance evaluation model can be used to evaluate different models to be evaluated, in order to improve the accuracy of performance scoring, the accuracy of the performance evaluation model can be verified by using test data before using the performance evaluation model in each detection cycle, wherein the test data can be the evaluation index data generated by the object to be evaluated in the previous detection cycle; if the verification result indicates that the accuracy of the result output by the performance evaluation model is less than the preset accuracy (such as 80%), the evaluation index data of the object to be evaluated to which the test data belongs is used to retrain the model to be evaluated, for example, the evaluation index data of the object to be evaluated to which the test data belongs in the previous 12 months at the current moment is used to retrain the performance evaluation model. In the embodiment of the present application, a long short-term memory network (LSTM) model can be used as the original model of the performance evaluation model, and it can be trained using the historical evaluation index data of multiple objects to be evaluated; during training, the training data is input into the LSTM model in batches, and passes through the input gate, forget gate and output gate in the LSTM respectively, and finally input into the fully connected neural layer to obtain the predicted value of the model; wherein, the calculation method of each gate in the LSTM is as follows: t =σ(W f ·[h t-1 ,x t ]+h f ),i t =σ(W i ·[h t-1 ,x t ]+b i ), o t =σ(W o ·[h t-1 ,x t ]+b o ), where f t ,i t ,o t Respectively represent the forget gate, input gate and output gate; W f ,W i ,W c ,W o represents weight; b f ,b i ,b c ,b o represents the bias term; Represents the unit state of the current input; c t represents the unit state at the current moment; σ,tanh represents the activation function; h t-1 represents the hidden layer state at the previous moment, that is, the output state at the previous moment, which contains all the information related to the input at the current moment. t Represents the input test data.

[0056] Through the above steps, it is possible to implement automated performance evaluation using a neural network model, thereby improving the accuracy of performance evaluation results; in addition, the neural network model performs performance evaluation on the object to be evaluated under multiple different scoring dimensions, and integrates multiple performance evaluation results of the object to be evaluated under different dimensions to obtain the final performance score of the object to be evaluated, thereby enriching the scoring dimensions and improving the comprehensiveness of the performance evaluation of the object to be evaluated.

[0057] Figure 3 is a structural diagram of a performance evaluation device provided in an embodiment of the present application, such as Figure 3 As shown, the performance evaluation device includes: an acquisition module 30, which is used to obtain the evaluation index data generated by the object to be evaluated in the previous detection cycle, wherein the evaluation index data includes: power operation data and service quality data, the power operation data is used to indicate the operation status of the power grid, and the service quality data is used to indicate the evaluation of the power grid on the user side, and the object to be evaluated is the object of managing the power grid; a determination module 32, which is used to determine the indicator type corresponding to each evaluation index data, and classify all the evaluation index data into multiple data sets according to the indicator type, wherein the indicator type includes: a first type of indicator for indicating the operation result of the power grid, a second type of indicator for indicating the operation efficiency of the power grid, and a third type of indicator for risk assessment of the operation of the power grid; a processing module 34, which is used to process and analyze multiple data sets using a performance evaluation model to obtain a data processing result, wherein the data processing result is used to indicate the performance score of the object to be evaluated, and the performance evaluation model is obtained by training a neural network model using historical evaluation index data of multiple different objects to be evaluated as training data.

[0058] It should be noted that Figure 3 The preferred implementation of the illustrated embodiment can be found in Figure 2 The relevant description of the illustrated embodiment will not be repeated here.

[0059] An embodiment of the present application further provides a non-volatile storage medium, in which a computer program is stored, wherein the above performance evaluation method is executed by running the computer program on a device where the non-volatile storage medium is located.

[0060] The above-mentioned non-volatile storage medium is used to store programs that perform the following functions: obtaining evaluation index data generated by the object to be evaluated in the previous detection cycle, wherein the evaluation index data includes: power operation data and service quality data, the power operation data is used to indicate the operation status of the power grid, the service quality data is used to indicate the evaluation of the power grid on the user side, and the object to be evaluated is the object of managing the power grid; determining the indicator type corresponding to each evaluation index data, and classifying all the evaluation index data into multiple data sets according to the indicator type, wherein the indicator type includes: a first type of indicator used to indicate the operation result of the power grid, a second type of indicator used to indicate the operation efficiency of the power grid, and a third type of indicator used to perform risk assessment on the operation of the power grid; using a performance evaluation model to process and analyze multiple data sets to obtain data processing results, wherein the data processing results are used to indicate the performance score of the object to be evaluated, and the performance evaluation model is obtained by training a neural network model using historical evaluation index data of multiple different objects to be evaluated as training data.

[0061] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above performance evaluation method through the computer program.

[0062] The processor in the above-mentioned electronic device is used to run a program that performs the following functions: obtaining evaluation index data generated by the object to be evaluated in the previous detection cycle, wherein the evaluation index data includes: power operation data and service quality data, the power operation data is used to indicate the operation status of the power grid, the service quality data is used to indicate the evaluation of the power grid on the user side, and the object to be evaluated is the object of managing the power grid; determining the indicator type corresponding to each evaluation index data, and classifying all the evaluation index data into multiple data sets according to the indicator type, wherein the indicator type includes: a first type of indicator for indicating the operation result of the power grid, a second type of indicator for indicating the operation efficiency of the power grid, and a third type of indicator for risk assessment of the operation of the power grid; using a performance evaluation model to process and analyze multiple data sets to obtain data processing results, wherein the data processing results are used to indicate the performance score of the object to be evaluated, and the performance evaluation model is obtained by training a neural network model using historical evaluation index data of multiple different objects to be evaluated as training data.

[0063] The embodiment of the present application also provides a computer program product, including computer instructions, which implement the steps of the above performance evaluation method when executed by a processor.

[0064] It should be noted that the various modules in the above-mentioned performance evaluation device can be program modules (for example, a set of program instructions that implement a certain specific function) or hardware modules. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0065] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0066] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0067] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be 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 system, 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 through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0068] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0069] 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-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0070] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the relevant technology or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0071] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A performance evaluation method, characterized in that: include: Acquire evaluation index data generated by the object to be evaluated in the previous detection cycle, wherein the evaluation index data includes: power operation data and service quality data, the power operation data is used to indicate the operation status of the power grid, the service quality data is used to indicate the evaluation of the power grid on the user side, and the object to be evaluated is the object that manages the power grid; Determine the indicator type corresponding to each of the evaluation indicator data, and classify all of the evaluation indicator data into multiple data sets according to the indicator type, wherein the indicator type includes: a first type of indicator for indicating the operation result of the power grid, a second type of indicator for indicating the operation efficiency of the power grid, and a third type of indicator for performing risk assessment on the operation of the power grid; A performance evaluation model is used to process and analyze the multiple data sets to obtain data processing results, wherein the data processing results are used to indicate the performance score of the object to be evaluated. The performance evaluation model is obtained by training a neural network model using multiple different historical evaluation index data of the object to be evaluated as training data.

2. The method according to claim 1, characterized in that The power operation data include: power sales, average power outage time for users, total profit, line loss rate, business expansion service time limit compliance rate, 10 kV line loss compliance rate, energy efficiency service index, the energy efficiency service index includes: energy consumption reduction rate, clean energy utilization rate; the service quality data include: the number of violations, the number of power outages exceeding 1,000 households due to a single fault, and the number of safety incidents, the safety incidents include: power equipment failure, personal injury incidents caused by power grid failure, power equipment network failure; According to the indicator type, all the evaluation indicator data are classified into multiple data sets, including: Classifying the power sales, the average power outage time of the users, the total profit and the energy efficiency service index as a data set corresponding to the first category of indicators; Classify the line loss rate, the business expansion service time limit compliance rate, and the 10 kV line loss compliance rate as a data set corresponding to the second category of indicators; The number of times the violation incidents occurred, the number of times the single failure caused power outages of more than 1,000 households, and the number of safety incidents are classified as a data set corresponding to the third category of indicators.

3. The method according to claim 1, characterized in that The performance evaluation model is used to process and analyze the data set to obtain data processing results, including: The performance evaluation model is used to process and analyze the first category of indicators, the second category of indicators and the third category of indicators respectively to obtain multiple prediction values, wherein the prediction values ​​include: a first prediction value corresponding to the first category of indicators, a second prediction value corresponding to the second category of indicators, and a third prediction value corresponding to the third category of indicators, the first prediction value is used to indicate the operation result of the power grid in the next detection cycle, the second prediction value is used to indicate the operation efficiency of the power grid in the next detection cycle, and the third prediction value is used to indicate the risk event of the power grid in the next detection cycle; The data processing result is determined according to the multiple prediction values.

4. The method according to claim 3, characterized in that: Determining the data processing result according to the multiple prediction values ​​includes: Acquire identification information of the object to be evaluated, wherein the identification information is used to indicate the functional attributes of the object to be evaluated; Determine a reference indicator value associated with the identification information, and obtain a plurality of weight coefficients associated with the identification information, wherein the plurality of weight coefficients correspond to a plurality of scoring dimensions, and the reference indicator value includes a plurality of reference values, and the plurality of reference values ​​include: a first reference value corresponding to the first category indicator, a second reference value corresponding to the second category indicator, and a third reference value corresponding to the third category indicator; The data processing result is determined based on the multiple predicted values, the multiple reference values, and the multiple weight coefficients.

5. The method according to claim 4, characterized in that Determining the data processing result according to the plurality of predicted values, the plurality of reference values, and the plurality of weight coefficients comprises: For each of the indicator types, determining the predicted value and the reference value corresponding to the indicator type, and determining a ratio of the predicted value to the reference value; Determine a scoring factor corresponding to each of the scoring dimensions, wherein the scoring factor includes: at least one of the ratios; For each of the scoring dimensions, determining the product of the scoring factor and the weight coefficient to obtain a plurality of the products; An accumulation result of a plurality of the products is determined as the data processing result.

6. The method according to claim 5, characterized in that Before obtaining the data processing result, the method includes: Determine a first ratio of the predicted value and the reference value corresponding to the first type of indicator, and issue a first alarm message when the first ratio is less than a first threshold, wherein the first alarm message is used to indicate that the operation result of the power grid is abnormal, and the first threshold is the minimum value of the first ratio when the power grid is operating normally; Determine a second ratio of the predicted value and the reference value corresponding to the second type of indicator, and issue a second alarm message when the second ratio is less than a second threshold value, wherein the second alarm message is used to indicate that the operating efficiency of the power grid is abnormal, and the second threshold value is the minimum value of the second ratio when the power grid is operating normally.

7. The method according to claim 1, characterized in that The method also includes: in each detection cycle, using the evaluation index data generated by the object to be evaluated in the previous detection cycle to test the performance evaluation model to obtain the prediction accuracy; when the prediction accuracy is less than the preset accuracy, retraining the performance evaluation model.

8. A performance evaluation device, characterized in that: include: An acquisition module, used to acquire evaluation index data generated by the object to be evaluated in the previous detection cycle, wherein the evaluation index data includes: power operation data and service quality data, the power operation data is used to indicate the operation status of the power grid, and the service quality data is used to indicate the evaluation of the power grid on the user side, and the object to be evaluated is an object that manages the power grid; A determination module, used to determine the indicator type corresponding to each of the evaluation indicator data, and classify all of the evaluation indicator data into multiple data sets according to the indicator type, wherein the indicator type includes: a first type of indicator for indicating the operation result of the power grid, a second type of indicator for indicating the operation efficiency of the power grid, and a third type of indicator for performing risk assessment on the operation of the power grid; A processing module is used to process and analyze the multiple data sets using a performance evaluation model to obtain data processing results, wherein the data processing results are used to indicate the performance score of the object to be evaluated, and the performance evaluation model is obtained by training a neural network model using multiple different historical evaluation indicator data of the object to be evaluated as training data.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a computer program, wherein the performance evaluation method described in any one of claims 1 to 7 is executed by running the computer program on the device where the non-volatile storage medium is located.

10. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to execute the performance evaluation method according to any one of claims 1 to 7 through the computer program.

11. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the performance evaluation method described in any one of claims 1 to 7 are implemented.

Images