Mine end data acquisition and analysis method

Abstract

The invention discloses a mine end data acquisition and analysis method, which comprises the following steps: S1, acquiring original data of a mine end, and distinguishing the original data according to categories; s2, storing the original data in different tables according to a set time slice and categories to obtain a plurality of data tables; s3, automatically generating a query statistical interface according to the structure of the data table; s4, associating the data between the data tables; s5, predicting the key data by using the prediction model; and S6, analyzing each data table by using a large language model to obtain an extended data table. The method shows remarkable technical advantages in the aspects of data storage and query efficiency, data association analysis capability, prediction precision, data mining and demand analysis intelligence, user experience and the like. The advantages not only solve the problems in the prior art, but also bring higher working efficiency, more accurate decision support and better user experience to enterprises.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a mine-side data collection and analysis method. Background Art

[0002] In the mining industry, with the rapid development of science and technology, especially the widespread application of information and intelligent technologies, the importance of mine data collection and analysis has become increasingly prominent. Key links such as mine production efficiency, resource utilization, safety management and operation optimization are highly dependent on accurate and timely data support. However, traditional data collection and analysis methods have many shortcomings, such as single data storage method, low query efficiency, limited data correlation analysis capabilities, low prediction accuracy, and data analysis capabilities lagging behind actual needs. These problems have seriously restricted the intelligent transformation and high-quality development of mining companies. Summary of the invention

[0003] In order to solve the problems existing in the prior art, the present invention provides a mine-side data collection and analysis method.

[0004] The technical solution adopted by the present invention to solve its technical problems is: a mine-end data collection and analysis method, including: S1, collecting original data from the mine end, and distinguishing the original data by category; S2, storing the original data in tables according to categories according to set time slices, and obtaining multiple data tables; S3, automatically generating a query statistics interface according to the structure of the data table; S4, associating the data between the data tables; S5, using a prediction model to predict key data; S6, using a large language model to analyze each of the data tables to obtain an extended data table and automatically generate a data display page.

[0005] Furthermore, the categories of the original data include: alarm data, fault data, power failure data, adjustment data, and early warning data.

[0006] Furthermore, the time slices include: days, hours, and minutes.

[0007] Furthermore, step S3 specifically includes:

[0008] The structure of the data table includes: field type, field name, and field association relationship;

[0009] Determine the field that needs to be screened according to the field type;

[0010] Generate query statements through ORM;

[0011] The relevant data output according to the query statement is automatically displayed in the interface.

[0012] Furthermore, step S4 specifically includes:

[0013] Mix the data in all data tables and sort them in timestamp order;

[0014] Label each piece of data;

[0015] Combine the data within a time period into a data group;

[0016] The Apriori algorithm is used to calculate the correlation between data in a data group;

[0017] Filter out highly correlated data for centralized display.

[0018] Furthermore, step S5 specifically includes:

[0019] Nearly two years of historical data from the mine side is used as training data for the prediction model;

[0020] The data of the first 18 months of the historical data are used as input data, and the data of the last 6 months are used as output data of the prediction model;

[0021] Use the trained prediction model to predict data for the next 6 to 12 months;

[0022] The forecast data is displayed centrally.

[0023] Furthermore, step S6 specifically includes:

[0024] Utilize a large language model to analyze the meaning of the data represented by each of the data tables;

[0025] The large language model expands the requirements according to its own understanding and generates an extended data table;

[0026] Automatically generate a display page based on the extended data table.

[0027] Furthermore, the prediction model is a time series analysis model, a regression analysis model, or a neural network model.

[0028] The beneficial effect of the present invention is that the present invention has significant technical advantages in data storage and query efficiency, data association analysis capability, prediction accuracy, intelligent data mining and demand analysis, and user experience. These advantages not only solve the problems existing in the prior art, but also bring higher work efficiency, more accurate decision support and better user experience to enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0030] Figure 1 It is a flow chart of automatic table storage of original data of the present invention.

[0031] Figure 2 It is a flow chart of the automatic generation of query statistics interface of the present invention.

[0032] Figure 3 It is a flow chart of data association of the present invention.

[0033] Figure 4 It is a flow chart of data prediction of the present invention.

[0034] Figure 5 It is a flowchart of the large language model parsing expansion of the present invention. DETAILED DESCRIPTION

[0035] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0036] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0037] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0038] like Figures 1 to 5As shown, the mine-side data collection and analysis method of the present invention includes: S1, collecting raw data from the mine side, and distinguishing the raw data by category. S2, storing the raw data in tables according to categories according to set time slices, and obtaining multiple data tables. S3, automatically generating a query statistics interface according to the structure of the data table. S4, associating data between data tables. S5, predicting key data using a prediction model. S6, using a large language model to analyze each data table to obtain an extended data table and automatically generate a data display page.

[0039] The categories of raw data include: alarm data, fault data, power outage data, adjustment data, early warning data, etc. These categories of data are collected in real time.

[0040] Data partitioning storage: The original data can be automatically partitioned and stored according to time slices to achieve efficient data management and access. During the implementation process, first, the data generated from various links of the mine end is received, and the data is stored in different data tables according to the preset time slices. Each data table corresponds to a time slice, such as days, hours or minutes. The data table can be named using time slices or other meaningful names for easy indexing and identification. By automatically partitioning data, reasonable data storage can be achieved, reducing the space occupied by data storage, and improving the efficiency of data query and processing.

[0041] Automatically generate query statistics interface: The structure of the data table includes field type, field name, and field association. According to the field type, the field to be filtered is determined, and a query statement is generated through ORM. The relevant data output according to the query statement is automatically displayed in the interface. The query statement generated by ORM is Select-From-Where-OrderBy, where Select represents the field to be displayed, From represents the data table, Where represents the field to be queried, and OrderBy represents the field to be sorted. This step can automatically generate a query statistics interface according to the structure of the data table, simplify the user's operation process, and improve query efficiency. Users do not need to manually create a query interface. The system will automatically generate a corresponding query interface according to the fields and relationships of the data table, which is convenient for users to retrieve and analyze data. During the implementation process, this step will automatically analyze the structure of the data table, including field name, field type, association, etc. Based on these analysis results, the system will automatically generate a query statistics interface to display the fields and data in the data table. The query statistics interface can provide a variety of query and statistical functions, such as query by time period, filter by field, sort and aggregate, etc. Users can quickly obtain the required data information through interactive operations on the interface without writing complex query statements or programs.

[0042] Data association: Mix the data in all data tables and sort them in timestamp order; label each piece of data; combine the data within a time period into a data group; use the Apriori algorithm to calculate the correlation between the data in the data group; filter out the data with high correlation for centralized display. Tags include: alarm, fault, power outage, adjustment, warning, etc. The correlation relationship refers to whether there is a correlation between the changes of two data. For example, there is a correlation between fault data and alarm data. After a certain device fails, the fault data will trigger an alarm when it reaches a certain level. This step aims to find the correlation between data to facilitate better data analysis. During the implementation process, this step will comprehensively consider the timestamps and associated fields in all data tables, calculate the correlation between each data through the Apriori algorithm, and evaluate the correlation and similarity between data. Through correlation analysis, the laws and trends hidden behind the data can be discovered, providing users with more comprehensive and accurate data insights.

[0043] Data prediction: The historical data of the mine end in the past two years is used as the training data of the prediction model; the data of the first 18 months of the historical data is used as the input data, and the data of the last 6 months is used as the output data of the prediction model; the trained prediction model is used to predict the data of the next 6 to 12 months; the predicted data is displayed in a centralized manner. For example, the historical data is the original data from 2022.1 to 2023.12. The data from 2022.1 to 2023.6 is used as the input data of the prediction model, and the data from 2023.7 to 2023.12 is used as the output of the prediction model to train the prediction model. The trained prediction model can predict future data changes. The currently collected data is input into the prediction model, and the prediction model can output the data of the next 6 to 12 months. The prediction model can infer the development trend of future data and give corresponding prediction results. During the implementation process, this step will select a suitable prediction algorithm for data prediction based on historical data and time series analysis methods. The prediction model is a time series analysis model, a regression analysis model, a neural network model, etc. By learning and modeling historical data, the prediction model can predict the value range and change trend of future key data. The prediction results can be presented to users in the form of charts, reports or other forms to help users make accurate predictions and decisions. Which data is key data can be set according to the actual scenario.

[0044] Large language model analysis: Use the large language model to parse the meaning of the data represented by each data table. The large language model expands the needs based on its own understanding, generates an extended data table, and automatically generates a data display page based on the extended data table. The large language model refers to a deep learning model trained with a large amount of text data, which can generate natural language text or understand the meaning of language text. During the implementation process, the large language model can parse and infer the meaning represented by each data table, and analyze the fields and data in the data table to parse the specific meaning and business scenarios represented by the data table. By automatically mining needs and parsing the meaning of data tables, users can be provided with more accurate and practical data analysis and decision support. For example, by understanding the data meaning of the sensor calibration record table, the calibration cycle is automatically analyzed, and a sensor calibration reminder is issued in the system before the next calibration date.

[0045] The mine-side data collection and analysis method of the present invention has the following advantages:

[0046] (1) Data storage and query efficiency significantly improved

[0047] The present invention adopts the automatic table storage technology of slice time, and automatically divides the data into different data tables according to the preset time slice setting. This storage method not only reduces the occupation of data storage space, but also greatly improves the query and processing efficiency of data. Compared with the traditional single data table storage method, the present invention makes data query faster and more accurate, supports users to retrieve data within a specific time period on demand, and greatly improves work efficiency and user experience.

[0048] (2) Enhanced data correlation analysis capabilities

[0049] The present invention uses association algorithms to automatically analyze the association relationships between different data tables, revealing the mutual influence and degree of association between data. This automated association analysis capability overcomes the limitations of traditional methods that require manual setting of rules and algorithms. Through in-depth data association analysis, users can better understand the laws and trends behind the data, discover potential problems and opportunities, and provide more comprehensive and accurate support for decision-making.

[0050] (3) Improved prediction accuracy

[0051] The present invention uses a prediction model to predict future key data. This intelligent prediction method is more accurate and reliable than traditional prediction methods. The improvement of prediction accuracy enables enterprises to more accurately grasp market trends and production needs, adjust production plans and resource allocation in a timely manner, reduce operational risks, and improve economic benefits.

[0052] (4) Intelligent data mining and demand analysis

[0053] The present invention uses a large language model to automatically mine the implicit needs and potential rules in existing data, while analyzing the meaning and business scenarios of each data table. This intelligent data analysis method greatly improves the depth and breadth of data analysis. Through intelligent data mining and demand analysis, enterprises can respond to market changes more quickly, discover new business growth points, optimize existing business processes, and improve overall operational efficiency.

[0054] (5) User experience optimization

[0055] The present invention automatically generates a query statistics interface according to the data table structure, simplifies the user's operation process, and improves query efficiency. At the same time, through the visual display of the prediction results, users can more intuitively understand the data and analysis results. The optimization of user experience allows non-professionals to easily use the data collection and analysis module of the present invention, lowering the threshold for use and improving user satisfaction and loyalty.

[0056] In summary, the method of the present invention has shown significant technical advantages and beneficial effects in data storage and query efficiency, data association analysis capabilities, prediction accuracy, intelligent data mining and demand analysis, and user experience. These advantages and effects not only solve the problems existing in the prior art, but also bring higher work efficiency, more accurate decision support and better user experience to enterprises.

[0057] Based on the above ideal embodiments of the present invention, the relevant staff can make various changes and modifications without departing from the technical concept of the present invention through the above description. The technical scope of the present invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A mine-side data collection and analysis method, characterized in that: include: S1. Collecting raw data from the mine end and classifying the raw data according to categories; S2. storing the original data in tables according to categories according to the set time slices to obtain multiple data tables; S3, automatically generating a query statistics interface according to the structure of the data table; S4, associating the data between the data tables; S5. Use the prediction model to predict key data; S6. Analyze each of the data tables using a large language model to obtain an extended data table and automatically generate a data display page.

2. The mine-side data collection and analysis method according to claim 1, characterized in that: The categories of the raw data include: alarm data, fault data, power failure data, adjustment data, and early warning data.

3. The mine-side data collection and analysis method according to claim 1, characterized in that: The time slices include: days, hours, and minutes.

4. The mine-side data collection and analysis method according to claim 1, characterized in that: Step S3 specifically includes: The structure of the data table includes: field type, field name, and field association relationship; Determine the field that needs to be screened according to the field type; Generate query statements through ORM; The relevant data output according to the query statement is automatically displayed in the interface.

5. The mine-side data collection and analysis method according to claim 1, characterized in that: Step S4 specifically includes: Mix the data in all data tables and sort them in timestamp order; Label each piece of data; Combine the data within a time period into a data group; The Apriori algorithm is used to calculate the correlation between data in a data group; Filter out highly correlated data for centralized display.

6. The mine-side data collection and analysis method according to claim 1, characterized in that: Step S5 specifically includes: Nearly two years of historical data from the mine side is used as training data for the prediction model; The data of the first 18 months of the historical data are used as input data, and the data of the last 6 months are used as output data of the prediction model; Use the trained prediction model to predict data for the next 6 to 12 months; The forecast data is displayed centrally.

7. The mine-side data collection and analysis method according to claim 1, characterized in that: Step S6 specifically includes: Utilize a large language model to analyze the meaning of the data represented by each of the data tables; The large language model expands the requirements according to its own understanding and generates an extended data table; Automatically generate a display page based on the extended data table.

8. The mine-side data collection and analysis method according to claim 1, characterized in that: The prediction model is a time series analysis model, a regression analysis model, or a neural network model.

Images