Intelligent fusion terminal program upgrading method and system

Abstract

The invention discloses an intelligent fusion terminal program upgrading method and system, and the method comprises the steps: predicting the collection prediction data of a data collection device according to the historical collection data corresponding to a target program, and screening out an alternative time window with stable change according to the change trend of the collection prediction data; and predicting various working condition data of the data acquisition equipment in the alternative time window through various working condition parameter historical data. And in combination with the working condition prediction data and the collection prediction data in the alternative time window, a KNN algorithm is adopted to screen a plurality of sample data, and the collection data in the alternative time window is subjected to weighted calculation, so that the accuracy of the collection data in the alternative time window is improved. According to the method, the stability degree of the collected data in each alternative time window is evaluated, and the alternative time window with the highest stability degree is selected as the time window for upgrading the target program, so that a proper time window upgrading program is quickly and effectively screened out, and the target program is prevented from being upgraded in a time period with relatively large fluctuation of the collected data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of software updating, in particular to a smart converged terminal program upgrading method and system. BACKGROUND

[0002] The smart converged terminal distributes and deploys corresponding collection business APPs according to the end device asset attribution to perform information interaction with the end device, so as to realize data collection and control instruction issuing. Most smart converged terminals support online software downloading through a remote communication channel. However, when upgrading the software, the smart converged terminal needs to suspend normal work to upgrade the program, which makes the smart converged terminal unable to continue normal data collection during the software upgrading process, resulting in data loss.

[0003] The end device may cause system state operation abnormity due to its own condition or external impact during data collection. If the program is upgraded during this time period, the smart converged terminal will be unable to collect relevant data, thereby affecting subsequent abnormality analysis. Therefore, it is particularly important to select a suitable time window to upgrade the program. SUMMARY

[0004] In view of the deficiencies in the prior art, the present application provides a smart converged terminal program upgrading method and system, which can quickly and effectively screen a suitable time window to upgrade the program. The specific technical solutions are as follows: In a first aspect, a smart converged terminal program upgrading method is provided. In a first implementable manner of the first aspect, the method comprises: obtaining historical collection data corresponding to a target program to perform data prediction, and preliminarily screening a time period with stable data variation trend as a candidate time window according to the predicted collection prediction data; predicting work condition prediction data of each work condition parameter of the data collection device in the candidate time window according to historical data of each work condition parameter of the data collection device; determining collection data corresponding to each candidate time window by using KNN algorithm through the work condition prediction data of each work condition parameter in the candidate time window and the collection prediction data in the candidate time window; evaluating the data stability degree in each candidate time window according to the collection data corresponding to each candidate time window, and selecting a candidate time window with the highest stability degree to upgrade the target program.

[0005] In a second implementable manner of the first aspect, the candidate time window is screened according to the data variation trend, comprising: set a sliding window based on the required upgrade duration of the target program, and obtain a plurality of time window data from the collected prediction data obtained from the trend prediction according to the set sliding window; respectively analyze the corresponding time window data, determine the stability indexes of the time windows, and select a time window with stable changes as a candidate time window according to the stability indexes.

[0006] In a third implementation manner of the first aspect, in the second implementation manner of the first aspect, the setting of the sliding window based on the upgrade duration comprises: adopting an autocorrelation coefficient algorithm to calculate autocorrelation coefficients corresponding to the collected prediction data, and adjusting the time step of the sliding window according to the autocorrelation coefficients with the upgrade duration as a constraint.

[0007] In a fourth implementation manner of the first aspect, in the first implementation manner of the first aspect, the working condition parameters comprise a network state, a device state, an environment state of a data collection device, and / or a concurrency of an intelligent fusion terminal.

[0008] In a fifth implementation manner of the first aspect, in the first implementation manner of the first aspect, the KNN algorithm is adopted to predict the collected data of the candidate time window, and the method comprises: respectively extract features of each type of working condition prediction data and collected prediction data in the candidate time window, and obtain data feature vectors corresponding to each candidate time window; extract sample feature vectors corresponding to the same time period of each data sample according to the time period corresponding to the candidate time window; combine the corresponding data feature vectors and sample feature vectors, and respectively calculate the Euclidean distances between each candidate time window and different data samples; select a plurality of data samples according to the Euclidean distances, and fuse collected sample data in the corresponding time period range of all selected data samples to calculate the collected data of the candidate time window.

[0009] In a sixth implementation manner of the first aspect, in the fifth implementation manner of the first aspect, the selecting of the plurality of data samples according to the Euclidean distances comprises: set the number of selected data samples according to the time step of the candidate time window.

[0010] In a seventh implementation manner of the first aspect, in the fifth implementation manner of the first aspect, the calculation of the Euclidean distances between the candidate time window and the data samples comprises: weighting calculate the Euclidean distances between the candidate time window and the data samples according to the working condition parameter features and the collected data features and the corresponding weights.

[0011] In a ninth implementation form of the first aspect, according to the first implementation form of the first aspect, the data prediction is performed by using an ARIMA model. The stability of the collected parameters in the candidate time window is evaluated by using an autocorrelation analysis method and / or an ADF test method.

[0012] In a ninth implementation form of the first aspect, according to the first implementation form of the first aspect, the data prediction is performed by using an ARIMA model.

[0013] In a second aspect, an intelligent fusion terminal program upgrading system is provided, which comprises: A trend prediction module is configured to perform data prediction on historical collected data corresponding to a target program, and preliminarily filter a time period with stable data variation trend as a candidate time window according to the predicted collected data variation trend. A working condition prediction module is configured to predict working condition prediction data of each working condition parameter of the data collection device in the candidate time window according to historical data of each working condition parameter of the data collection device. A data prediction module is configured to determine collected data corresponding to each candidate time window by using a KNN algorithm on the basis of the working condition prediction data of each working condition parameter in the candidate time window and the collected prediction data in the candidate time window. A window decision module is configured to evaluate the stability of data in each candidate time window according to the collected data corresponding to each candidate time window, and select a candidate time window with the highest stability as a time window for upgrading the target program.

[0014] The intelligent fusion terminal program upgrading method and system can perform data prediction on the basis of historical collected data corresponding to a target program to be upgraded, quickly determine a future variation trend of a collection index, preliminarily filter a time period with stable device state as a candidate time window for program upgrading on the basis of the future variation trend of the collection index, accurately predict collected data in each candidate time window by using a KNN algorithm on the basis of working condition prediction data of a collection terminal in the candidate time window and prediction data of the collection index, and finally evaluate the stability of collected data in each candidate time window and select a candidate time window with the highest stability as a time window for upgrading the target program, so that the target program is upgraded in a time period with stable device state, and the target program is not upgraded in a time period with large data fluctuation. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the specific embodiments of the present application, the drawings required to be used in the specific embodiments will be briefly introduced below. In all the drawings, the elements or parts are not necessarily drawn according to the actual proportions.

[0016] Figure 1 A flowchart of a smart fusion terminal program upgrade method provided in an embodiment of the present invention; Figure 2 The system framework of an intelligent fusion terminal program upgrade system provided in an embodiment of the present invention. Detailed Implementation

[0017] The embodiments of the technical solution of the present invention will now be described in detail with reference to the accompanying drawings. These embodiments are merely illustrative of the technical solution of the present invention and are therefore intended to limit the scope of protection of the present invention.

[0018] Example 1 like Figure 1 The flowchart shown illustrates a method for upgrading the application of a smart converged terminal. This method includes: Step 1: Obtain historical data corresponding to the target program for data prediction, and preliminarily select time periods with stable data changes as candidate time windows based on the predicted data change trends. Step 2: Based on the historical data of various operating parameters of the data acquisition equipment, predict the predicted operating data of various operating parameters of the data acquisition equipment within the selected time window; Step 3: Using the predicted operating conditions for each operating condition parameter within the alternative time window, and combining the collected predicted data within the alternative time window, the KNN algorithm is used to determine the collected data corresponding to each alternative time window. Step 4: Evaluate the stability of the data within each alternative time window based on the collected data, and select the alternative time window with the highest stability to upgrade the target program.

[0019] Specifically, firstly, historical data can be retrieved based on the business type of the target program to be upgraded. For example, historical data from electricity meters can be retrieved for electricity metering, and historical data from water meters can be retrieved for water metering. High-precision prediction models, such as LSTM models, require a large amount of data and computing resources, and have a long training time, resulting in low efficiency. Furthermore, the intelligent fusion terminal handles multiple business types, each requiring different types of data to be collected, necessitating significant resources and time to train data predictions adapted to different business types. Therefore, this application can employ traditional statistical models such as ARIMA and SARIMA models, relying solely on the collected historical data to predict the data collected by the data acquisition equipment within a set future timeframe. Data trends can reflect the working status of the data acquisition equipment or its ability to withstand external shocks. Based on the trends in the collected prediction data, stable time periods can be selected as alternative time windows within the timeframe.

[0020] The traditional ARIMA model, the SARIMA model and other traditional statistical models have high calculation efficiency and are easy to explain, and can quickly filter out multiple candidate time windows, but are difficult to integrate external variables, and the accuracy of the predicted data is limited, resulting in large errors in the predicted data in the selected candidate time windows.

[0021] To improve the accuracy of the data in the candidate time window, the historical data of various working condition parameters of the data collection device can be first called to predict the various working condition data of the data collection device in the candidate time window. Then, the KNN algorithm is used to select multiple sample data with high similarity to the candidate time window from the pre-constructed sample library by combining the working condition prediction data and the collected prediction data of the data collection device in the candidate time window, and the collected data in the candidate time window is weighted calculated, so as to integrate multiple external variables to improve the accuracy of the collected data in the candidate time window and provide a basis for selecting a suitable upgrade time window. Finally, the existing data stability evaluation algorithm can be used to evaluate the stability of the collected data corresponding to each candidate time window, and the candidate time window with the highest stability is selected as the time window of the upgrade target program, so as to quickly and effectively filter out a suitable time window upgrade program to avoid upgrading the target program in a time period with large fluctuations in the collected data.

[0022] In this embodiment, the candidate time window can be selected according to the data variation trend, including: A sliding window is set based on the required upgrade duration of the target program, and multiple time window data are intercepted from the collected prediction data obtained from the trend prediction according to the set sliding window; The stability index of each time window is determined by respectively statistically analyzing the corresponding time window data, and the time window with stable variation is selected as the candidate time window according to the stability index.

[0023] Specifically, in step 1, a sliding window can be first set based on the required upgrade duration of the target program, and multiple time window data are intercepted from the collected prediction data sequence obtained by the statistical model according to the set sliding window. Then, the stability index of each time window, such as variance, standard deviation or interquartile range, can be statistically analyzed, and the time window with high stability is selected as the candidate time window according to the stability index. For example, the time window with small variance, standard deviation or interquartile range is selected as the candidate time window. The algorithm of the stability index is simple, and multiple candidate time windows can be quickly filtered out by the stability index, thereby improving the efficiency of filtering the time window of the upgrade target program.

[0024] In this embodiment, the working condition parameters can include the network status, device status, environment status of the data collection device, and / or the concurrency of the intelligent fusion terminal.

[0025] Specifically, in step 2, the working condition parameters include the network status of the data acquisition device, the device status, the environment status, and the concurrency of the intelligent fusion terminal. Among them, the device status includes device temperature, working current, working voltage, etc., which reflect the working status of the data acquisition device. The environment status includes the temperature and humidity of the environment where the data acquisition device is located, which will affect the working of the data acquisition device. The network status and concurrency will affect the data interaction efficiency between the data acquisition device and the intelligent fusion terminal. By fusing the network status, device status, environment status, and concurrency of the intelligent fusion terminal, the acquisition data in the candidate time window is predicted, thereby improving the accuracy of the acquisition data in the candidate time window.

[0026] In this embodiment, the KNN algorithm is used to predict the acquisition data in the candidate time window, which includes: Feature extraction is performed on each type of working condition prediction data and acquisition prediction data in the candidate time window to obtain the data feature vector corresponding to each candidate time window; According to the time period corresponding to the candidate time window, the sample feature vector corresponding to each data sample in the same time period is extracted; The Euclidean distance between each candidate time window and different data samples is calculated by combining the corresponding data feature vector and sample feature vector; According to the Euclidean distance, a plurality of data samples are selected, and the acquisition sample data in the corresponding time period range of all selected data samples is fused to calculate the acquisition data of the candidate time window.

[0027] Specifically, first, the working condition prediction data corresponding to each candidate time window can be extracted from the corresponding working condition prediction data according to the time period corresponding to the candidate time window, and the feature extraction is performed on each type of working condition prediction data and the acquisition prediction data extracted in the candidate time window. The extracted features can include mean, median, variance, standard deviation, etc. Thus, the data feature vector corresponding to each working condition data feature and acquisition data feature of the candidate time window is obtained.

[0028] Then, the sample data in the same time period can be extracted from each data sample according to the time period corresponding to the candidate time window, and the feature extraction is performed on the sample data in the time period to obtain the sample feature vector with the same feature type.

[0029] The sample data can be historical collection data obtained by other intelligent fusion terminals of the same business type, such as historical meter data collected by intelligent fusion terminals covering different residential communities. The sample data can also be historical collection data obtained by the same intelligent fusion terminal in different collection periods, such as historical collection data obtained by the intelligent fusion terminal every day in the past.

[0030] Then, according to the features in the standardized data feature vector and the sample feature vector, the existing multi-dimensional Euclidean distance algorithm can be used to calculate the Euclidean distance between the candidate time window and the sample data. Finally, according to the Euclidean distances between the candidate time window and different sample data, the sample data closest to the candidate time window can be selected, the weights of the sample data corresponding to the Euclidean distances can be set, and the collection sample data in the same time period as the candidate time window can be extracted from each selected sample data for weighted averaging, so as to obtain the collection data corresponding to the candidate time window. In this way, the collection data of the candidate time window can be accurately predicted without training, and the efficiency of the upgrade time window screening is improved. Moreover, it can adapt to different types of collection data prediction, so as to meet the target program update of different business types.

[0031] In this embodiment, optionally, the stability of the collection data in the candidate time window is evaluated, including: The autocorrelation analysis method and / or the ADF test method are used to evaluate the stability of the collection parameters in the candidate time window.

[0032] Specifically, the existing autocorrelation analysis method or ADF test method can be used alone to quickly evaluate the stability of the collection data in the candidate time window, and according to the autocorrelation coefficient or the test statistic and P value obtained by the evaluation, the most suitable candidate time window upgrade program can be selected from all candidate time windows. For example, the candidate time window with the autocorrelation coefficient closest to 1 is selected, or the candidate time window with the smallest test statistic and P value is selected. In order to improve the evaluation accuracy of the stability, the autocorrelation analysis method and the ADF test method can be combined to evaluate the stability of the collection data in the candidate time window, and the evaluation results of the two evaluation methods can be used to select the candidate time window upgrade program.

[0033] Embodiment Two Embodiment Two is substantially the same as Embodiment One, and the main difference is that in this embodiment, the sliding window is set based on the upgrade duration, including: The autocorrelation coefficient algorithm is used to calculate the autocorrelation coefficient corresponding to the collection prediction data, and the time step of the sliding window is adjusted according to the autocorrelation coefficient with the upgrade duration as a constraint.

[0034] Specifically, the time step of the sliding window needs to match the stationarity of the collected prediction data. If the collected prediction data has large fluctuations, a smaller time step needs to be set to quickly respond to data changes, or the collected prediction data needs to be differentiated to make it stationary. If the collected prediction data has small fluctuations, a larger time step can be set to capture longer trends when filtering sample data. Therefore, when setting the time step of the sliding window, the collected prediction data obtained by prediction can first be subjected to ADF test to determine whether the collected prediction data is stable. When the collected prediction data is not stable, the collected prediction data can be differentiated, and the autocorrelation coefficient algorithm is used to calculate the autocorrelation coefficients of the differentiated collected prediction data under different lag orders, and an ACF graph is drawn according to the calculated autocorrelation coefficients. Finally, a plurality of significant lag orders are selected from the ACF graph, and a lag order with a time step longer than the upgrade length is selected as the time step of the sliding window. In this way, the sliding window can be deeply matched with the time variation rule of the collected prediction data, the time-dependent capturing ability of the subsequent KNN algorithm can be improved, and the data prediction accuracy and stability of the candidate time window can be improved.

[0035] Embodiment three Embodiment three is substantially the same as embodiment one, and the main difference is that the plurality of data samples are selected according to the Euclidean distance, including: The number of selected data samples is set according to the time step of the candidate time window.

[0036] Specifically, the number of data samples has a significant impact on the performance of the KNN algorithm, and too small or too large data sample quantity will have a risk of fitting, and will also affect the calculation efficiency. In this embodiment, the number of data samples can be set according to the time step of the candidate time window. When the time step is large, the KNN algorithm is easy to lose local features and rapid change trends, and may appear under-fitting. Therefore, at this time, a smaller number of data samples needs to be set to effectively capture local features and avoid under-fitting. Conversely, when the time step is small, a larger number of data samples can be set to avoid over-fitting caused by noise and short-term fluctuations.

[0037] Embodiment four Embodiment four is substantially the same as embodiment one, and the main difference is that the Euclidean distance between the candidate time window and the data sample is calculated, including: The Euclidean distance between the candidate time window and the data sample is weighted calculated according to the characteristics of each working condition parameter and the characteristics of the collected data and the corresponding weights.

[0038] Specifically, different operating parameters and data acquisition characteristics have different dimensions and varying importance to the data acquired by the data acquisition equipment. Therefore, when calculating the Euclidean distance between the acquired data and the sample data within the candidate time window, different weights can be assigned to each operating parameter and data acquisition characteristic to highlight the more important characteristics and make the distance calculation results more reasonable and accurate. For example, data acquisition characteristics directly reflect the changes in data within the candidate time window, so they can be assigned the highest weight. The equipment status of the data acquisition equipment itself reflects its working state when acquiring data, so it can be assigned a relatively high weight. Environmental parameter characteristics reflect the environmental conditions when the data acquisition equipment acquires data and have a relatively small impact on the acquired data, so they can be assigned a relatively low weight.

[0039] like Figure 2 The system block diagram shown is for the intelligent converged terminal program upgrade system. The upgrade system includes: The trend prediction module is configured to acquire historical data corresponding to the target program for data prediction, and preliminarily select time periods with stable data changes as alternative time windows based on the predicted trend of the acquired data. The operating condition prediction module is configured to predict the operating condition data of the data acquisition equipment within a selected time window based on the historical data of the various operating condition parameters of the data acquisition equipment. The data prediction module is configured to predict the operating conditions within the alternative time window using each operating condition parameter, and then use the KNN algorithm to determine the corresponding collected data for each alternative time window in combination with the collected prediction data within the alternative time window. The window decision module is configured to evaluate the data stability within each alternative time window based on the collected data corresponding to each alternative time window, and select the alternative time window with the highest stability to upgrade the target program.

[0040] Specifically, the upgraded system includes a trend prediction module, a working condition prediction module, a data prediction module, and a window decision module. The trend prediction module retrieves relevant historical data based on the business type of the target program to be upgraded. Using traditional statistical models such as ARIMA and SARIMA, it predicts the data collection data that the data acquisition equipment will collect within a set future time frame. Based on the trend of the collected predicted data, it selects stable time periods as candidate time windows from within this time frame.

[0041] The working condition prediction module can first call the historical data of various working condition parameters of the data acquisition device, and predict the various working condition data of the data acquisition device in the selected time window. The data prediction module can combine the working condition prediction data and the acquisition prediction data of the data acquisition device in the selected time window, use the KNN algorithm to select a plurality of sample data with high similarity to the selected time window from the pre-constructed sample library, and weightedly calculate the acquisition data in the selected time window, so as to integrate various external variables to improve the accuracy of the acquisition data in the selected time window, and provide a basis for selecting a suitable upgrade time window. The window decision module can use an existing data stability evaluation algorithm to evaluate the stability of the acquisition data corresponding to each selected time window, and select the selected time window with the highest stability as the time window of the upgrade target program, so as to quickly and effectively select a suitable time window to upgrade the program.

[0042] The above embodiments are only used to illustrate the technical solutions of the present application, but not to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can still be modified, or some or all of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and they should be covered in the scope of the claims and the specification of the present application.

Claims

1. A method for upgrading a smart converged terminal program, characterized in that, include: Historical data collected for the target program is obtained for data prediction, and time periods with stable data changes are initially selected as candidate time windows based on the predicted data change trends. Based on the historical data of various operating parameters of the data acquisition equipment, predict the operating condition data of various operating parameters of the data acquisition equipment within the alternative time window. The KNN algorithm is used to determine the collected data for each alternative time window by combining the predicted operating conditions for each operating condition parameter within the alternative time window with the collected predicted data within the alternative time window. The stability of the data within each alternative time window is evaluated based on the collected data, and the alternative time window with the highest stability is selected to upgrade the target program.

2. The intelligent converged terminal program upgrade method according to claim 1, characterized in that, Based on data trends, alternative time windows are selected, including: A sliding window is set based on the upgrade time required by the target program, and multiple time window data are extracted from the collected prediction data obtained by trend prediction according to the set sliding window. Statistical analysis was performed on the data of the corresponding time windows to determine the stability index of each time window, and time windows with stable changes were selected as alternative time windows based on the stability index.

3. The intelligent converged terminal program upgrade method according to claim 2, characterized in that, The sliding window is set based on the upgrade duration, including: The autocorrelation coefficient algorithm is used to calculate the autocorrelation coefficient corresponding to the collected prediction data, and the time step of the sliding window is adjusted according to the autocorrelation coefficient, with the upgrade duration as a constraint.

4. The intelligent converged terminal program upgrade method according to claim 1, characterized in that, The operating parameters include the network status, device status, environmental status of the data acquisition equipment, and / or the number of concurrent connections of the intelligent fusion terminal.

5. The intelligent converged terminal program upgrade method according to claim 1, characterized in that, The KNN algorithm is used to predict the collected data for the candidate time window, including: Feature extraction is performed on the prediction data and collected prediction data of various working conditions within the candidate time window to obtain the data feature vector corresponding to each candidate time window; Based on the time periods corresponding to the candidate time windows, extract the sample feature vectors of each data sample in the same time period; By combining the corresponding data feature vectors and sample feature vectors, the Euclidean distance between each candidate time window and different data samples is calculated respectively; Multiple data samples are selected based on the Euclidean distance, and the collected sample data within the corresponding time period range of all selected data samples are merged to calculate the collected data of the alternative time window.

6. The intelligent converged terminal program upgrade method according to claim 5, characterized in that, Multiple data samples are selected based on the Euclidean distance, including: The number of data samples to be selected is set according to the time step of the alternative time window.

7. The intelligent converged terminal program upgrade method according to claim 5, characterized in that, Calculate the Euclidean distance between the alternative time window and the data sample, including: Based on the characteristics of each operating condition parameter and the characteristics of the collected data and their corresponding weights, the Euclidean distance between the candidate time window and the data sample is calculated using a weighted average method.

8. The intelligent converged terminal program upgrade method according to claim 1, characterized in that, Assess the stability of data collected within the alternative time window, including: The stability of the collected parameters within the alternative time window is evaluated using autocorrelation analysis and / or ADF test.

9. The intelligent converged terminal program upgrade method according to claim 1, characterized in that, The ARIMA model is used for data prediction.

10. A smart converged terminal program upgrade system, characterized in that, include: The trend prediction module is configured to acquire historical data corresponding to the target program for data prediction, and preliminarily select time periods with stable data changes as alternative time windows based on the predicted trend of the acquired data. The operating condition prediction module is configured to predict the operating condition data of the data acquisition equipment within a selected time window based on the historical data of the various operating condition parameters of the data acquisition equipment. The data prediction module is configured to predict the operating conditions within the alternative time window using each operating condition parameter, and then use the KNN algorithm to determine the corresponding collected data for each alternative time window in combination with the collected prediction data within the alternative time window. The window decision module is configured to evaluate the data stability within each alternative time window based on the collected data corresponding to each alternative time window, and select the alternative time window with the highest stability to upgrade the target program.

Images