Operation and maintenance dispatching method, device, computer equipment, storage medium and program product

Abstract

The present application relates to an operation and maintenance dispatching method, device, computer equipment, storage medium and program product. The method comprises: obtaining the monitoring value of the water station equipment, and the indicator type of the monitoring indicator corresponding to the monitoring value; for each monitoring indicator, based on the monitoring value and indicator type corresponding to the monitoring indicator, determining the indicator score corresponding to the monitoring indicator; based on the indicator score corresponding to each monitoring indicator, determining the current health score of the water station equipment; based on the current health score, predicting the predicted health scores corresponding to multiple future moments; based on the predicted health scores corresponding to multiple future moments, generating and dispatching the operation and maintenance work order corresponding to the water station equipment. The use of this method can improve the utilization rate of operation and maintenance resources.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an operation and maintenance dispatching method, apparatus, computer equipment, storage medium, and program product. Background Art

[0002] Water quality monitoring equipment in environmental monitoring requires operation and maintenance management to ensure the normal operation of the water quality monitoring equipment.

[0003] In traditional technologies, regardless of whether the water quality monitoring equipment has a fault, equipment maintenance personnel need to periodically inspect and maintain the water quality monitoring equipment, resulting in low utilization of operation and maintenance resources. Summary of the Invention

[0004] Based on this, it is necessary to provide an operation and maintenance dispatching method, device, computer equipment, computer-readable storage medium and program product that can improve the utilization rate of operation and maintenance resources in response to the above technical problems.

[0005] In a first aspect, the present application provides an operation and maintenance dispatching method. The method comprises:

[0006] Obtaining monitoring values ​​of water station equipment and indicator types of monitoring indicators corresponding to the monitoring values;

[0007] For each monitoring indicator, determining an indicator score corresponding to the monitoring indicator based on the monitoring value and indicator type corresponding to the monitoring indicator;

[0008] Determining a current health score of the water station equipment based on the indicator scores corresponding to the respective monitoring indicators;

[0009] Based on the current health score, predicting predicted health scores corresponding to multiple future moments;

[0010] Based on the predicted health scores corresponding to the multiple future moments, an operation and maintenance work order corresponding to the water station equipment is generated and dispatched.

[0011] In some exemplary embodiments, determining the indicator score corresponding to the monitoring indicator based on the monitoring value and indicator type corresponding to the monitoring indicator includes:

[0012] Obtaining a target calculation formula corresponding to the indicator type; the indicator type is one of a gradual acceleration indicator, a state indicator, a time interval control indicator, a balance indicator, and a narrow interval smooth transition indicator;

[0013] The monitoring value corresponding to the monitoring indicator is substituted into the target calculation formula to obtain the indicator score corresponding to the monitoring indicator.

[0014] In some exemplary embodiments, determining the current health score of the water station equipment based on the indicator score corresponding to each of the monitoring indicators includes:

[0015] Obtaining the monitoring indicator weight corresponding to each of the monitoring indicators;

[0016] The product of the indicator score corresponding to each monitoring indicator and the monitoring indicator weight is statistically calculated to obtain the initial health score of the water station equipment;

[0017] Counting the number of indicator scores that are less than the indicator threshold to obtain a correction coefficient;

[0018] The initial health score is corrected based on the correction coefficient to obtain a current health score of the water station equipment.

[0019] In some exemplary embodiments, the correcting the initial health score based on the correction coefficient to obtain the current health score of the water station equipment includes:

[0020] Determining a correction value based on the correction coefficient; wherein the correction value is less than zero and is inversely proportional to the correction coefficient;

[0021] The initial health score is added to the correction value to obtain the current health score of the water station equipment.

[0022] In some exemplary embodiments, obtaining the monitoring indicator weight corresponding to each of the monitoring indicators includes:

[0023] Determine a plurality of first-level indicators corresponding to a plurality of the monitoring indicators; one first-level indicator corresponds to a plurality of the monitoring indicators;

[0024] Obtaining an importance matrix corresponding to the plurality of first-level indicators; an element in the importance matrix represents a relative importance between two first-level indicators corresponding to the element;

[0025] Determining a first-level indicator weight corresponding to each first-level indicator based on the importance matrix;

[0026] Based on the first-level indicator weight corresponding to the first-level indicator, the monitoring indicator weights corresponding to the multiple monitoring indicators corresponding to the first-level indicator are determined.

[0027] In some exemplary embodiments, before determining the monitoring indicator weights corresponding to the plurality of monitoring indicators corresponding to the first-level indicator based on the first-level indicator weight corresponding to the first-level indicator, the method includes:

[0028] Determining a characteristic matrix corresponding to the importance matrix based on the first-level indicator weights corresponding to each of the first-level indicators; determining an element in the characteristic matrix based on a ratio of the first-level indicator weights of the first-level indicators corresponding to the rows of the elements to the sum of the first-level indicator weights of the first-level indicators corresponding to the rows of the elements and the first-level indicator weights corresponding to the first-level indicators corresponding to the columns of the elements;

[0029] Determining a consistency check result between the importance matrix and the feature matrix based on the importance matrix and the feature matrix;

[0030] When the consistency check result is less than the check threshold, the step of determining the monitoring indicator weights corresponding to the plurality of monitoring indicators corresponding to the first-level indicator based on the first-level indicator weight corresponding to the first-level indicator is performed.

[0031] In some exemplary embodiments, generating and dispatching an operation and maintenance work order corresponding to the water station equipment based on the predicted health scores corresponding to the multiple future moments includes:

[0032] The predicted health scores corresponding to the multiple future moments are input into an operation and maintenance mode prediction model to obtain a target operation and maintenance mode; the operation and maintenance mode prediction model is updated by: the operation and maintenance mode prediction model determines a first error loss based on a difference between the predicted health score and the current health score, determines a second error loss based on the target operation and maintenance mode, determines a third error loss based on an absolute difference between the predicted health score and the current health score, determines a target error loss based on the first error loss, the second error loss, and the third error loss, and updates the operation and maintenance mode prediction model based on the target error loss to obtain an updated operation and maintenance mode prediction model;

[0033] Based on the target operation and maintenance mode, an operation and maintenance work order corresponding to the water station equipment is generated and distributed.

[0034] In a second aspect, the present application further provides an operation and maintenance dispatching device. The device comprises:

[0035] An acquisition module, used to obtain the monitoring value of the water station equipment and the indicator type of the monitoring indicator corresponding to the monitoring value;

[0036] An indicator score determination module is used to determine, for each monitoring indicator, an indicator score corresponding to the monitoring indicator based on the monitoring value and indicator type corresponding to the monitoring indicator;

[0037] A health score determination module, configured to determine a current health score of the water station equipment based on the indicator scores corresponding to the monitoring indicators;

[0038] A prediction module, configured to predict predicted health scores corresponding to a plurality of future moments based on the current health score;

[0039] The operation and maintenance dispatching module is used to generate and dispatch operation and maintenance work orders corresponding to the water station equipment based on the predicted health scores corresponding to the multiple future moments.

[0040] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.

[0041] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any one of the methods described in the first aspect when the computer program is executed by a processor.

[0042] In a fifth aspect, the present application also provides a program product, comprising a computer program, which implements the steps of any one of the methods described in the first aspect when executed by a processor.

[0043] The above-mentioned operation and maintenance dispatching method, device, computer equipment, storage medium and program product obtain the monitoring value of the water station equipment and the indicator type of the monitoring indicator corresponding to the monitoring value, determine the indicator score corresponding to the monitoring indicator based on the monitoring value and indicator type corresponding to the monitoring indicator, use different calculation methods to calculate the indicator score for monitoring indicators of different indicator types, improve the accuracy of the indicator score, determine the current health score of the water station equipment based on the indicator score corresponding to each monitoring indicator, improve the accuracy of the current health score; predict the predicted health scores corresponding to multiple future moments based on the current health score, generate and dispatch the operation and maintenance work order corresponding to the water station equipment based on the predicted health scores corresponding to multiple future moments, which can be understood as dispatching the operation and maintenance work order only when the water station equipment is likely to fail in the future, so that the operation and maintenance personnel can perform inspection and maintenance. Compared with the operation and maintenance personnel performing periodic inspection and maintenance, this saves operation and maintenance resources and improves the utilization of operation and maintenance resources. Moreover, dispatching the operation and maintenance work order when it is predicted that the water station equipment may fail in the future allows the operation and maintenance personnel to perform inspection and maintenance on the water station equipment before the water station equipment actually fails, thereby avoiding the actual failure of the water station equipment and improving the stability of the water station equipment operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is an application environment diagram of the operation and maintenance dispatching method in one embodiment;

[0045] Figure 2 Schematic diagram of the process of an operation and maintenance dispatching method in one embodiment;

[0046] Figure 3 A mapping relationship table between monitoring indicators and indicator types in one embodiment;

[0047] Figure 4 A flowchart of a monitoring indicator weight determination step in one embodiment;

[0048] Figure 5 A schematic diagram of the corresponding relationship between the primary indicators and the monitoring indicators in an embodiment;

[0049] Figure 6 Schematic diagram of a table corresponding to the importance matrix A in one embodiment;

[0050] Figure 7 A schematic diagram of monitoring indicators in one embodiment;

[0051] Figure 8 Schematic diagram of the process of an operation and maintenance dispatching method in one embodiment;

[0052] Figure 9 This is a structural block diagram of an operation and maintenance dispatching device in one embodiment;

[0053] Figure 10 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0055] The operation and maintenance dispatching method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store data that server 104 needs to process. The data storage system can be integrated with server 104, or placed on a cloud or other network server. Both the terminal and the server can be used independently to execute the operation and maintenance dispatching method provided in the embodiments of the present application. The terminal and the server can also be used together to execute the operation and maintenance dispatching method provided in the embodiments of the present application. For example, terminal 102 obtains monitoring values ​​of water station equipment and the indicator type of the monitoring indicator corresponding to the monitoring value; for each monitoring indicator, based on the monitoring value and indicator type corresponding to the monitoring indicator, determines the indicator score corresponding to the monitoring indicator; based on the indicator score corresponding to each monitoring indicator, determines the current health score of the water station equipment; based on the current health score, predicts the corresponding predicted health scores for multiple future time points; and if at least one predicted health score is less than a score threshold, generates and dispatches an operation and maintenance work order for the water station equipment. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, etc. The portable wearable device may be a smart watch, a smart bracelet, a head-mounted device, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0056] In an exemplary embodiment, Figure 2 As shown, a method for dispatching operations and maintenance orders is provided. The method can be applied to a computer device, which can be a terminal or a server. The method can be executed by the terminal or server alone, or through interaction between the terminal and the server. This embodiment uses the method applied to a computer device as an example to illustrate, including steps 202 to 210.

[0057] Step 202: Acquire the monitoring value of the water station equipment and the indicator type of the monitoring indicator corresponding to the monitoring value.

[0058] Among them, water station equipment refers to water quality monitoring equipment. Water station equipment is an instrument used to monitor various physical, chemical and biological indicators in water bodies, aiming to ensure that the water quality of the water body meets relevant standards or regulatory requirements. Monitoring value refers to the numerical value obtained by monitoring water station equipment. The monitoring value reflects the status of the water station equipment at the time of monitoring. Monitoring indicators refer to parameters or items used to describe and evaluate water station equipment. There is a corresponding relationship between the detection value and the monitoring indicator. One monitoring indicator can correspond to one monitoring value, and one monitoring indicator can also correspond to multiple monitoring values. Indicator type refers to an identifier that characterizes the classification of monitoring indicators. Indicator type can be divided according to the degree of change of the monitoring value of the monitoring indicator and the degree of influence on the indicator score corresponding to the monitoring indicator. Indicator types may include but are not limited to gradual acceleration indicators, state indicators, time interval control indicators, balance indicators, narrow interval smooth transition indicators and fuzzy hierarchical analysis indicators.

[0059] For example, the mapping relationship table between monitoring indicators and indicator types is as follows: Figure 3 As shown, Figure 3 The secondary indicators shown in are monitoring indicators, which include online status, key parameters, communication failure, instrument failure, operating status, average failure rate, task overdue, number of operation and maintenance, operation and maintenance interval, reagent remaining, station stop / abnormal situation, inspection status, average fault recovery time, daily quality control, weekly quality control, monthly quality control, data transmission rate and data efficiency. The indicator type for online status is a gradual acceleration indicator, the indicator type for key parameters is a status indicator, the indicator type for communication failure is a time interval control indicator, the indicator type for instrument failure is a time interval control indicator, the indicator type for operation status is a gradual acceleration indicator, the indicator type for average failure rate is a gradual acceleration indicator, the indicator type for task overdue is a time interval control indicator, the indicator type for operation and maintenance times is a time interval control indicator, the indicator type for operation and maintenance interval is a balance indicator, the indicator type for reagent residue is a narrow interval smooth transition indicator, the indicator type for stop / abnormal situation is a gradual acceleration indicator, the indicator type for inspection situation is a fuzzy hierarchical analysis indicator, the indicator type for average fault recovery time is a narrow interval smooth transition indicator, the indicator type for daily quality control is a gradual acceleration indicator, the indicator type for weekly quality control is a gradual acceleration indicator, the indicator type for monthly quality control is a gradual acceleration indicator, the indicator type for data transmission rate is an efficiency weighted score, and the indicator type for data efficiency is an efficiency weighted score.

[0060] Exemplarily, the computer device obtains the monitoring value of the water station device and the indicator type of the monitoring indicator corresponding to the monitoring value.

[0061] Step 204 : For each monitoring indicator, determine an indicator score corresponding to the monitoring indicator based on the monitoring value and indicator type corresponding to the monitoring indicator.

[0062] Among them, the indicator score refers to the score determined based on the monitoring value of the monitoring indicator, and the indicator score is between 0 and 100.

[0063] Exemplarily, for each monitoring indicator, the computer device determines a target calculation formula corresponding to the monitoring indicator based on the indicator type corresponding to the monitoring indicator, and determines an indicator score corresponding to the monitoring indicator based on the monitoring value and the target calculation formula corresponding to the monitoring indicator.

[0064] Step 206: Determine the current health score of the water station equipment based on the indicator score corresponding to each monitoring indicator.

[0065] The current health score refers to a value representing the current health of the water station equipment. The higher the current health score, the higher the current health of the water station equipment. The lower the current health score, the lower the current health of the water station equipment.

[0066] Exemplarily, the computer device obtains the monitoring indicator weight corresponding to each monitoring indicator, and weights the indicator score corresponding to each monitoring indicator based on the monitoring indicator weight corresponding to each monitoring indicator to obtain the current health score of the water station equipment.

[0067] Step 208: Based on the current health score, predict the predicted health scores corresponding to multiple future moments.

[0068] The predicted health score refers to the health score at a future moment predicted based on the current health score.

[0069] For example, a computer device inputs the current health score into a prediction model to obtain predicted health scores corresponding to multiple future moments. The prediction model refers to a trained neural network model used to predict health scores corresponding to multiple future moments. The prediction model can be a Long Short-Term Memory (LSTM) model, which is a special recurrent neural network (RNN) architecture.

[0070] Step 210: Based on the predicted health scores corresponding to multiple future moments, generate and distribute operation and maintenance work orders corresponding to the water station equipment.

[0071] Among them, the operation and maintenance work order refers to the form for operation and maintenance, which includes but is not limited to the work order number, work order type, priority and maintenance personnel.

[0072] For example, the computer device compares each predicted health score against a scoring threshold. If one or more predicted health scores are below the scoring threshold, an operation and maintenance work order corresponding to the water station device is generated and assigned to the target device. The target device can be a terminal of a person maintaining the water station device. The scoring threshold refers to a pre-set value used for comparison with the predicted health score.

[0073] In the above-mentioned operation and maintenance dispatching method, the monitoring value of the water station equipment and the indicator type of the monitoring indicator corresponding to the monitoring value are obtained, and the indicator score corresponding to the monitoring indicator is determined based on the monitoring value and indicator type corresponding to the monitoring indicator. The monitoring indicators of different indicator types use different calculation methods to calculate the indicator score, which improves the accuracy of the indicator score. The current health score of the water station equipment is determined according to the indicator score corresponding to each monitoring indicator, which improves the accuracy of the current health score; based on the current health score, the predicted health scores corresponding to multiple future moments are predicted, and the operation and maintenance work order corresponding to the water station equipment is generated and dispatched based on the predicted health scores corresponding to multiple future moments. It can be understood that the operation and maintenance work order is dispatched only when the water station equipment is likely to fail in the future, so that the operation and maintenance personnel can perform inspection and maintenance. Compared with the operation and maintenance personnel performing periodic inspection and maintenance, it saves operation and maintenance resources and improves the utilization of operation and maintenance resources. Moreover, the operation and maintenance work order is dispatched when it is predicted that the water station equipment may fail in the future, so that the operation and maintenance personnel can perform inspection and maintenance on the water station equipment before the water station equipment actually fails, thereby avoiding the actual failure of the water station equipment, thereby improving the stability of the water station equipment operation.

[0074] In an exemplary embodiment, determining an indicator score corresponding to a monitoring indicator based on a monitoring value and an indicator type corresponding to the monitoring indicator includes:

[0075] Obtain the target calculation formula corresponding to the indicator type; the indicator type is one of the gradual acceleration indicator, state indicator, time interval control indicator, balance indicator and narrow interval smooth transition indicator; substitute the monitoring value corresponding to the monitoring indicator into the target calculation formula to obtain the indicator score corresponding to the monitoring indicator.

[0076] Among them, the target calculation formula refers to the calculation formula corresponding to the indicator type. The progressive acceleration indicator refers to the type of monitoring indicator in which the indicator score changes slowly when the monitoring value is small, and the indicator score changes quickly when the monitoring value is large. The state indicator refers to an indicator that characterizes the state. It can be understood that the value of the state indicator is 0 or 1, 0 represents an abnormal state, and 1 represents a normal state. The indicator score in the abnormal state is 0, and the indicator score in the normal state is 100. The time interval control indicator refers to an indicator with the time interval as the monitoring value. The balance indicator refers to an indicator with the average interval length and standard deviation as the monitoring value. The narrow interval smoothing indicator refers to an indicator with a monitoring value in a smaller range. It can be understood as an indicator with a smaller difference between the maximum monitoring value and the minimum monitoring value.

[0077] Exemplarily, the computer device obtains a target calculation formula corresponding to the indicator type, substitutes the monitoring value corresponding to the monitoring indicator into the target calculation formula, and obtains an indicator score corresponding to the monitoring indicator.

[0078] In an exemplary embodiment, when the indicator type of the monitoring indicator is a progressive acceleration indicator, the target calculation formula is as follows:

[0079] Formula (1)

[0080] Among them, Score(x) is the indicator score of the monitoring value x, and Score(x) is between 0 and 100; x0 is the ideal duration, which can be preset. Different progressive acceleration indicators may correspond to different ideal durations; k is the adjustment factor, which can be preset. Different progressive acceleration indicators may correspond to different adjustment factors, for example, k=10 or k=15.

[0081] When the indicator type of the monitoring indicator is a time interval control indicator, the target calculation formula is as follows:

[0082] Formula (2)

[0083] Formula (3)

[0084] Formula (4)

[0085] in, The score of the time interval measured for the preset time period; d i is the time interval of the i-th measurement; T is the ideal time interval; n is the number of time intervals measured in the preset time period; is the relative deviation between the time interval of i measurements and the ideal time interval; The meaning of is that when the time interval between the i-th measurement is too large, The value of is 0; is the score of the number of measurements in the preset time period; m is the number of time intervals measured in the preset time period; scoring indicators for monitoring targets;

[0086] For example, the indicator type of the operation and maintenance times is the time interval control indicator, and the indicator value of the operation and maintenance times is the operation and maintenance interval length and number. The time interval lengths of the four operation and maintenance times measured in the preset time period are (28 days, 32 days, 29 days, 35 days). ,

[0087] , .

[0088] When the indicator type of the monitoring indicator is a narrow range smooth transition indicator, the target calculation formula is as follows:

[0089] Formula (5)

[0090] Wherein, P is the percentage of the remaining amount; is the threshold parameter; λ is the parameter that controls the steepness of the curve. Increasing λ will make the curve close to The curve becomes steeper when λ is less than 0, and decreasing λ will make the curve smoother. γ is the smoothing factor, which is used to further adjust the smoothness of the curve. Increasing γ will make the curve smoother when it is close to 0 points and full score, but increasing γ may also reduce the sensitivity of the curve near sensitive points.

[0091] For example, the indicator type of reagent surplus is a narrow range smooth transition indicator, and the indicator value of reagent surplus is the surplus of reaction reagents. Generally, in order to maintain sufficient surplus of reaction reagents, the surplus of reaction reagents is kept above 25% as much as possible. Above 25% is considered to be full score, and below 25% is scored nonlinearly. When λ=3 and γ=10, Score(25%)=99.9, Score(15%)=85.85, Score(10%)=46.22, and Score(0)=0.

[0092] When the indicator type of the monitoring indicator is a balance indicator, the target calculation formula is as follows:

[0093] Formula (6)

[0094] Formula (7)

[0095] Formula (8)

[0096] in, is the average interval length; Score for average interval duration; is the ideal average interval length; is the interval duration threshold; STD is the standard deviation of the interval duration; is the standard deviation score for interval duration; is the maximum standard deviation; is the weight corresponding to the average interval duration score; is the weight corresponding to the standard deviation score of the interval duration; Score the indicators for the balance index.

[0097] When the indicator type of the monitoring indicator is a status indicator and the monitoring value of the monitoring indicator is 0, the indicator score of the monitoring indicator is 0; when the monitoring value of the monitoring indicator is 1, the indicator score of the monitoring indicator is 100.

[0098] When the indicator type of the monitoring indicator is a fuzzy hierarchical analysis indicator, the fuzzy hierarchical analysis method is used to calculate the indicator score of the monitoring indicator.

[0099] In this embodiment, the target calculation formula corresponding to the indicator type is obtained, and the monitoring value corresponding to the monitoring indicator is substituted into the target calculation formula to obtain the indicator score corresponding to the monitoring indicator. That is, when the indicator type is one of the progressive acceleration indicator, state indicator, time interval control indicator, balance indicator and narrow interval smooth transition indicator, the monitoring indicators of different indicator types use different calculation methods to calculate the indicator score, which improves the accuracy of the indicator score.

[0100] In an exemplary embodiment, determining the current health score of the water station equipment based on the indicator scores corresponding to the various monitoring indicators includes:

[0101] Obtain the monitoring indicator weight corresponding to each monitoring indicator; perform statistics on the product of the indicator score corresponding to each monitoring indicator and the monitoring indicator weight to obtain the initial health score of the water station equipment; perform statistics on the number of indicator scores less than the indicator threshold to obtain the correction coefficient; correct the initial health score based on the correction coefficient to obtain the current health score of the water station equipment.

[0102] The monitoring indicator weight refers to the weight coefficient corresponding to the monitoring indicator. The initial health score refers to the uncorrected health score. The indicator threshold refers to the value used to compare the indicator score of the monitoring indicator. The indicator threshold can be pre-set, for example, the indicator threshold is 50 or 60. The correction factor refers to the factor used to correct the initial health score.

[0103] Exemplarily, the computer device obtains the monitoring indicator weight corresponding to each monitoring indicator, adds the product of the indicator score corresponding to each monitoring indicator and the monitoring indicator weight, and obtains the initial health score of the water station equipment; compares the indicator score of each monitoring indicator with the indicator threshold, counts the number of indicator scores less than the indicator threshold, obtains the correction coefficient, and corrects the initial health score based on the correction coefficient to obtain the current health score of the water station equipment.

[0104] In an exemplary embodiment, the calculation formula for the initial health score is as follows:

[0105] Formula (9)

[0106] in, Score the indicator of the i-th monitoring indicator; is the monitoring indicator weight of the i-th monitoring indicator; n is the total number of monitoring indicators.

[0107] In this embodiment, the initial health score of the water station equipment is obtained by statistically analyzing the product of the indicator score corresponding to each monitoring indicator and the monitoring indicator weight. In order to avoid low indicator scores being ignored, the number of indicator scores less than the indicator threshold is counted to obtain a correction coefficient. The initial health score is corrected based on the correction coefficient to obtain the current health score of the water station equipment, so as to highlight the importance of the indicator score less than the indicator threshold, thereby improving the accuracy of the current health score.

[0108] In an exemplary embodiment, the initial health score is corrected based on the correction coefficient to obtain the current health score of the water station equipment, including:

[0109] Based on the correction coefficient, a correction value is determined; the correction value is less than zero and is inversely proportional to the correction coefficient; the initial health score is added to the correction value to obtain the current health score of the water station equipment.

[0110] The correction value refers to the value used to correct the initial health score.

[0111] For example, after determining the correction coefficient, the computer device determines whether the correction coefficient is zero. If the correction coefficient is zero, the correction value is determined to be zero; if the correction coefficient is not equal to zero, the correction coefficient is substituted into the correction value calculation formula to obtain the correction value, and then the initial health score is added to the correction value to obtain the current health score of the water station equipment.

[0112] In an exemplary embodiment, the correction value calculation formula is as follows:

[0113] Formula (10)

[0114] Among them, F is the correction value; m is the correction coefficient, that is, the number of indicator scores that are less than the indicator threshold.

[0115] In this embodiment, the initial health score is corrected based on the correction coefficient to obtain the current health score of the water station equipment, so as to highlight the importance of the index score less than the index threshold, thereby improving the accuracy of the current health score.

[0116] In an exemplary embodiment, Figure 4 As shown, obtain the monitoring indicator weights corresponding to each monitoring indicator, including:

[0117] Step 402: Determine multiple first-level indicators corresponding to multiple monitoring indicators; one first-level indicator corresponds to multiple monitoring indicators.

[0118] Among them, the first-level indicators refer to comprehensive indicators that reflect the monitoring dimensions. It can be understood that the first-level indicators are a summary of multiple monitoring indicators. The first-level indicators include but are not limited to equipment conditions, operation and maintenance conditions, quality control conditions and data efficiency. For example, the diagram of the corresponding relationship between the first-level indicators and monitoring indicators is as follows: Figure 5 As shown, the first-level indicators include equipment status, operation and maintenance status, quality control status and data efficiency. Equipment status includes online status, key parameters, communication failure, instrument failure, operation status and average failure rate; operation and maintenance status includes task overdue, number of operation and maintenance, operation and maintenance interval, reagent remaining, station stop / abnormal situation, inspection status and average fault recovery time; quality control status includes daily quality control, weekly quality control and monthly quality control; data efficiency includes data transmission rate and data efficiency.

[0119] Exemplarily, the computer device determines multiple first-level indicators based on multiple monitoring indicators, and multiple monitoring indicators corresponding to each first-level indicator.

[0120] Step 404: Obtain an importance matrix corresponding to a plurality of first-level indicators; an element in the importance matrix represents the relative importance between two first-level indicators corresponding to the element.

[0121] Among them, the importance matrix refers to a matrix containing the relative importance between each two first-level indicators. The importance matrix can be used to establish a complementary fuzzy decision matrix through expert voting. The relative importance refers to the value that represents the importance of a first-level indicator compared to another first-level indicator. For example, the importance matrix , the diagram of the importance matrix A corresponding to the table is as follows Figure 6As shown, the first-level indicators corresponding to the first row to the fourth row of the importance matrix A are equipment condition, operation and maintenance condition, quality control condition and data efficiency, respectively. The first-level indicators corresponding to the first column to the fourth column of the importance matrix A are equipment condition, operation and maintenance condition, quality control condition and data efficiency, respectively. The relative importance of equipment condition and operation and maintenance condition is 0.6, which indicates that the equipment condition is slightly more important than the operation and maintenance condition; the relative importance of quality control condition and operation and maintenance condition is 0.7, which indicates that the quality control condition is significantly more important than the operation and maintenance condition; the relative importance of quality control condition and equipment condition is 0.8, which indicates that the quality control condition is much more important than the equipment condition.

[0122] Exemplarily, an operator inputs an importance matrix corresponding to a plurality of first-level indicators, and a computer device obtains the importance matrix corresponding to the plurality of first-level indicators.

[0123] Step 406: Determine the first-level indicator weight corresponding to each first-level indicator based on the importance matrix.

[0124] The first-level indicator weight refers to the value that represents the importance of the first-level indicator among multiple first-level indicators. The sum of the first-level indicator weights of all first-level indicators is equal to 1.

[0125] Exemplarily, the computer device determines, for each row in the importance matrix, a primary indicator weight of the primary indicator corresponding to the row based on multiple elements in the row.

[0126] In an exemplary embodiment, the calculation formula for the first-level indicator weight is as follows:

[0127] Formula (11)

[0128] Where i is the number of rows in the importance matrix; j is the number of columns in the importance matrix; n is the total number of rows or columns in the importance matrix; is the first-level indicator weight of the first-level indicator corresponding to the i-th row. For example, according to Figure 6 The importance matrix shown in the figure shows that W1=0.233, W2=0.217, W3=0.300, and W4=0.250. That is, the weight of the first-level indicator of equipment condition is 0.233, the weight of the first-level indicator of operation and maintenance condition is 0.217, the weight of the first-level indicator of quality control condition is 0.300, and the weight of the first-level indicator of data efficiency is 0.250.

[0129] Step 408: Based on the first-level indicator weight corresponding to the first-level indicator, determine the monitoring indicator weights corresponding to the multiple monitoring indicators corresponding to the first-level indicator.

[0130] Exemplarily, for each first-level indicator, the computer device obtains the indicator weight ratio of each monitoring indicator corresponding to the first-level indicator. For each monitoring indicator, the first-level indicator weight is multiplied by the indicator weight ratio of the monitoring indicator to obtain the initial indicator weight corresponding to the monitoring indicator; based on the initial indicator weights corresponding to all monitoring indicators, the initial indicator weights corresponding to all monitoring indicators are normalized to obtain the monitoring indicator weight of each monitoring indicator. The indicator weight ratio refers to the ratio of a monitoring indicator in the first-level indicator to all the monitoring indicators of the first-level indicator. The sum of the indicator weight ratios of multiple monitoring indicators included in a first-level indicator is 1. For example, the schematic diagram of the monitoring indicator is as follows: Figure 7 As shown in the figure, the initial indicator weight of the monitoring indicator is equal to the first-level indicator weight multiplied by the indicator weight ratio corresponding to the monitoring indicator, and the sum of the monitoring indicator weights of all monitoring indicators is equal to 1.

[0131] In this embodiment, the computer device first determines multiple first-level indicators corresponding to multiple monitoring indicators, determines the first-level indicator weight corresponding to each first-level indicator based on the obtained importance matrix, and then determines the monitoring indicator weights corresponding to the multiple monitoring indicators corresponding to the first-level indicators based on the first-level indicator weights corresponding to the first-level indicators. The monitoring indicator weights corresponding to the monitoring indicators are more suitable for determining the initial health score of the water station equipment, thereby improving the accuracy of the initial health score.

[0132] In an exemplary embodiment, before determining the monitoring indicator weights corresponding to the plurality of monitoring indicators corresponding to the first-level indicator based on the first-level indicator weight corresponding to the first-level indicator, the method further includes:

[0133] Based on the first-level indicator weights corresponding to each first-level indicator, determine the characteristic matrix corresponding to the importance matrix; the elements in the characteristic matrix are determined based on the ratio of the first-level indicator weights of the first-level indicators corresponding to the rows of the elements to the sum of the first-level indicator weights of the first-level indicators corresponding to the rows of the elements and the first-level indicator weights corresponding to the columns of the elements; based on the importance matrix and the characteristic matrix, determine the consistency test result between the importance matrix and the characteristic matrix; when the consistency test result is less than the test threshold, execute the steps of determining the monitoring indicator weights corresponding to the multiple monitoring indicators corresponding to the first-level indicators based on the first-level indicator weights corresponding to the first-level indicators.

[0134] The characteristic matrix refers to the matrix used to verify the rationality of the importance matrix. The consistency test result refers to the result obtained by verifying the rationality of the importance matrix. The test threshold refers to a pre-set value used for comparison with the consistency test result. The test threshold can be set according to actual needs, for example, the test threshold is 0.1 or 0.15.

[0135] Exemplarily, for each element to be determined in the feature matrix, the computer device divides the first-level indicator weight of the first-level indicator corresponding to the row of the element to be determined by the sum of the first-level indicator weight of the first-level indicator corresponding to the row of the element to be determined and the first-level indicator weight corresponding to the column of the element to be determined to obtain the element, until the feature matrix corresponding to the importance matrix is ​​obtained; based on the importance matrix and the feature matrix, the consistency test result between the importance matrix and the feature matrix is ​​determined, and the consistency test result is compared with the test threshold; if the consistency test result is less than the test threshold, the step of determining the monitoring indicator weights corresponding to multiple monitoring indicators corresponding to the first-level indicator based on the first-level indicator weight corresponding to the first-level indicator is executed; if the consistency test result is equal to or greater than the test threshold, a prompt is given to update the importance matrix.

[0136] In an exemplary embodiment, the formula for determining the elements in the feature matrix is ​​as follows:

[0137] Formula (12)

[0138] in, is the element in row i and column j of the feature matrix; is the first-level indicator weight of the first-level indicator corresponding to the i-th row, that is, the first-level indicator weight of the i-th first-level indicator; is the first-level indicator weight of the first-level indicator corresponding to the j-th column, that is, the first-level indicator weight of the j-th first-level indicator.

[0139] In an exemplary embodiment, the formula for determining the consistency check result is as follows:

[0140] Formula (13)

[0141] Among them, A is the importance matrix; W is the feature matrix corresponding to the importance matrix; is the element in row i and column j in the importance matrix; The element in row j and column i of the important features matrix.

[0142] In this embodiment, the importance matrix and the characteristic matrix are used to determine the consistency test result between the importance matrix and the characteristic matrix. When the consistency test result is less than the test threshold, the first-level indicator weight corresponding to the first-level indicator is based on the first-level indicator to determine the monitoring indicator weights corresponding to the multiple monitoring indicators corresponding to the first-level indicator. That is, the rationality of the importance matrix is ​​tested using the characteristic matrix. When the importance matrix is ​​reasonable, the monitoring indicator weights corresponding to each monitoring indicator are determined according to the importance matrix, thereby improving the rationality of the monitoring indicator weights.

[0143] In an exemplary embodiment, generating and dispatching an operation and maintenance work order corresponding to the water station equipment based on the predicted health scores corresponding to the multiple future moments includes:

[0144] The predicted health scores corresponding to multiple future moments are input into the operation and maintenance mode prediction model to obtain the target operation and maintenance mode; the operation and maintenance mode prediction model is updated by the operation and maintenance mode prediction model, which includes: the operation and maintenance mode prediction model determines a first error loss based on the difference between the predicted health score and the current health score, determines a second error loss based on the target operation and maintenance mode, determines a third error loss based on the absolute difference between the predicted health score and the current health score, determines a target error loss based on the first error loss, the second error loss and the third error loss, and updates the operation and maintenance mode prediction model based on the target error loss to obtain an updated operation and maintenance mode prediction model; based on the target operation and maintenance mode, generates and distributes an operation and maintenance work order corresponding to the water station equipment.

[0145] The operation and maintenance method prediction model refers to a neural network model that determines the target operation and maintenance method based on the predicted health scores corresponding to multiple future moments. The operation and maintenance method prediction model can be a DQN (Deep Q-Network) model. The target operation and maintenance method refers to the method of maintaining water station equipment. The difference between the predicted health score and the current health score is the value obtained by subtracting the current health score from the predicted health score. The absolute difference between the predicted health score and the current health score is the absolute value of the value obtained by subtracting the current health score from the predicted health score. The target error loss refers to the error loss used to correct the parameters of the operation and maintenance method prediction model. The target error loss is composed of the first error loss, the second error loss, and the third error loss.

[0146] Exemplarily, a computer device inputs the predicted health scores corresponding to multiple future moments into an operation and maintenance mode prediction model, which outputs a target operation and maintenance mode. After obtaining the target operation and maintenance mode, the computer device generates and dispatches an operation and maintenance work order corresponding to the water station equipment based on the target operation and maintenance mode. After outputting the target operation and maintenance mode, the operation and maintenance mode prediction model further includes: the operation and maintenance mode prediction model calculates the difference between the predicted health score and the current health score to obtain a first error loss; obtains a loss value corresponding to the target operation and maintenance mode to obtain a second error loss; calculates the absolute difference between the predicted health score and the current health score to obtain a third error loss; performs statistics on the first error loss, the second error loss, and the third error loss to obtain a target error loss; and updates the operation and maintenance mode prediction model based on the target error loss to obtain an updated operation and maintenance mode prediction model.

[0147] In an exemplary embodiment, the operation mode prediction model calculates the difference between the predicted health score and the current health score to obtain a first error loss; obtains the loss value corresponding to the target operation mode to obtain a second error loss; and calculates the absolute difference between the predicted health score and the current health score to obtain a third error loss, including: the operation mode prediction model calculates the difference between the predicted health score corresponding to the first predicted future moment and the current health score to obtain the first error loss; obtains the loss value corresponding to the target operation mode from the operation mode loss mapping table to obtain the second error loss; and calculates the absolute difference between the predicted health score corresponding to the first predicted future moment and the current health score to obtain the third error loss. Wherein, the first predicted future moment refers to the first future moment among multiple future moments, for example, the multiple future moments are T1, T2, T3, T4 and T5, T1 is before T2, T2 is before T3, T3 is before T4, and T4 is before T5, then T1 is the first future moment. The operation and maintenance method loss mapping table refers to a table containing the mapping relationship between operation and maintenance methods and loss values, that is, each operation and maintenance method in the operation and maintenance method loss mapping table corresponds to a loss value.

[0148] In an exemplary embodiment, calculating the absolute difference between the predicted health score corresponding to the first predicted future time and the current health score to obtain the third error loss includes:

[0149] Formula (14)

[0150] Formula (15)

[0151] Where Diff is the absolute difference between the predicted health score corresponding to the first predicted future time and the current health score; health_score is the predicted health score corresponding to the first predicted future time; ture_score is the previous health score; Coefficient is the third error loss; α is a hyperparameter that can be set according to actual needs; max(1-α×Diff,0) is the maximum value between 1-α×Diff and 0.

[0152] In this embodiment, the operation and maintenance mode prediction model determines the target operation and maintenance mode based on the predicted health scores corresponding to multiple future moments, improving the accuracy of the target operation and maintenance mode. Operation and maintenance work orders corresponding to the water station equipment are generated and dispatched based on the target operation and maintenance mode, thereby improving the accuracy of the operation and maintenance work orders. Furthermore, the operation and maintenance mode prediction model determines a target error loss based on the predicted health score, the current health score, and the target operation and maintenance mode. This target error loss is used to update the operation and maintenance mode prediction model to obtain an updated operation and maintenance mode prediction model. This continuously trains the operation and maintenance mode prediction model, thereby improving its accuracy.

[0153] In an exemplary embodiment, the operation and maintenance dispatching method includes:

[0154] First, establish a health evaluation index system.

[0155] Determine the monitoring indicators of water station equipment, including online status, key parameters, communication failure, instrument failure, operating status, average failure rate, task overdue, number of operation and maintenance, operation and maintenance interval, reagent remaining, station stop / abnormal situation, inspection status, average fault recovery time, daily quality control, weekly quality control, monthly quality control, data transmission rate and data efficiency.

[0156] Determine the first-level indicators of water station equipment. The first-level indicators include equipment status, operation and maintenance status, quality control status and data efficiency. Equipment status includes online status, key parameters, communication failure, instrument failure, operation status and average failure rate; operation and maintenance status includes task overdue, operation and maintenance times, operation and maintenance intervals, reagent remaining, station stop / abnormal situation, inspection status and average fault recovery time; quality control status includes daily quality control, weekly quality control and monthly quality control; data efficiency includes data transmission rate and data efficiency.

[0157] The operator inputs the importance matrix corresponding to multiple first-level indicators. The computer device obtains the importance matrix corresponding to the multiple first-level indicators and uses formula (11) to determine the first-level indicator weight corresponding to each first-level indicator. Based on the first-level indicator weight corresponding to each first-level indicator, the characteristic matrix corresponding to the importance matrix is ​​determined using formula (12). Based on the importance matrix and the characteristic matrix, the consistency test result corresponding to the importance matrix is ​​determined using formula (13). If the consistency test result is equal to or greater than the test threshold, a prompt is given to update the importance matrix.

[0158] If the consistency test result is less than the test threshold, for each first-level indicator, the computer device obtains the indicator weight ratio of each monitoring indicator corresponding to the first-level indicator. For each monitoring indicator, the first-level indicator weight is multiplied by the indicator weight ratio of the monitoring indicator to obtain the initial indicator weight corresponding to the monitoring indicator; based on the initial indicator weights corresponding to all monitoring indicators, the initial indicator weights corresponding to all monitoring indicators are normalized to obtain the monitoring indicator weights of each monitoring indicator.

[0159] Based on the establishment of a health evaluation index system, the operation and maintenance dispatching method is implemented. The flow chart of the operation and maintenance dispatching method is as follows: Figure 8 Shown, including:

[0160] The computer device obtains the monitoring value of the water station equipment and the indicator type of the monitoring indicator corresponding to the monitoring value. For each detection indicator, based on the indicator type of the detection indicator, the target calculation formula corresponding to the detection indicator is determined. When the indicator type of the monitoring indicator is a gradual acceleration indicator, the target calculation formula is formula (1); when the indicator type of the monitoring indicator is a time interval control indicator, the target calculation formula is formula (2), (3) and (4); when the indicator type of the monitoring indicator is a narrow interval smooth conversion indicator, the target calculation formula is formula (5); when the indicator type of the monitoring indicator is a balance indicator, the target calculation formula is formula (6), (7) and (8); when the indicator type of the monitoring indicator is a state indicator, when the monitoring value of the monitoring indicator is 0, the indicator score of the monitoring indicator is 0, and when the monitoring value of the monitoring indicator is 1, the indicator score of the monitoring indicator is 100; when the indicator type of the monitoring indicator is a fuzzy hierarchical analysis indicator, the fuzzy hierarchical analysis method is used to calculate the indicator score of the monitoring indicator. The monitoring value corresponding to the monitoring indicator is substituted into the target calculation formula to obtain the indicator score corresponding to the monitoring indicator.

[0161] The computer device obtains the monitoring indicator weight corresponding to each monitoring indicator, adds the product of the indicator score corresponding to each monitoring indicator and the monitoring indicator weight, and uses formula (9) to calculate the initial health score of the water station equipment; compares the indicator score of each monitoring indicator with the indicator threshold, and counts the number of indicator scores less than the indicator threshold to obtain the correction coefficient. After determining the correction coefficient, it is determined whether the correction coefficient is zero. If the correction coefficient is zero, the correction value is determined to be zero; if the correction coefficient is not equal to zero, the correction coefficient is substituted into formula (10) to obtain the correction value, and then the initial health score is added to the correction value to obtain the current health score of the water station equipment.

[0162] The computer device inputs the current health score into the prediction model to obtain the predicted health scores corresponding to multiple future moments.

[0163] The computer device inputs the predicted health scores corresponding to multiple future moments into the operation and maintenance mode prediction model, and the operation and maintenance mode prediction model outputs a target operation and maintenance mode. After obtaining the target operation and maintenance mode, the computer device generates and dispatches an operation and maintenance work order corresponding to the water station equipment based on the target operation and maintenance mode. After outputting the target operation and maintenance mode, the operation and maintenance mode prediction model further includes: the operation and maintenance mode prediction model calculates the difference between the predicted health score and the current health score to obtain a first error loss; obtains the loss value corresponding to the target operation and maintenance mode to obtain a second error loss; calculates the absolute difference between the predicted health score and the current health score to obtain a third error loss; performs statistics on the first error loss, the second error loss, and the third error loss to obtain a target error loss; and updates the operation and maintenance mode prediction model based on the target error loss to obtain an updated operation and maintenance mode prediction model.

[0164] In the above-mentioned operation and maintenance dispatching method, the monitoring value of the water station equipment and the indicator type of the monitoring indicator corresponding to the monitoring value are obtained, and the indicator score corresponding to the monitoring indicator is determined based on the monitoring value and indicator type corresponding to the monitoring indicator. The monitoring indicators of different indicator types use different calculation methods to calculate the indicator score, which improves the accuracy of the indicator score. The current health score of the water station equipment is determined according to the indicator score corresponding to each monitoring indicator, which improves the accuracy of the current health score; based on the current health score, the predicted health scores corresponding to multiple future moments are predicted, and the operation and maintenance work order corresponding to the water station equipment is generated and dispatched based on the predicted health scores corresponding to multiple future moments. It can be understood that the operation and maintenance work order is dispatched only when the water station equipment is likely to fail in the future, so that the operation and maintenance personnel can perform inspection and maintenance. Compared with the operation and maintenance personnel performing periodic inspection and maintenance, it saves operation and maintenance resources and improves the utilization of operation and maintenance resources. Moreover, the operation and maintenance work order is dispatched when it is predicted that the water station equipment may fail in the future, so that the operation and maintenance personnel can perform inspection and maintenance on the water station equipment before the water station equipment actually fails, thereby avoiding the actual failure of the water station equipment, thereby improving the stability of the water station equipment operation.

[0165] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0166] Based on the same inventive concept, the embodiments of the present application also provide an operation and maintenance dispatching device for implementing the above-mentioned operation and maintenance dispatching method. The implementation solution provided by this device is similar to the implementation solution described in the above-mentioned method. Therefore, the specific limitations in one or more embodiments of the operation and maintenance dispatching device provided below can be referred to the limitations of the operation and maintenance dispatching method above, and will not be repeated here.

[0167] In one embodiment, Figure 9 As shown, an operation and maintenance dispatching device is provided, including: an acquisition module 902, an indicator score determination module 904, a health score determination module 906, a prediction module 908 and an operation and maintenance dispatching module 910, wherein:

[0168] An acquisition module 902 is used to acquire the monitoring value of the water station equipment and the indicator type of the monitoring indicator corresponding to the monitoring value;

[0169] An indicator score determination module 904 is configured to determine, for each monitoring indicator, an indicator score corresponding to the monitoring indicator based on the monitoring value and indicator type corresponding to the monitoring indicator;

[0170] A health score determination module 906 is configured to determine the current health score of the water station equipment based on the indicator scores corresponding to the various monitoring indicators;

[0171] A prediction module 908 is configured to predict predicted health scores corresponding to multiple future moments based on the current health score;

[0172] The operation and maintenance dispatching module 910 is used to generate and dispatch operation and maintenance work orders corresponding to water station equipment based on the predicted health scores corresponding to multiple future moments.

[0173] In an exemplary embodiment, the indicator score determination module 904 is also used to: obtain a target calculation formula corresponding to the indicator type; the indicator type is one of a progressive acceleration indicator, a state indicator, a time interval control indicator, a balance indicator, and a narrow interval smooth transition indicator; and substitute the monitoring value corresponding to the monitoring indicator into the target calculation formula to obtain the indicator score corresponding to the monitoring indicator.

[0174] In an exemplary embodiment, the health score determination module 904 is also used to: obtain the monitoring indicator weight corresponding to each monitoring indicator; perform statistics on the product of the indicator score corresponding to each monitoring indicator and the monitoring indicator weight to obtain the initial health score of the water station equipment; perform statistics on the number of indicator scores that are less than the indicator threshold to obtain a correction coefficient; and correct the initial health score based on the correction coefficient to obtain the current health score of the water station equipment.

[0175] In an exemplary embodiment, the health score determination module 906 is further used to: determine a correction value based on a correction coefficient; the correction value is less than zero and is inversely proportional to the correction coefficient; and add the correction value to the initial health score to obtain the current health score of the water station equipment.

[0176] In an exemplary embodiment, the health score determination module 906 is also used to: determine multiple first-level indicators corresponding to multiple monitoring indicators; one first-level indicator corresponds to multiple monitoring indicators; obtain the importance matrix corresponding to multiple first-level indicators; the elements in the importance matrix represent the relative importance between the two first-level indicators corresponding to the elements; based on the importance matrix, determine the first-level indicator weight corresponding to each first-level indicator; based on the first-level indicator weight corresponding to the first-level indicator, determine the monitoring indicator weights corresponding to the multiple monitoring indicators corresponding to the first-level indicator.

[0177] In an exemplary embodiment, the health score determination module 906 is also used to: determine the characteristic matrix corresponding to the importance matrix based on the first-level indicator weights corresponding to each first-level indicator; the elements in the characteristic matrix are determined based on the ratio of the first-level indicator weights of the first-level indicators corresponding to the rows of the elements to the sum of the first-level indicator weights of the first-level indicators corresponding to the rows of the elements and the first-level indicator weights corresponding to the columns of the elements; determine the consistency test results between the importance matrix and the characteristic matrix based on the importance matrix and the characteristic matrix; when the consistency test result is less than the test threshold, execute the steps of determining the monitoring indicator weights corresponding to multiple monitoring indicators corresponding to the first-level indicators based on the first-level indicator weights corresponding to the first-level indicators.

[0178] In an exemplary embodiment, the operation and maintenance dispatch module 910 is also used to: input the predicted health scores corresponding to multiple future moments into the operation and maintenance mode prediction model to obtain the target operation and maintenance mode; the operation and maintenance mode prediction model update method includes: the operation and maintenance mode prediction model determines the first error loss based on the difference between the predicted health score and the current health score, determines the second error loss based on the target operation and maintenance mode, determines the third error loss based on the absolute difference between the predicted health score and the current health score, determines the target error loss based on the first error loss, the second error loss and the third error loss, and updates the operation and maintenance mode prediction model based on the target error loss to obtain an updated operation and maintenance mode prediction model; based on the target operation and maintenance mode, generates and dispatches the operation and maintenance work order corresponding to the water station equipment.

[0179] Each module in the above-mentioned operation and maintenance dispatching device can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor of the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each of the above modules.

[0180] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 10 As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless means, and the wireless means can be implemented via Wi-Fi, mobile cellular networks, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements an operation and maintenance dispatching method. The display unit of the computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0181] Those skilled in the art will understand that Figure 10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0182] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0183] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0184] In one embodiment, a program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0185] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0186] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0187] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0188] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for dispatching operations and maintenance, characterized in that: The method comprises: Obtaining monitoring values ​​of water station equipment and indicator types of monitoring indicators corresponding to the monitoring values; For each of the monitoring indicators, based on the monitoring value and indicator type corresponding to the monitoring indicator, determine the indicator score corresponding to the monitoring indicator; Determine the current health score of the water station equipment based on the indicator score corresponding to each of the monitoring indicators; Based on the current health score, predicting predicted health scores corresponding to multiple future moments; Based on the predicted health scores corresponding to the multiple future moments, an operation and maintenance work order corresponding to the water station equipment is generated and distributed.

2. The method according to claim 1, characterized in that The determining, based on the monitoring value and the indicator type corresponding to the monitoring indicator, the indicator score corresponding to the monitoring indicator comprises: Obtaining a target calculation formula corresponding to the indicator type; the indicator type is one of a gradual acceleration indicator, a state indicator, a time interval control indicator, a balance indicator, and a narrow interval smooth transition indicator; The monitoring value corresponding to the monitoring indicator is substituted into the target calculation formula to obtain the indicator score corresponding to the monitoring indicator.

3. The method according to claim 1, characterized in that The determining of the current health score of the water station equipment based on the indicator score corresponding to each of the monitoring indicators includes: Obtaining the monitoring indicator weight corresponding to each of the monitoring indicators; The product of the indicator score corresponding to each of the monitoring indicators and the monitoring indicator weight is statistically analyzed to obtain the initial health score of the water station equipment; Counting the number of the indicator scores that are less than the indicator threshold to obtain a correction coefficient; The initial health score is corrected based on the correction coefficient to obtain a current health score of the water station equipment.

4. The method according to claim 3, characterized in that The correcting the initial health score based on the correction coefficient to obtain the current health score of the water station equipment includes: Based on the correction coefficient, determining a correction value; the correction value is less than zero and is inversely proportional to the correction coefficient; The initial health score is added to the correction value to obtain the current health score of the water station equipment.

5. The method according to claim 3, characterized in that: The obtaining of the monitoring indicator weights corresponding to the respective monitoring indicators comprises: Determine a plurality of first-level indicators corresponding to a plurality of the monitoring indicators; one first-level indicator corresponds to a plurality of the monitoring indicators; Obtaining an importance matrix corresponding to the plurality of first-level indicators; an element in the importance matrix represents a relative importance between two first-level indicators corresponding to the element; Based on the importance matrix, determining a first-level indicator weight corresponding to each first-level indicator; Based on the first-level indicator weight corresponding to the first-level indicator, the monitoring indicator weights respectively corresponding to the multiple monitoring indicators corresponding to the first-level indicator are determined.

6. The method according to claim 5, characterized in that Before determining the monitoring indicator weights respectively corresponding to the plurality of monitoring indicators corresponding to the first-level indicator based on the first-level indicator weight corresponding to the first-level indicator, the method further includes: Based on the first-level indicator weights corresponding to each of the first-level indicators, a feature matrix corresponding to the importance matrix is ​​determined; the elements in the feature matrix are determined based on the ratio of the first-level indicator weights of the first-level indicators corresponding to the rows of the elements to the sum of the first-level indicator weights of the first-level indicators corresponding to the rows of the elements and the first-level indicator weights corresponding to the first-level indicators corresponding to the columns of the elements; Based on the importance matrix and the characteristic matrix, determining a consistency check result between the importance matrix and the characteristic matrix; When the consistency check result is less than the check threshold, the step of determining the monitoring indicator weights corresponding to the multiple monitoring indicators corresponding to the first-level indicator based on the first-level indicator weight corresponding to the first-level indicator is performed.

7. The method according to claim 1, characterized in that The generating and dispatching of operation and maintenance work orders corresponding to the water station equipment based on the predicted health scores corresponding to the multiple future moments includes: The predicted health scores corresponding to the multiple future moments are input into the operation and maintenance mode prediction model to obtain the target operation and maintenance mode; the updating method of the operation and maintenance mode prediction model comprises: the operation and maintenance mode prediction model determines a first error loss based on the difference between the predicted health score and the current health score, determines a second error loss based on the target operation and maintenance mode, determines a third error loss based on the absolute difference between the predicted health score and the current health score, determines a target error loss based on the first error loss, the second error loss and the third error loss, and updates the operation and maintenance mode prediction model based on the target error loss to obtain an updated operation and maintenance mode prediction model; Based on the target operation and maintenance mode, an operation and maintenance work order corresponding to the water station equipment is generated and distributed.

8. An operation and maintenance dispatching device, characterized in that: The device comprises: An acquisition module, used to acquire the monitoring value of the water station equipment and the indicator type of the monitoring indicator corresponding to the monitoring value; An indicator score determination module, used to determine, for each of the monitoring indicators, an indicator score corresponding to the monitoring indicator based on the monitoring value and indicator type corresponding to the monitoring indicator; A health score determination module, used to determine the current health score of the water station equipment based on the indicator scores corresponding to each of the monitoring indicators; A prediction module, configured to predict predicted health scores corresponding to a plurality of future moments based on the current health score; The operation and maintenance dispatching module is used to generate and dispatch the operation and maintenance work order corresponding to the water station equipment based on the predicted health scores corresponding to the multiple future moments.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images