Geological data acquisition method and system and electronic equipment

Abstract

The invention discloses a geological data acquisition method and system and electronic equipment, and the method comprises the following steps: monitoring microphone input, starting an audio recording function when a keyword preset by a user is recognized, recording voice information dictated by the user, and converting the obtained voice information into text information; key information in the character information is extracted; generating initial geological description data according to the key information; and correcting the initial geological description data by using historical geological data to obtain final geological description data. According to the invention, the geological description and the geological profile map are automatically generated by using the mobile terminal device according to the voice keyword instruction, and large model analysis is combined, so that the efficiency and accuracy of data acquisition and processing can be remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of geological data acquisition, and in particular to a geological data acquisition method, system and electronic equipment. Background Art

[0002] During field geological data collection, personnel often manually enter the collected geological information using an app. However, this method is subject to errors, time-consuming inefficiencies, and complex and slow processes, often leading to inaccurate data. In particular, fields with extensive content, such as geological descriptions, are particularly tedious for geologists to manually input.

[0003] Currently, there is a lack of a system that can efficiently and quickly collect field geological data based on voice commands on mobile devices.

[0004] At present, the traditional collection methods in the field of geological collection may have the following problems:

[0005] Inefficiency: Manual data entry takes a long time, especially when entering large amounts of information or detailed geological descriptions, which can slow down the data collection process. Operations are cumbersome, requiring multiple steps to switch between input interfaces or fields, and entering complex data reduces efficiency. Drawing geological profiles also requires professional personnel to carefully verify the data, and the process takes considerable time to accurately create the profiles.

[0006] High error rate: Manual data entry is prone to spelling errors, data omissions, and inconsistent formats, especially when using specialized terminology or complex data. Furthermore, in a high-intensity work environment, manual data entry may lead to duplicate records or omission of important data.

[0007] Data consistency and integrity issues: Standardization is difficult, and manually entered data may be inconsistently formatted, especially when multiple people are involved in data collection. This increases the workload of data standardization and collation. Real-time verification and validation of input data is difficult, which may lead to problems in subsequent data processing and analysis.

[0008] Poor user experience: Manual input on mobile devices in outdoor or field environments is limited by the device's display size, touchscreen sensitivity, and environmental conditions (such as lighting and weather). Long-term manual input can lead to user fatigue and hand discomfort, especially in harsh conditions (such as cold weather).

[0009] Cost and resource loss: Manual data entry, collation, and verification require significant human resources, increasing operational costs. Operators also need to be trained to ensure they can correctly use data entry applications and maintain data consistency. Summary of the Invention

[0010] The present invention aims to solve at least one of the technical problems existing in the prior art and proposes a geological data acquisition method, system and electronic equipment.

[0011] The technical solution of the present invention is achieved as follows: The present invention provides a geological data acquisition method, comprising the following steps:

[0012] S1: converting the acquired voice information into text information;

[0013] S2: extract key information from text information;

[0014] S3: generating initial geological description data according to the key information;

[0015] S4: Using historical geological data to correct the initial geological description data to obtain final geological description data.

[0016] Furthermore, before step S1, the following steps are further included: monitoring user input, and when a user-preset keyword is recognized, starting the recording function, obtaining the user's spoken voice information, and then executing step S1. Furthermore, converting the obtained voice information into text information specifically includes:

[0017] Preprocessing the speech signal;

[0018] Use speech recognition models to convert speech information into text information.

[0019] Furthermore, generating initial geological description data according to the key information specifically includes: matching a geological knowledge base according to the key information to generate the initial geological description data.

[0020] Furthermore, the initial geological description data is corrected using historical geological data, specifically including:

[0021] Access to historical geological data;

[0022] Calculate similarity: Calculate the similarity between the initial geological description data and each historical geological instance in the historical geological data, and find the K historical geological instances that are most similar to the initial geological description data from the historical geological data;

[0023] The average characteristic value of the target feature of the K most similar historical geological instances is calculated, and the original value of the corresponding target feature in the initial geological description data is replaced by the average characteristic value.

[0024] Furthermore, the initial geological description data is corrected using historical geological data, specifically including:

[0025] Access to historical geological data;

[0026] Build regression models;

[0027] Using historical geological data to train regression models;

[0028] The initial geological description data were modified using regression models.

[0029] Furthermore, the geological data acquisition method of the present invention further comprises the steps of: generating at least one form of output from the final geological description data;

[0030] or / and,

[0031] The method further comprises the following steps: generating a geological cross-section map according to the final geological description data.

[0032] Furthermore, after the geological profile is generated, the following step is also included: superimposing the profile onto the GIS map.

[0033] The present invention also discloses a geological data acquisition system, including an acquisition module, wherein the acquisition module includes:

[0034] A voice information acquisition module, wherein the voice information acquisition module is used to acquire voice information;

[0035] A voice information conversion module, configured to convert the acquired voice information into text information;

[0036] A keyword analysis module, which is used to extract key information from text information;

[0037] A geological description data generation module, wherein the geological description data generation module is used to generate geological description data according to the key information;

[0038] The geological description data optimization module is used to optimize the geological description data using historical geological data to obtain final geological description data.

[0039] Generating at least one form of output from the final geological description data specifically includes: generating one or more of text description and structured data from the final geological description data.

[0040] Furthermore, the geological data acquisition system of the present invention further includes a voice wake-up module, which is used to monitor user input and wake up the acquisition module when a user-preset keyword is recognized;

[0041] The acquisition module also includes a recording module, which is used to record the voice information spoken by the user when the acquisition module is awakened;

[0042] or / and,

[0043] The acquisition module further includes a geological description data output module, which is used to generate at least one form of output from the final geological description data;

[0044] or / and,

[0045] The acquisition module further includes a geological profile generating module, and the geological profile generating module is used to generate a geological profile according to the final geological description data.

[0046] Furthermore, the geological data acquisition system also includes a display module, which is used to display geological description data and geological profiles.

[0047] The present invention also discloses an electronic device, comprising:

[0048] at least one processor; and

[0049] a memory communicatively connected to the at least one processor; wherein,

[0050] The memory stores one or more computer programs executable by the at least one processor. The one or more computer programs are executed by the at least one processor to enable the at least one processor to perform the geological data acquisition method as described above.

[0051] Compared with the existing technology, the present invention has the following advantages: the present invention integrates the function of automatically generating geological descriptions and profiles through voice keyword commands in the geological collection app, which can bring the following benefits:

[0052] 1. The present invention can improve data collection efficiency: Through voice keyword commands, geological workers can quickly collect complex geological information, simplifying the data collection process, especially in field environments where manual input may be inconvenient or limited, while reducing the delays and possible omissions of traditional note-taking or manual entry.

[0053] 2. This invention can enhance data accuracy and consistency: The combination of speech recognition and large-scale model analysis can reduce spelling and recording errors during manual input, ensuring data accuracy and consistency. The large-scale model can automatically format the collected data to ensure data standardization, facilitating subsequent analysis and comparison.

[0054] 3. This invention enables real-time analysis and feedback: The large model can process and analyze collected data in real time, providing immediate feedback and suggestions, such as geological descriptions and geological profiles. During the data collection process, the model analysis results can help geologists make more timely and accurate decisions and provide corresponding automatic data calibration methods.

[0055] 4. This invention supports complex tasks and large-scale data processing: Large models can integrate and analyze diverse data types from diverse sources, providing comprehensive support for complex geological tasks through homogeneous data analysis. Large models can also efficiently process and analyze datasets, discovering patterns and trends within the data and supporting in-depth geological analysis.

[0056] 5. The present invention is user-friendly: in the field or in harsh environments, voice command recognition input is more convenient than manual input, especially when a large amount of equipment needs to be carried or when the hands are inconvenient (such as wearing gloves). Geologists can record data through voice input while measuring, supporting more efficient work.

[0057] In general, using mobile devices to automatically generate relevant design documents for geological descriptions and geological profiles based on voice keyword commands, and combining them with large-scale model analysis, can significantly improve the efficiency and accuracy of data collection and processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 A flow chart of a geological data acquisition method provided by an embodiment of the present invention;

[0059] Figure 2 Example code for generating a geological profile provided by an embodiment of the present invention;

[0060] Figure 3 The figure is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0061] In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the present disclosure is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0062] Unless otherwise defined, the technical or scientific terms used in this disclosure should have the usual meanings understood by people with ordinary skills in the field to which this disclosure belongs. The "first", "second" and similar words used in this disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, similar words such as "one", "an" or "the" do not indicate a quantitative limitation, but rather indicate the presence of at least one. Similar words such as "include" or "comprise" mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects.

[0063] In each accompanying drawing, identical element adopts similar reference numeral to represent.For the sake of clarity, each part in the accompanying drawings is not all drawn to scale.In addition, some well-known parts may not be shown in the drawings.

[0064] Many specific details of the present disclosure are described below to provide a clearer understanding of the present disclosure. However, as will be appreciated by those skilled in the art, the present disclosure may be implemented without following these specific details.

[0065] The present invention is aimed at geological collection work in the mobile field. By obtaining relevant voice keyword instructions, it intelligently recognizes voice information, performs associative checks on the recognized information, and executes relevant data collection operations. The main steps are: identifying the user's wake-up word, waking up the collection system, identifying the user's keyword voice information, converting the voice information into text information, and assisting GPS / mobile phone camera / sensor and other equipment to collect geological data. The professional geological big data model is used to extract relevant entity data and perform accuracy correction and completion on it. Finally, accurate geological collection data can be generated and filled in the collection text displayed on the mobile terminal device. After the collection is completed, the corresponding freehand profile can be automatically generated according to the relevant collection data for reference by the field collection personnel.

[0066] Figure 1 The following is a flow chart of a geological data acquisition method provided by an embodiment of the present disclosure. Figure 1 As shown, the present invention provides a geological data acquisition method, which is applied to an electronic device and includes the following steps:

[0067] S1: converting the acquired voice information into text information;

[0068] S2: extract key information from text information;

[0069] S3: generating initial geological description data of the current location based on the key information;

[0070] S4: Using historical geological data to correct the initial geological description data to obtain final geological description data.

[0071] Furthermore, the following steps are also included before step S1: monitoring the microphone input, waking up the acquisition module when the user's preset keyword is recognized, and after the acquisition module is woken up, turning on the audio recording function to record the user's spoken voice information, and then executing step S1.

[0072] Preferably, the electronic device is a mobile device.

[0073] The electronic device of the present invention can integrate a wake-up SDK. This SDK enables access to keyword-setting functions. The user first sets the keyword "XX" and continuously monitors the microphone input. When the user says "XX," the electronic device automatically recognizes it and wakes up the relevant app. Once the relevant app is woken up, the app's internal audio recording function can be activated to record the relevant voice information spoken by the field data collector.

[0074] After receiving the voice message, the relevant app performs voice recognition (ASR) services. ASR services primarily convert voice signals into text messages. Before voice recognition, the voice signal needs to be processed to improve recognition accuracy.

[0075] Furthermore, the acquired voice information is converted into text information, specifically including:

[0076] Preprocessing the speech signal;

[0077] Use speech recognition models to convert speech information into text information.

[0078] Furthermore, the speech signal is preprocessed, specifically including:

[0079] Noise suppression;

[0080] Speech segmentation: Segmenting long speech into multiple segments based on sentences or semantics;

[0081] Feature extraction: Extract Mel-frequency cepstral coefficients as input features for deep learning speech recognition models.

[0082] Noise suppression mainly suppresses background noise such as noise and equipment noise.

[0083] Speech segmentation mainly involves dividing long speech into segmented segments (in sentences or semantic units).

[0084] Feature extraction mainly uses Mel-Frequency Cepstral Coefficients (MFCC) and logarithmic Mel as feature inputs. The speech signal is converted into frequency domain feature analysis to provide the speech recognition model with use.

[0085] Furthermore, the speech recognition model adopts a deep learning speech recognition model, which uses a deep learning model (such as Wav2Vec2.0 or DeepSpeech, etc.) to convert the subsequent speech signal into text.

[0086] Speech recognition model training uses common speech recognition datasets (such as LibriSpeech). It identifies relevant keyword commands, such as taking a photo, positioning, or using an electronic compass. This facilitates mobile devices to interpret relevant execution commands and prepare the corresponding geographic information, such as using GPS to obtain longitude and latitude, extracting stratigraphic information from speech text, using an electronic compass to obtain current location information such as azimuth, slope angle, inclination, and dip, and using the camera to automatically take photos.

[0087] The speech recognition model is trained using general speech recognition datasets (such as LibriSpeech) and a geological domain corpus (including common vocabulary and sentence patterns in geological descriptions).

[0088] Display result: Input voice: "The lower layer is limestone, 20 meters thick, and the upper layer is sandstone."

[0089] Output text: The lower layer is limestone, 20 meters thick, and the upper layer is sandstone.

[0090] Combine the two types of parsed data above: for example, after using the positioning command, at the longitude and latitude XX position, the relevant rock type is XX, the thickness is X meters, etc.

[0091] Extract key information from text messages and output related json, including:

[0092] System parsing: Use natural language processing technology to parse text and extract key information, such as geological professional terms (such as "limestone", "sandstone", "crack", etc.), and annotate parameters (such as "thickness", "inclination").

[0093] Dependency parsing: Analyze sentence structure and extract the relationship between parameters.

[0094] Example: Input sentence: The sandstone layer is 15 meters thick and has a dip angle of 20°.

[0095] Output dependency-related JSON: {"layer":"sandstone","thickness":"15 meters","inclination":"20°"}.

[0096] The keyword extraction of the present invention extracts key geological descriptions in speech through pattern matching (regular expressions) and semantic models (such as BERT).

[0097] Regular expression matching example:

[0098] Input text: The bottom is shale, 10 meters thick, with fractures in the NW-SE direction.

[0099] Matching rule: (shale|sandstone|limestone).*thickness.*(\d+) meters

[0100] The result json is displayed: {"layer":"shale","thickness":"10 meters","features":[{"type":"fracture","direction":"NW-SE"}]}.

[0101] The above matching rules are just one example, and specific adjustments can be made based on the geological data of the region.

[0102] Furthermore, generating initial geological description data based on the key information (i.e., geological features) specifically includes matching the key information with a geological knowledge base to generate the initial geological description data. The present invention can match the key information with the geological knowledge base to generate initial geological description data that matches a standardized description template. Matching the key information with the geological knowledge base can obtain relevant information that matches the key information, such as attribute information of the key information.

[0103] The knowledge base is the core of speech-generated geological descriptions. It contains terms, parameter ranges, and standardized description templates related to geological features. The knowledge base structure is as follows:

[0104] Lithology data: Common lithology types: sandstone, shale, limestone, tectonic rock, etc.

[0105] The rock characteristics studied: sandstone is yellow or light brown.

[0106] Structure: such as cross-bedding, horizontal bedding, etc.

[0107] Geological structure data: including faults, cracks, folds and other structural types.

[0108] Parameters: fault dip, void direction (e.g. NW-SE).

[0109] Stratigraphic sequence data: Common sequence models, including the superposition relationship between sedimentary strata and igneous rock sequences.

[0110] Description template: Example: The {serial number} layer is {lithology}, thickness {value} meters, dip {angle}, and the main feature is {feature description}.

[0111] The content of the geological knowledge base of one embodiment may be similar to the following:

[0112]

[0113] Sources for geological databases may include standard description corpora from historical geological reports, geological expert summary templates, or regional geological survey databases. A geological database is a structured semantic database that supports the system's understanding and generation of geological descriptions after speech-to-text conversion, identifying address-specific / structured fields. It typically comes from industry standards, textbooks, historical field reports, sampling databases, and collections of manually curated expert knowledge. It can be stored as a JSON rule library, SQLite, MongoDB database, or vector knowledge base.

[0114] Generally speaking, the amount of data in geological databases is relatively large. It is placed on the server side and used in conjunction with large models. Mobile devices use related service requests to call it.

[0115] Furthermore, after obtaining the above-mentioned initial geological description data, it is necessary to optimize the geological description results of the current location area in combination with historical geological data (specifically, using historical geological data to correct the initial geological description data), which is a key step in improving the accuracy and reliability of the automated geological profile generation system.

[0116] The first step in optimizing geological description data is to prepare historical geological data and preprocess them. Historical geological data usually contains confirmed geological characteristics of different locations, such as lithology, layer thickness, dip angle, and other information.

[0117] Preprocessing of historical geological data, including:

[0118] Data cleaning: Remove invalid or erroneous geological data, such as extremely abnormal layer thickness or dip angle, to ensure data quality. For missing geological features (such as the thickness of certain strata), interpolation methods (such as linear interpolation) or other relevant features can be used to fill in the gaps.

[0119] Data normalization: Standardize or normalize geological data to ensure that the scales of different features are consistent and avoid the impact of certain features on model training due to excessively large or small values.

[0120] Data enhancement: To address the imbalance problem in geological data or to increase the amount of training data, data enhancement techniques (such as random rotation, scaling, noise injection, etc.) can be used to generate new samples to improve the generalization ability of the model.

[0121] The core idea of optimizing geological descriptions in combination with historical geological data is to use historical geological examples to adjust the prediction results of the speech recognition model so that they are more consistent with real geological features. The correction methods used in the present invention include the K nearest neighbor algorithm and the regression algorithm (linear regression, ridge regression, etc.). The present invention can call the applicable correction method according to the user's selection. For example, when the amount of historical geological data obtained is small, the regression algorithm (i.e., the geological data prediction correction based on machine learning) is selected to optimize the geological description. When the amount of historical geological data obtained is large, the K nearest neighbor algorithm is selected (after obtaining the similarity verification comparison, the data is modified). Of course, the K nearest neighbor algorithm and the regression algorithm can also be used in combination.

[0122] The present invention can use instances in historical geological data that are similar to the current prediction results to adjust the new geological description. Relevant geological features, such as lithology, stratum thickness, inclination, etc., are extracted from the prediction results of the speech recognition model. By calculating the similarity between the prediction results and each instance in the historical geological data (commonly measured by Euclidean distance, Manhattan distance, etc.), the K most similar historical geological instances are found, and the prediction results are adjusted by calculating the average value of these K most similar instances. The result after neighborhood averaging is output as the final geological description. The advantage is that it has strong adaptability and is dynamically adjusted according to the distribution and similarity of historical geological data. It is intuitive and easy to understand, and the predicted value is directly corrected by "neighborhood averaging", which is easy to understand and implement.

[0123] In some embodiments, the initial geological description data is modified using historical geological data, specifically including:

[0124] Access to historical geological data;

[0125] Extracting input features: extracting relevant geological features, such as lithology, stratum thickness, dip angle, etc., from the initial geological description data.

[0126] Calculate similarity: Calculate the similarity between the initial geological description data and each historical geological instance in the historical geological data, and find K (set as needed) historical geological instances that are most similar to the initial geological description data from the historical geological data;

[0127] The average characteristic value of the target feature (numerical feature) of the K most similar historical geological instances is calculated. The original value of the corresponding target feature in the initial geological description data can be directly replaced by the average characteristic value, or the average characteristic value can be compared with the original value. If the original value differs greatly from the average characteristic value (i.e., the difference exceeds a preset range), the original value of the corresponding target feature in the initial geological description data is replaced by the average characteristic value. If the original value differs little from the average characteristic value (i.e., the difference is within a preset range), the original value is retained without replacement, i.e., the original value does not need to be corrected.

[0128] For example, if the predicted sandstone layer thickness is 10 meters, and the thicknesses of the K most similar historical geological examples are 9.8 meters, 10.2 meters, 10 meters, etc., the final adjusted thickness may be 9.9 meters.

[0129] The present invention can also use regression algorithms (such as linear regression and ridge regression) to optimize current prediction results: regression algorithms adjust new prediction results by establishing a relationship model between geological features and geological descriptions in historical geological data. The advantage is that regression algorithms can better fit continuous data and are suitable for numerical features such as thickness and inclination involved in geological descriptions. Good stability: Ridge regression has strong stability when dealing with collinearity and high-dimensional data, avoiding overfitting.

[0130] In other embodiments, the initial geological description data is modified using historical geological data, specifically including:

[0131] Access to historical geological data;

[0132] Select geological features (such as lithology, layer thickness, dip angle, etc.) and target variables (such as actual layer thickness, dip angle, etc.) from historical geological data to construct a regression model;

[0133] Using historical geological data to train regression models: Use linear regression or ridge regression algorithms to fit the relationship between features and targets in historical geological data;

[0134] Using a regression model to correct the initial geological description data involves taking the initial geological description data as input and substituting it into a trained regression model to produce the corrected geological description data. For example, if the predicted result is "thickness 10 meters, dip 20°," the regression model will adjust this prediction based on the characteristic relationships in the historical geological data.

[0135] Preferably, after obtaining the historical geological data, the similarity between the initial geological description data and each historical geological instance in the historical geological data is calculated, and M (set as needed) historical geological instances that are most similar to the initial geological description data are found from the historical geological data for training the regression model.

[0136] Linear regression: Assuming a linear relationship between features and targets, the least squares method is used to fit the regression equation.

[0137] Ridge regression: Add L2 regularization to linear regression to solve the problem of multicollinearity.

[0138] Optimized geological description: The regression model is used to obtain prediction results that are more consistent with historical geological data.

[0139] Using the above algorithm optimization example, assume that the parsed address description is: the stratum at this address contains a sandstone layer with a thickness of 10 meters and a dip of 20 degrees, and a shale layer with a thickness of 5 meters and a dip of 10 degrees.

[0140] When using regression models to correct initial geological description data, first extract features from the geological data, such as lithology, color, structure, thickness, layer depth, etc., and select the corresponding training model: such as Linear Regression / XGBoost / LightGBM / BERT+Dense Layer;

[0141] Use historical data sample sets to train the model;

[0142] If the initial data's "Litic Type" is "Sandstone", "Color" is "Grayish Yellow", "Thickness" is 9, and "Structure" is "Bedding";

[0143] Through model correction, the corrected "lithology" is "medium-fine sandstone", the "corrected structure" is "parallel bedding", and the "corrected description" is "gray-yellow medium-fine sandstone, about 10 cm thick, with parallel bedding".

[0144] The common dip ranges for sandstones and shales are calibrated using historical geological data (e.g., regional lithologic datasets).

[0145] Use the K-nearest neighbor algorithm to correct the dip and thickness: find K instances similar to the current address data from the historical geological data, average the dip and thickness of these instances, and replace the original values with the corrected values. Generate the corrected geological description:

[0146] The strata at this site include a 10-meter-thick sandstone layer with a dip of 22°, and a 5-meter-thick shale layer with a dip of 12°.

[0147] Through these methods, combined with the optimization processing of historical geological data, the accuracy of geological description can be greatly improved, making the automatically generated profiles more consistent with actual geological laws.

[0148] Furthermore, the geological data acquisition method of the present invention further includes the following steps: generating at least one form of output from the final geological description data, such as text description and / or structured data, etc. The matching results are output in multiple forms to facilitate use in different scenarios.

[0149] Convert the final geological description data into a textual description: Generate a highly readable geological description in natural language. For example: The first layer is yellow sandstone, 10 meters thick, with a dip of 20° and cross-bedding. The second layer is gray shale, 5 meters thick, with a dip of 15° and horizontal bedding.

[0150] The final geological description data is converted into structured data: it is output in JSON or XML format for integration with other systems. {"Horizon":[{"Lithology":"Sandstone","Thickness":10,"Dip":20,"Color":"Yellow","Feature":"Cross-Bedding"},{"Lithology":"Shale","Thickness":5,"Dip":15,"Color":"Gray","Feature":"Horizontal Bedding"}]}.

[0151] Furthermore, the geological data acquisition method of the present invention further includes the following step: generating a geological profile according to the final geological description data.

[0152] The core process of generating cross-sections based on the above geological descriptions includes drawing frame selection, geometric construction, dynamic adjustment, and graphic output.

[0153] Generate geological cross-sections, including:

[0154] 1. Determine your drawing tools based on your needs. For Python tools, use Matplotlib or Plotly to generate static or interactive 2D cross-section plots. For graphics rendering tools, use Unity or OpenGL to create interactive cross-section plots. For web front-end tools, use D3.js or Three.js to create dynamic web cross-section plots.

[0155] 2. Section drawing, including:

[0156] Geometry initialization: Define the coordinate system of the cross-section, with the X-axis representing horizontal distance and the Y-axis representing vertical depth or altitude. The vertical position of each layer is calculated based on its thickness, and the inclination angle determines the slope of each layer.

[0157] Draw each stratum using polygons. If the dip is zero, a rectangle is drawn. If the dip is non-zero, a parallelogram is drawn, starting at the end point of the previous layer. The horizontal length is fixed, and the thickness adjusts the slope based on the dip.

[0158] Color: Fill in color according to the rock type (such as sandstone yellow, shale gray).

[0159] Boundary Lines: The upper and lower boundaries of each layer are drawn as solid lines.

[0160] See also Figure 2 A sample code for generating a geological cross-section diagram is disclosed.

[0161] 3. Mapping geological structures:

[0162] Fault: Insert inclined dividing lines in the cross-section to represent the fault interface. Adjust the displacement of the upper and lower contact layers of the fault according to the displacement.

[0163] Wrinkles: Uses a sine function to draw a wavy curve to represent wrinkles. Adjust the shape and position of the curve based on amplitude and wavelength.

[0164] Draw geological structures: Label each layer with information such as lithology name, thickness, and dip. Add a legend to the cross-section to explain the correspondence between color and lithology.

[0165] Dynamic adjustment: Through the interactive interface, users can adjust the geological parameters of the profile in real time.

[0166] Thickness Adjustment: Users can adjust the thickness of each layer via a slider. The drawing module updates the graphics in real time.

[0167] Tilt adjustment: The user enters a new tilt value and the profile automatically recalculates the tilt angle.

[0168] Fault displacement adjustment: Users can drag the relative position of the upper and lower contact surfaces to update the fault morphology in real time.

[0169] Data verification and optimization: Verify whether the layer sequence conforms to the regional stratigraphic superposition rules and ensure that parameters such as dip angle and thickness are within a reasonable range.

[0170] Model optimization: Update the graphical model based on user adjustments. Dynamically optimize the geological knowledge base to improve the accuracy of the next match.

[0171] Furthermore, after generating the geological profile, you can export the profile: multiple formats are supported: PNG, JPEG (for reporting), SVG, PDF (for high-definition printing).

[0172] Furthermore, after generating the geological profile, the following steps are also included: overlaying the profile onto the GIS map. Overlaying the profile onto the GIS map integrates the data with the GIS, matches the actual topographic and geological conditions, and outputs it in formats such as GeoJSON and Shapefile for further analysis.

[0173] Furthermore, the aforementioned geological description and profile generation functions are deployed as API services, accessible to mobile applications. Upon receiving a voice command, the mobile application automatically calls this API service, formats the text entities output by the service, parses the geological description / profile for the current location, and displays the results on the mobile device. Field data collectors verify the data in the relevant collection forms and upload and save it, completing the process.

[0174] The technical value of automatically generating geological descriptions and geological profiles through voice keyword commands in the geological collection app is mainly reflected in the following aspects:

[0175] 1. This invention improves data collection efficiency and accuracy: Using voice keyword recognition technology, geologists can quickly and accurately record field observations and measurement data, eliminating the tedious and error-prone manual input. Voice input instantly captures data, ensuring the timeliness and completeness of information and reducing omissions and delays associated with traditional data recording methods.

[0176] 2. This invention enhances data processing and analysis capabilities: Incorporating big data technologies, collected data can be processed and analyzed instantly, providing real-time feedback, such as preliminary identification and analysis of geological features. Big data technologies can process and analyze massive amounts of data, including data from multiple formats and sources (e.g., seismic, magnetic, geological exploration, etc.), revealing complex patterns and trends within the data.

[0177] 3. This invention enhances decision support and insight: Utilizing machine learning and big data analytics, we can conduct in-depth analysis of collected data, generate geological models and predictions, and help geologists make more informed decisions. Through big data analysis, we can identify potential geological risks (such as landslides and earthquakes) in advance, providing risk warnings and management strategies.

[0178] 4. This invention enhances innovation in geological research and exploration: Big data technology supports the creation of sophisticated geological models, which, combined with voice-based data, provide precise geological descriptions and analyses. Big data analysis can develop new research methods and techniques, explore new patterns and associations in geological data, and advance geological science.

[0179] 5. This invention enhances work safety and efficiency: Automated data collection and processing reduces the workload and risks for field personnel, especially in harsh or hazardous geological environments. Big data analysis can help optimize resource allocation, such as manpower, equipment, and funding, improving the overall efficiency and effectiveness of geological projects.

[0180] In summary, the value of automatically generating geological descriptions and profiles through voice keyword commands within a geological data collection app lies primarily in improving data processing capabilities, automation, widespread application, and innovation. This technology can promote the development and progress of related disciplines while also improving the efficiency and accuracy of geological surveys and research.

[0181] Based on the same inventive concept, the present invention also discloses a geological data acquisition system, including an acquisition module, wherein the acquisition module includes:

[0182] A voice information acquisition module, wherein the voice information acquisition module is used to acquire voice information;

[0183] A voice information conversion module, configured to convert the acquired voice information into text information;

[0184] A keyword analysis module, which is used to extract key information from text information;

[0185] A geological description data generation module, wherein the geological description data generation module is used to generate geological description data according to the key information;

[0186] The geological description data optimization module is used to optimize the geological description data using historical geological data to obtain final geological description data.

[0187] Generating at least one form of output from the final geological description data specifically includes: generating one or more of text description and structured data from the final geological description data.

[0188] Furthermore, the geological data acquisition system of the present invention further includes a voice wake-up module, which is used to monitor microphone input and wake up the acquisition module when a user-preset keyword is recognized;

[0189] The acquisition module also includes an audio recording module, which is used to record the voice information spoken by the user when the acquisition module is awakened.

[0190] Furthermore, the acquisition module further includes a geological description data output module, and the geological description data output module is used to generate at least one form of output from the final geological description data.

[0191] Furthermore, the acquisition module also includes a geological profile generating module, and the geological profile generating module is used to generate a geological profile according to the final geological description data.

[0192] Furthermore, the geological data acquisition system also includes a display module, which is used to display geological description data and geological profiles.

[0193] Based on the same inventive concept, an embodiment of the present disclosure further provides an electronic device. Figure 3 FIG. 1 is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. Figure 3 As shown, an electronic device includes: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement any of the geological data acquisition methods in the above embodiments. The one or more I / O interfaces 103 are connected between the processor and the memory and are configured to implement information exchange between the processor and the memory.

[0194] Among them, the processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically such as SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read-write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus), etc.

[0195] In some embodiments, the processor 101 , the memory 102 , and the I / O interface 103 are connected to each other via a bus 104 , and further connected to other components of the computing device.

[0196] In some embodiments, the one or more processors 101 include a field programmable gate array.

[0197] Based on the same inventive concept, the present disclosure also provides a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the steps of any of the geological data acquisition methods in the above embodiments are implemented.

[0198] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, including a computer program carried on a machine-readable medium, the computer program containing program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), the above-mentioned functions defined in the system of the present disclosure are executed.

[0199] It should be noted that the computer-readable medium described in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, or any suitable combination thereof.

[0200] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the aforementioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0201] It is understood that the above embodiments are merely exemplary embodiments for illustrating the principles of the present disclosure, and the present disclosure is not limited thereto. Those skilled in the art may make various modifications and improvements without departing from the spirit and substance of the present disclosure, and such modifications and improvements are also considered to be within the scope of protection of the present disclosure.

Claims

1. A geological data acquisition method, characterized in that: The steps include: S1: converting the acquired voice information into text information; S2: extract key information from text information; S3: generating initial geological description data according to the key information; S4: Using historical geological data to correct the initial geological description data to obtain final geological description data.

2. The geological data acquisition method according to claim 1, characterized in that: Before step S1, the following steps are also included: monitoring user input, when a keyword preset by the user is recognized, starting the recording function, obtaining the voice information spoken by the user, and then executing step S1.

3. The geological data acquisition method according to claim 1, wherein: Convert the acquired voice information into text information, including: Preprocessing the speech signal; Use speech recognition models to convert speech information into text information.

4. The geological data acquisition method according to claim 1, wherein: Generating initial geological description data according to the key information specifically includes: matching a geological knowledge base according to the key information to generate the initial geological description data.

5. The geological data acquisition method according to claim 1, characterized in that: The initial geological description data is corrected using historical geological data, specifically including: Access to historical geological data; Calculate similarity: Calculate the similarity between the initial geological description data and each historical geological instance in the historical geological data, and find the K historical geological instances that are most similar to the initial geological description data from the historical geological data; The average characteristic value of the target feature of the K most similar historical geological instances is calculated, and the original value of the corresponding target feature in the initial geological description data is replaced by the average characteristic value.

6. The geological data acquisition method according to claim 1, characterized in that: The initial geological description data is corrected using historical geological data, specifically including: Access to historical geological data; Build regression models; Using historical geological data to train regression models; The initial geological description data were modified using regression models.

7. The geological data acquisition method according to claim 1, wherein: The method further includes the following steps: generating at least one form of output from the final geological description data; or / and, The method further includes the following steps: generating a geological cross-section map according to the final geological description data.

8. A geological data acquisition system, characterized in that: The acquisition module includes: A voice information acquisition module, wherein the voice information acquisition module is used to acquire voice information; A voice information conversion module, configured to convert the acquired voice information into text information; A keyword analysis module, which is used to extract key information from text information; A geological description data generation module, wherein the geological description data generation module is used to generate geological description data according to the key information; The geological description data optimization module is used to optimize the geological description data using historical geological data to obtain final geological description data. Generating at least one form of output from the final geological description data specifically includes: generating one or more of text description and structured data from the final geological description data.

9. The geological data acquisition system according to claim 8, characterized in that: It also includes a voice wake-up module, which is used to monitor user input and wake up the acquisition module when a user-preset keyword is recognized; The acquisition module also includes a recording module, which is used to record the voice information spoken by the user when the acquisition module is awakened; or / and, The acquisition module further includes a geological description data output module, which is used to generate at least one form of output from the final geological description data; or / and, The acquisition module further includes a geological profile generating module, and the geological profile generating module is used to generate a geological profile according to the final geological description data.

10. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores one or more computer programs executable by the at least one processor. The one or more computer programs are executed by the at least one processor to enable the at least one processor to perform the geological data acquisition method according to any one of claims 1 to 7.

Images