Personnel evaluation method, device and electronic equipment

Abstract

This application discloses a method, apparatus, and electronic device for personnel evaluation. The method includes: responding to a selection command, selecting a target prediction model from multiple prediction models pre-deployed on a cloud platform, wherein the prediction model is used to predict indicator values ​​for different stages of a chemical production process; inputting the data to be predicted into the target prediction model for prediction, obtaining a prediction result, wherein the data to be predicted is data generated after the operator adjusts the parameters of the operated equipment according to the target prediction model; and scoring the operator's operational quality based on the prediction result. This application solves the technical problem in related technologies where operator competence assessments are based solely on actual production and operational data, resulting in a single evaluation dimension and an inability to improve operator competence.

Description

Technical Field

[0001] The present application relates to the field of industrial automation, and in particular to a personnel evaluation method, device and electronic equipment. Background Art

[0002] In chemical production, the evaluation of personnel capabilities and performance is often limited to the direct results of actual operations, such as production efficiency, product quality, energy consumption indicators, etc. These evaluations are mainly based on daily production data and operation records. The evaluation dimensions are relatively single, and it is difficult to provide precise guidance on personnel operations based on the 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 personnel evaluation method, device and electronic device to at least solve the technical problem that the evaluation of operator capabilities in the related technology is based on actual production data and operation data, the evaluation dimension is single, and the operator's operating ability cannot be improved.

[0005] According to one aspect of an embodiment of the present application, a personnel evaluation method is provided, comprising: in response to a selection instruction, selecting a target prediction model from a plurality of prediction models pre-deployed on a cloud platform, wherein the prediction model is used to predict index values ​​of different sections of a chemical production process; inputting data to be predicted into the target prediction model for prediction to obtain a prediction result, wherein the data to be predicted is data generated after the operator adjusts the parameters of the operated equipment according to the target prediction model; and scoring the operator's operation quality according to the prediction result.

[0006] In some embodiments of the present application, the method further includes: predicting the data to be predicted by using a target prediction model deployed on a cloud server in the cloud platform to obtain a prediction result; and sending the prediction result to a local edge server.

[0007] In some embodiments of the present application, the data to be predicted is input into the target prediction model for prediction to obtain a prediction result, including: when the target prediction model is a first model, the prediction result is determined as a first prediction result, wherein the first model is used to predict the trend of the index value of the first section of the chemical production process within a preset time period; when the target prediction model is a second model, the prediction result is determined as a second prediction result, wherein the second model is used to predict the optimal index value of the chemical production process in the second section.

[0008] In some embodiments of the present application, the operation quality of the operator is scored based on the prediction results, including: determining the first indicator score corresponding to each indicator prediction value in the first prediction result; taking the weighted sum of the first indicator scores of all indicator prediction values ​​in the first prediction result and the indicator weights corresponding to the first indicator scores to determine the total score of the operator's operation quality.

[0009] In some embodiments of the present application, determining the first indicator score corresponding to each indicator prediction value in the first prediction result includes: when the first indicator prediction value in the first prediction result is less than the minimum value of the normal interval, determining the first indicator score corresponding to the first indicator prediction value as a first score, wherein the first score is determined by the minimum value of the normal interval, the first indicator prediction value and the first weight, the first weight is used to indicate the degree of difference between the minimum value of the normal interval and the first indicator prediction value, and the first indicator prediction value is the prediction value corresponding to any indicator in the first prediction result; when the first indicator prediction value is greater than or equal to the minimum value of the normal interval, and the first indicator prediction value is less than or equal to the maximum value of the normal interval, determining the first indicator score corresponding to the first indicator prediction value as a second score, wherein the second score is greater than the first score; when the first indicator prediction value is greater than the maximum value of the normal interval, determining the first indicator score corresponding to the first indicator prediction value as a third score, wherein the third score is determined by the maximum value of the normal interval, the first indicator prediction value and the second weight, the second weight is used to indicate the degree of difference between the first indicator prediction value and the maximum value of the normal interval, and the third score is less than the second score.

[0010] In some embodiments of the present application, the operation quality of the operator is scored based on the prediction result, including: determining the gap value between the optimal indicator value in the second prediction result and the data to be predicted; when the gap value is less than the minimum value of the evaluation interval, determining the operation quality score of the operator to be a fourth score; when the gap value is greater than the minimum value of the evaluation interval and less than or equal to the maximum value of the evaluation interval, determining the operation quality score of the operator to be a fifth score, wherein the fifth score is less than the fourth score; when the gap value is greater than the maximum value of the evaluation interval, determining the operation quality score of the operator to be a sixth score, wherein the sixth score is less than the fifth score.

[0011] In some embodiments of the present application, the method also includes: when the network of the cloud server is interrupted, predicting the data to be predicted by using the prediction model deployed on the local edge server to obtain intermediate calculation results; when the network of the cloud server is restored, sending the intermediate calculation results and the data to be predicted to the cloud server, and performing subsequent calculations on the data to be predicted based on the intermediate calculation results by the cloud server.

[0012] In some embodiments of the present application, the method also includes: when a target operating device fails, obtaining alarm information of the target operating device, wherein the alarm information includes the position number of the target operating device; querying a solution and operating experience matching the alarm information from an experience library based on the alarm information; and returning the solution and operating experience to the target operator corresponding to the target operating device.

[0013] According to another aspect of the embodiment of the present application, a personnel evaluation device is also provided, including: a selection module, used to select a target prediction model from multiple prediction models pre-deployed on a cloud platform in response to a selection instruction, wherein the prediction model is used to predict the index values ​​of different sections of a chemical production process; a prediction module, used to input the data to be predicted into the target prediction model for prediction to obtain a prediction result, wherein the data to be predicted is data generated after the operator adjusts the parameters of the operated equipment according to the target prediction model; and a scoring module, used to score the operator's operation quality based on the prediction result.

[0014] According to another aspect of the embodiment of the present application, there is also provided an electronic device, including: a memory and a processor, the memory being used to store program instructions; the processor being connected to the memory and being used to execute the above-mentioned personnel evaluation method.

[0015] In the embodiment of the present application, a cloud-edge collaborative computing method is adopted to predict data through a prediction model, and the operators are evaluated based on the prediction results, thereby achieving the purpose of intelligent guidance and evaluation of the chemical production process, thereby achieving the technical effect of timely feedback on the operation quality of personnel, improving the operation skills of personnel, and improving the safety and efficiency of chemical production, thereby solving the technical problem that the operator's ability assessment in the related technology is based on actual production data and operation data, the evaluation dimension is single, and the operator's operation ability cannot be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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:

[0017] Figure 1 It is a hardware structure block diagram of a computer terminal of a personnel evaluation method according to an embodiment of the present application;

[0018] Figure 2 is a flow chart of a personnel evaluation method according to an embodiment of the present application;

[0019] Figure 3 is a schematic diagram of an operation flow of a personnel evaluation method according to an embodiment of the present application;

[0020] Figure 4 It is a structural schematic diagram of a personnel 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] Cloud Platform (CP) refers to a platform in a computer network that provides data storage, computing resources, and application operating environment on the Internet through centralized hardware devices and software services, allowing users to obtain computing resources on an on-demand basis without the need for local hardware devices, thereby reducing operating costs and improving resource utilization.

[0025] AI model (Artificial Intelligence Model, abbreviated as AIM): refers to a mathematical model established using artificial intelligence technologies such as machine learning and deep learning. It can learn from historical data and predict future trends. It is used in anomaly detection and trend prediction in chemical production to assist production decision-making.

[0026] Mechanism Model (MM) refers to a mathematical model based on scientific principles such as physics and chemistry. It is used to simulate and predict phenomena such as material transformation and energy conversion in the chemical production process, guide the optimization of production parameters, and maximize production efficiency.

[0027] In the relevant technologies, the ability and performance evaluation of production personnel in chemical enterprises mainly relies on actual production data and operation records, which leads to a single evaluation dimension. In addition, during the evaluation process, it over-relies on the computing and storage resources of local servers, which increases the operating costs of enterprises. Due to the lack of an effective guidance mechanism, the evaluation results make it difficult for production personnel to obtain timely and accurate operation suggestions when facing complex working conditions, affecting production efficiency and safety. In addition, the relevant cloud platform technology has not effectively solved the problem of sharing production data. The lack of data sharing means that model optimization and learning between enterprises cannot form a network effect, which limits the accumulation and dissemination of overall knowledge and experience in the industry.

[0028] In order to solve the above technical problems, the embodiments of the present application provide corresponding solutions, which are described in detail below.

[0029] The personnel evaluation method embodiment provided in the embodiment 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 personnel evaluation method. Figure 1 As shown, the computer terminal 10 may include one or more (102a, 102b, ..., 102n are used to illustrate) processors (the processor 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 module 106 for communication functions connected via a wired and / or wireless network. In addition, it may also include: a display, a keyboard, a cursor control device, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, and a BUS bus. Those skilled in the art can understand 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 shown.

[0030] It should be noted that the one or more processors 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).

[0031] 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 personnel evaluation method in the embodiment of the present application. The processor 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 personnel evaluation 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 examples, the memory 104 may further include a memory remotely arranged relative to the processor, 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 combinations thereof.

[0032] The transmission module 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 module 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 module 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0033] 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 .

[0034] It should be noted that, in some optional embodiments, the above Figure 1 The computer terminal shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of hardware elements and software elements. It should be noted that Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computer terminal described above.

[0035] In the above-mentioned operating environment, an embodiment of the present application provides an embodiment of a personnel evaluation method. 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 the 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.

[0036] Figure 2 is a flow chart of a personnel evaluation method according to an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0037] Step S202, in response to the selection instruction, select a target prediction model from a plurality of prediction models pre-deployed on the cloud platform, wherein the prediction model is used to predict the index values ​​of different working sections of the chemical production process.

[0038] In the above step S202, the selection instruction includes an instruction issued by an operator or a system management terminal, which is used to select a target prediction model suitable for a specific production section or parameter optimization from multiple prediction models pre-deployed on the cloud platform. The target prediction model refers to a model selected in the cloud platform for predicting the index value of a specific section of a chemical production process according to the selection instruction of the operator. The model can be one or more combinations of models such as an AI model, a mechanism model or an empirical model to meet different prediction needs. Among them, the AI ​​model predicts the future trend of the key indicator value based on historical production data through an AI intelligent algorithm, and provides early warning; the mechanism model constructs a mathematical model based on the reaction principle, predicts the reaction situation in the chemical production process, and calculates the indicator value that can maximize the production efficiency as an adjustment target to guide the operation; the empirical model is based on the production experience and excellent operation cases of the enterprise personnel, integrated into an experience library, so that the personnel's operation level is continuously improved.

[0039] In some embodiments of the present application, the cloud platform can automatically recommend the most suitable prediction model based on the operator's historical operation data, equipment type and production section, and the selection is completed after the operator confirms; alternatively, the cloud platform provides a comparison interface for multiple models, and the operator can directly view the prediction performance and application cases of different models and manually select the most satisfactory target prediction model.

[0040] Step S204, inputting the data to be predicted into the target prediction model for prediction to obtain a prediction result, wherein the data to be predicted is data generated after the operator adjusts the parameters of the operated equipment according to the target prediction model.

[0041] In the above step S204, the data to be predicted includes real-time or historical data related to specific work sections or indicators collected by operators during the chemical production process by sensors, equipment monitoring systems or other data acquisition means, and data generated after the parameters of the operated equipment are adjusted according to the target prediction model. These data are used as input to predict the indicator value or operating status of the equipment in the future.

[0042] When the target prediction model is an AI model, the parameters of the operating equipment may include at least one of the following: historical process parameters, such as temperature, pressure, flow, liquid level, gas composition, etc.; environmental condition parameters, such as external temperature, humidity, light, etc.; equipment status parameters, including equipment operating time, maintenance records, fault history, etc.; raw material and product parameters, such as raw material purity, component ratio, product specification requirements, etc.; operation instruction parameters, that is, the operation instructions given by the operator to the equipment, such as adjusting the valve opening, switching the process route, etc.

[0043] In the case where the target prediction model is a mechanism model, the parameters of the operating equipment may include at least one of the following: chemical reaction parameters, such as the concentration of reactants, reaction rate constant, activation energy, etc.; thermodynamic parameters, including heat capacity, thermal conductivity, specific heat, etc.; fluid mechanics parameters, such as flow rate, pressure drop, Reynolds number, etc.; material parameters, including the physicochemical properties of raw materials and catalysts, such as particle size, specific surface area, catalytic activity, etc.; operating condition parameters, such as the operating pressure of the reactor, reaction temperature, stirring speed, etc. The parameter selection under each model is to simulate and predict the chemical production process as accurately as possible. For example, AI models tend to use actual observed data for learning and prediction, while mechanism models focus on theoretical calculations and the application of physical and chemical principles.

[0044] The prediction result refers to the index value or future trend of a specific section of the chemical production process calculated by the target prediction model based on the data to be predicted. In some embodiments of the present application, after the operator adjusts the equipment parameters, the real-time data can be transmitted to the cloud through the edge server, and the target prediction model processes and returns the prediction results in real time. In order to provide more comprehensive prediction results, the target prediction model can also combine historical data trends to predict the future operating status of the equipment, or integrate the prediction results of multiple models, for example, the prediction results of the AI ​​model, mechanism model and empirical model are integrated, and the advantages and disadvantages of different models are comprehensively considered to obtain the prediction results. The operator can adjust the equipment parameters, raw material ratios in production, reaction temperature and other indicators according to the prediction results to optimize the production operations.

[0045] In order to more accurately evaluate the operating quality of different work sections, different models can be used to perform predictions separately to obtain multiple prediction results. Specifically: when the target prediction model is the first model, the prediction result is determined as the first prediction result, wherein the first model is used to predict the trend of the index value of the first work section of the chemical production process within a preset time period; when the target prediction model is the second model, the prediction result is determined as the second prediction result, wherein the second model is used to predict the optimal index value of the chemical production process in the second work section.

[0046] The first model includes an AI prediction model pre-deployed in the cloud platform, and the second model includes a mechanism model or an empirical model pre-deployed in the cloud platform. In some embodiments of the present application, the data to be predicted within a certain period of time can be packaged and organized to form a data batch, which can be uploaded to the cloud platform at regular intervals. This batch of data is used as input to perform predictions on the first model or the second model, wherein the first model can be the above-mentioned AI model, and the second model can be the above-mentioned mechanism model. In an optional embodiment, before the data is input into the model, pre-processing steps such as data cleaning and normalization can also be performed to ensure data quality.

[0047] The prediction result of the first model is the first prediction result. In some embodiments of the present application, the first model can use a time series analysis algorithm to predict the changing trend of the index value of the first work section in the future period of time, and output the predicted trend curve as the first prediction result; or, the first model can integrate multiple AI algorithms, such as deep learning, support vector machine, etc., to perform multi-dimensional prediction of the index value of the first work section, and obtain the first prediction result by combining the prediction results of each algorithm.

[0048] The prediction result of the second model is the second prediction result. In some embodiments of the present application, the second model can calculate the optimal production index value under given raw material input and environmental conditions based on mechanism equations such as chemical reactions and material balance as the second prediction result; or, the second model can integrate the historical experience library of the enterprise or industry, and quickly match the optimal operation case according to the production parameters and operating status of the current section, and the recommended parameter combination is the second prediction result.

[0049] Step S206: Score the operator's operation quality based on the prediction result.

[0050] In the above step S206, the operation quality score refers to a quantitative evaluation of the operator's operation quality based on the matching degree, stability or optimization effect of the prediction results and the actual production indicators. The scoring system can be based on multiple dimensions such as prediction accuracy, production efficiency improvement, and safety incident reduction.

[0051] In order to more comprehensively evaluate the operation quality of operators, an operation quality scoring mechanism can be designed in combination with the accuracy of the prediction results and the importance of the indicators to the production process. Specifically: determine the first indicator score corresponding to each indicator prediction value in the first prediction result; perform weighted summation of the first indicator scores of all indicator prediction values ​​in the first prediction result and the indicator weights corresponding to the first indicator scores to determine the total score of the operator's operation quality.

[0052] The first indicator score is used to reflect the closeness of the equipment operation indicator to the expected result of the prediction model, as well as the stability of the indicator itself, and may include one or more of an accuracy score, a stability score, an efficiency improvement score, etc.

[0053] (1) Accuracy score: measures the degree of closeness between the actual indicator value and the predicted value in the first prediction result. For example, this can be achieved by calculating the absolute or relative error between the two. The smaller the error, the higher the score.

[0054] (2) Stability score: evaluates the degree of fluctuation of equipment operating indicators within a preset time period. For example, it is evaluated by calculating the standard deviation or fluctuation range of the indicator value. The smaller the fluctuation, the higher the score.

[0055] (3) Efficiency improvement score: When the model is able to predict the efficiency improvement after the operation is adjusted, such as increased conversion rate, reduced energy consumption, etc., the score can be calculated by comparing the efficiency changes before and after the adjustment. The greater the efficiency improvement, the higher the score.

[0056] The indicator weight refers to the quantification of the importance of different indicators when scoring the operation quality of the operator, so as to reflect the impact of the indicator on the production process, and to assign different weights when weighted summing the scores. In some embodiments of the present application, the total score of the operation quality of the operator can be determined by linear weighted summation, weighted average calculation, and application of segmented scoring functions. For example, according to the importance of the indicator, the scoring function of different segments is set, and each indicator score is nonlinearly converted and then weighted summed to reflect the greater impact of the key indicator on the total score.

[0057] In order to motivate operators to control indicators within the optimal range, give timely feedback to operations that deviate from normal, and promote the optimization and safety of the production process, the first indicator score corresponding to each indicator prediction value in the first prediction result can be determined by the following steps: when the first indicator prediction value in the first prediction result is less than the minimum value of the normal interval, determine the first indicator score corresponding to the first indicator prediction value as a first score, wherein the first score is determined by the minimum value of the normal interval, the first indicator prediction value and the first weight, the first weight is used to represent the difference between the minimum value of the normal interval and the first indicator prediction value, and the first indicator prediction value is the minimum value of the normal interval in the first prediction result. The predicted value corresponding to any one indicator; when the predicted value of the first indicator is greater than or equal to the minimum value of the normal interval, and the predicted value of the first indicator is less than or equal to the maximum value of the normal interval, the first indicator score corresponding to the predicted value of the first indicator is determined to be the second score, wherein the second score is greater than the first score; when the predicted value of the first indicator is greater than the maximum value of the normal interval, the first indicator score corresponding to the predicted value of the first indicator is determined to be the third score, wherein the third score is determined by the maximum value of the normal interval, the predicted value of the first indicator and the second weight, the second weight is used to indicate the degree of difference between the predicted value of the first indicator and the maximum value of the normal interval, and the third score is less than the second score.

[0058] The normal range refers to the normal operating range defined for each key indicator in chemical production. This range can be determined based on historical data, process requirements and safety standards. Exceeding this range may indicate an abnormal production process or a safety risk. The first indicator prediction value refers to the predicted value of any indicator in the first prediction result. This predicted value can be calculated by the AI ​​model based on the data to be predicted and is used to predict the change trend of the indicator within a preset time period.

[0059] The first score refers to the corresponding indicator score when the predicted value of the first indicator is less than the minimum value of the normal interval, indicating that the predicted value is lower than the normal range and may have an adverse effect on the production process. The first score can be determined by the linear proportional method (setting the first score to decrease in proportion to the difference between the predicted value of the first indicator and the minimum value of the normal interval), the exponential decay method (the first score decreases rapidly in an exponential form as the difference between the predicted value and the minimum value of the normal interval increases), the step function method, etc. For example, when the step function method is used, when the predicted value of the first indicator is lower than the minimum value of the normal interval, the first score decreases linearly from the maximum value to 0 until the predicted value reaches a preset lower limit, at which time the score is 0.

[0060] The second score refers to the index score corresponding to when the predicted value of the first index is between the minimum and maximum values of the normal range, indicating that the predicted value is within the normal range and is safe and effective for the production process. The second score can be determined by methods such as the constant value method (when the predicted value falls within the normal range, the second score is set to a fixed constant value), the smooth curve method (even when the predicted value is within the normal range, a fine-tuned score is given according to the proximity of the predicted value to the median of the normal range), the exponential proximity method (the second score increases exponentially as the predicted value approaches the median of the normal range, ensuring that the predicted value closest to the median obtains the highest score), etc.

[0061] The third score refers to the index score corresponding to when the predicted value of the first index is greater than the maximum value of the normal range, indicating the degree to which the predicted value exceeds the normal range and may have an adverse impact on the production process, and the third score is less than the second score, indicating that the impact of exceeding the range is negative. The third score can be determined by methods such as the linear ratio method, the logarithmic penalty method (decaying according to the logarithmic ratio), the step function method, etc.

[0062] In some embodiments of the present application, the score can be determined according to whether the predicted value of the parameter is within the specified range. If the predicted value remains within the range, a full score can be obtained; if it exceeds the specified range, points will be deducted as appropriate according to the over-limit situation. The score calculation formula is as follows:

[0063] When s < x0, H = 100 - (x0 - s) × t1

[0064] When x0 ≤ s ≤ x1, H = 100

[0065] When x1 < s, H = 100 - (s - x1) × t2

[0066] Where s is the predicted value of the parameter (or index), for example, it can be the predicted value of the first index, [x0, x1] is the normal range of the predicted value of this parameter, H is the corresponding score, for example, it can be the score of the first index. When the predicted value of the parameter is within this range, the score of this parameter is 100; when the predicted value of this parameter is not within the normal range, the integral is calculated according to the distance from the range, and the farther the distance, the smaller the score, and the minimum value is 0; t1 and t2 are the above-mentioned first weight and second weight respectively. When s < x0, H = 100 - (x0 - s) × t1 represents the above-mentioned first score; when x0 ≤ s ≤ x1, H = 100 represents the above-mentioned second score; when x1 < s, H = 100 - (s - x1) × t2 represents the above-mentioned third score.

[0067] When the scores of all parameters (or indices) are calculated, the total operation quality score H1 of the operator is obtained by weighted calculation of the scores of each parameter. The formula is as follows:

[0068]

[0069] Among them, H i is the score value of each parameter, x i is the weight of each parameter.

[0070] In order to fully consider the degree of closeness between the operation and the optimal index and quantify the negative impact of deviation from the optimal state, the data of the mechanism model can also be processed to score the operation quality of the operator: determine the gap value between the optimal index value in the second prediction result and the data to be predicted; when the gap value is less than the minimum value of the evaluation interval, determine the operation quality score of the operator as the fourth score; when the gap value is greater than the minimum value of the evaluation interval and less than or equal to the maximum value of the evaluation interval, determine the operation quality score of the operator as the fifth score, wherein the fifth score is less than the fourth score; when the gap value is greater than the maximum value of the evaluation interval, determine the operation quality score of the operator as the sixth score, wherein the sixth score is less than the fifth score.

[0071] The second prediction result includes a set of index values ​​in the second stage obtained after optimizing the chemical production process based on the mechanism model. The optimal index value includes the index value that can maximize the production efficiency calculated by the mechanism model according to the principles of chemical reaction kinetics, mass conservation, energy conservation, etc. The gap value between the optimal index value and the data to be predicted can be calculated by the objective function deviation, that is, if the optimal index value is obtained by minimizing or maximizing a certain objective function, the gap value between the actual index value and the optimal solution of the objective function can be calculated; or, for the case where there are multiple indicators to be optimized, the comprehensive deviation between the actual index value set and the optimal index value set in multiple dimensions can be calculated, such as using Euclidean distance or other distance measurement methods.

[0072] The fourth score refers to the high evaluation score obtained by the operator's operation quality when the gap value is less than the minimum value of the evaluation interval, indicating that the operation quality is good. In some embodiments, the fourth score can be determined by the constant value method, that is, if the gap value is less than the minimum value of the evaluation interval, it means that the operator's operation is very close to the optimal index, and the operation quality score is full marks or a preset high score (such as 100 points); or, based on the constant value method, if the gap value is much less than the minimum value, additional bonus points can be given.

[0073] The fifth score refers to the evaluation score of the operator's operation quality when the gap value is between the minimum and maximum values ​​of the evaluation interval. This score is less than the fourth score, indicating that the operation quality is acceptable but has room for improvement. In some embodiments of the present application, the fifth score can be determined by a linear proportional method, that is, a linear function is designed so that when the gap value increases from the minimum value to the maximum value of the evaluation interval, the operation quality score decreases linearly from the fourth score to the sixth score.

[0074] The sixth score refers to the low evaluation score obtained by the operator's operation quality when the gap value is greater than the maximum value of the evaluation interval, indicating that the operation quality needs to be greatly improved. In some embodiments of the present application, the sixth score can be determined by the minimum score method, that is, when the gap value exceeds the maximum value of the evaluation interval, the operation quality score is a set low score or 0, indicating that the operation is far from the optimal state.

[0075] In some embodiments of the present application, the score can be determined based on the difference between the actual value of the optimization parameter and the optimization value calculated by the model. The smaller the difference between the actual value and the optimization value, the higher the score, and vice versa. The difference value is calculated using the variance, and the formula is as follows:

[0076]

[0077] Among them, y is the actual value of the production indicator, which takes n values ​​within the specified time period, and each value is y i , p is the optimal value calculated by the mechanism model, s1 2 That is, the variance between the actual value and the optimized value during the time period, which can represent the gap with the optimized value.

[0078] Based on the calculated variance, the operator's operation quality score H2 can be calculated according to the piecewise function, and the formula is as follows:

[0079]

[0080] Among them, H2 is the score corresponding to the operator's operation quality under the mechanism model, s max and min They are variance evaluation intervals. Different scores are obtained according to the variance values ​​in different intervals. The smaller the variance value, the higher the score.

[0081] In order to ensure the efficiency of data processing, a quick response can be made through the local server even in an unstable network condition. Therefore, in some embodiments of the present application, the target prediction model deployed on the cloud server in the cloud platform can be used to predict the data to be predicted to obtain the prediction result; and the prediction result is sent to the local edge server.

[0082] Cloud servers refer to the core computing resources in the cloud platform, which are used to perform various computing tasks, including model training, prediction, data processing, etc. The target prediction model is deployed on the cloud server to process the data to be predicted uploaded by various enterprises and generate prediction results.

[0083] The cloud platform supports multiple enterprises to settle in, and the target prediction model deployed on the cloud server can be shared and used by multiple enterprise tenants. After the enterprise uploads the data to be predicted, the cloud server will automatically allocate computing resources according to the model type and enterprise needs, process the data, and generate prediction results.

[0084] Real-time communication protocols such as MQTT (Message Queuing Telemetry Transport) or AMQP (Advanced Message Queuing Protocol) are used between cloud servers and edge servers to ensure that prediction results are sent to edge servers quickly and reliably.

[0085] The edge server has a local cache function that can temporarily store prediction results when the network is unstable. Once the network is restored, the edge server will immediately apply the prediction results to guide production operations and upload the production data after the operation to the cloud server for model retraining.

[0086] In order to ensure that the evaluation system can still operate normally when the cloud server network fails, the following steps can be performed: when the cloud server network is interrupted, the prediction model deployed on the local edge server is used to predict the data to be predicted to obtain intermediate calculation results; when the cloud server network is restored, the intermediate calculation results and the data to be predicted are sent to the cloud server, and the cloud server performs subsequent calculations on the data to be predicted based on the intermediate calculation results.

[0087] Network failure refers to an abnormality in the network connecting the cloud server and the local edge server, such as disconnection, high latency, or packet loss, which affects data upload, download, and real-time interaction. The key to ensuring that the evaluation system can still operate normally when the cloud server network fails lies in the independent processing capability and data caching mechanism of the local edge server.

[0088] Step 1: Local data caching and preprocessing.

[0089] (1) Local caching mechanism: The edge server is equipped with sufficient storage space to cache the data to be predicted and historical production data. Under normal circumstances, the edge server uploads the data to the cloud server for processing, but in the event of a network failure, the data will be cached and uploaded after the network is restored.

[0090] (2) Local preprocessing: Data preprocessing modules are deployed on edge servers to clean, format, and standardize data. Even during network failures, preliminary data processing can be completed to ensure data quality. Once the network is restored, the data is immediately uploaded to the cloud server for model prediction and evaluation.

[0091] (3) Redundant data storage: Redundant data storage is set up on the edge server, that is, a backup storage area is set up in addition to the main storage area to ensure that when the main storage area fails, the backup data can be quickly called up to ensure the uninterrupted operation of the evaluation system.

[0092] Step 2: Local model prediction and preliminary evaluation.

[0093] (1) Local model deployment: Deploy simplified AI models, mechanism models, and empirical models on edge servers. These models can run independently during network failures, perform preliminary predictions and evaluations on cached data to be predicted, and ensure the continuity of production guidance and personnel evaluation.

[0094] (2) Prediction result cache: The edge server caches the prediction results of the local model, including the stability score of the AI ​​model prediction, the gap value score of the mechanism model, and the matching score of the empirical model. These cached results will be uploaded to the cloud server after the network is restored for further evaluation and integration.

[0095] (3) Local fault tolerance mechanism: The edge server is designed with fault detection and self-recovery functions, which can automatically detect network failures and switch to the local model for prediction during failures. At the same time, it also monitors the health status of the local model and storage to ensure operational efficiency and data security during failures.

[0096] Step 3: Data synchronization and evaluation integration when the network is restored.

[0097] (1) Breakpoint resume: After the network is restored, the edge server will automatically detect the network connection and upload the cached data to the cloud server starting from the breakpoint. In some embodiments, after receiving the intermediate calculation results and the data to be predicted, the cloud server can verify the intermediate calculation results and merge the intermediate calculation results with the global data model on the cloud platform, taking into account the broader and more complex data relationships and optimization strategies contained in the global data model, and correct or supplement the intermediate calculation results.

[0098] (2) Evaluation result integration: The cloud server compares and integrates the received local prediction results and evaluation scores with the calculation results on the cloud, corrects the evaluation deviation that may be caused by network failure, and ensures the accuracy and consistency of the evaluation.

[0099] In order to provide operators with troubleshooting guidance in a timely manner and reduce production downtime, the following steps can also be performed: when a target operating device fails, obtain the alarm information of the target operating device, where the alarm information includes the position number of the target operating device; query the experience library for solutions and operating experience that match the alarm information based on the alarm information; and return the solutions and operating experience to the target operator corresponding to the target operating device.

[0100] In some embodiments of the present application, sensors and monitoring modules can be installed on the equipment to collect the equipment operation status and key indicator data in real time. Once the data exceeds the preset normal range, an alarm message is immediately generated and sent to the edge server. In an optional embodiment of the present application, when the alarm message is generated, the bit number of the device can be automatically associated to ensure the accuracy and traceability of the alarm message.

[0101] The company's historical production experience and excellent operation cases can be integrated into an experience database, and relevant experience can be automatically matched when similar problems occur to provide guidance for operators. The company can integrate and upload relevant production experience, and can also connect to the experience database of the same section of other companies to achieve industry experience sharing.

[0102] In the experience library of the cloud server, a fast indexing mechanism based on the bit number and fault type is established to facilitate quick query of relevant solutions and operational experience. In some embodiments, machine learning algorithms can be used to parse alarm information and automatically match the most similar fault cases and solutions, including text matching based on alarm information features, learning and prediction of historical fault cases, etc.

[0103] The enterprise's experience database and matching mechanism can be deployed on the central cloud server. The enterprise needs to upload its production experience and excellent operation cases to the cloud and store them in the enterprise experience database. At the same time, it can be connected to the experience databases of other enterprises. Under the unified coordination of the matching mechanism, production personnel can view the solutions to corresponding problems in different enterprises and select appropriate experience to optimize production.

[0104] A real-time push system can be deployed on edge servers or cloud servers. Once a matching solution and operational experience are found, it will be pushed immediately through the production personnel's operation interface or mobile terminal in real time to ensure timely communication of information.

[0105] Through the above steps S202 to S206, cloud-edge collaborative computing is adopted to predict data through a prediction model, and the operator is evaluated according to the prediction results, thereby achieving the purpose of intelligent guidance and evaluation of the chemical production process, thereby achieving the technical effect of timely feedback on the operation quality of personnel, improving the operation skills of personnel, and improving the safety and efficiency of chemical production, thereby solving the technical problem that the operator's ability assessment in related technologies is based on actual production data and operation data, the evaluation dimension is single, and the operator's operation ability cannot be improved.

[0106] Figure 3 This is a schematic diagram of the operational flow of a personnel evaluation method according to an embodiment of the present application. In a specific embodiment, a cloud platform is built based on the production scenario of a chemical enterprise, and the permission for multiple enterprises to enter can be opened through SaaS-based operation services. The platform will pre-launch multiple models and develop AI, mechanism, experience guidance and other functions for different work sections. The settled enterprises can pay to unlock the corresponding functions according to their own needs, upload the required production data, and use the model on the cloud platform for optimization calculation or experience reference. The following roles need to be assigned to the management and use of the cloud platform:

[0107] (1) Operator: The main manager and maintainer of the cloud platform system, responsible for the review of model listing, review of enterprise entry certification, unlocking of enterprise model usage permissions, as well as model management, certified enterprise management, user management, etc.

[0108] (2) Developers: Responsible for developing customized models for different work sections and uploading them to the cloud platform. After passing the review, they can be opened to corporate users for paid use.

[0109] (3) Enterprise side: You can view the functional details of the model, purchase and unlock the model, upload corresponding data according to model requirements, and open usage permissions for operators in the enterprise.

[0110] (4) User side: production operators in the enterprise, users of the model, who optimize the operation of the device based on the model's optimization results or production experience.

[0111] like Figure 3 As shown in the figure, it mainly describes the interaction process between developers, enterprises and users in the cloud platform system:

[0112] (1) Model creation: Developers first create AI models, mechanism models or empirical models based on the needs of the chemical production process. These models are tools used to predict, optimize or provide production guidance. The created models need to be submitted to the cloud platform operator for review. The review ensures the accuracy and security of the model and prevents non-compliant or low-quality models from being put on the shelves.

[0113] (2) Model listing review: The operator conducts a detailed review of the model, including the model's functions, performance, scope of application, and security. After passing the review, the model will be listed in the cloud platform's model library. The developer receives a successful review notification, and the model is officially listed and available for enterprise users to select and use.

[0114] (3) Model listing: The model is listed in the model library of the cloud platform, displaying the model's functional details, use cases, user reviews and other information, making it easier for enterprises to evaluate the applicability and value of the model.

[0115] (4) Create an enterprise: The enterprise creates an enterprise account on the cloud platform and provides necessary enterprise information, such as enterprise name, address, contact information, and chemical production type. The created enterprise account must be reviewed by the cloud platform operator to ensure the accuracy and legality of the enterprise information.

[0116] (5) Enterprise certification review: The operator reviews the qualifications of the enterprise to confirm whether the enterprise meets the entry conditions, including safety production license, environmental protection standards, technical capabilities, etc. After the enterprise account passes the review, the enterprise can browse the model library on the cloud platform to select and understand the functions and usage methods of different models.

[0117] (6) Complete enterprise certification: After passing the review and certification, the enterprise can officially enter the cloud platform and start using the services and models provided by the cloud platform.

[0118] (7) Model viewing: Enterprises can view all model information listed on the cloud platform, including model functions, scope of use, price, etc., so as to make a selection. Enterprises select appropriate models based on their own needs and pay for them through the cloud platform. After purchasing the model, the enterprise will obtain the right to use the model and technical support for a period of time.

[0119] (8) Purchase status review: After an enterprise purchases a model, the cloud platform will review the purchase status to confirm the integrity of the payment and purchase process. After the review confirms that the purchase is correct, the enterprise obtains the right to use the model.

[0120] (9) Activate model usage rights: The cloud platform activates the usage rights of the purchased model for the enterprise, allowing the enterprise to upload data to the cloud server and use the model for optimization and prediction.

[0121] (10) Create users: The enterprise creates user accounts for specific production operators and assigns user permissions to ensure that only authorized personnel can access and use specific models.

[0122] (11) Assigning user permissions: The enterprise administrator assigns corresponding permissions to each user on the cloud platform, including which models can be used and which data can be viewed. The cloud platform opens corresponding usage rights for the user account based on the permissions assigned by the enterprise, and the user can log in to the system and start using the model.

[0123] (12) Use the model: Users can use the model in the cloud platform to analyze and predict data in the production process, obtain operational guidance and optimization suggestions, and improve production quality and efficiency. After using the model, users can evaluate the accuracy and practicality of the model, and these evaluations are fed back to the developers and operators for model optimization and improvement. Since in chemical production, the same section of the same industry has similar device reflection principles and production operations, the operational quality of model optimization can be compared horizontally between different companies in the same industry. Under the premise of unified evaluation standards, points ranking can be carried out to help workshops, teams and personnel find their own position in the industry, discover their strengths and weaknesses, and achieve common progress in the industry. The evaluation system can be deployed in the company's local server, and the personnel's evaluation results can be uploaded to the cloud platform to achieve intercommunication between enterprises. Through real-time comparison and ranking, the advanced experience of other companies can be learned to improve their own production efficiency.

[0124] Figure 4 is a structural diagram of a personnel evaluation device according to an embodiment of the present application, such as Figure 4 As shown, the device comprises:

[0125] A selection module 402 is used to select a target prediction model from a plurality of prediction models pre-deployed on the cloud platform in response to a selection instruction, wherein the prediction model is used to predict the index values ​​of different sections of a chemical production process;

[0126] The prediction module 404 is used to input the data to be predicted into the target prediction model for prediction to obtain a prediction result, wherein the data to be predicted is data generated after the operator adjusts the parameters of the operated equipment according to the target prediction model;

[0127] The scoring module 406 is used to score the operation quality of the operator according to the prediction result.

[0128] In the above-mentioned personnel evaluation device, the selection module is also used to predict the data to be predicted through the target prediction model deployed on the cloud server in the cloud platform to obtain the prediction result; and send the prediction result to the local edge server.

[0129] In the evaluation device of the above-mentioned personnel, the prediction module is also used to determine the prediction result as the first prediction result when the target prediction model is the first model, wherein the first model is used to predict the trend of the index value of the first section of the chemical production process within a preset time period; when the target prediction model is the second model, the prediction result is determined as the second prediction result, wherein the second model is used to predict the optimal index value of the chemical production process in the second section.

[0130] In the above-mentioned personnel evaluation device, the scoring module is also used to determine the first indicator score corresponding to each indicator prediction value in the first prediction result; weighted sum of the first indicator scores of all indicator prediction values ​​in the first prediction result and the indicator weights corresponding to the first indicator scores is performed to determine the total score of the operator's operation quality.

[0131] In the above-mentioned personnel evaluation device, the scoring module is also used to determine that the first indicator score corresponding to the first indicator prediction value is a first score when the first indicator prediction value in the first prediction result is less than the minimum value of the normal interval, wherein the first score is determined by the minimum value of the normal interval, the first indicator prediction value and the first weight, the first weight is used to indicate the degree of difference between the minimum value of the normal interval and the first indicator prediction value, and the first indicator prediction value is the prediction value corresponding to any indicator in the first prediction result; when the first indicator prediction value is greater than or equal to the minimum value of the normal interval, and the first indicator prediction value is less than or equal to the maximum value of the normal interval, determine that the first indicator score corresponding to the first indicator prediction value is a second score, wherein the second score is greater than the first score; when the first indicator prediction value is greater than the maximum value of the normal interval, determine that the first indicator score corresponding to the first indicator prediction value is a third score, wherein the third score is determined by the maximum value of the normal interval, the first indicator prediction value and the second weight, the second weight is used to indicate the degree of difference between the first indicator prediction value and the maximum value of the normal interval, and the third score is less than the second score.

[0132] In the above-mentioned personnel evaluation device, the scoring module is also used to determine the gap value between the optimal indicator value in the second prediction result and the data to be predicted; when the gap value is less than the minimum value of the evaluation interval, the operation quality score of the operator is determined to be the fourth score; when the gap value is greater than the minimum value of the evaluation interval and less than or equal to the maximum value of the evaluation interval, the operation quality score of the operator is determined to be the fifth score, wherein the fifth score is less than the fourth score; when the gap value is greater than the maximum value of the evaluation interval, the operation quality score of the operator is determined to be the sixth score, wherein the sixth score is less than the fifth score.

[0133] In the above-mentioned personnel evaluation device, the prediction module is also used to predict the data to be predicted through the prediction model deployed on the local edge server when the network of the cloud server is interrupted, and obtain intermediate calculation results; when the network of the cloud server is restored, the intermediate calculation results and the data to be predicted are sent to the cloud server, and the cloud server performs subsequent calculations on the data to be predicted based on the intermediate calculation results.

[0134] In the above-mentioned personnel evaluation device, the scoring module is also used to obtain the alarm information of the target operating equipment when a failure occurs in the target operating equipment, wherein the alarm information includes the position number of the target operating equipment; query the solution and operating experience matching the alarm information from the experience library based on the alarm information; and return the solution and operating experience to the target operator corresponding to the target operating equipment.

[0135] It should be noted that Figure 4 The personnel evaluation device shown is used to perform Figure 2 The evaluation method of the personnel shown is therefore Figure 2 The relevant explanations in the evaluation method of personnel in the Figure 4 The personnel evaluation device shown will not be described in detail here.

[0136] An embodiment of the present application also provides an electronic device, which includes a memory and a processor, wherein the memory is used to store program instructions; the processor is connected to the memory and is used to execute the steps of the personnel evaluation method in each embodiment of the present application.

[0137] For example, the processor performs the following functions by executing program instructions stored in the memory:

[0138] In response to the selection instruction, a target prediction model is selected from multiple prediction models pre-deployed on the cloud platform, wherein the prediction model is used to predict the index values ​​of different sections of the chemical production process; the data to be predicted is input into the target prediction model for prediction to obtain a prediction result, wherein the data to be predicted is the data generated after the operator adjusts the parameters of the operated equipment according to the target prediction model; the operator's operation quality is scored according to the prediction result.

[0139] An embodiment of the present application further provides a non-volatile storage medium, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the steps of the personnel evaluation method in each embodiment of the present application by running the computer program.

[0140] The embodiments of the present application also provide a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the personnel evaluation method in each embodiment of the present application.

[0141] The embodiments of the present application also provide a computer program, which, when executed by a processor, implements the steps of the personnel evaluation method in each embodiment of the present application.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable 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 and other media that can store program codes.

[0148] The above is only a preferred embodiment 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 personnel evaluation method, characterized in that: include: In response to the selection instruction, a target prediction model is selected from a plurality of prediction models pre-deployed on the cloud platform, wherein the prediction model is used to predict the index values ​​of different working sections of the chemical production process; Inputting the data to be predicted into the target prediction model for prediction to obtain a prediction result, wherein the data to be predicted is data generated after the operator adjusts the parameters of the operated equipment according to the target prediction model; The operation quality of the operator is scored according to the prediction result.

2. The method according to claim 1, characterized in that The method further comprises: Predicting the data to be predicted by using the target prediction model deployed on the cloud server in the cloud platform to obtain the prediction result; The prediction result is sent to the local edge server.

3. The method according to claim 1, characterized in that The data to be predicted is input into the target prediction model for prediction to obtain prediction results, including: In the case where the target prediction model is a first model, determining the prediction result as a first prediction result, wherein the first model is used to predict the trend of the index value of the first stage of the chemical production process within a preset time period; In the case where the target prediction model is a second model, the prediction result is determined as a second prediction result, wherein the second model is used to predict the optimal index value of the chemical production process in the second stage.

4. The method according to claim 3, characterized in that Scoring the operation quality of the operator according to the prediction result includes: Determine a first indicator score corresponding to each indicator prediction value in the first prediction result; A weighted sum is taken of the first indicator scores of all indicator prediction values ​​in the first prediction result and the indicator weights corresponding to the first indicator scores to determine a total score of the operation quality of the operator.

5. The method according to claim 4, characterized in that Determining a first indicator score corresponding to each indicator prediction value in the first prediction result includes: In the case where the predicted value of the first indicator in the first prediction result is less than the minimum value of the normal interval, determining the first indicator score corresponding to the predicted value of the first indicator as a first score, wherein the first score is determined by the minimum value of the normal interval, the predicted value of the first indicator and a first weight, the first weight is used to indicate the degree of difference between the minimum value of the normal interval and the predicted value of the first indicator, and the predicted value of the first indicator is the predicted value corresponding to any one indicator in the first prediction result; When the predicted value of the first indicator is greater than or equal to the minimum value of the normal interval, and the predicted value of the first indicator is less than or equal to the maximum value of the normal interval, determining that the first indicator score corresponding to the predicted value of the first indicator is a second score, wherein the second score is greater than the first score; In the case that the predicted value of the first indicator is greater than the maximum value of the normal interval, the first indicator score corresponding to the predicted value of the first indicator is determined to be a third score, wherein the third score is determined by the maximum value of the normal interval, the first indicator predicted value and a second weight, the second weight is used to represent the degree of difference between the predicted value of the first indicator and the maximum value of the normal interval, and the third score is less than the second score.

6. The method according to claim 3, characterized in that Scoring the operation quality of the operator according to the prediction result includes: Determine the gap value between the optimal indicator value in the second prediction result and the data to be predicted; When the difference value is less than the minimum value of the evaluation interval, determining the operation quality score of the operator to be a fourth score; When the difference value is greater than the minimum value of the evaluation interval and less than or equal to the maximum value of the evaluation interval, determining the operation quality score of the operator to be a fifth score, wherein the fifth score is less than the fourth score; When the difference value is greater than the maximum value of the evaluation interval, the operation quality score of the operator is determined to be a sixth score, wherein the sixth score is smaller than the fifth score.

7. The method according to claim 2, characterized in that: The method further comprises: When the network of the cloud server is interrupted, the data to be predicted is predicted by using the prediction model deployed on the local edge server to obtain an intermediate calculation result; When the network of the cloud server is restored, the intermediate calculation result and the data to be predicted are sent to the cloud server, and the cloud server performs subsequent calculations on the data to be predicted based on the intermediate calculation result.

8. The method according to claim 1, characterized in that: The method further comprises: When a target operating device fails, obtaining alarm information of the target operating device, wherein the alarm information includes a position number of the target operating device; According to the alarm information, searching the experience database for solutions and operation experiences matching the alarm information; The solution and the operation experience are returned to the target operator corresponding to the target operation device.

9. A personnel evaluation device, characterized in that: include: A selection module, for selecting a target prediction model from a plurality of prediction models pre-deployed on the cloud platform in response to a selection instruction, wherein the prediction model is used to predict the index values ​​of different working sections of a chemical production process; A prediction module, used for inputting the data to be predicted into the target prediction model for prediction to obtain a prediction result, wherein the data to be predicted is data generated after the operator adjusts the parameters of the operated equipment according to the target prediction model; The scoring module is used to score the operation quality of the operator according to the prediction result.

10. An electronic device, characterized in that: include: A memory for storing program instructions; A processor is connected to the memory and is used to execute program instructions to implement the following functions: in response to a selection instruction, a target prediction model is selected from multiple prediction models pre-deployed on the cloud platform, wherein the prediction model is used to predict the index values ​​of different sections of a chemical production process; the data to be predicted is input into the target prediction model for prediction to obtain a prediction result, wherein the data to be predicted is data generated after an operator adjusts the parameters of the operated equipment according to the target prediction model; and the operation quality of the operator is scored according to the prediction result.

Images