Big data-based 5G industrial terminal equipment quality evaluation method

Abstract

The invention discloses a quality evaluation method for 5G industrial terminal equipment based on big data, and the method comprises the steps: collecting working data and feedback data of the 5G industrial terminal equipment, and carrying out the preprocessing of the working data and the feedback data; obtaining quality data through the working data; the quality data comprises first quality data and second quality data; comprehensively analyzing the feedback data according to a decision threshold to obtain user satisfaction, and constructing a quality evaluation function according to the quality data and the user satisfaction; and constructing a 5G industrial terminal equipment quality evaluation model according to the quality evaluation function, optimizing the 5G industrial terminal equipment quality evaluation model, inputting to-be-evaluated data into the 5G industrial terminal equipment quality evaluation model, and outputting an evaluation result. The method not only can improve the quality evaluation precision of the 5G industrial terminal equipment based on big data, but also has good interpretability, and can be directly applied to a quality evaluation system.

Description

Technical Field

[0001] The present invention relates to the field of evaluation, and in particular to a quality evaluation method for 5G industrial terminal equipment based on big data. Background Art

[0002] With the rapid development and widespread application of 5G technology, 5G industrial terminal equipment, as a key component of intelligent manufacturing, faces significant challenges. Its performance stability and network efficiency directly impact the overall operational efficiency and product quality of production lines. Currently, quality assessments for 5G industrial terminal equipment in the market primarily rely on traditional testing methods, such as regular manual inspections and equipment self-diagnosis reports. While these methods can reflect device status to a certain extent, they suffer from significant shortcomings: Traditional methods primarily rely on the device's built-in self-diagnosis capabilities, ignoring dynamic data in the actual working environment, such as network fluctuations and load changes, resulting in inaccurate and incomplete assessment results; manual inspections and data analysis are cumbersome and time-consuming, making it impossible to achieve real-time monitoring of device status and rapid response; and traditional assessment methods lack intelligent analysis models based on big data and machine learning algorithms, making it difficult to deeply explore the underlying patterns and root causes of problems behind the data.

[0003] Therefore, it is particularly important to develop a method that can comprehensively, real-timely and intelligently evaluate the quality of 5G industrial terminal equipment. Summary of the Invention

[0004] The purpose of this invention is to provide a quality assessment method for 5G industrial terminal equipment based on big data.

[0005] To achieve the above object, the present invention is implemented according to the following technical solutions: The present invention comprises the following steps: Collecting working data and feedback data of 5G industrial terminal equipment, and preprocessing the working data and the feedback data; Quality data is obtained through the working data; the quality data includes first quality data and second quality data; the first quality data represents the network performance index of the working data; the second quality data represents the difference in data processing of the device's working stability reflected by the working data; Performing a comprehensive analysis on the feedback data according to a decision threshold to obtain user satisfaction, and constructing a quality evaluation function according to the quality data and the user satisfaction; A 5G industrial terminal equipment quality assessment model is constructed according to the quality assessment function, the 5G industrial terminal equipment quality assessment model is optimized, the data to be evaluated is input into the 5G industrial terminal equipment quality assessment model, and the evaluation result is output.

[0006] Furthermore, the method for obtaining the first quality data includes: Sort the work data by time, and perform sliding window division on the sorted work data to obtain a time series; The autoregressive integrated moving average model converts non-stationary time series into stationary time series through difference operation, and uses autoregressive and moving average models to capture the dynamic characteristics of time series; The offset of the stationary time series is calculated based on the dynamic characteristics, and the network performance index of the working data is calculated based on the offset: The network performance index of the ath working data is , the time series offset between the sth moment and the s+1th moment is , the heritability coefficient is , the standard deviation is , the control constant is , the upper limit of time is m, and the performance of the a-th network is , network performance and offset The correlation degree is .

[0007] Furthermore, the method for obtaining the second quality data includes: Enter the working data into the control chart and calculate the unilateral chart statistic: The first smoothing coefficient is , the second smoothing coefficient is , the working data statistics of unilateral truncation indentation at time s is , the working data statistics of unilateral truncation indentation at the s-1th moment is , the graphical statistics of unilateral working data at time s is , the graphical statistics of the unilateral working data at the s-1th moment is ; When the second smoothing coefficient is equal to zero, let , calculate the mean and variance of the plot statistics of the controlled state: The mean of the graph statistics of the lower side is , the variance of the unilateral graph statistic is , the third smoothing coefficient is ; Calculate the lower unilateral control limit: The control limit coefficient of the lower unilateral side is , the control limits of the unilateral plot statistic are , calculate the graph statistics of the upper edge: The working data statistics of unilateral truncation indentation at the sth moment are: , the working data statistics of the unilateral truncation indentation at the s-1th moment is , the graphical statistics of the unilateral working data at the sth moment is , the graphical statistics of the unilateral working data at the s-1th moment is ; When the second smoothing coefficient is equal to zero, calculate the mean and variance of the upper unilateral plot statistics: The mean of the upper unilateral graph statistics is , the variance of the unilateral graph statistic is ; Calculate the upper unilateral control limit: The upper unilateral control limit coefficient is , the control limits of the upper unilateral plot statistic are ; when When , the control chart sends out an out-of-control signal, and the working data that sends out-of-control signals at the observation time is regarded as the problem data; Calculate the difference of the problem data: The difference of the data of the ath question is , the modulation coefficient is L, and the ath working data at the sth moment is , the ath working data at the kth moment is , the natural constant is e, and the set of problem data at the time is , the number of problem data at the time is , the ath work data is .

[0008] Furthermore, the method for obtaining user satisfaction by comprehensively analyzing the feedback data according to the decision threshold includes: Feedback data is input into the deep semantic matching module, and a hierarchical autoencoder is used to pre-train the modality deep network. The expression of the semantic matching function is: The semantic matching function is , the number of modes b is , the shared feature matrix is , the regularization parameter of the bth mode is , the b-th modal basis matrix is , the private feature matrix of the b-th mode is , the private deep transformation output feature matrix of the b-th modality is , the shared depth conversion output feature matrix of the b-th modality is , transposed to T; Obtain the modal basis matrix and shared feature matrix according to the semantic matching function, and initialize the private feature matrix; The deep transformation output features of the feedback data are obtained through the forward propagation of the deep neural network, and the modal adjustment is performed according to the semantic matching function to construct a shared feature matrix; Matching the shared feature matrix and the private feature matrix with the standard database to obtain matching data; Decision curve analysis was used to evaluate the risk-benefit of the matching data, and a risk-benefit assessment of 0.391 was used as the decision threshold; Calculate user satisfaction based on the decision threshold: The user satisfaction is , the number of shared features is , the number of private features is p, and the shared weight is , the private weight is , the vth shared eigenvalue is , the decision threshold of the shared feature is , the standard value of the shared feature is , the vth private eigenvalue is , the decision threshold of private features is , the standard value of private characteristics is .

[0009] Furthermore, the method of constructing a quality evaluation function based on the quality data and the user satisfaction includes: The quality evaluation function at the sth moment is: , the network performance weight is , the difference weight is , the satisfaction weight is , the network performance index at the sth moment is , the difference at the sth moment is , the user satisfaction at the sth moment is .

[0010] Furthermore, a method for constructing a 5G industrial terminal equipment quality assessment model based on the quality assessment function includes: The objective function is constructed based on the quality assessment function and loss function. The 5G industrial terminal equipment quality assessment model includes the gradient boosting algorithm, the long short-term memory network algorithm, and the machine learning algorithm. The predicted quality evaluation value of the input data is obtained according to the quality evaluation function. The gradient boosting algorithm improves the residual between the predicted quality evaluation value and the actual quality evaluation by iteratively adding weak prediction models until the residual reaches the minimum value, and then outputs the comparison classification data; The principle of long short-term memory network algorithm is to learn the long-term dependency relationship in the classification data through the gating mechanism, and capture the mutation characteristics in the time series of the classification data. The machine learning algorithm uses the algorithm to monitor the input data according to the mutation characteristics to obtain monitoring data, inputs the monitoring data into the objective function, and adjusts the learning rate of the 5G industrial terminal equipment quality assessment model through the objective function.

[0011] Furthermore, the method for optimizing the 5G industrial terminal equipment quality assessment model includes: Calculate the searcher position: The position of the search sub is , a random number between 0 and 1 is , the upper bound of the population space range is , the lower bound of the population space range is ; Update the position of the searcher, the expression is: The updated search sub-position is , the current number of evaluations is The maximum number of evaluations is , the random function is , the skew factor is , the logarithmic sigmoid transfer function is ; Calculate the threshold: The threshold is , a random number between 0 and 1 is , introducing the inertia weight, the expression is: The inertia weight of the tth iteration is , the maximum value of inertia weight is , the minimum value of inertia weight is , the maximum number of iterations is ; When the optimal individual is not updated ,on the contrary , when the inertia weight is greater than the threshold, a random search sub-position is generated using Levy flight, and the expression is: The random search sub-position of the t-th iteration is , the Levy random vector of dimension d is , the optimal position of the searcher is , the random position of the searcher is ; The combined search sub-position is obtained based on the random search sub-position and the updated search sub-position. The expression is: The updated search subposition of the tth iteration is , the combined search sub-position of the t+1th iteration is ; Update the optimal individual, let , a local escape strategy is used to generate a new search sub-individual, the expression is: The new individual position of the tth iteration is , the position of the optimal individual is , with a mean of ; the standard deviation of a normal distribution with zero is , the average value of the new individual position is ; Update the individual and position, the expression is: The position of the new individual 1 in the t+1th iteration is , the position of the new individual 2 in the t+1th iteration is , a random number from 0 to 1 is , the random position of the new individual in the tth iteration is , the position of auxiliary individual 1 is , the position of auxiliary individual 2 is ; Continue iterating until the maximum number of iterations is reached, otherwise update the search sub.

[0012] In a second aspect, an embodiment of the present application further provides an electronic device, including: A processor; and a memory arranged to store computer executable instructions, which when executed cause the processor to perform the method steps described in the first aspect.

[0013] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple applications, the electronic device executes the method steps described in the first aspect.

[0014] The beneficial effects of the present invention are: The present invention is a quality assessment method for 5G industrial terminal equipment based on big data. Compared with the existing technology, the present invention has the following technical effects: The present invention can improve the accuracy of quality assessment of 5G industrial terminal equipment through preprocessing, obtaining quality data, comprehensive analysis, constructing quality assessment function, model construction and model optimization steps, thereby improving the precision of quality assessment of 5G industrial terminal equipment. Optimizing the quality assessment of 5G industrial terminal equipment can greatly save resources and improve work efficiency. It can realize automatic quality assessment of 5G industrial terminal equipment, and perform multi-data input and comprehensive assessment of the quality assessment of 5G industrial terminal equipment in real time. It is of great significance to the quality assessment of 5G industrial terminal equipment of big data, and can adapt to the quality assessment of 5G industrial terminal equipment of big data with different standards and the quality assessment needs of 5G industrial terminal equipment of different big data, and has a certain universality. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flowchart of the steps of a quality assessment method for 5G industrial terminal equipment based on big data of the present invention; Figure 2 This is a schematic diagram of the structure of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION

[0016] The present invention will be further described below through specific examples. The illustrative examples and descriptions of the present invention are used to explain the present invention but are not intended to limit the present invention.

[0017] The present invention provides a quality assessment method for 5G industrial terminal equipment based on big data, comprising the following steps: like Figure 1 As shown, in this embodiment, the following steps are included: Collecting working data and feedback data of 5G industrial terminal equipment, and preprocessing the working data and the feedback data; In the actual evaluation, XX company's 5G industrial terminal equipment was used as the research object to obtain work data and feedback data in 2022; Working data includes temperature, humidity, pressure, flow, vibration, images, video information, motor speed, current, voltage, equipment wear, fault warning information, production progress, output, qualified rate, and control instruction data; feedback data includes response time, transmission efficiency, failure rate, recovery time, production efficiency, fault warning information, fault diagnosis report, and user evaluation; Quality data is obtained through the working data; the quality data includes first quality data and second quality data; the first quality data represents the network performance index of the working data; the second quality data represents the difference in data processing of the device's working stability reflected by the working data; In the actual evaluation, the first quality data and the second quality data in the second quarter were 0.714 and 0.225 respectively; Performing a comprehensive analysis on the feedback data according to a decision threshold to obtain user satisfaction, and constructing a quality evaluation function according to the quality data and the user satisfaction; In the actual evaluation, the user satisfaction in the second quarter was 0.734; A 5G industrial terminal equipment quality assessment model is constructed according to the quality assessment function, the 5G industrial terminal equipment quality assessment model is optimized, the data to be evaluated is input into the 5G industrial terminal equipment quality assessment model, and the evaluation result is output.

[0018] In this embodiment, the method for obtaining the first quality data includes: Sort the work data by time, and perform sliding window division on the sorted work data to obtain a time series; The autoregressive integrated moving average model converts non-stationary time series into stationary time series through difference operation, and uses autoregressive and moving average models to capture the dynamic characteristics of time series; The offset of the stationary time series is calculated based on the dynamic characteristics, and the network performance index of the working data is calculated based on the offset: The network performance index of the ath working data is , the time series offset between the sth moment and the s+1th moment is , the heritability coefficient is , the standard deviation is , the control constant is , the upper limit of time is m, and the performance of the a-th network is , network performance and offset The correlation degree is .

[0019] In this embodiment, the method for obtaining the second quality data includes: Enter the working data into the control chart and calculate the unilateral chart statistic: The first smoothing coefficient is , the second smoothing coefficient is , the working data statistics of unilateral truncation indentation at time s is , the working data statistics of unilateral truncation indentation at the s-1th moment is , the graphical statistics of unilateral working data at time s is , the graphical statistics of the unilateral working data at the s-1th moment is ; When the second smoothing coefficient is equal to zero, let , calculate the mean and variance of the plot statistics of the controlled state: The mean of the graph statistics of the lower side is , the variance of the unilateral graph statistic is , the third smoothing coefficient is ; Calculate the lower unilateral control limit: The control limit coefficient of the lower unilateral side is , the control limits of the unilateral plot statistic are , calculate the graph statistics of the upper edge: The working data statistics of unilateral truncation indentation at the sth moment are: , the working data statistics of the unilateral truncation indentation at the s-1th moment is , the graphical statistics of the unilateral working data at the sth moment is , the graphical statistics of the unilateral working data at the s-1th moment is ; When the second smoothing coefficient is equal to zero, calculate the mean and variance of the upper unilateral plot statistics: The mean of the upper unilateral graph statistics is , the variance of the unilateral graph statistic is ; Calculate the upper unilateral control limit: The upper unilateral control limit coefficient is , the control limits of the upper unilateral plot statistic are ; when When , the control chart sends out an out-of-control signal, and the working data that sends out-of-control signals at the observation time is regarded as the problem data; Calculate the difference of the problem data: The difference of the data of the ath question is , the modulation coefficient is L, and the ath working data at the sth moment is , the ath working data at the kth moment is , the natural constant is e, and the set of problem data at the time is , the number of problem data at the time is , the ath work data is .

[0020] In this embodiment, the method for obtaining user satisfaction by comprehensively analyzing the feedback data according to the decision threshold includes: Feedback data is input into the deep semantic matching module, and a hierarchical autoencoder is used to pre-train the modality deep network. The expression of the semantic matching function is: The semantic matching function is , the number of modes b is , the shared feature matrix is , the regularization parameter of the bth mode is , the b-th modal basis matrix is , the private feature matrix of the b-th mode is , the private deep transformation output feature matrix of the b-th modality is , the shared depth conversion output feature matrix of the b-th modality is , transposed to T; Obtain the modal basis matrix and shared feature matrix according to the semantic matching function, and initialize the private feature matrix; The deep transformation output features of the feedback data are obtained through the forward propagation of the deep neural network, and the modal adjustment is performed according to the semantic matching function to construct a shared feature matrix; Matching the shared feature matrix and the private feature matrix with the standard database to obtain matching data; Decision curve analysis was used to evaluate the risk-benefit of the matching data, and a risk-benefit assessment of 0.391 was used as the decision threshold; Calculate user satisfaction based on the decision threshold: The user satisfaction is , the number of shared features is , the number of private features is p, and the shared weight is , the private weight is , the vth shared eigenvalue is , the decision threshold of the shared feature is , the standard value of the shared feature is , the vth private eigenvalue is , the decision threshold of private features is , the standard value of private characteristics is .

[0021] In this embodiment, the method for constructing a quality evaluation function based on the quality data and the user satisfaction includes: The quality evaluation function at the sth moment is: , the network performance weight is , the difference weight is , the satisfaction weight is , the network performance index at the sth moment is , the difference at the sth moment is , the user satisfaction at the sth moment is .

[0022] In this embodiment, the method for constructing a 5G industrial terminal equipment quality assessment model according to the quality assessment function includes: The objective function is constructed based on the quality assessment function and loss function. The 5G industrial terminal equipment quality assessment model includes the gradient boosting algorithm, the long short-term memory network algorithm, and the machine learning algorithm. The predicted quality evaluation value of the input data is obtained according to the quality evaluation function. The gradient boosting algorithm improves the residual between the predicted quality evaluation value and the actual quality evaluation by iteratively adding weak prediction models until the residual reaches the minimum value, and then outputs the comparison classification data; The principle of long short-term memory network algorithm is to learn the long-term dependency relationship in the classification data through the gating mechanism, and capture the mutation characteristics in the time series of the classification data. The machine learning algorithm uses the algorithm to monitor the input data according to the mutation characteristics to obtain monitoring data, inputs the monitoring data into the objective function, and adjusts the learning rate of the 5G industrial terminal equipment quality assessment model through the objective function.

[0023] In this embodiment, the method for optimizing the 5G industrial terminal equipment quality assessment model includes: Calculate the searcher position: The position of the search sub is , a random number between 0 and 1 is , the upper bound of the population space range is , the lower bound of the population space range is ; Update the position of the searcher, the expression is: The updated search sub-position is , the current number of evaluations is The maximum number of evaluations is , the random function is , the skew factor is , the logarithmic sigmoid transfer function is ; Calculate the threshold: The threshold is , a random number between 0 and 1 is , introducing the inertia weight, the expression is: The inertia weight of the tth iteration is , the maximum value of inertia weight is , the minimum value of inertia weight is , the maximum number of iterations is ; When the optimal individual is not updated ,on the contrary , when the inertia weight is greater than the threshold, a random search sub-position is generated using Levy flight, and the expression is: The random search sub-position of the t-th iteration is , the Levy random vector of dimension d is , the optimal position of the searcher is , the random position of the searcher is ; The combined search sub-position is obtained based on the random search sub-position and the updated search sub-position. The expression is: The updated search subposition of the tth iteration is , the combined search sub-position of the t+1th iteration is ; Update the optimal individual, let , a local escape strategy is used to generate a new search sub-individual, the expression is: The new individual position of the tth iteration is , the position of the optimal individual is , with a mean of ; the standard deviation of a normal distribution with zero is , the average value of the new individual position is ; Update the individual and position, the expression is: The position of the new individual 1 in the t+1th iteration is , the position of the new individual 2 in the t+1th iteration is , a random number from 0 to 1 is , the random position of the new individual in the tth iteration is , the position of auxiliary individual 1 is , the position of auxiliary individual 2 is ; Continue iterating until the maximum number of iterations is reached, otherwise update the search sub.

[0024] Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 2 At the hardware level, the electronic device includes a processor and, optionally, an internal bus, a network interface, and memory. The memory may include internal memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for its services.

[0025] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 2 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0026] The memory is used to store programs. Specifically, the program may include program code, which includes computer operating instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.

[0027] The processor reads the corresponding computer program from the non-volatile memory into the internal memory and then runs it, forming a quality assessment device for 5G industrial terminal equipment based on big data at the logical level. The processor executes the program stored in the memory and is specifically configured to perform any of the aforementioned quality assessment methods for 5G industrial terminal equipment based on big data.

[0028] The above application Figure 1 The illustrated embodiment discloses a method for quality assessment of 5G industrial terminal equipment based on big data that can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the method described above can be completed by hardware integrated logic circuits or software instructions within the processor. The processor described above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The methods, steps, and logic block diagrams disclosed in the embodiments of this application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly executed by a hardware decoding processor or by a combination of hardware and software modules within the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0029] The electronic device may also perform Figure 1 A quality assessment method for 5G industrial terminal equipment based on big data is proposed and implemented Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0030] An embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by an electronic device including multiple applications, any one of the aforementioned quality assessment methods for 5G industrial terminal equipment based on big data is executed.

[0031] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0032] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0033] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0034] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0035] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0036] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0037] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can be implemented using any method or technology to store information. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change RAM (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0038] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0039] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0040] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A quality assessment method for 5G industrial terminal equipment based on big data, characterized in that: The following steps are involved: Collecting working data and feedback data of 5G industrial terminal equipment, and preprocessing the working data and the feedback data; Obtaining quality data through the working data; the quality data includes first quality data and second quality data; The first quality data represents a network performance index of the working data; the second quality data represents a difference in data processing reflecting the working stability of the device according to the working data; Performing a comprehensive analysis on the feedback data according to a decision threshold to obtain user satisfaction, and constructing a quality evaluation function according to the quality data and the user satisfaction; A 5G industrial terminal equipment quality assessment model is constructed according to the quality assessment function, the 5G industrial terminal equipment quality assessment model is optimized, the data to be evaluated is input into the 5G industrial terminal equipment quality assessment model, and the evaluation result is output.

2. The quality assessment method for 5G industrial terminal equipment based on big data according to claim 1 is characterized in that: The method for obtaining the first quality data includes: Sort the work data by time, and perform sliding window division on the sorted work data to obtain a time series; The autoregressive integrated moving average model converts non-stationary time series into stationary time series through difference operation, and uses autoregressive and moving average models to capture the dynamic characteristics of time series; The offset of the stationary time series is calculated based on the dynamic characteristics, and the network performance index of the working data is calculated based on the offset: The network performance index of the ath working data is , the time series offset between the sth moment and the s+1th moment is , the heritability coefficient is , the standard deviation is , the control constant is , the upper limit of time is m, and the performance of the a-th network is , network performance and offset The correlation degree is .

3. The quality assessment method for 5G industrial terminal equipment based on big data according to claim 1 is characterized in that: The method for obtaining the second quality data includes: Enter the working data into the control chart and calculate the unilateral chart statistic: The first smoothing coefficient is , the second smoothing coefficient is , the working data statistics of unilateral truncation indentation at time s is , the working data statistics of unilateral truncation indentation at the s-1th moment is , the graphical statistics of unilateral working data at time s is , the graphical statistics of the unilateral working data at the s-1th moment is ; When the second smoothing coefficient is equal to zero, let , calculate the mean and variance of the plot statistics of the controlled state: The mean of the graph statistics of the lower unilateral side is , the variance of the unilateral graph statistic is , the third smoothing coefficient is ; Calculate the lower unilateral control limit: The control limit coefficient of the lower unilateral side is , the control limits of the unilateral plot statistic are , calculate the graph statistics of the upper edge: The working data statistics of unilateral truncation indentation at the sth moment are: , the working data statistics of the unilateral truncation indentation at the s-1th moment is , the graphical statistics of the unilateral working data at the sth moment is , the graphical statistics of the unilateral working data at the s-1th moment is ; When the second smoothing coefficient is equal to zero, calculate the mean and variance of the upper unilateral plot statistics: The mean of the upper unilateral graph statistics is , the variance of the unilateral graph statistic is ; Calculate the upper unilateral control limit: The upper unilateral control limit coefficient is , the control limits of the upper unilateral plot statistic are ; when When , the control chart sends out an out-of-control signal, and the working data that sends out-of-control signals at the observation time is regarded as the problem data; Calculate the difference of the problem data: The difference of the data of the ath question is , the modulation coefficient is L, and the ath working data at the sth moment is , the ath working data at the kth moment is , the natural constant is e, and the set of problem data at the time is , the number of problem data at the time is , the ath work data is .

4. The quality assessment method for 5G industrial terminal equipment based on big data according to claim 1 is characterized in that: The method for obtaining user satisfaction by comprehensively analyzing the feedback data according to a decision threshold includes: Feedback data is input into the deep semantic matching module, and a hierarchical autoencoder is used to pre-train the modality deep network. The expression of the semantic matching function is: The semantic matching function is , the number of modes b is , the shared feature matrix is , the regularization parameter of the bth mode is , the b-th modal basis matrix is , the private feature matrix of the b-th mode is , the private deep transformation output feature matrix of the b-th modality is , the shared depth conversion output feature matrix of the b-th modality is , transposed to T; Obtain the modal basis matrix and shared feature matrix according to the semantic matching function, and initialize the private feature matrix; The deep transformation output features of the feedback data are obtained through the forward propagation of the deep neural network, and the modal adjustment is performed according to the semantic matching function to construct a shared feature matrix; Matching the shared feature matrix and the private feature matrix with the standard database to obtain matching data; Decision curve analysis was used to evaluate the risk-benefit of the matching data, and a risk-benefit assessment of 0.391 was used as the decision threshold; Calculate user satisfaction based on the decision threshold: The user satisfaction is , the number of shared features is , the number of private features is p, and the shared weight is , the private weight is , the vth shared eigenvalue is , the decision threshold of the shared feature is , the standard value of the shared feature is , the vth private eigenvalue is , the decision threshold of private features is , the standard value of private characteristics is .

5. The quality assessment method of 5G industrial terminal equipment based on big data according to claim 1 is characterized in that: The method for constructing a quality evaluation function according to the quality data and the user satisfaction comprises: The quality evaluation function at the sth moment is: , the network performance weight is , the difference weight is , the satisfaction weight is , the network performance index at the sth moment is , the difference at the sth moment is , the user satisfaction at the sth moment is .

6. The quality assessment method for 5G industrial terminal equipment based on big data according to claim 1 is characterized in that: The method for constructing a 5G industrial terminal equipment quality assessment model according to the quality assessment function includes: The objective function is constructed based on the quality assessment function and loss function. The 5G industrial terminal equipment quality assessment model includes the gradient boosting algorithm, the long short-term memory network algorithm, and the machine learning algorithm. The predicted quality evaluation value of the input data is obtained according to the quality evaluation function. The gradient boosting algorithm improves the residual between the predicted quality evaluation value and the actual quality evaluation by iteratively adding weak prediction models until the residual reaches the minimum value, and then outputs the comparison classification data; The principle of long short-term memory network algorithm is to learn the long-term dependency relationship in the classification data through the gating mechanism, and capture the mutation characteristics in the time series of the classification data. The machine learning algorithm uses the algorithm to monitor the input data according to the mutation characteristics to obtain monitoring data, inputs the monitoring data into the objective function, and adjusts the learning rate of the 5G industrial terminal equipment quality assessment model through the objective function.

7. The quality assessment method for 5G industrial terminal equipment based on big data according to claim 1 is characterized in that: The method for optimizing the 5G industrial terminal equipment quality assessment model includes: Calculate the searcher position: The position of the search sub is , a random number between 0 and 1 is , the upper bound of the population space range is , the lower bound of the population space range is ; Update the position of the searcher, the expression is: The updated search sub-position is , the current number of evaluations is The maximum number of evaluations is , the random function is , the skew factor is , the logarithmic sigmoid transfer function is ; Calculate the threshold: The threshold is , a random number between 0 and 1 is , introducing the inertia weight, the expression is: The inertia weight of the tth iteration is , the maximum value of inertia weight is , the minimum value of inertia weight is , the maximum number of iterations is ; When the optimal individual is not updated ,on the contrary , when the inertia weight is greater than the threshold, a random search sub-position is generated using Levy flight, and the expression is: The random search sub-position of the t-th iteration is , the Levy random vector of dimension d is , the optimal position of the searcher is , the random position of the searcher is ; The combined search sub-position is obtained based on the random search sub-position and the updated search sub-position. The expression is: The updated search subposition of the tth iteration is , the combined search sub-position of the t+1th iteration is ; Update the optimal individual, let , a local escape strategy is used to generate a new search sub-individual, the expression is: The new individual position of the tth iteration is , the position of the optimal individual is , with a mean of ; the standard deviation of a normal distribution with zero is , the average value of the new individual position is ; Update the individual and position, the expression is: The position of the new individual 1 in the t+1th iteration is , the position of the new individual 2 in the t+1th iteration is , a random number from 0 to 1 is , the random position of the new individual in the tth iteration is , the position of auxiliary individual 1 is , the position of auxiliary individual 2 is ; Continue iterating until the maximum number of iterations is reached, otherwise update the search sub.

8. An electronic device comprising: processor; as well as A memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform the method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to execute the method according to any one of claims 1 to 6.

Images