Analysis and management method and system for improving voltage reduction rate of opinion work order

Abstract

The invention relates to the field of data model integration evaluation analysis, in particular to an analysis management method and system for improving the voltage reduction rate of an opinion work order, and the method comprises the steps: generating a multi-source integration evaluation model through an influence factor parameter and a voltage reduction rate observation value in a corresponding associated time period, and obtaining a total voltage reduction rate observation value in all time periods; the integration of multi-source data can make full use of information of different sources, the understanding and prediction ability of the model on the change of the pressure reduction rate is enhanced, so that the prediction accuracy is improved, the integrated model combines the advantages of a plurality of prediction algorithms, the deviation and error possibly generated by a single model are reduced, the overall prediction is more stable, and the prediction efficiency is improved. By quantifying the parameters of the influence factors, the model can clearly identify the specific influence of each factor on the pressure reduction rate, and powerful support is provided for subsequent decision making.

Description

Technical Field

[0001] The present invention relates to the field of data model integration evaluation and analysis, and more specifically to an analysis management method and system for improving the pressure reduction rate of opinion work orders. Background Art

[0002] The number of opinion work orders is an important indicator to measure the service quality and customer satisfaction of power supply companies. It refers to the work documents generated after customers report problems or make opinions and suggestions by calling the power supply service hotline of various channels. The high number of work orders reflects that there are many problems with the service in the area. Processing a large number of work orders requires more manpower, material resources and time, which increases the pressure on employees, irrational resource allocation, increases operating costs, and affects the economic benefits of the enterprise; too many work orders externally may cause congestion in the processing process, resulting in reduced overall service efficiency, and failure to solve customer problems in a timely and effective manner, forming a vicious circle, resulting in poor customer experience, reduced satisfaction, and affecting the image and reputation of the company.

[0003] At this stage, the parameters of the factors that have the greatest impact on the number of opinion tickets are analyzed. The existing technology mainly uses data survey table analysis and grading to gradually confirm the weighted influencing factors with the largest final proportion, and then takes measures to reduce the reduction rate of opinion tickets based on the proportion factors. The reduction rate of opinion tickets is mainly predicted by selecting a suitable model, but there are disadvantages: 1) There may be outliers or erroneous data in the data, resulting in deviations during model training; 2) If the selected model is too complex, it may lead to overfitting; and simple models may not be able to capture important trends and relationships in the data; 3) The reduction rate is affected by a variety of dynamic factors, which may change over time. If the model is not updated in time or new factors are not considered, the prediction may be inaccurate.

[0004] Therefore, the present invention proposes an analysis management method and system for improving the pressure reduction rate of opinion work orders. Summary of the invention

[0005] In order to address the deficiencies in the prior art, the present invention provides an analysis and management method and system for improving the pressure reduction rate of opinion work orders. A multi-source integrated evaluation model is generated through influencing factor parameters and corresponding observed values ​​of the pressure reduction rate in associated time periods to obtain the total observed value of the pressure reduction rate for all time periods. The integration of multi-source data can make full use of information from different sources, enhance the model's understanding and prediction capabilities of pressure reduction rate changes, and thus improve the accuracy of the prediction. The integrated model combines the advantages of multiple prediction algorithms to reduce the deviations and errors that may be generated by a single model, making the overall prediction more stable. By quantifying the parameters of the influencing factors, the model can clearly identify the specific impact of each factor on the pressure reduction rate, providing strong support for subsequent decision-making.

[0006] The present invention adopts the following technical solution.

[0007] The present invention provides an analysis and management method for improving the pressure reduction rate of opinion work orders, which is characterized by comprising the following steps:

[0008] S1: Collect and obtain the influencing factor parameters associated with the pressure reduction rate of the opinion work order, obtain the measured values ​​to construct the parameter measurement value sequence, analyze the trend characteristic values ​​of the parameter measurement value sequence in combination with the time series analysis model, and import the trend characteristic values ​​into the deep neural network learning model to calculate and obtain the weight priority of the influencing factor parameters;

[0009] S2: The weight priority values ​​of the d influencing factor parameters obtained based on S1 constitute the weight priority value sequence W, and the K influencing factor parameters with the highest weight priority are selected to provide a parameter basis for the subsequent corresponding relationship.

[0010] S3: Collect the observed values ​​of the pressure reduction rate of opinion work orders in each period, and pre-process the observed values ​​of the pressure reduction rate of opinion work orders by interpolation;

[0011] S4: matching the observed value of the pressure reduction rate after interpolation by the interpolation method with the K influencing factor parameters with the highest weight priority;

[0012] S5: Generate a multi-source integrated evaluation model through the influencing factor parameters and the observed values ​​of the blood pressure reduction rate in the corresponding associated time period to obtain the total observed value of the blood pressure reduction rate in all time periods.

[0013] Preferably, in step S1, the t-th influencing factor parameter A is analyzed, H measured values ​​of the influencing factor parameter A are obtained based on h different time points, and the measured time-varying parameter sequence is constructed as follows: The s-1th measurement time-varying parameter value and the sth measured time-varying parameter value The time period between s -T s-1 , T s Expressed as The total time period, T s-1 Expressed as The total time period between, then after the next interval, the sth parameter measurement value The single cumulative value of for:

[0014]

[0015] in, A single accumulation of Single accumulation of

[0016] The time series analysis model is:

[0017]

[0018] in, express The trend characteristic value of , β and γ are the discrimination coefficients.

[0019] Then after N intervals, the sth parameter measurement value After N times, the cumulative value is The trend characteristic value of

[0020] Preferably, the trend characteristic values ​​corresponding to the H parameter measurement values ​​in the parameter measurement value sequence are generated to construct a trend characteristic value sequence, and the trend characteristic value sequence is The trend characteristic value sequence is imported into the deep neural network learning model to obtain the generated derived sequence A'(N); the generated derived sequence A'(N) is imported into the deep neural network learning model again to obtain the secondary generated sequence A"(N).

[0021] Preferably, the operation in S1 to obtain the weight priority of the influencing parameter and derive the result includes:

[0022] Arbitrarily select the weight priority W of the tth influencing factor parameter C among the influencing factor parameters i for:

[0023]

[0024] in, represents the weight coefficient of the g-th convolutional network layer in the deep neural network learning model, p tg represents the activation function of the g-th convolutional network layer, and the number of convolutional network layers is G;

[0025] p tg The activation function of the g-th convolutional network layer is:

[0026]

[0027] Among them, τ g represents the expansion rate of the g-th convolutional network layer, B g Represents the convolution kernel parameters of the g-th convolutional network layer.

[0028] Preferably, by comparing the time period dispersion of the observed value of the pressure reduction rate and the time period dispersion of K influencing factor parameters on the pressure reduction rate of the opinion work order, if there is an overlap in the time period dispersion between them and this overlap follows a certain correspondence, if the overlapping range of the time period dispersion of the observed value of the pressure reduction rate and the time period dispersion of a certain influencing factor parameter exceeds a preset limit value, then it is judged that the influencing factor parameter has a decisive role in the observed value of the pressure reduction rate, and at the same time, this decisive influencing factor parameter is matched with the current time period based on a certain correspondence.

[0029] Preferably, in step S4, the specific workflow includes:

[0030] Based on the nonlinear correspondence constraint, the jth influencing factor parameter a j and the observed value C of the pressure reduction rate in the vth period v For corresponding association, the nonlinear corresponding relationship constraints are as follows:

[0031] Minimize the objective function:

[0032] Constraints: 1-θ j ≤C v (Q T δ(a j )+L);

[0033] Among them, K represents the total number of influencing factor parameters, e represents the distance parameter, θ j Represents the distance variable, indicating the jth influencing factor parameter a j and the observed value C of the pressure reduction rate in the vth period v The length of the interval. j ) indicates that the jth influencing factor parameter a j After mapping and associating to the vth period, the feature vector is obtained, Q represents the mapping association direction vector, and L represents the offset term.

[0034] Preferably, different weights are assigned in advance to the corresponding associated influencing factor parameters in the two adjacent time periods. When analyzing the fluctuating outlier observed values ​​of the blood pressure reduction rate generated in all time periods, the corresponding associated influencing factor parameters at the intersection of the ranges in the adjacent time periods are allocated according to certain weights, which enables these influencing factor parameters to affect the analysis results of the two time periods at the same time.

[0035] Preferably, in step S5,

[0036] Set the observed value sequence of the pressure reduction rate in the Dth period to C D For {c Dn, n=1,2,3,...,N}, N represents the number of observed values ​​of the blood pressure reduction rate, n represents the nth observed value of the blood pressure reduction rate, and based on the different time periods corresponding to the K influencing factor parameters, a corresponding short-term blood pressure reduction rate observation model is constructed for each influencing factor parameter.

[0037] Preferably, in step S5,

[0038] set up is the total value of the pressure reduction rate observation of the short-term pressure reduction rate observation model in all time periods through the multi-source integrated evaluation model, W D is the weight priority of the influencing factor parameters in the short-term pressure reduction rate observation model affecting the Dth period, then the multi-source integrated evaluation model is

[0039] The present invention also provides an analysis and management system for improving the pressure reduction rate of opinion work orders, using the analysis and management method for improving the pressure reduction rate of opinion work orders, including an element parameter weight analysis module, a pressure reduction rate observation numerical preprocessing module, and a multi-source integrated evaluation module.

[0040] The factor parameter weight analysis module is used to import trend characteristic values ​​into the deep neural network learning model to obtain the weight priority of the influencing factor parameters;

[0041] The depressurization rate observation value preprocessing module is used to match the depressurization rate observation value after interpolation and the K influencing factor parameters with the highest weight priority.

[0042] The multi-source integrated evaluation module is used to generate a multi-source integrated evaluation model through the influencing factor parameters and the observed values ​​of the pressure reduction rate in the corresponding associated time period, and obtain the total observed value of the pressure reduction rate in all time periods.

[0043] The beneficial effect of the present invention is that, compared with the prior art, a certain influencing factor parameter is associated with the observed value of the pressure reduction rate in a certain period of time based on a nonlinear correspondence constraint. Through the nonlinear correspondence, the influencing factor parameter can be more accurately associated with the observed value of the pressure reduction rate, so as to analyze the influence relationship more deeply. Through the influencing factor parameters and the observed values ​​of the pressure reduction rate in the corresponding associated time period, a multi-source integrated evaluation model is generated to obtain the total value of the pressure reduction rate observation for all time periods. The integration of multi-source data can make full use of information from different sources, enhance the model's understanding and prediction ability of the change in the pressure reduction rate, and thus improve the accuracy of the prediction. The integrated model combines the advantages of multiple prediction algorithms to reduce the deviation and error that may be generated by a single model, making the overall prediction more stable. By quantifying the parameters of the influencing factors, the model can clearly identify the specific impact of each factor on the pressure reduction rate, providing strong support for subsequent decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flow chart of an analysis and management method for improving the pressure reduction rate of opinion work orders in the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in this application are only part of the embodiments of the present invention, not all of them. Based on the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.

[0046] refer to Figure 1 , an embodiment of the present invention provides an analysis and management method for improving the pressure reduction rate of opinion work orders, comprising the following steps:

[0047] S1: Collect and obtain the influencing factor parameters associated with the pressure reduction rate of the opinion work order, obtain the measurement values ​​to construct the parameter measurement value sequence, combine the time series analysis model to analyze the trend characteristic values ​​of the parameter measurement value sequence, and import the trend characteristic values ​​into the deep neural network learning model to obtain the weight priority of the influencing factor parameters.

[0048] At intervals of one time period, the measured values ​​of each influencing factor parameter are collected in turn, and a parameter measurement value sequence is constructed according to the measured value of each influencing factor parameter. The trend characteristic value of the parameter measurement value sequence is analyzed in combination with a time series analysis model.

[0049] Assume that the total number of influencing factor parameters is d, arbitrarily select the tth influencing factor parameter A from the influencing factor parameters for analysis, and obtain H measured values ​​of the influencing factor parameter A based on h different time points, that is, assume that there are H time periods T1, T2, …, T H and the corresponding measured values The order of constructing the measurement time-varying parameters is: The s-1th measurement time-varying parameter value and the sth measured time-varying parameter value The time period between s -T s-1 , T s Expressed as The total time period, T s-1 Expressed as The total time period between, then after the next interval, the sth parameter measurement value The single cumulative value of for:

[0050]

[0051] in, A single accumulation of Single accumulation of

[0052] The time series analysis model is:

[0053]

[0054] in, express The trend characteristic value of , β and γ are the discrimination coefficients.

[0055] Then after N intervals, the sth parameter measurement value After N times, the cumulative value is The trend characteristic value of

[0056] The N trend feature values ​​obtained are imported into the deep neural network learning model to calculate the weight priority of the influencing parameters and export the results.

[0057] Generate the trend characteristic values ​​corresponding to the H parameter measurement values ​​in the parameter measurement value sequence to construct the trend characteristic value sequence. The trend characteristic value sequence is And the trend characteristic value sequence is imported into the deep neural network learning model to obtain the generated derived sequence A'(N);

[0058] The generated derived sequence A'(N) is re-introduced into the deep neural network learning model to obtain the secondary generated sequence A"(N).

[0059] Arbitrarily select the weight priority W of the tth influencing factor parameter C among the influencing factor parameters i for:

[0060]

[0061] in, represents the weight coefficient of the g-th convolutional network layer in the deep neural network learning model, p tg Represents the activation function of the g-th convolutional network layer, and the number of convolutional network layers is G.

[0062] p tg The activation function of the g-th convolutional network layer is:

[0063]

[0064] Among them, τ g represents the expansion rate of the g-th convolutional network layer, B g Represents the convolution kernel parameters of the g-th convolutional network layer.

[0065] The above processing flow is adopted for d influencing factor parameters in turn, and the weight priority values ​​of the d influencing factor parameters finally obtained constitute the weight priority value sequence W. The d influencing factor parameters are arranged in sequence from small to large according to the weights of the influencing factor parameters. The influencing factor parameter with the highest weight priority is at the end of the sequence. At the same time, the influencing factor parameter with the highest weight priority is also the factor that has the greatest impact on the pressure reduction rate of opinion work orders.

[0066] S2: The weight priority values ​​of the d influencing factor parameters obtained based on S1 constitute the weight priority value sequence W, and the K influencing factor parameters with the highest weight priority are selected to provide a parameter basis for the subsequent corresponding relationship.

[0067] S3: Collect the observed values ​​of the pressure reduction rate of opinion work orders in each period, and pre-process the observed values ​​of the pressure reduction rate of opinion work orders by interpolation.

[0068] In the embodiment of the present invention, in view of the fact that the observation values ​​of the pressure reduction rate of opinion work orders are not collected regularly based on the same interval time periods, the observation values ​​of the pressure reduction rate of opinion work orders need to be preprocessed by interpolation. The interpolation method refers to interpolating a continuous function on the basis that the observation values ​​of the pressure reduction rate of opinion work orders are discrete data, so that the observation values ​​of the pressure reduction rate of opinion work orders of this continuous curve have the same interval time period.

[0069] A line graph of the initial and interpolated observed values ​​of the pressure reduction rate. In the embodiment of the present invention, the interpolation algorithm is used to interpolate the observed values ​​of the pressure reduction rate of the opinion work order, and the observed values ​​of the pressure reduction rate of the opinion work order are interpolated at monthly intervals to obtain a time series after interpolation. After the interpolation, there are a total of Z groups of values, which refer to the observed values ​​of Z months.

[0070] S4: Match the observed value of the pressure reduction rate after interpolation by the interpolation method with the K influencing factor parameters with the highest weight priority.

[0071] By comparing the time period dispersion of the observed value of the pressure reduction rate and the time period dispersion of the influence of K influencing factor parameters on the pressure reduction rate of the opinion work order, if there is overlap in the time period dispersion between them and this overlap follows a certain corresponding relationship, if the overlapping range of the time period dispersion of the observed value of the pressure reduction rate and the time period dispersion of a certain influencing factor parameter exceeds the preset limit value, then it is judged that the influencing factor parameter has a decisive role in the observed value of the pressure reduction rate, and at the same time, this decisive influencing factor parameter is matched with the current time period based on a certain corresponding relationship.

[0072] The specific workflow includes:

[0073] Based on the nonlinear correspondence constraint, the jth influencing factor parameter a j and the observed value C of the pressure reduction rate in the vth periodv For corresponding association, the nonlinear corresponding relationship constraints are as follows:

[0074] Minimize the objective function:

[0075] Constraints: 1-θ j ≤C v (Q T δ(a j )+L);

[0076] Among them, K represents the total number of influencing factor parameters, e represents the distance parameter, θ j Represents the distance variable, indicating the jth influencing factor parameter a j and the observed value C of the pressure reduction rate in the vth period v The length of the interval. j )show

[0077] The jth influencing factor parameter a j After mapping and associating to the vth period, the feature vector is obtained, Q represents the mapping association direction vector, and L represents the offset term.

[0078] Further explanation: In order to reduce the boundary effect (i.e., the error or inaccuracy that may occur at the intersection) when analyzing the observed values ​​of the decompression rate in adjacent time periods, different weights are assigned to the corresponding and associated influencing factor parameters in the two adjacent time periods in advance. Therefore, when analyzing the fluctuating outlier decompression rate observed values ​​generated in all time periods, the corresponding and associated influencing factor parameters at the intersection of the range in the adjacent time periods will be allocated according to certain weights, which enables these influencing factor parameters to affect the analysis results of the two time periods at the same time.

[0079] S5: Generate a multi-source integrated evaluation model through the influencing factor parameters and the observed values ​​of the blood pressure reduction rate in the corresponding associated time period to obtain the total observed value of the blood pressure reduction rate in all time periods.

[0080] Set the observed value sequence of the pressure reduction rate in the Dth period to C D For {c Dn , n=1,2,3,...,N}, N represents the number of observed values ​​of the pressure reduction rate, and n represents the nth observed value of the pressure reduction rate.

[0081] Based on the different time periods corresponding to the K influencing factor parameters, a corresponding short-term blood pressure reduction rate observation model is constructed for each influencing factor parameter to ensure that the model can reflect the characteristics of each time period. The K short-term blood pressure reduction rate observation models are reflected in multiple time periods. Collect and organize the blood pressure reduction rate observation numerical sequence in each time period. D , evaluate the weight priority W of each influencing factor parameter in its corresponding short-term pressure reduction rate observation modelD , use historical data to train each short-term pressure reduction rate observation model to ensure that the model can effectively learn the pattern in the data, use the trained model to estimate the pressure reduction rate for each time period, and the short-term pressure reduction rate observation model will sequence the pressure reduction rate observation values ​​in the current period. D Input model, output estimate Combine all the short-term forecast results and use the multi-source integrated evaluation model to derive the total estimated value of the pressure reduction rate

[0082] set up is the total value of the pressure reduction rate observation of the short-term pressure reduction rate observation model in all time periods through the multi-source integrated evaluation model, W D is the weight priority of the influencing factor parameters in the short-term pressure reduction rate observation model affecting the Dth period, then the multi-source integrated evaluation model is

[0083] The embodiment of the present invention also provides an analysis and management system for improving the pressure reduction rate of opinion work orders, using the analysis and management method for improving the pressure reduction rate of opinion work orders, including an element parameter weight analysis module, a pressure reduction rate observation numerical preprocessing module, and a multi-source integrated evaluation module.

[0084] The factor parameter weight analysis module is used to import trend characteristic values ​​into the deep neural network learning model to obtain the weight priority of the influencing factor parameters;

[0085] The depressurization rate observation value preprocessing module is used to match the depressurization rate observation value after interpolation and the K influencing factor parameters with the highest weight priority.

[0086] The multi-source integrated evaluation module is used to generate a multi-source integrated evaluation model through the influencing factor parameters and the observed values ​​of the pressure reduction rate in the corresponding associated time period, and obtain the total observed value of the pressure reduction rate in all time periods.

[0087] The beneficial effect of the present invention is that, compared with the prior art, a certain influencing factor parameter is associated with the observed value of the pressure reduction rate in a certain period of time based on a nonlinear correspondence constraint. Through the nonlinear correspondence, the influencing factor parameter can be more accurately associated with the observed value of the pressure reduction rate, so as to analyze the influence relationship more deeply. Through the influencing factor parameters and the observed values ​​of the pressure reduction rate in the corresponding associated time period, a multi-source integrated evaluation model is generated to obtain the total value of the pressure reduction rate observation for all time periods. The integration of multi-source data can make full use of information from different sources, enhance the model's understanding and prediction ability of the change in the pressure reduction rate, and thus improve the accuracy of the prediction. The integrated model combines the advantages of multiple prediction algorithms to reduce the deviation and error that may be generated by a single model, making the overall prediction more stable. By quantifying the parameters of the influencing factors, the model can clearly identify the specific impact of each factor on the pressure reduction rate, providing strong support for subsequent decision-making.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. An analysis and management method for improving the pressure reduction rate of opinion work orders, characterized in that: The following steps are involved: S1: Collect and obtain the influencing factor parameters associated with the pressure reduction rate of the opinion work order, obtain the measured values ​​to construct the parameter measurement value sequence, analyze the trend characteristic values ​​of the parameter measurement value sequence in combination with the time series analysis model, and import the trend characteristic values ​​into the deep neural network learning model to calculate and obtain the weight priority of the influencing factor parameters; S2: The weight priority values ​​of the d influencing factor parameters obtained based on S1 constitute the weight priority value sequence W, and the K influencing factor parameters with the highest weight priority are selected to provide a parameter basis for the subsequent corresponding relationship. S3: Collect the observed values ​​of the pressure reduction rate of opinion work orders in each period, and pre-process the observed values ​​of the pressure reduction rate of opinion work orders by interpolation; S4: matching the observed value of the pressure reduction rate after interpolation by the interpolation method with the K influencing factor parameters with the highest weight priority; S5: Generate a multi-source integrated evaluation model through the influencing factor parameters and the observed values ​​of the blood pressure reduction rate in the corresponding associated time period to obtain the total observed value of the blood pressure reduction rate in all time periods.

2. According to claim 1, a method for analyzing and managing the pressure reduction rate of opinion work orders is characterized in that: In step S1, the t-th influencing factor parameter A is analyzed, and H measured values ​​of the influencing factor parameter A are obtained based on h different time points, and the measured time-varying parameter sequence is constructed as follows: The s-1th measurement time-varying parameter value and the sth measured time-varying parameter value The time period between s -T s-1 , T s Expressed as and The total time period, T s-1 Expressed as and The total time period between, then after the next interval, the sth parameter measurement value The single cumulative value of for: in, yes A single accumulation of yes Single accumulation of The time series analysis model is: in, express The trend characteristic value of , β and γ are the discrimination coefficients. Then after N intervals, the sth parameter measurement value After N times, the cumulative value is The trend characteristic value of 3. The analysis and management method for improving the pressure reduction rate of opinion work orders according to claim 2 is characterized by: Generate the trend characteristic values ​​corresponding to the H parameter measurement values ​​in the parameter measurement value sequence to construct the trend characteristic value sequence. The trend characteristic value sequence is The trend characteristic value sequence is imported into the deep neural network learning model to obtain the generated derived sequence A'(N); the generated derived sequence A'(N) is imported into the deep neural network learning model again to obtain the secondary generated sequence A"(N).

4. The analysis and management method for improving the pressure reduction rate of opinion work orders according to claim 1 is characterized in that: The operation in S1 obtains the weight priority of the influencing parameters and derives the result including: Arbitrarily select the weight priority W of the tth influencing factor parameter C among the influencing factor parameters i for: in, represents the weight coefficient of the g-th convolutional network layer in the deep neural network learning model, p tg represents the activation function of the g-th convolutional network layer, and the number of convolutional network layers is G; p tg The activation function of the g-th convolutional network layer is: Among them, τ g represents the expansion rate of the g-th convolutional network layer, B g Represents the convolution kernel parameters of the g-th convolutional network layer.

5. The analysis and management method for improving the pressure reduction rate of opinion work orders according to claim 1 is characterized by: By comparing the time period dispersion of the observed value of the pressure reduction rate and the time period dispersion of the influence of K influencing factor parameters on the pressure reduction rate of the opinion work order, if there is overlap in the time period dispersion between them and this overlap follows a certain corresponding relationship, if the overlapping range of the time period dispersion of the observed value of the pressure reduction rate and the time period dispersion of a certain influencing factor parameter exceeds the preset limit value, then it is judged that the influencing factor parameter has a decisive role in the observed value of the pressure reduction rate, and at the same time, this decisive influencing factor parameter is matched with the current time period based on a certain corresponding relationship.

6. The analysis and management method for improving the pressure reduction rate of opinion work orders according to claim 1 is characterized in that: The specific workflow in step S4 includes: Based on the nonlinear correspondence constraint, the jth influencing factor parameter a j and the observed value C of the pressure reduction rate in the vth period v For corresponding association, the nonlinear corresponding relationship constraints are as follows: Minimize the objective function: Constraints: 1-θ j ≤C v (Q T δ(a j )+L); Among them, K represents the total number of influencing factor parameters, e represents the distance parameter, θ j Represents the distance variable, indicating the jth influencing factor parameter a j and the observed value C of the pressure reduction rate in the vth period v The length of the interval. j ) indicates that the jth influencing factor parameter a j After mapping and associating to the vth period, the feature vector is obtained, Q represents the mapping association direction vector, and L represents the offset term.

7. The analysis and management method for improving the pressure reduction rate of opinion work orders according to claim 6 is characterized by: Different weights are assigned in advance to the corresponding associated influencing factor parameters in the two adjacent time periods. When analyzing the fluctuating outlier pressure reduction rate observation values ​​generated in all time periods, the corresponding associated influencing factor parameters at the intersection of the ranges in the adjacent time periods are allocated according to certain weights, which enables these influencing factor parameters to affect the analysis results of the two time periods at the same time.

8. The analysis and management method for improving the pressure reduction rate of opinion work orders according to claim 9 is characterized in that: In step S5, Set the observed value sequence of the pressure reduction rate in the Dth period to C D For {c Dn , n=1,2,3,...,N}, N represents the number of observed values ​​of the blood pressure reduction rate, n represents the nth observed value of the blood pressure reduction rate, and based on the different time periods corresponding to the K influencing factor parameters, a corresponding short-term blood pressure reduction rate observation model is constructed for each influencing factor parameter.

9. The analysis and management method for improving the pressure reduction rate of opinion work orders according to claim 6 is characterized in that: In step S5, set up is the total value of the pressure reduction rate observation of the short-term pressure reduction rate observation model in all time periods through the multi-source integrated evaluation model, W D is the weight priority of the influencing factor parameters in the short-term pressure reduction rate observation model affecting the Dth period, then the multi-source integrated evaluation model is 10. An analysis and management system for improving the pressure reduction rate of opinion work orders, using an analysis and management method for improving the pressure reduction rate of opinion work orders as described in any one of claims 1 to 9, comprising an element parameter weight analysis module, a pressure reduction rate observation numerical preprocessing module, and a multi-source integrated evaluation module. The factor parameter weight analysis module is used to import trend characteristic values ​​into the deep neural network learning model to obtain the weight priority of the influencing factor parameters; The depressurization rate observation value preprocessing module is used to match the depressurization rate observation value after interpolation and the K influencing factor parameters with the highest weight priority. The multi-source integrated evaluation module is used to generate a multi-source integrated evaluation model through the influencing factor parameters and the observed values ​​of the pressure reduction rate in the corresponding associated time period, and obtain the total observed value of the pressure reduction rate in all time periods.

Images