Interaction instruction response efficiency evaluation method and system for multiple service scenes

Abstract

The invention provides an interaction instruction response efficiency evaluation method and system oriented to multiple service scenarios, and the method comprises the steps: building a physical node response topological graph based on receiving equipment information of a service response instruction sent by a power utilization information collection system; obtaining instruction issuing response time historical sample data of each data transmission path based on the obtained physical node response topological graph, and constructing a sample data set based on the obtained instruction issuing response time historical sample data; based on the constructed sample data set, constructing an interaction instruction response efficiency evaluation model oriented to multiple service scenes; obtaining response time and probability values at different moments, different data transmission paths and different services by taking to-be-sent service types, service volume and instruction sending time as input of the interaction instruction response efficiency evaluation model; and based on the obtained response time and the probability value, interaction instruction response efficiency evaluation of the multiple service scenes is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of power systems, and in particular relates to a method and system for evaluating interactive instruction response efficiency for multiple business scenarios. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] With the continuous development of the power system and the acceleration of the intelligent process, the interactive command response efficiency in multiple business scenarios has become an important indicator for measuring the operating efficiency of the power system. The business scenarios involved in the power system are extensive, including but not limited to load scheduling, remote fee control, spot trading, etc. These scenarios all put forward high requirements on the response speed, accuracy and stability of interactive commands. The inventors found that most of the existing evaluation methods use manual or semi-automatic methods, and the accuracy and efficiency of their evaluation results are low. Their evaluation results cannot guide the system side to adjust and optimize the number and order of business interactions, so that the interactive command response efficiency of the current system in multiple business scenarios cannot meet the efficiency requirements for the normal operation of the business. Summary of the invention

[0004] The present invention provides an interactive instruction response efficiency evaluation method and system for multiple business scenarios, so as to solve the problem that the traditional evaluation method has low accuracy and low evaluation efficiency in evaluation results, and is unable to guide the system side to adjust and optimize the number and sequence of business interactions, so that the interactive instruction response efficiency of the system's current multiple business scenarios cannot meet the efficiency requirements for the normal development of the business.

[0005] According to a first aspect of an embodiment of the present invention, a method for evaluating interactive instruction response efficiency for multiple business scenarios is provided, comprising:

[0006] Based on the device information receiving the business response instruction sent by the power consumption information collection system, a physical node response topology diagram is constructed;

[0007] Based on the obtained physical node response topology diagram, historical sample data of instruction issuance response time of each data transmission path is obtained, and based on the obtained historical sample data of instruction issuance response time, a sample data set is constructed;

[0008] Based on the constructed sample data set, an interactive instruction response efficiency evaluation model for multiple business scenarios is constructed; wherein the construction of the interactive instruction response efficiency evaluation model is specifically as follows: based on the sample data set, a Monte Carlo algorithm is used in combination with a non-embedded chaotic polynomial method to obtain a transmission link response time probability box;

[0009] The type of service to be sent, the amount of service and the time of sending the instruction are used as the input of the interactive instruction response efficiency evaluation model to obtain the response time and probability value at different times, different data transmission paths and different services;

[0010] Based on the obtained response time and probability values, the interactive instruction response efficiency evaluation of multiple business scenarios is realized.

[0011] Furthermore, the construction of the interactive instruction response efficiency evaluation model is specifically as follows:

[0012] Based on the sample data set and the physical node response topology, obtain all data transmission paths and quantities;

[0013] The data transmission path is taken as the cognitive uncertainty parameter, and the number of data transmission paths is taken as the number of cognitive uncertainty parameters;

[0014] Constructing a sub-sample set based on sample data of the cognitive uncertain parameter in the sample data set, and performing sampling on the sub-sample set for a first preset number of times to obtain a first sampling result;

[0015] The business instruction issuing category carried by the sample data in the first sampling result is used as a random uncertain parameter, and the random uncertain parameter is sampled a second preset number of times to obtain a second sampling result;

[0016] Based on the second sampling result, construct a non-embedded chaotic polynomial;

[0017] Obtaining a response time evaluation value of a sampling sample in the second sampling result by using a non-embedded chaotic polynomial;

[0018] Building a response time probability curve based on the obtained response time evaluation values ​​of the sampling samples;

[0019] Based on the obtained response time probability curve, the construction of the conduction link response time probability box is realized, and the interactive instruction response efficiency evaluation model is obtained.

[0020] Furthermore, the construction of the non-embedded chaotic polynomial is specifically as follows:

[0021] Determine an orthogonal polynomial basis function according to a distribution type of a random uncertain parameter in a first sampling result;

[0022] Initialize the custom order, substitute the sample data in the second sampling result into the non-embedded chaotic polynomial, and obtain the response time value of the sample;

[0023] Linearly solving the coefficients and truncation coefficients of the non-embedded chaotic polynomial according to the input data and output data of the sampling sample in the second sampling result to obtain an initial non-embedded chaotic polynomial;

[0024] Select samples from the distribution of random uncertain parameters, calculate the difference between the sample estimated response time value and the sample actual response time value, if it is less than the error precision threshold, complete the construction of the non-embedded chaotic polynomial; otherwise, return to update the initialized custom order, and update the process of constructing the non-embedded chaotic polynomial until the difference is less than the error precision threshold.

[0025] Furthermore, the first preset number is determined by using a Latin hypercube sampling method, which is specifically expressed as follows:

[0026] M≥m 3 +2

[0027] Wherein, M is the first preset number of times; m is the number of data transmission paths.

[0028] Furthermore, the business instruction issuing category represents a category formed by different business types and different business volumes contained therein.

[0029] Furthermore, based on the obtained response time and probability value, the interactive instruction response efficiency of multiple business scenarios is evaluated, specifically: based on the response time and probability value obtained at different times, different data transmission paths and different businesses, combined with pre-set thresholds, through threshold comparison, the businesses that do not meet the interactive instruction response efficiency indicators are obtained.

[0030] According to a second aspect of an embodiment of the present invention, a system for evaluating interactive instruction response efficiency for multiple business scenarios is provided, including:

[0031] A topology map construction unit, which is used to construct a physical node response topology map based on the device information receiving the service response instruction sent by the power consumption information collection system;

[0032] A sample data set construction unit, which is used to obtain historical sample data of instruction issuance response time of each data transmission path based on the obtained physical node response topology diagram, and construct a sample data set based on the obtained historical sample data of instruction issuance response time;

[0033] An evaluation model construction unit is used to construct an interactive instruction response efficiency evaluation model for multiple business scenarios based on the constructed sample data set; wherein the construction of the interactive instruction response efficiency evaluation model is specifically: based on the sample data set, a Monte Carlo algorithm is used in combination with a non-embedded chaotic polynomial method to obtain a transmission link response time probability box;

[0034] The efficiency evaluation unit is used to use the service type to be sent, the service volume and the instruction sending time as the input of the interactive instruction response efficiency evaluation model, and obtain the response time and probability values ​​at different times, different data transmission paths and different services; based on the obtained response time and probability values, the interactive instruction response efficiency evaluation of multiple business scenarios is realized.

[0035] According to a third aspect of an embodiment of the present invention, there is provided an electronic device, comprising a memory, a processor, and a computer program stored and running on the memory, wherein when the processor executes the program, the method for evaluating the efficiency of interactive instruction responses for multiple business scenarios is implemented.

[0036] According to a fourth aspect of an embodiment of the present invention, a non-transitory computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method for evaluating the efficiency of interactive instruction responses for multiple business scenarios is implemented.

[0037] According to a fifth aspect of an embodiment of the present invention, there is provided a computer program product, comprising a computer program, characterized in that when the computer program is executed by a processor, the method for evaluating the efficiency of interactive instruction responses for multiple business scenarios is implemented.

[0038] One or more of the above technical solutions have the following beneficial effects:

[0039] The present invention provides a method and system for evaluating the response efficiency of interactive instructions for multiple business scenarios. The scheme obtains the instruction response delay samples of each line by constructing a physical node response topology diagram, and adopts a time response probability box to quantify the execution response delay time and probability of each business instruction, thereby achieving accurate evaluation of the interactive instruction response efficiency and providing data support for optimizing the overall operation efficiency of the power system.

[0040] Aiming at the problem that the power consumption information collection system has many business types, complex data interaction, and a large amount of collected data, resulting in the fact that the response time of some equipment interaction instructions does not meet the efficiency requirements of normal business development, the solution described in the present invention is based on Monte Carlo combined with non-embedded chaotic polynomials to construct a transmission link response time probability box to obtain the response time and probability values ​​of different businesses at different times, different data transmission paths, and different services. The sample size required by this method is only one percent of that of the traditional data fitting method, which greatly improves the calculation efficiency, thereby realizing the rapid evaluation of the response efficiency of the interaction instruction;

[0041] In order to solve the problem that there are differences in the response efficiency of interactive instructions between various services on the system side, the solution described in the present invention adopts a time response probability box to fit the response efficiency of each service interactive instruction. It can not only fit historical data, but also fit the subsequent change trend of the output response efficiency according to the change trend of historical data, and quantify and present it with upper and lower boundary probabilities, thereby providing reliable fitting data for accurate evaluation of response efficiency and avoiding the problem of modeling timeliness over time.

[0042] In order to solve the problem of data collection failure caused by interactive command response delay in multiple business scenarios, the solution described in the present invention can more accurately evaluate the performance bottlenecks and resource requirements of each business module through response efficiency evaluation, thereby achieving optimal resource allocation and load balancing, avoiding resource waste, and improving the overall operation efficiency and stability of the system.

[0043] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0045] Figure 1 It is a flow chart of a method for evaluating interactive instruction response efficiency for multiple business scenarios described in an embodiment of the present invention;

[0046] Figure 2 A flow chart for constructing an interactive instruction response efficiency evaluation model described in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0048] It should be noted that the terms used herein are for describing specific embodiments only and are not intended to be limiting of exemplary embodiments according to the present invention.

[0049] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0050] In one or more embodiments, Figure 1 As shown, this embodiment provides an interactive instruction response efficiency evaluation method for multiple business scenarios, which specifically includes the following processing procedures:

[0051] Step 1: Based on the device information receiving the business response instruction sent by the power consumption information collection system, a physical node response topology diagram is constructed;

[0052] In a specific implementation, the construction of the topology map is specifically as follows:

[0053] Given n remote devices and n locations, assign a location to each device. Define two n×n matrices, namely the traffic matrix (f cd ) n×n and the distance matrix (d Lc,Ld ) n×n Among them, f cd is the traffic between devices c and d, L c and L d are the locations assigned to devices c and d, respectively. Lc,Ld For position L c and L d The distance between them is the physical node response topology constructed according to the above definition.

[0054] Step 2: Based on the obtained physical node response topology diagram, obtain the historical sample data of the instruction response time of each data transmission path, and construct a sample data set based on the obtained historical sample data of the instruction response time;

[0055] In the specific implementation, the data characteristics of the business response instruction samples are analyzed horizontally, vertically and multi-dimensionally, and the historical sample data of the instruction response time of each data transmission path is obtained in combination with the topology map, where:

[0056] Examples of business response instruction types include daily power consumption data upload instructions and remote fee control instructions;

[0057] The horizontal dimension in the vertical dimension refers to the spatial path data of the topological graph passed during the transmission of the sample data, and the vertical dimension refers to the response time data of the sample data at a certain moment; the multi-dimensional dimension refers to different sample data characteristics, including business type and business volume;

[0058] Response time refers to the time it takes from sending a business instruction from the electricity consumption information collection system to receiving data returned from the device.

[0059] Furthermore, the acquired historical sample data of response time is summarized and collated, and a sample data set is constructed after preprocessing, wherein the preprocessing process includes removing abnormal sample data, removing missing sample data, and normalizing the sample data;

[0060] Step 3: Based on the constructed sample data set, construct an interactive instruction response efficiency evaluation model for multiple business scenarios; wherein the construction of the interactive instruction response efficiency evaluation model is specifically as follows: based on the sample data set, a Monte Carlo algorithm combined with a non-embedded chaotic polynomial method is used to obtain a conduction link response time probability box;

[0061] In a specific implementation, the construction of the interactive instruction response efficiency evaluation model is specifically as follows:

[0062] Based on the sample data set and the physical node response topology, obtain all data transmission paths and quantities;

[0063] The data transmission path is taken as the cognitive uncertainty parameter, and the number of data transmission paths is taken as the number of cognitive uncertainty parameters;

[0064] Constructing a sub-sample set based on sample data of the cognitive uncertain parameter in the sample data set, and performing sampling on the sub-sample set for a first preset number of times to obtain a first sampling result;

[0065] The business instruction issuing category carried by the sample data in the first sampling result is used as a random uncertain parameter, and the random uncertain parameter is sampled a second preset number of times to obtain a second sampling result;

[0066] Based on the second sampling result, construct a non-embedded chaotic polynomial;

[0067] Obtaining a response time evaluation value of a sampling sample in the second sampling result by using a non-embedded chaotic polynomial;

[0068] Building a response time probability curve based on the obtained response time evaluation values ​​of the sampling samples;

[0069] Based on the obtained response time probability curve, the construction of the conduction link response time probability box is realized, and the interactive instruction response efficiency evaluation model is obtained.

[0070] The construction of the non-embedded chaotic polynomial is specifically as follows:

[0071] Determine an orthogonal polynomial basis function according to a distribution type of a random uncertain parameter in a first sampling result;

[0072] Initialize the custom order, substitute the sample data in the second sampling result into the non-embedded chaotic polynomial, and obtain the response time value of the sample;

[0073] Linearly solving the coefficients and truncation coefficients of the non-embedded chaotic polynomial according to the input data and output data of the sampling sample in the second sampling result to obtain an initial non-embedded chaotic polynomial;

[0074] Select samples from the distribution of random uncertain parameters, calculate the difference between the sample estimated response time value and the sample actual response time value, if it is less than the error precision threshold, complete the construction of the non-embedded chaotic polynomial; otherwise, return to update the initialized custom order, and update the process of constructing the non-embedded chaotic polynomial until the difference is less than the error precision threshold.

[0075] The first preset number is determined by using the Latin hypercube sampling method, which is specifically expressed as follows:

[0076] M≥m 3 +2

[0077] Wherein, M is the first preset number of times; m is the number of data transmission paths.

[0078] Specifically, based on the constructed sample data set, the Monte Carlo algorithm combined with the non-embedded chaotic polynomial method is used to construct the transmission link response time probability box, and this is used as an interactive instruction response efficiency evaluation model for multiple business scenarios, such as Figure 2 As shown, the specific processing process includes the following:

[0079] Step 301: Based on the sample data in the sample set and in combination with the data transmission path in the topology diagram, the data transmission path is defined as a cognitive uncertainty parameter, and the total number of transmission paths from the system end to each device end is taken as the total number m of cognitive uncertainty parameters;

[0080] Step 302: Based on a certain cognitive uncertainty parameter m i The sample data existing in the sample set forms a sub-sample set, samples the sub-sample set data M times, and calculates the instruction sending time, business type, business volume and response time of the M sampling samples;

[0081] Among them, m i represents the i-th data transmission path, i.e., the i-th cognitive uncertainty parameter, i∈[1,m]; M sampling times are determined by the Latin hypercube sampling method, M≥m 3 +2;

[0082] Step 303: Based on the sample data of the sub-sample set, the service instruction issuing category carried by the sub-sample set is defined as a random uncertain parameter, and a random uncertain parameter is sampled N times, wherein the N sampling data include the maximum response time data and the minimum response time data of the sub-sample set, and the minimum response time data and the maximum response time data are used as the sample response time value interval of the sub-sample set;

[0083] The business instruction issuing category represents different business types and the categories formed by different business volumes. For example, if one business type contains three volumes of business data, the business instruction issuing category is 1*3=3 categories.

[0084] Step 304: Under the condition of a given cognitive uncertainty sample set, determine the orthogonal polynomial basis function according to the distribution type of the random uncertainty parameter Initialize the custom order, substitute the N-times sample data into the non-embedded chaotic polynomial, obtain the response time value of the output N-times sample, and linearly solve the coefficients and truncation coefficients of the non-embedded chaotic polynomial according to the input data and output data of the N samples, so as to initially complete the construction of the non-embedded chaotic polynomial, select samples from the distribution of the random uncertain parameters of the sub-sample set, calculate the difference between the sample estimated response time value and the sample actual response time value, if it is less than the error precision threshold, then the construction of the non-embedded chaotic polynomial is completed; otherwise, return to update the initialized custom order, and update the process of constructing the non-embedded chaotic polynomial until the difference is less than the error precision threshold;

[0085] Among them, the N sampling sample data includes the instruction sending time, business type, and business volume;

[0086] The non-embedded chaotic polynomial uses the chaotic sum of orthogonal polynomials to establish the functional relationship between the output variable and the input variable, which is defined as Y = M (β), where β = [β 1 ,β 2 ,...,β n ] is the sample data. The orthogonal expansion of Y in the basis function space is

[0087]

[0088] in, is the orthogonal polynomial basis function selected based on the probability distribution type of the input data β, α i are the polynomial coefficients.

[0089] Initialize the randomly selected order d and sample size N, introduce truncation error, and based on the finite term fitting formula, the d-order truncated chaotic polynomial expansion of Y with respect to the n-dimensional random input data β is:

[0090]

[0091] Among them, p is the cutoff coefficient, which is used to calculate The number of non-embedded chaotic polynomial terms.

[0092] N samples are used to solve the non-embedded chaotic polynomial coefficients, that is, the chaotic polynomial is converted into a linear equation system.

[0093]

[0094] The right side of the above equation is the calculation result of substituting N sample data into the non-embedded chaotic polynomial. By performing linear calculation on the above equation, the polynomial coefficient α can be obtained. i .

[0095] In order to evaluate the accuracy of the non-embedded chaotic polynomial, the error err[Y] is introduced and defined as follows:

[0096]

[0097] Among them, Y i is the actual output response time of the ith sample of N data, is the ith simulated output response time of the non-embedded chaotic polynomial, i = 1, 2, ..., N, μγ is the mean of the actual output response time of N sample data;

[0098] If the error err[Y] is less than the set error threshold, the coefficient α of the non-embedded chaotic polynomial is solved according to N sample data. i Substitute the order d and random variable dimension n into the truncation coefficient formula to calculate p, and then substitute p, the selected and the solved α i Substitute them into the chaotic polynomial expansion respectively to complete the construction of non-embedded chaotic polynomial. If the error err[Y] is not less than the set error threshold, return to update the initialized custom order, and update the process of constructing non-embedded chaotic polynomial until the difference is less than the error accuracy threshold;

[0099] Step 305: Calculate the response time of N sampled samples in Q business instruction issuing categories by using non-embedded chaotic polynomials, determine whether the N samples of random uncertain parameters have been evaluated, and use Q groups of response time samples (each group has N samples) to construct Q time-varying probability curves respectively, and obtain the evolution law of the time-varying probability of the response time in the Q business instruction issuing categories;

[0100] Among them, Q refers to the total number of business instruction categories;

[0101] Step 306: Determine whether the M samples of the cognitive uncertainty parameters have been evaluated, if not, return to step D2; if yes, determine whether the m cognitive uncertainty parameters have been evaluated, if not, return to step D1; if yes, draw m*Q groups of time response probability boxes (each group has M time response probability curves) on the same graph, and the time response probability box of a certain specific service instruction issuance category of a certain data transmission path is determined between the lower boundary F(x) and the upper boundary F(x) of a group of time response probability curves, so that the instruction sending time, service type, and service volume can be input to obtain the response time and probability value of different services at different times, different data transmission paths, and different times.

[0102] in, Recorded as F(x) and A probability box is defined between them.

[0103] Step 4: Take the service type, service volume and command sending time to be sent as the input of the interactive command response efficiency evaluation model to obtain the response time and probability value at different times, different data transmission paths and different services;

[0104] Step 5: Based on the obtained response time and probability value, the interactive instruction response efficiency of multiple business scenarios is evaluated.

[0105] In the specific implementation, the interactive instruction response efficiency evaluation of multiple business scenarios is realized based on the obtained response time and probability value, specifically: based on the response time and probability value obtained at different times, different data transmission paths and different businesses, combined with the pre-set thresholds, through threshold comparison, the businesses that do not meet the interactive instruction response efficiency indicators are obtained.

[0106] In the specific implementation, based on the obtained interactive command response efficiency evaluation results, early warning is implemented for the business and topology paths that do not meet the business response efficiency indicators, and the system is guided to adjust and optimize the number and sequence of business interactions, thereby improving the response execution efficiency of business command interactions and avoiding non-fault warnings caused by large-scale data collection.

[0107] Taking the full collection of network-wide measurement data in minutes as an example, the interactive command response delay threshold is set as follows:

[0108] The equipment includes: various metering devices for access to the gateway of traditional energy and new energy power stations, settlement and assessment gateways at all levels of the power grid, and user electricity sales gateways. In order to realize real-time and full collection of electric energy data from metering points at all levels, the data density power gateway and special transformer user interaction command response delay threshold is 1 minute, and the low-voltage user interaction command response delay threshold is 15 minutes.

[0109] Taking the user load real-time monitoring service as an example, the interactive command response delay threshold is set as follows:

[0110] The equipment includes: access to enterprise user load management terminals, area energy collaborative service terminals, distributed power generation and energy storage devices, and load energy efficiency interactive equipment. In order to realize real-time collection of user-side load data, the business command response delay threshold is 60s.

[0111] Randomly select two types of service sample data, namely, the minute-level full collection service of the whole network measurement data and the real-time monitoring service of user load carried out in X month of XX year, to verify the effectiveness of the proposed evaluation method. In the comparative evaluation process, the root mean square error (RMSE) is selected as an indicator to measure the evaluation accuracy of the interactive command response efficiency evaluation model for multiple service scenarios, which is defined as follows:

[0112]

[0113] Among them, Y i For the response time estimate, is the actual value of response time.

[0114] The scheme described in this embodiment evaluates the interactive instruction response efficiency based on 100 sets of data and two types of services. In each service scenario, a certain number of interactive instructions are sent respectively, and the service type, service volume, instruction sending time, data transmission path involved, and response time of the overall instructions are recorded. The experimental results of the three methods are shown in Table 1.

[0115] Table 1 Comparison of evaluation accuracy

[0116]

[0117] From the experimental results in Table 1, it can be seen that the evaluation method proposed in this patent can accurately evaluate the response time of interactive instructions in different business scenarios and different transmission paths. Compared with the other two methods, method 1 uses a machine learning algorithm, which has an overfitting problem, so the accuracy is low; method 2 uses a clustering algorithm that is sensitive to the initial value of the data, which may cause different initial centroids to lead to completely different clustering results. Therefore, when processing large-scale data sets, there will be problems such as inflexible classification and inaccurate evaluation. Therefore, the method of this patent effectively improves the accuracy of the response time estimation of business instructions.

[0118] In one or more implementations, a system for evaluating the efficiency of interactive instruction response for multiple business scenarios is provided corresponding to the method provided in the above embodiment, including:

[0119] A topology map construction unit, which is used to construct a physical node response topology map based on the device information receiving the service response instruction sent by the power consumption information collection system;

[0120] A sample data set construction unit, which is used to obtain historical sample data of instruction issuance response time of each data transmission path based on the obtained physical node response topology diagram, and construct a sample data set based on the obtained historical sample data of instruction issuance response time;

[0121] An evaluation model construction unit is used to construct an interactive instruction response efficiency evaluation model for multiple business scenarios based on the constructed sample data set; wherein the construction of the interactive instruction response efficiency evaluation model is specifically: based on the sample data set, a Monte Carlo algorithm is used in combination with a non-embedded chaotic polynomial method to obtain a transmission link response time probability box;

[0122] The efficiency evaluation unit is used to use the service type to be sent, the service volume and the instruction sending time as the input of the interactive instruction response efficiency evaluation model, and obtain the response time and probability values ​​at different times, different data transmission paths and different services; based on the obtained response time and probability values, the interactive instruction response efficiency evaluation of multiple business scenarios is realized.

[0123] In a specific implementation, the construction of the interactive instruction response efficiency evaluation model is specifically as follows:

[0124] Based on the sample data set and the physical node response topology, obtain all data transmission paths and quantities;

[0125] The data transmission path is taken as the cognitive uncertainty parameter, and the number of data transmission paths is taken as the number of cognitive uncertainty parameters;

[0126] Constructing a sub-sample set based on sample data of the cognitive uncertain parameter in the sample data set, and performing sampling on the sub-sample set for a first preset number of times to obtain a first sampling result;

[0127] The business instruction issuing category carried by the sample data in the first sampling result is used as a random uncertain parameter, and the random uncertain parameter is sampled a second preset number of times to obtain a second sampling result;

[0128] Based on the second sampling result, construct a non-embedded chaotic polynomial;

[0129] Obtaining a response time evaluation value of a sampling sample in the second sampling result by using a non-embedded chaotic polynomial;

[0130] Building a response time probability curve based on the obtained response time evaluation values ​​of the sampling samples;

[0131] Based on the obtained response time probability curve, the construction of the conduction link response time probability box is realized, and the interactive instruction response efficiency evaluation model is obtained.

[0132] In a specific implementation, the construction of the non-embedded chaotic polynomial is specifically as follows:

[0133] Determine an orthogonal polynomial basis function according to a distribution type of a random uncertain parameter in a first sampling result;

[0134] Initialize the custom order, substitute the sample data in the second sampling result into the non-embedded chaotic polynomial, and obtain the response time value of the sample;

[0135] Linearly solving the coefficients and truncation coefficients of the non-embedded chaotic polynomial according to the input data and output data of the sampling sample in the second sampling result to obtain an initial non-embedded chaotic polynomial;

[0136] Select samples from the distribution of random uncertain parameters, calculate the difference between the sample estimated response time value and the sample actual response time value, if it is less than the error precision threshold, complete the construction of the non-embedded chaotic polynomial; otherwise, return to update the initialized custom order, and update the process of constructing the non-embedded chaotic polynomial until the difference is less than the error precision threshold.

[0137] In a specific implementation, the first preset number is determined using a Latin hypercube sampling method, which is specifically expressed as follows:

[0138] M≥m 3 +2

[0139] Wherein, M is the first preset number of times; m is the number of data transmission paths.

[0140] In a specific implementation, the business instruction issuing category represents a category formed by different business types and different business volumes contained therein.

[0141] In the specific implementation, the interactive instruction response efficiency evaluation of multiple business scenarios is realized based on the obtained response time and probability value, specifically: based on the response time and probability value obtained at different times, different data transmission paths and different businesses, combined with the pre-set thresholds, through threshold comparison, the businesses that do not meet the interactive instruction response efficiency indicators are obtained.

[0142] In further embodiments, there is also provided:

[0143] An electronic device includes a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method described in Embodiment 1 is performed. For the sake of brevity, no further description is given here.

[0144] It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general-purpose processors, digital signal processors DSP, application-specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0145] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0146] A computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the method described in embodiment 1 is completed.

[0147] The method in the first embodiment can be directly embodied as a hardware processor, or a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0148] A computer program product includes a computer program, wherein the computer program implements the method described in Embodiment 1 when executed by a processor.

[0149] Those skilled in the art will appreciate that the units, i.e., algorithm steps, of the various examples described in the present embodiment can be implemented in electronic hardware or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0150] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for evaluating interactive instruction response efficiency for multiple business scenarios, characterized in that: include: Based on the device information receiving the business response instruction sent by the power consumption information collection system, a physical node response topology diagram is constructed; Based on the obtained physical node response topology diagram, historical sample data of instruction issuance response time of each data transmission path is obtained, and based on the obtained historical sample data of instruction issuance response time, a sample data set is constructed; Based on the constructed sample data set, an interactive instruction response efficiency evaluation model for multiple business scenarios is constructed; wherein the construction of the interactive instruction response efficiency evaluation model is specifically as follows: based on the sample data set, a Monte Carlo algorithm is used in combination with a non-embedded chaotic polynomial method to obtain a transmission link response time probability box; The type of service to be sent, the amount of service and the time of sending the instruction are used as the input of the interactive instruction response efficiency evaluation model to obtain the response time and probability value at different times, different data transmission paths and different services; Based on the obtained response time and probability values, the interactive instruction response efficiency evaluation of multiple business scenarios is realized.

2. The method for evaluating interactive instruction response efficiency for multiple business scenarios according to claim 1, characterized in that: The construction of the interactive instruction response efficiency evaluation model is specifically as follows: Based on the sample data set and the physical node response topology, obtain all data transmission paths and quantities; The data transmission path is taken as the cognitive uncertainty parameter, and the number of data transmission paths is taken as the number of cognitive uncertainty parameters; Constructing a sub-sample set based on sample data of the cognitive uncertain parameter in the sample data set, and performing sampling on the sub-sample set for a first preset number of times to obtain a first sampling result; The business instruction issuing category carried by the sample data in the first sampling result is used as a random uncertain parameter, and the random uncertain parameter is sampled a second preset number of times to obtain a second sampling result; Based on the second sampling result, construct a non-embedded chaotic polynomial; Obtaining a response time evaluation value of a sampling sample in the second sampling result by using a non-embedded chaotic polynomial; Building a response time probability curve based on the obtained response time evaluation values ​​of the sampling samples; Based on the obtained response time probability curve, the construction of the conduction link response time probability box is realized, and the interactive instruction response efficiency evaluation model is obtained.

3. The method for evaluating the efficiency of interactive instruction response in multiple business scenarios according to claim 2, characterized in that: The construction of the non-embedded chaotic polynomial is specifically as follows: Determine an orthogonal polynomial basis function according to a distribution type of a random uncertain parameter in a first sampling result; Initialize the custom order, substitute the sample data in the second sampling result into the non-embedded chaotic polynomial, and obtain the response time value of the sample; Linearly solving the coefficients and truncation coefficients of the non-embedded chaotic polynomial according to the input data and output data of the sampling sample in the second sampling result to obtain an initial non-embedded chaotic polynomial; Select samples from the distribution of random uncertain parameters, calculate the difference between the sample estimated response time value and the sample actual response time value, if it is less than the error precision threshold, complete the construction of the non-embedded chaotic polynomial; otherwise, return to update the initialized custom order, and update the process of constructing the non-embedded chaotic polynomial until the difference is less than the error precision threshold.

4. The method for evaluating interactive instruction response efficiency for multiple business scenarios according to claim 2, characterized in that: The first preset number is determined by using the Latin hypercube sampling method, which is specifically expressed as follows: M≥m 3 +2 Wherein, M is the first preset number of times; m is the number of data transmission paths.

5. The method for evaluating interactive instruction response efficiency for multiple business scenarios according to claim 2, characterized in that: The business instruction issuing category represents a category formed by different business types and different business volumes contained therein.

6. The method for evaluating interactive instruction response efficiency for multiple business scenarios according to claim 1, characterized in that: The interactive instruction response efficiency evaluation of multiple business scenarios is realized based on the obtained response time and probability value, specifically: based on the response time and probability value obtained at different times, different data transmission paths and different businesses, combined with the pre-set thresholds, through threshold comparison, the businesses that do not meet the interactive instruction response efficiency indicators are obtained.

7. An interactive instruction response efficiency evaluation system for multiple business scenarios, characterized in that: include: A topology map construction unit, which is used to construct a physical node response topology map based on the device information receiving the service response instruction sent by the power consumption information collection system; A sample data set construction unit, which is used to obtain historical sample data of instruction issuance response time of each data transmission path based on the obtained physical node response topology diagram, and construct a sample data set based on the obtained historical sample data of instruction issuance response time; An evaluation model construction unit is used to construct an interactive instruction response efficiency evaluation model for multiple business scenarios based on the constructed sample data set; wherein the construction of the interactive instruction response efficiency evaluation model is specifically: based on the sample data set, a Monte Carlo algorithm is used in combination with a non-embedded chaotic polynomial method to obtain a transmission link response time probability box; The efficiency evaluation unit is used to use the service type to be sent, the service volume and the instruction sending time as the input of the interactive instruction response efficiency evaluation model, and obtain the response time and probability values ​​at different times, different data transmission paths and different services; based on the obtained response time and probability values, the interactive instruction response efficiency evaluation of multiple business scenarios is realized.

8. An electronic device comprising a memory, a processor and a computer program stored and running on the memory, characterized in that: When the processor executes the program, it implements an interactive instruction response efficiency evaluation method for multiple business scenarios as described in any one of claims 1-6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, it implements an interactive instruction response efficiency evaluation method for multiple business scenarios as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it implements a method for evaluating the efficiency of interactive instruction responses for multiple business scenarios as described in any one of claims 1 to 6.

Images