Processing method for performing data intelligent analysis based on time sequence analysis model

Abstract

The invention provides a processing method for performing data intelligent analysis based on a time sequence analysis model, which comprises the following steps of: performing time sequence data analysis and extraction on a task data packet uploaded at a front end based on timestamps to obtain time sequence data under each timestamp in a current task; in order to facilitate data analysis of a current task by a background, AI identification is performed on time sequence data under each timestamp, and time sequence change features in the time sequence data are identified by using a time sequence analysis model constructed by big data training; and recording the time sequence change characteristics of the time sequence data under each timestamp in the current task and generating a data change characteristic table of the current task, so that a user can conveniently check an analysis processing result of the time sequence data of the current task. Compared with manual analysis, the analysis efficiency of the time series data can be greatly improved, online real-time analysis of massive time series data can be adapted, and higher data support capability is provided. The time sequence analysis model has high robustness, randomness and prediction generalization ability.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a processing method for performing intelligent data analysis based on a time series analysis model, and a processing device, electronic device and computer-readable storage medium for performing intelligent data analysis based on a time series analysis model. Background Art

[0002] Time series data, also known as time series data, is a type of data collected at different time points, used to describe the changes of phenomena over time. This type of data reflects the state or degree of change of a thing or phenomenon over time, such as stock prices, temperature changes, website visits, server logs, etc. Its characteristics include timestamps, values, and possible periodicity, trend, and seasonality.

[0003] Time series data can also be subdivided into quarterly data, monthly data, etc., which have the characteristics of periodic changes. A time series database is a database system specifically used to process data with time tags (which change in the order of time, i.e., time serialization). Typical characteristics of time series data include high frequency of generation, heavy dependence on acquisition time, large number of measurement points, and large amount of information.

[0004] Time series data is widely used in various fields. For example, the Internet of Things (IoT) field needs to process a large amount of real-time data; in the industrial Internet, a large amount of sensor data with timestamps will be generated in the production, testing, and operation stages; in the Internet of Vehicles, real-time vehicle network quality monitoring can be achieved through the analysis of vehicle-computer messages; in the power industry, the amount of data generated in each link of generation, transmission, transformation, distribution, and use is huge, which requires a professional time series database to process.

[0005] Time series data analysis plays an important role in various fields, mainly including the following aspects: 1. Predict future trends: Through the analysis of historical data, time series data analysis can predict future market trends, user needs, etc., and provide a basis for corporate decision-making.

[0006] 2. Optimize resource allocation: By analyzing historical data, time series data analysis can help companies optimize resource allocation such as production, inventory, and human resources, reduce costs, and improve efficiency.

[0007] 3. Quality control: Time series data analysis can monitor product quality, detect potential problems in a timely manner, avoid the production of defective products, and improve product quality.

[0008] 4. Risk warning: Through the analysis of risk factors such as financial markets and natural disasters, time series data analysis can provide companies with risk warnings and help avoid potential risks.

[0009] 5. Intelligent decision-making: The combination of time series data analysis and artificial intelligence technology can provide enterprises with intelligent decision-making support and improve decision-making efficiency.

[0010] However, the traditional methods for analyzing and processing time series data are mainly as follows: First, manual analysis is used. Manual analysis requires that the analytical technicians have high data analysis capabilities and entry level, and need to master a high level of data analysis professional capabilities. Therefore, the entry requirements are high and the labor cost is extremely high. In addition, when facing big data analysis, human analysis is limited and cannot improve the efficiency of data analysis of big data. It is only suitable for small-scale data analysis scenarios.

[0011] Second, the traditional machine analysis methods, including autoregression (AR), moving average (MA), autoregression moving average (ARMA), and autoregression integrated moving average (ARIMA), can improve efficiency to a certain extent, but these models rely on the order of events to make predictions, so the analysis capabilities lack breadth and accuracy. Because traditional models can only analyze and predict according to the events / logs generated by time series data, and cannot accurately and randomly find time series data features from time series data, traditional models lack strong generalization, robustness, and stability in predictive analysis of time series data. Summary of the invention

[0012] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions: On the one hand, a processing method for performing intelligent data analysis based on a time series analysis model is provided, the method being implemented by an electronic device, the method comprising: S1, collect and parse the task data packets uploaded by the front end in real time, and extract time series data under several timestamps from the parsed data; S2, traversing the time series data at each time stamp, and importing the time series data into a preset time series analysis model, identifying the time series change features in the time series data through the time series analysis model, and outputting them; S3, binding the time series change feature with the corresponding timestamp to generate a data change feature table corresponding to the task data packet; S4, feeding back the data change characteristic table to the front end in the original path.

[0013] Preferably, the S1, real-time collection and analysis of task data packets uploaded by the front end, and extraction of time series data under several timestamps from the analyzed data, includes: Receive the task data packet uploaded by the front end through the backend server interface; Identify the data format of the task data packet, and parse the task data packet according to the parsing method of the corresponding data format to obtain a plurality of time series data marked with a timestamp; Traverse and identify the timestamps of each of the time series data, and determine whether the timestamps of each of the time series data are qualified based on the digital signature judgment rule pre-configured for the task data packet: If qualified, the time series data under the qualified timestamp is stored in the backend MySQL database in order; Otherwise, the front end is notified to correct the time series data under the unqualified timestamp; after the correction is qualified, it is stored in the backend MySQL database.

[0014] Preferably, the traversing and identifying the timestamps of each of the time series data, and judging whether the timestamps of each of the time series data are qualified based on the digital signature judgment rule preconfigured for the task data packet, comprises: Extracting keywords and judgment logic from the digital signature judgment rule pre-configured for the task data packet, wherein the keywords include timestamp type, version, format, and digital signature identifier; Input the keywords and the judgment logic as prompt words into a preset LLM large language model; The timestamps of each of the time series data are traversed, and the timestamps of each of the time series data are identified and judged whether they are qualified based on the keywords and the judgment logic by the LLM large language model.

[0015] Preferably, the method for constructing the timing analysis model comprises: Collect and parse several historical task data packets to construct a historical time series data set consisting of several historical time series data; Traversing the historical time series data set, finding and removing the historical time series data without timestamps, and sorting the remaining historical time series data according to timestamps to reconstruct the historical time series data set; Perform feature engineering on the historical time series data set to extract time series change features, including: Extracting time features from the timestamps of each of the historical time series data; Utilizing a preset sliding window, extracting data characteristic values ​​including mean, variance, maximum value, minimum value and / or median from each of the historical time series data; Identify and extract trend / seasonal features between each of the time features; Counting each of the time features, the data feature values, and the trend / seasonal features corresponding to each of the time features to form a feature set; Dividing the feature set into a training set and a validation set according to a preset ratio; Inputting the training set into a preset time series analysis model to perform feature learning, and optimizing the time series analysis model according to preset model optimization iteration conditions; Use the verification set to perform performance verification on the timing analysis model: If the verification passes, the timing analysis model is deployed and applied; Otherwise, repeat the above steps.

[0016] Preferably, traversing the historical time series data set to find and remove the historical time series data without a timestamp includes: Traversing the timestamps of each of the historical time series data in the historical time series data set, and identifying the historical time series data in the historical time series data set that does not have the keyword based on the keyword through the LLM large language model; The historical time series data that is traversed and identified and does not have the keyword is removed from the historical time series data set.

[0017] Preferably, the step S3, binding the time series variation feature with the corresponding timestamp to generate a data variation feature table corresponding to the task data packet, comprises: Read the time series variation characteristics under each of the timestamps: the time characteristics, the data characteristic value, and the trend / seasonality characteristics corresponding to each of the time characteristics; According to the time sequence, the time sequence change characteristics under each time stamp are written into the preset data fluctuation statistical table in turn, and the data change characteristic table of this time is generated for the task data packet.

[0018] On the other hand, a processing device for performing intelligent data analysis based on a time series analysis model is provided, wherein the processing device for performing intelligent data analysis based on a time series analysis model is used to implement the processing method for performing intelligent data analysis based on a time series analysis model, and the device comprises: The front end is used to collect and upload task data packets to the data analysis backend in real time; Data analysis backend, including: Data receiving port, used to receive task data packets uploaded by the front end; A parsing module, used for parsing the task data packet and extracting time series data under a plurality of timestamps from the parsed data; A time series feature recognition module, used to traverse the time series data at each time stamp, import the time series data into a preset time series analysis model, identify the time series change features in the time series data through the time series analysis model, and output; A timing fluctuation recording module, used for binding the timing variation characteristics with the corresponding timestamps to generate a data variation characteristic table corresponding to the task data packet; The message center is used to feed back the data change characteristic table to the front end in the original path; MySQL database, used to store data; The front end is communicatively connected with the data analysis back end.

[0019] On the other hand, an electronic device is provided, comprising: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the processing methods for performing intelligent data analysis based on a timing analysis model as described above is implemented.

[0020] On the other hand, a computer-readable storage medium is provided, in which at least one instruction is stored. The at least one instruction is loaded and executed by a processor to implement any one of the above-mentioned processing methods for performing data intelligent analysis based on a timing analysis model.

[0021] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: The present invention parses and extracts the time series data of the task data packet uploaded by the front end based on the timestamp, and obtains the time series data under each timestamp in the current task. In order to facilitate the background to perform data analysis on the current task, AI recognition is performed on the time series data under each timestamp, and the time series analysis model constructed by big data training is used to identify the time series change characteristics (time characteristics, data characteristic values ​​include mean, variance, maximum value, minimum value and / or median, and trend / seasonal characteristics) in the time series data, and the time series change characteristics of the time series data under each timestamp in the current task are recorded and a data change characteristic table of the current task is generated, so that users can view the analysis and processing results of the time series data of the current task. Therefore, it is possible to quickly analyze the change characteristics of the task data based on the time series AI analysis. Compared with manual analysis, the present invention can greatly improve the analysis efficiency of the time series data, and can adapt to the online real-time analysis of massive time series data, providing higher data support capabilities.

[0022] The present invention is based on feature engineering and uses a time series analysis model to perform feature training and learning. The model is trained and learned on the extracted feature set. The model is trained and learned through the feature set of time series changing features instead of learning in sequence. The model obtains feature training and learning of massive training sets, which is convenient for improving the robustness and randomness of the model for feature recognition and improving the generalization ability of the model prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a flow chart of a processing method for performing intelligent data analysis based on a time series analysis model provided by an embodiment of the present invention; Figure 2 It is a data parsing schematic diagram of a task data packet provided by an embodiment of the present invention; Figure 3 It is a schematic diagram of intelligent qualification judgment of timestamp data based on the LLM large language model provided by an embodiment of the present invention; Figure 4 It is a block diagram of a processing device for performing intelligent data analysis based on a time series analysis model provided by an embodiment of the present invention; Figure 5 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0026] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0027] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0028] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are consistent.

[0029] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0030] The embodiment of the present invention provides a processing method for intelligent data analysis based on a time series analysis model, which can be implemented by an electronic device, which can be a terminal or a server. Figure 1 The flowchart of the processing method for performing data intelligent analysis based on the time series analysis model shown in the figure may include the following steps: S1, collect and parse the task data packets uploaded by the front end in real time, and extract time series data under several timestamps from the parsed data; S2, traversing the time series data at each time stamp, and importing the time series data into a preset time series analysis model, identifying the time series change features in the time series data through the time series analysis model, and outputting them; S3, binding the time series change feature with the corresponding timestamp to generate a data change feature table corresponding to the task data packet; S4, feeding back the data change characteristic table to the front end in the original path.

[0031] The task data packet solved by the present invention can be production task data (involving production data output and possible costs, profits, etc.) or industrial sensor data, etc., or it can be other data that changes with time, such as stock data, power generation data (involving future power generation power prediction), etc.

[0032] The present invention uses artificial intelligence technology to perform intelligent analysis of continuous data, uses a deep learning model to learn the continuous change characteristics of time series data, and uses the trained time series analysis model to perform intelligent analysis of continuous data on the task data packet currently uploaded by the front end, so that the model analyzes the change characteristics of each time series data and feeds back to the front end. In this way, manual analysis is replaced and the change characteristics of the corresponding time series data are output for reference by the front-end user. It can quickly show the change rules, change characteristics, etc. of the current continuous data to the front-end user, providing data analysis support for the front end.

[0033] like Figure 2 As shown, preferably, the S1, real-time collection and analysis of task data packets uploaded by the front end, and extraction of time series data under several timestamps from the analyzed data, includes: Receive the task data packet uploaded by the front end through the backend server interface; Identify the data format of the task data packet, and parse the task data packet according to the parsing method of the corresponding data format to obtain a plurality of time series data marked with a timestamp; Traverse and identify the timestamps of each of the time series data, and determine whether the timestamps of each of the time series data are qualified based on the digital signature judgment rule pre-configured for the task data packet: If qualified, the time series data under the qualified timestamp is stored in the backend MySQL database in order; Otherwise, the front end is notified to correct the time series data under the unqualified timestamp; after the correction is qualified, it is stored in the backend MySQL database.

[0034] The task data packet uploaded by the front end, such as the business data packet that needs to be analyzed for a certain task at present (for example, the change analysis of the power output power at the current stage needs to be predicted and analyzed, and the data here can include the power generation operation data at different time periods / points (power generation voltage, current, temperature, wind speed, pitch angle, high-speed characteristic number, wind wheel diameter, rated power, conversion efficiency and power generation coefficient of each unit, etc.)) or other data forms of task data packets, the front end needs to let the back end analyze the data change rules. Therefore, the current task data packet can be uploaded, received by the background service server interface, and the data packet is parsed to obtain the task data (time series data, such as the operation data of the generator set at a certain point, minute or hour) at each time point / segment. The task task data contains time series data in several time periods, and it needs to be parsed to obtain the time series data at different time points. In this aspect, the time stamp method is used to mark the time series data at different time points, time periods, etc., so as to perform encrypted digital transmission and analysis authentication of the time series data.

[0035] The way to add a timestamp is: add a new column to the data record and name it "timestamp"; use the computer system time or the actual time point of the data record to convert each time point / segment into a timestamp format; if the data already contains date and time, you can use the timestamp() function in Python's datetime library to convert the datetime object into a timestamp; if the data only contains the date, you need to convert it to a datetime object first, and then to a timestamp; if the data contains different time formats, you need to unify the time format first, and then convert the timestamp; add the converted timestamp to the corresponding data record. The front end can add it specifically.

[0036] Adding a timestamp to time series data can accurately record the time point when the data is generated, which is convenient for subsequent analysis of the time series characteristics and trend changes of the data, and is also helpful for data synchronization and event sorting. And the time series data can be digitally authenticated by using the timestamp to identify the generation time of specific time series data, which is convenient for the system to prove the integrity of the data, and the time series data can be electronically verified by the background based on the digital signature judgment rules of the timestamp to verify whether the data is complete. The digital signature judgment rules are composed of keywords and judgment logic, where the keywords include timestamp type, version, format and digital signature identifier. The background can pre-configure the digital signature judgment rules required for different tasks, which are used to perform digital signature judgment on the time series data of each task, so as to filter out the time series data with unqualified timestamps or not for this task, and avoid the mixing of time series error data in this task.

[0037] The background traverses each parsed time series data based on the digital signature judgment rule, judges whether the timestamp of each time series data is qualified, and removes the unqualified time series data. The timestamp recording information in the time series data can refer to the above timestamp adding method.

[0038] In order to improve efficiency, the present invention adopts the LLM large language model to assist in completing the above-mentioned digital signature judgment link, thereby replacing the background administrator, improving the screening efficiency of time series data, and realizing intelligent and automated judgment work.

[0039] like Figure 3 As shown, preferably, the traversal identifies the timestamps of each of the time series data, and determines whether the timestamps of each of the time series data are qualified based on the digital signature judgment rule preconfigured for the task data packet, including: Extracting keywords and judgment logic from the digital signature judgment rule pre-configured for the task data packet, wherein the keywords include timestamp type, version, format, and digital signature identifier; Input the keywords and the judgment logic as prompt words into a preset LLM large language model; The timestamps of each of the time series data are traversed, and the timestamps of each of the time series data are identified and judged whether they are qualified based on the keywords and the judgment logic by the LLM large language model.

[0040] By receiving prompt words, the LLM large language model can screen and analyze data to generate relevant content or provide decision support.

[0041] The steps of traversing and screening data matching the prompt word based on the input prompt word of the LLM large language model may include the following steps: 1. Word Segmentation and Embedding ‌Word segmentation‌: LLM first uses a word segmenter to split the input prompt word into several small text blocks (tokens). These tokens can be words, partial words or character sequences.

[0042] ‌Embedding‌: The segmented tokens are mapped to specific token indices and converted into numerical representations of high-dimensional vectors, i.e., embeddings, which capture the semantic relationships and contextual information between words.

[0043] 2. Prediction and screening ‌Prediction‌: After completing word segmentation and embedding, LLM enters the prediction stage, generating grammatically and semantically correct text through multi-layer neural networks and attention mechanisms.

[0044] Filtering: Based on the generated text, LLM will traverse its internal data and filter out the data that is most relevant and consistent with the prompt word as output.

[0045] This process ensures that LLM can accurately understand and respond to the input prompt words, thereby providing the information required by the user. Combined with Figure 4 As shown, the time series feature recognition module on the background can log in to the third-party AI platform through the large language model API interface and request to call the LLM large language model to complete the judgment work of the present invention. The administrator can construct prompt words and input them into the large language model, so that the large language model can judge each time series data according to the keywords and judgment logic of the time series data digital judgment configured by the present invention.

[0046] Third-party LLM large language models, such as Baidu's Wenxinyiyan, etc. Users can decide for themselves.

[0047] The model is used to traverse the timestamps of each time series data, and based on the keywords and the judgment logic, the timestamps of each time series data are identified and judged to be qualified. If qualified, the time series data under the qualified timestamps are sequentially stored in the backend MySQL database; Otherwise, the front end is notified to correct the time series data under the unqualified timestamp; after the correction is qualified, it is stored in the backend MySQL database. During the correction, the backend can generate corresponding correction instructions based on the model recognition results and send them to the front end, so that the front end can re-add the timestamp to the unqualified data. The instruction needs to include the time series of the time series data to be corrected, so as to remind the front end to perform corresponding data processing.

[0048] The following describes the training and construction scheme of the time series analysis model.

[0049] Preferably, the method for constructing the timing analysis model comprises: Collect and parse several historical task data packets to construct a historical time series data set consisting of several historical time series data; Traversing the historical time series data set, finding and removing the historical time series data without timestamps, and sorting the remaining historical time series data according to timestamps to reconstruct the historical time series data set; Perform feature engineering on the historical time series data set to extract time series change features, including: Extracting time features from the timestamps of each of the historical time series data; Utilizing a preset sliding window, extracting data characteristic values ​​including mean, variance, maximum value, minimum value and / or median from each of the historical time series data; Identify and extract trend / seasonal features between each of the time features; Counting each of the time features, the data feature values, and the trend / seasonal features corresponding to each of the time features to form a feature set; Dividing the feature set into a training set and a validation set according to a preset ratio; Inputting the training set into a preset time series analysis model to perform feature learning, and optimizing the time series analysis model according to preset model optimization iteration conditions; Use the verification set to perform performance verification on the timing analysis model: If the verification passes, the timing analysis model is deployed and applied; Otherwise, repeat the above steps.

[0050] 1. Data Collection The historical task data packets can be collected from the background database (MySQL database). Specifically, the data packets of several historical tasks can be collected, wherein the data packets contain several historical time series data (historical generator set operation data, etc.).

[0051] After collecting the historical task data packets, it is necessary to parse and obtain the historical time series data composition under several tasks, divide them according to the task time sequence, and form a historical time series data set (historical time series data under each time sequence task). Here, one task is taken as an example, for example, historical power generation data under different time sequences can be collected, and other power generation cost analysis tasks, etc., can be performed based on the analysis model of the present invention, which will not be repeated here.

[0052] After collecting various historical time series data, you can perform preprocessing, such as: ‌Data Understanding‌: Analyze the nature of the data, including timestamp format, data frequency (such as every second, every minute, etc.), missing values, outliers, etc.

[0053] 2. Data Preprocessing ‌Timestamp processing‌: unify the timestamp format, ensure that all timestamps are in the same time zone, and convert to the appropriate granularity (such as day, hour, minute, etc.) as needed; ‌Missing value processing‌: Based on the characteristics of the data and business needs, choose to fill in missing values ​​(such as mean, median, previous value, etc.) or delete records containing missing values; ‌Outlier detection and processing‌: Use statistical methods or machine learning algorithms to detect outliers and correct or delete them as appropriate; ‌Data normalization / standardization‌: According to the distribution characteristics of the data, select an appropriate normalization or standardization method to eliminate dimensional differences.

[0054] Data timestamp verification, elimination of data with unqualified timestamp marks: traverse the historical time series data set, find and eliminate the historical time series data without timestamps, and sort the remaining historical time series data according to timestamps to reconstruct the historical time series data set. In order to avoid data loss affecting the accuracy of subsequent model recognition, it is necessary to verify the historical time series data set. Here, based on the previous method of traversing and identifying data using the LLM large language model, the model training big data (historical time series data set) is verified and identified, and the historical time series data without timestamps is found and eliminated, so as to quickly clean the training big data and improve the efficiency of model training.

[0055] Preferably, traversing the historical time series data set to find and remove the historical time series data without a timestamp includes: Traversing the timestamps of each of the historical time series data in the historical time series data set, and identifying the historical time series data in the historical time series data set that does not have the keyword based on the keyword through the LLM large language model; The historical time series data that is traversed and identified and does not have the keyword is removed from the historical time series data set.

[0056] The method of using a large language model to traverse and identify historical time series data sets can refer to the application of the previous large model. The model prompt words prepared for traversing and identifying the data in the historical time series data sets required for model training only need to use keywords to identify and clean the data, thereby reducing the difficulty of cleaning the training data here, and the prepared keywords can be determined by the user.

[0057] 3. Feature engineering, extracting time series change features Next, we need to extract time series features from historical time series data. The following time series change features are mainly extracted: 3.1 Extracting time features from the timestamps of each of the historical time series data; ‌Time features‌, such as extracting date, time, week, month, quarter and other time-related information.

[0058] 3.2 Data characteristic values ​​can be calculated in a statistical manner using a preset sliding window to calculate the mean, variance, maximum value, minimum value, median and other statistics within the sliding window, so as to extract the data characteristic values ​​in each of the historical time series data, including the mean, variance, maximum value, minimum value and / or median; that is, the data change characteristic values ​​of the time series data at each timestamp, such as the data characteristic values ​​of the unit power generation operation data in a certain time period.

[0059] The sliding window is used to process linear data such as arrays / strings, and examines or calculates the changes in the data within the window by moving the boundaries. The following are the basic steps and key points for building a sliding window: ‌Define Window‌: Determine the initial size, starting position, and ending condition of the window based on the requirements of the problem.

[0060] The window size can be fixed or dynamically changing.

[0061] Initialize variables: Set the left and right edge pointers of the window (usually initialized to 0 or a specific starting position).

[0062] Initialize variables used to store or calculate results (such as maximum, minimum, sum, frequency, etc.).

[0063] ‌Window moving and updating‌: Traverse the data by moving the left and right boundaries of the window as required by the problem.

[0064] During the window movement, the calculation results or status of the data in the window are updated.

[0065] Pay attention to maintaining the validity and correctness of the data in the window.

[0066] ‌Handling boundary conditions‌: Ensure correct handling logic when the window moves to the boundaries of an array / string.

[0067] Consider the impact of window size, start position, and end condition on boundary processing.

[0068] Output: According to the requirements of the problem, output the results obtained during the window movement process (such as maximum / minimum value, sum, frequency statistics, etc.).

[0069] If desired, the start and end positions of the window can be recorded for subsequent analysis or verification.

[0070] 3.3 Trend features: mainly identify and extract the trend change characteristics between the various time features, and use linear regression, polynomial fitting and other methods to extract the long-term trend and short-term fluctuations of the time series.

[0071] 3.4 Seasonal features: mainly to identify and extract seasonal changes between the various time features. Fourier transform, autocorrelation function and other methods can be used to capture seasonal changes and periodic patterns in time series.

[0072] In addition, it can also provide: ‌Lag feature‌: use historical data as the feature of the current time to capture the autocorrelation and lag effect of the time series; ‌Rate of change feature‌: calculate the first-order difference, second-order difference, etc. of the time series to capture the speed and acceleration of data changes.

[0073] The above-mentioned feature processing methods can be processed by the administrator with reference to corresponding technical means, which will not be described in detail in this embodiment.

[0074] The trend change characteristics between the above time features are mainly to analyze the change rules between the data feature values ​​under each time feature, so as to show the change trend and seasonal change characteristics of the data. The time series change characteristics under each timestamp will be bound to the corresponding timestamp after feature extraction, which is convenient for the next step of feature engineering or feature recording.

[0075] Therefore, finally, each of the time features, the data feature values, and the trend / seasonal features corresponding to each of the time features are counted to form a feature set.

[0076] After extracting features, you can also perform feature selection and dimensionality reduction: ‌Feature Importance Assessment‌: Use algorithms such as random forest and gradient boosting tree to assess the importance of each feature for trend analysis; ‌Correlation analysis‌: Calculate the correlation coefficient between features and remove redundant and highly correlated features; Dimensionality reduction: Use methods such as PCA (principal component analysis) and LDA (linear discriminant analysis) to reduce the high-dimensional feature space to a low-dimensional space, thereby improving the computational efficiency and generalization ability of the model.

[0077] 4. Model Training Dividing the feature set into a training set and a validation set according to a preset ratio; Inputting the training set into a preset time series analysis model to perform feature learning, and optimizing the time series analysis model according to preset model optimization iteration conditions; Use the verification set to perform performance verification on the timing analysis model: If the verification passes, the timing analysis model is deployed and applied; Otherwise, repeat the above steps.

[0078] ‌Model selection‌: According to the characteristics of the data and business needs, select a suitable time series analysis model, such as ARIMA, LSTM, GRU, Prophet, XGBoost, etc.

[0079] ‌Model Training‌: Train the model using the training dataset and adjust the model parameters as needed.

[0080] ‌Cross-validation‌: Use cross-validation (such as K-fold cross-validation, time series-specific rolling window validation) to evaluate the performance of the model. ‌Evaluation indicators‌: Select appropriate evaluation indicators, such as mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), etc. As for traditional model performance verification methods, such as precision, recall, and F1 score (F1 Score): used for classification problems, evaluate the model's prediction accuracy for the positive category, and can also perform model verification, which can be performed by the administrator.

[0081] ‌Model optimization‌: Based on the evaluation results, adjust model parameters, feature selection, data preprocessing and other steps to improve model performance.

[0082] ‌Model deployment‌: Deploy the trained model to a production environment for real-time or batch prediction.

[0083] ‌Performance Monitoring‌: Continuously monitor the performance of the model to promptly detect and address issues such as model drift and data changes.

[0084] Preferably, the step S3, binding the time series variation feature with the corresponding timestamp to generate a data variation feature table corresponding to the task data packet, comprises: Read the time series variation characteristics under each of the timestamps: the time characteristics, the data characteristic value, and the trend / seasonality characteristics corresponding to each of the time characteristics; According to the time sequence, the time sequence change characteristics under each time stamp are written into the preset data fluctuation statistical table in turn, and the data change characteristic table of this time is generated for the task data packet.

[0085] Data fluctuation statistics table, such as using line charts or other change charts, records the data change characteristics at different time points recorded by different timestamps, and imports characteristic data to generate corresponding data fluctuation changes. The production method of this table can be: 1. Determine statistical indicators ‌Select key data‌: clarify the data types and indicators that need to be counted. The data change characteristic values ​​and change trends at each time point / period, etc.

[0086] ‌Set time range‌: Determine the statistical time period, such as day, week, month, etc. It is determined based on the sequence of timestamps.

[0087] 2. Collect data ‌Data source‌: Collect data from database, API or manually. The time series change characteristics at each time stamp counted above.

[0088] 3. Calculate volatility ‌ Fluctuation formula‌: Select a suitable fluctuation calculation formula, such as standard deviation, variance, etc. Here, you only need to import the time series change characteristics under each time stamp.

[0089] ‌Software Tools‌: Use Excel, Python and other tools for calculations.

[0090] 4. Make a statistical table ‌Table header design‌: including columns such as time, data indicators, and fluctuation values. The time series change characteristics under each timestamp under each task occupy a column of the table respectively.

[0091] ‌Data entry‌: Enter the calculated fluctuation values ​​into the table.

[0092] ‌Chart display‌: You can add line charts, bar charts, etc. to intuitively display fluctuations.

[0093] 5. Analysis and interpretation ‌Causes of Fluctuation‌: Analyze the causes and trends of data fluctuations.

[0094] ‌Make suggestions‌: Make corresponding suggestions or measures based on the analysis results.

[0095] Therefore, the present invention can quickly analyze the changing characteristics of task data based on time series AI analysis. Compared with manual analysis, the present invention can greatly improve the analysis efficiency of time series data, and can adapt to the online real-time analysis of massive time series data, providing higher data support capabilities. The present invention is based on feature engineering, using a time series analysis model to perform feature training and learning, allowing the model to train and learn the extracted feature set, allowing the model to train and learn through the feature set of time series change features instead of learning in sequence, so that the model obtains feature training and learning of massive training sets, which is convenient for improving the robustness and randomness of the model for feature recognition, and improving the generalization ability of model prediction.

[0096] Figure 31 is a block diagram of a processing device for performing intelligent data analysis based on a time series analysis model according to an exemplary embodiment. The device is used for performing intelligent data analysis based on a time series analysis model. Figure 3 , the device comprises: The front end is used to collect and upload task data packets to the data analysis backend in real time; Data analysis backend, including: Data receiving port, used to receive task data packets uploaded by the front end; A parsing module, used for parsing the task data packet and extracting time series data under a plurality of timestamps from the parsed data; A time series feature recognition module, used to traverse the time series data at each time stamp, import the time series data into a preset time series analysis model, identify the time series change features in the time series data through the time series analysis model, and output; A timing fluctuation recording module, used for binding the timing variation characteristics with the corresponding timestamps to generate a data variation characteristic table corresponding to the task data packet; The message center is used to feed back the data change characteristic table to the front end in the original path; MySQL database, used to store data; The front end is communicatively connected with the data analysis back end.

[0097] Please refer to the above method steps to understand the interaction between the front-end and the back-end. Please refer to the corresponding descriptions for understanding the various functional service modules on the back-end. I will not repeat them here.

[0098] Figure 5 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 5 As shown, the electronic device 410 may include a first processor 2001 .

[0099] Optionally, the electronic device 410 may further include a memory 2002 and a transceiver 2003 .

[0100] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0101] Combine the following Figure 5 The components of the electronic device 410 are described in detail: The first processor 2001 is the control center of the electronic device 410, and may be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or may be application specific integrated circuits (ASICs), or may be one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0102] Optionally, the first processor 2001 can execute various functions of the electronic device 410 by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002 .

[0103] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 5 CPU0 and CPU1 are shown in FIG.

[0104] In a specific implementation, as an embodiment, the electronic device 410 may also include multiple processors, such as Figure 5 The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0105] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0106] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently and access the first processor 2001 through the interface circuit ( Figure 5 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0107] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0108] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 5 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0109] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently and communicate with the first processor 2001 through the interface circuit ( Figure 5 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0110] It should be noted that Figure 5 The structure of the electronic device 410 shown in the figure does not constitute a limitation on the router, and the actual knowledge structure recognition device may include more or fewer components than those shown in the figure, or combine certain components, or arrange the components differently.

[0111] In addition, the technical effects of the electronic device 410 can refer to the technical effects of the processing method for performing intelligent data analysis based on a timing analysis model described in the above method embodiment, and will not be repeated here.

[0112] It should be understood that the first processor 2001 in the embodiment of the present invention 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), field 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.

[0113] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0114] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0115] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0116] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0117] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0118] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or 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.

[0119] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0120] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0121] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0122] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0123] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0124] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A processing method for intelligent data analysis based on a time series analysis model, characterized in that: The method comprises: S1, collect and parse the task data packets uploaded by the front end in real time, and extract time series data under several timestamps from the parsed data; S2, traversing the time series data at each time stamp, and importing the time series data into a preset time series analysis model, identifying the time series change features in the time series data through the time series analysis model, and outputting them; S3, binding the time series change feature with the corresponding timestamp to generate a data change feature table corresponding to the task data packet; S4, feeding back the data change characteristic table to the front end in the original path.

2. The method for performing intelligent data analysis based on a time series analysis model according to claim 1, characterized in that: S1, real-time collection and analysis of task data packets uploaded by the front end, extracting time series data under several timestamps from the analyzed data, including: Receive the task data packet uploaded by the front end through the backend server interface; Identify the data format of the task data packet, and parse the task data packet according to the parsing method of the corresponding data format to obtain a plurality of time series data marked with a timestamp; Traverse and identify the timestamps of each of the time series data, and determine whether the timestamps of each of the time series data are qualified based on the digital signature judgment rule pre-configured for the task data packet: If qualified, the time series data under the qualified timestamp is stored in the backend MySQL database in order; Otherwise, the front end is notified to correct the time series data under the unqualified timestamp; after the correction is qualified, it is stored in the backend MySQL database.

3. The method for performing intelligent data analysis based on a time series analysis model according to claim 2, characterized in that: The traversing and identifying the timestamps of each of the time series data, and judging whether the timestamps of each of the time series data are qualified based on the digital signature judgment rule pre-configured for the task data packet, includes: Extracting keywords and judgment logic from the digital signature judgment rule pre-configured for the task data packet, wherein the keywords include timestamp type, version, format, and digital signature identifier; Input the keywords and the judgment logic as prompt words into a preset LLM large language model; The timestamps of each of the time series data are traversed, and the timestamps of each of the time series data are identified and judged whether they are qualified based on the keywords and the judgment logic by the LLM large language model.

4. The method for performing intelligent data analysis based on a time series analysis model according to claim 3, characterized in that: The method for constructing the timing analysis model comprises: Collect and parse several historical task data packets to construct a historical time series data set consisting of several historical time series data; Traversing the historical time series data set, finding and removing the historical time series data without timestamps, and sorting the remaining historical time series data according to timestamps to reconstruct the historical time series data set; Perform feature engineering on the historical time series data set to extract time series change features, including: Extracting time features from the timestamps of each of the historical time series data; Utilizing a preset sliding window, extracting data characteristic values ​​including mean, variance, maximum value, minimum value and / or median from each of the historical time series data; Identify and extract trend / seasonal features between each of the time features; Counting each of the time features, the data feature values, and the trend / seasonal features corresponding to each of the time features to form a feature set; Dividing the feature set into a training set and a validation set according to a preset ratio; Inputting the training set into a preset time series analysis model to perform feature learning, and optimizing the time series analysis model according to preset model optimization iteration conditions; Use the verification set to perform performance verification on the timing analysis model: If the verification passes, the timing analysis model is deployed and applied; Otherwise, repeat the above steps.

5. The method for performing intelligent data analysis based on a time series analysis model according to claim 4, characterized in that: The traversing the historical time series data set to find and remove the historical time series data without a timestamp includes: Traversing the timestamps of each of the historical time series data in the historical time series data set, and identifying the historical time series data in the historical time series data set that does not have the keyword based on the keyword through the LLM large language model; The historical time series data that is traversed and identified and does not have the keyword is removed from the historical time series data set.

6. The method for performing intelligent data analysis based on a time series analysis model according to claim 4, characterized in that: The step S3, binding the time series change feature with the corresponding timestamp to generate a data change feature table corresponding to the task data packet, comprises: Read the time series variation characteristics under each of the timestamps: the time characteristics, the data characteristic value, and the trend / seasonality characteristics corresponding to each of the time characteristics; According to the time sequence, the time sequence change characteristics under each time stamp are written into the preset data fluctuation statistical table in turn, and the data change characteristic table of this time is generated for the task data packet.

7. A processing device for performing intelligent data analysis based on a time series analysis model, wherein the processing device for performing intelligent data analysis based on a time series analysis model is used to implement the processing method for performing intelligent data analysis based on a time series analysis model as claimed in any one of claims 1 to 6, characterized in that: The device comprises: The front end is used to collect and upload task data packets to the data analysis backend in real time; Data analysis backend, including: Data receiving port, used to receive task data packets uploaded by the front end; A parsing module, used for parsing the task data packet and extracting time series data under a plurality of timestamps from the parsed data; A time series feature recognition module, used to traverse the time series data at each time stamp, import the time series data into a preset time series analysis model, identify the time series change features in the time series data through the time series analysis model, and output; A timing fluctuation recording module, used for binding the timing variation characteristics with the corresponding timestamps to generate a data variation characteristic table corresponding to the task data packet; The message center is used to feed back the data change characteristic table to the front end in the original path; MySQL database, used to store data; The front end is communicatively connected with the data analysis back end.

8. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 6.

Images