CN117807220A - Geological forecast generation method and device based on natural language processing and electronic equipment - Google Patents
Geological forecast generation method and device based on natural language processing and electronic equipment Download PDFInfo
- Publication number
- CN117807220A CN117807220A CN202311826368.9A CN202311826368A CN117807220A CN 117807220 A CN117807220 A CN 117807220A CN 202311826368 A CN202311826368 A CN 202311826368A CN 117807220 A CN117807220 A CN 117807220A
- Authority
- CN
- China
- Prior art keywords
- data
- result
- geological
- target
- forecast
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000003058 natural language processing Methods 0.000 title claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 29
- 238000007781 pre-processing Methods 0.000 claims abstract description 20
- 230000011218 segmentation Effects 0.000 claims description 40
- 238000012360 testing method Methods 0.000 claims description 37
- 230000008569 process Effects 0.000 claims description 28
- 238000004140 cleaning Methods 0.000 claims description 27
- 239000013598 vector Substances 0.000 claims description 25
- 238000012549 training Methods 0.000 claims description 23
- 238000004891 communication Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 8
- 238000013136 deep learning model Methods 0.000 claims description 4
- 238000005520 cutting process Methods 0.000 claims description 3
- 238000005065 mining Methods 0.000 abstract description 13
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- 230000002159 abnormal effect Effects 0.000 abstract description 3
- 230000002349 favourable effect Effects 0.000 abstract description 3
- 239000003245 coal Substances 0.000 description 16
- 238000010586 diagram Methods 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 6
- 230000008451 emotion Effects 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 4
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 230000005641 tunneling Effects 0.000 description 3
- 238000009423 ventilation Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 229910052500 inorganic mineral Inorganic materials 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 239000011707 mineral Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000004080 punching Methods 0.000 description 2
- 239000011435 rock Substances 0.000 description 2
- 238000012384 transportation and delivery Methods 0.000 description 2
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000009933 burial Methods 0.000 description 1
- 229910052729 chemical element Inorganic materials 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000004992 fission Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 229910052717 sulfur Inorganic materials 0.000 description 1
- 239000011593 sulfur Substances 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/34—Browsing; Visualisation therefor
- G06F16/345—Summarisation for human users
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a geological forecast generation method and device based on natural language processing and electronic equipment, and relates to the field of geological forecast, wherein the method comprises the following steps: obtaining geological data of a target area, wherein the geological data comprises text data and space data; respectively carrying out data preprocessing on the text data and the space data to obtain a first result corresponding to the text data and a second result corresponding to the space data; and processing the first result and the second result by adopting the trained geological forecast model to generate a target geological forecast. The method is favorable for guiding production operation in advance. The model is combined with three-dimensional geology (space data), abnormal information is identified, extracted, generalized, tidied and complete geological forecast content is generated, and the accuracy of the content of geological forecast generated by the geological model can be evaluated according to actual mining conditions, so that the geological forecast model is fed back and optimized. The method can greatly improve the efficiency and accuracy of geological forecast.
Description
Technical Field
The application relates to the field of geological forecast, in particular to a geological forecast generation method and device based on natural language processing and electronic equipment.
Background
In the underground operation process of the coal mine, the underground operation process is greatly influenced by factors such as geological environment, and particularly in the fully mechanized mining and tunneling processes, a certain place can be constructed, and serious safety accidents can be caused if the underground operation process is not predicted or monitored.
At present, geological forecast is more traditional, such as manual observation or detection by using a detector or punching, and then various data are summarized and reported.
Disclosure of Invention
The embodiment of the application aims to provide a geological forecast generation method, device and electronic equipment based on natural language processing, which are used for solving the problems in the prior art and obtaining geological forecast with high accuracy.
In a first aspect, a method for generating a geological forecast based on natural language processing is provided, which may include:
obtaining geological data of a target area, wherein the geological data comprises text data and space data;
respectively carrying out data preprocessing on the text data and the space data to obtain a first result corresponding to the text data and a second result corresponding to the space data;
and processing the first result and the second result by adopting a trained geological forecast model to generate a target geological forecast.
In one possible implementation, the data preprocessing is performed on the text data to obtain the first result, including:
performing text cleaning on the text data to obtain a cleaning result;
performing word segmentation on the cleaning result to generate a word segmentation result;
determining target word segmentation with the same classification identifier as each target keyword in the word segmentation result based on the configured target keywords;
and determining the first result as a data set formed by each target keyword, the corresponding target word and the relation between the target keywords and the corresponding target word.
In one possible implementation, the word segmentation processing is performed on the cleaning result to obtain a word segmentation result, including:
cutting the cleaning result to obtain a plurality of vocabulary sequences;
aiming at any vocabulary sequence, classifying and identifying the vocabulary sequence to obtain a target classifying and identifying, and identifying the word position of each character in the vocabulary sequence to obtain a target word position identification;
and determining a data set consisting of the vocabulary sequences, the target classification identifiers corresponding to the vocabulary sequences and the target word position identifiers of each character in the vocabulary sequences as a word segmentation result.
In one possible implementation, the performing data preprocessing on the spatial data to obtain the second result includes:
extracting target data comprising comprehensive digging directions and reporting ranges from the space data according to a digging plan;
and vectorizing and converting the target data to obtain the second result.
In one possible implementation, the training process of the geological forecast model includes:
performing data preprocessing on the acquired historical geological data to obtain a historical first result and a historical second result; wherein the historical geological data comprises historical text data and historical space data;
training the deep learning model by taking the historical first result and the historical second result as training samples and taking the historical geological forecast as a training label to obtain an initial geological forecast model;
predicting a test sample by adopting the initial geological prediction model to obtain a test result;
calculating actual data corresponding to the test result and the test sample to obtain prediction accuracy;
and if the prediction precision reaches the expected precision, determining the initial geological prediction model as a geological prediction model.
In one possible implementation, calculating actual data corresponding to the test result and the test sample to obtain prediction accuracy;
converting the test result and the actual data into corresponding test result high-dimensional vectors and actual report high-dimensional vectors;
converting the high-dimensional vector of the test result and the actual reporting high-dimensional vector into a corresponding low-dimensional vector of the test result and an actual reporting low-dimensional vector;
and calculating cosine similarity between the low-dimensional vector of the test result and the actual report low-dimensional vector to obtain forecast accuracy.
In a second aspect, a geological forecast generating device based on natural language processing is provided, and the device may include:
the acquisition unit is used for acquiring geological data of the target area, wherein the geological data comprises text data and space data;
the processing unit is used for respectively carrying out data preprocessing on the text data and the space data to obtain a first result corresponding to the text data and a second result corresponding to the space data;
and processing the first result and the second result by adopting a trained geological forecast model to generate a target geological forecast.
In one possible implementation, the processing unit includes a cleaning module, a word segmentation module, a determination module, and a composition module;
the cleaning module is used for cleaning the text of the text data to obtain a cleaning result;
the word segmentation module is used for carrying out word segmentation on the cleaning result to generate a word segmentation result;
the determining module is used for determining target word segmentation with the same classification identifier as each target keyword in the word segmentation result based on the configured target keywords;
the composition module is used for determining each target keyword, a corresponding target word and a data set formed by the relation between the target keywords and the corresponding target word as the first result.
In a third aspect, an electronic device is provided, the electronic device comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory are in communication with each other via the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any one of the above first aspects when executing a program stored on a memory.
In a fourth aspect, a computer-readable storage medium is provided, in which a computer program is stored which, when being executed by a processor, carries out the method steps of any of the first aspects.
The application provides a geological forecast generation method based on natural language processing, which comprises the following steps: obtaining geological data of a target area, wherein the geological data comprises text data and space data; respectively carrying out data preprocessing on the text data and the space data to obtain a first result corresponding to the text data and a second result corresponding to the space data; and processing the first result and the second result by adopting the trained geological forecast model to generate a target geological forecast. The method is favorable for guiding production operation in advance. The model is combined with three-dimensional geology (space data), abnormal information is identified, extracted, generalized, tidied and complete geological forecast content is generated, and the accuracy of the content of geological forecast generated by the geological model can be evaluated according to actual mining conditions, so that the geological forecast model is fed back and optimized. The method can greatly improve the efficiency and accuracy of geological forecast.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a system architecture diagram of a geological forecast generating method applied to natural language processing according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of a geological forecast generating method based on natural language processing according to an embodiment of the present application;
fig. 3 is a schematic flow chart of a text data preprocessing process provided in an embodiment of the present application;
FIG. 4 is a first schematic diagram of a target geological forecast provided by an embodiment of the present application;
FIG. 5 is a second schematic illustration of a target geological forecast provided by an embodiment of the present application;
fig. 6 is a schematic structural diagram of a geological forecast generating device based on natural language processing according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, and not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present application without making any inventive effort, are intended to be within the scope of the present application.
The geological forecast generation method based on natural language processing provided by the embodiment of the application can be applied to a system architecture shown in fig. 1, and as shown in fig. 1, the system can comprise: server and terminal. The server may be a physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), basic cloud computing services such as big data and artificial intelligent platforms. The Terminal may be a Mobile phone, a smart phone, a notebook computer, a digital broadcast receiver, a Personal Digital Assistant (PDA), a tablet personal computer (PAD), or other User Equipment (UE), a handheld device, a car-mounted device, a wearable device, a computing device, or other processing device connected to a wireless modem, a Mobile Station (MS), a Mobile Terminal (Mobile Terminal), or the like. The terminal and the server may be directly or indirectly connected through wired or wireless communication, which is not limited herein.
And the terminal is used for acquiring the geological data of the target area and sending the geological data to the server.
And the server is used for receiving the geological data sent by the terminal so as to execute the geological forecast generation method based on natural language processing.
For ease of understanding, the terms referred to in the embodiments of the present application are explained below:
spatial data: spatial data, also called geometric data, is used to represent information about the position, shape, size distribution, etc. of objects, and is a quantitative description of things and phenomena that exist in the current world and have positioning significance. The spatial data may be further divided into graphic data and image data. In the present application, spatial data may be understood as image data or graphic data corresponding to the target region position.
In the underground operation process of the coal mine, the underground operation process is greatly influenced by factors such as geological environment, and particularly in the fully mechanized mining and tunneling processes, a certain place can be constructed, and serious safety accidents can be caused if the underground operation process is not predicted or monitored.
Because the current geological forecast is more traditional, such as manual observation or detection by using a detector or punching, and then summarizing various data and reporting, the mode is too labor-consuming and time-consuming, and is often interfered by various human factors, so that the front structure cannot be accurately judged. Therefore, in order to solve the technical problems, the application provides a geological forecast generating method based on natural language processing, which adopts natural language to process geological data and aims at solving the accuracy and the credibility of the address report content.
The preferred embodiments of the present application will be described below with reference to the accompanying drawings of the specification, it being understood that the preferred embodiments described herein are for illustration and explanation only, and are not intended to limit the present application, and embodiments and features of embodiments of the present application may be combined with each other without conflict.
Fig. 2 is a flow chart of a geological forecast generating method based on natural language processing according to an embodiment of the present application. As shown in fig. 2, the method may include:
step S210, geological data of the target area are acquired.
Wherein the geological data includes text data and spatial data.
Specifically, the geological prospecting instrument collects text data aiming at the geological condition of the target area. The collected text data may include: macroscopic aspects include various physical parameters of the earth structure, topography, stratum, geophysical field, rock and mineral, the content and distribution of chemical elements in soil and water areas, and the like; microscopic aspects include the composition of matter, structure and evolution characteristics of rock, mineral light sheets and flakes under the microscope, fission tracks of elements, and the like.
The GIS platform provides a bottom layer ore map analysis service to provide corresponding space data, and specifically, the GIS platform controls the display and the hiding of different layers and scale ore maps according to the report range and the comprehensive digging direction, so that the space data of a target area are thinned or omitted. In addition, the roadway is cut, and the trend or the existence of the structure of a part and the whole roadway can be clearly seen.
Step S220, respectively carrying out data preprocessing on the text data and the space data to obtain a first result corresponding to the text data and a second result corresponding to the space data.
Referring to fig. 3, in particular, the preprocessing process of the text data may include:
and 2-1, performing text cleaning on the text data to obtain a cleaning result.
The cleaning process removes useless symbols, language words and special structures to obtain corresponding cleaning results.
2-2, performing word segmentation on the cleaning result to generate a word segmentation result.
The process specifically may include: a. cutting the cleaning result to obtain a plurality of vocabulary sequences;
b. aiming at any vocabulary sequence, classifying and identifying the vocabulary sequence to obtain a target classifying and identifying, and identifying the word position of each character in the vocabulary sequence to obtain a target word position identification;
for example: the a-b process is a vocabulary sequence process for segmenting the cleaning result into semantic rationality and integrity. Each word occupies a certain word forming position (word position) when constructing a specific word, and in general, we consider that the word position of each word may include 4 cases: b (Begin), E (End), M (Middle), S (Single), the segmentation of a sentence can be converted into a process of tagging each word in the sentence.
For example: the vocabulary sequence is: the working surface is designed to be one kilometer in length.
After marking the word position of each character in the vocabulary sequence, obtaining: work B works M surface M to design M length M-S kiloB meters E.
In this way, a word position is assigned to each word in the sentence, that is, a label in the BEMS, so that we accomplish the goal of word segmentation.
Meanwhile, the vocabulary sequence is classified and identified, characteristic vocabularies are extracted from the vocabulary sequence, for example, the working face and the length are extracted from the 'working face design length of one kilometer', and the classification of the vocabulary sequence can be identified as the length of the working face.
In this way, a vocabulary sequence, classification of the vocabulary sequence, and each word in each vocabulary sequence are used to construct a semantic relationship network. According to the word relation network, accurate geological term description is provided for the identification and generation stage of the forecast processing stage. Because the machine can not directly recognize the association relationship between emotion and words in natural language, a semantic relationship network needs to be constructed, and a precise data basis is provided for subsequent data processing.
c. And determining a data set consisting of each vocabulary sequence, the corresponding target classification identifier of each vocabulary sequence and the target word position identifier of each character in each vocabulary sequence as a word segmentation result.
In some embodiments, in the word segmentation process, an emotion analysis algorithm is integrated, specifically, a vocabulary sequence is divided according to a target word position identifier in a word segmentation result, so that a plurality of words in the vocabulary sequence are obtained, and clustering analysis is performed among the words to obtain a plurality of clusters. Calculating a clustering center of each cluster to obtain a target word corresponding to the clustering center, matching the target word with a reference word in a configured emotion word dictionary to obtain a target reference word, and replacing the target reference word with the target word. Further, calculating the distance between each word in each cluster and the cluster center, and replacing the word with the corresponding word with the distance smaller than the preset distance with the target reference word. That is to say, the configured emotion word dictionary is a reference word corresponding to the coal mine personnel expression habit, and the mode can be integrated into the emotion analysis process, so that the description of the vocabulary sequence is more fit with the coal mine personnel expression habit.
2-3, determining target word segmentation with the same classification identification as each target keyword in the word segmentation result based on the configured target keywords.
In some embodiments, before determining the target word segmentation with the same classification identifier as each target keyword, the word segmentation result is subjected to standardized processing according to the configured words, sentences and paragraphs of the geological term base so as to enable the word segmentation result to meet the geological term standard. And then, feature extraction can be carried out on the standardized word segmentation result so as to retain the word segmentation result with the features, thereby eliminating useless words.
2-4, determining each target keyword, the corresponding target word and a data set formed by the relation between the target keywords and the corresponding target word as a first result.
The data preprocessing process of the spatial data specifically may include:
extracting target data comprising comprehensive digging directions and reporting ranges from the space data according to the digging plan;
the mining plan is information such as comprehensive mining direction, mining point position, inflection point position and the like which are planned in advance aiming at a target area.
Because the space data has a plurality of sources, such as a map, an engineering drawing, a planning drawing, aviation and remote sensing influences and the like, in order to analyze the space data more accurately, the feature extraction model is used for extracting the features of the target data, and the extracted features are subjected to vectorization conversion to obtain a second result.
The report content generated by the traditional AI is hard and inaccurate. The application refers to a target keyword, and content related to the keyword is fully analyzed to perform semantic and structural processing. Such as: the content to be reported is gas-related so that the analysis is based on the key word in the analysis of the historical first result and the historical second result.
And step S230, processing the first result and the second result by adopting a trained geological forecast model to generate a target geological forecast.
The training process of the geological forecast model specifically may include:
performing data preprocessing on the acquired historical geological data to obtain a historical first result and a historical second result; the historical geological data comprises historical text data and historical space data;
taking the historical first result and the historical second result as training samples and taking the historical geological forecast as a training label, training the deep learning model, and obtaining an initial geological forecast model;
in some embodiments, since coal mining has a certain risk, it is particularly important for the prediction event in the geological forecast result, in the training process of the geological forecast model, the selection of the training sample may include the occurrence time and the ending time of the historical occurrence event, the geological data change trend corresponding to the event duration, the historical meteorological data of the event duration, the historical meteorological data include the historical wind speed, the historical rainfall and the corresponding historical geological data change trend corresponding to the event duration, which are collected in the event duration according to the preset period (generally set to 10 s) and are collected in the event duration according to the preset period before the occurrence time (generally set to 10 min), in the area with the historical event occurrence area as the center (generally taking the most serious point of the occurrence event as the center) and the preset distance as the radius. The duration of the event, that is, the time from the beginning to the death of the historical event, may be calculated according to the occurrence time and the ending time of the historical event. And then, taking the historical wind speed, the historical rainfall and the corresponding historical geologic data change trend as training samples, taking the wind speed and the rainfall geologic data change trend as training labels, and training the deep learning model to obtain a geologic prediction model capable of carrying out advanced prediction and analysis on the geologic data (the historical first result at the moment comprises the historical meteorological data, and the first result should also comprise the corresponding meteorological data when the trained model is actually used). This way only illustrates the training process of geological and meteorological data, and based on this way, the acquisition of training samples can also be performed in the same way on geological data and related data, thus training the model. For example, coordinates of the historical mining points and geological data corresponding to the historical mining points are obtained as training samples, and events and geological data generated after the actual mining of the points are used as training labels to train the model.
Predicting a test sample by adopting an initial geological prediction model to obtain a test result;
calculating an actual report corresponding to the test result and the test sample to obtain prediction accuracy, wherein the method can comprise the following steps: converting the test result and the actual report into corresponding test result high-dimensional vectors and actual report high-dimensional vectors; converting the high-dimensional vector of the test result and the high-dimensional vector of the actual report into a low-dimensional vector of the corresponding test result and a low-dimensional vector of the actual report; and calculating cosine similarity between the low-dimensional vector of the test result and the actual report low-dimensional vector to obtain prediction accuracy.
And if the prediction precision reaches the expected precision, determining the initial geological prediction model as a geological prediction model.
If the prediction accuracy does not reach the expected accuracy, determining to perform repeated training on the initial geological report model so as to enable the prediction accuracy to reach the expected accuracy.
In some embodiments, the method for obtaining the forecast accuracy by operating the actual data corresponding to the test result and the test sample may further include:
and (3) performing effect evaluation on the geological forecast model by adopting a model effect evaluation algorithm to determine the accuracy of the geological forecast model.
Common effect evaluation algorithms may include mean absolute percent error (mean absolute percentage error, MAPE) to measure the relative error percentage between the true value and the generated value, and root mean square error (root mean square error, RMSE) to represent the root mean square error of the true value (actual data) and the generated value (test result). The smaller the MAPE and RMSE values, the higher the accuracy of the model test results. MAPE indexes are generally adopted for measurement in the prediction of the geological prediction model, so that the effect of model generation results can be intuitively shown.
The formula of the MAPE evaluation algorithm can be expressed as:
the formula of the RMSE evaluation algorithm may be expressed as:
wherein y is actual data, yhat is a test result, and n is the number of test results.
In the actual operation process, text information and table information in the actual data need to be converted into corresponding feature vectors for operation.
And finally, combining the images shown in fig. 4 and 5 to obtain a trained geological forecast model, and processing the first result and the second result by adopting the geological forecast model to generate a target geological forecast.
The target geological forecast includes a quantity portion, a first portion of which is shown in fig. 4 as a plan cross-section of the roadway, showing dimensional information in the roadway. And the second part is shown in fig. 5, and outputs data of coal seam structure, geological structure, top floor lithology, water enrichment, aquifer and gas, wherein the contents of each part comprise actual data and predicted contents. Specifically, the coal seam structure: 1. the coal bed belongs to No. 15 coal; coal quality: full moisture 5%; ash content 2%; 3% of total sulfur. 2. The trend of the coal bed is 1 degree, the trend of the coal bed is 2 degrees, the inclination angle of the coal bed is 4 degrees, the average coal thickness is 3 meters, and the burial depth of the coal bed is 7 meters. Geological structure: the forecasting area has 3 structures, the structure influence area is 528,228.53 square meters, the working face is predicted to be free of structures, the structures are not actually free, and the influence of hidden structures is not excluded. Top floor lithology and water-rich nature: the roof lithology mudstone and the floor lithology siltstone of the coal seam are subjected to strict construction measures during stoping, so that the roof side management and gas detection work are enhanced. Water content: the expected normal water inflow is 4m 3 /h, maximum water inflow of 8m 3 And/h. Gas: 1. absolute gas emission amount 3m 3 A/min; air distribution amount 3.3m 3 Per min, extraction yield 1.22m 3 And/min. 2. The ventilation department needs to strengthen ventilation management, check that the ventilation facilities in the area are perfect and reliable, and ensure sufficient air quantity; the gas inspection management work is enhanced, and the found problems are treated in time.
Since the geological forecast model provides multiple data type entries, such as: the method comprises the steps of comprehensively analyzing multi-element data, such as geodetic measurement data, tunneling disclosure data, geophysical prospecting, drilling detection data and the like; through a geological forecast model, contents corresponding to the target keywords can be obtained, such as: data such as mining face, scale, lithology, gas, hydrology, various types of structures, spatial position, size and the like. Especially for the non-extracted places, advanced forecast is carried out.
The application provides a geological forecast generation method based on natural language processing, which comprises the following steps: obtaining geological data of a target area, wherein the geological data comprises text data and space data; respectively carrying out data preprocessing on the text data and the space data to obtain a first result corresponding to the text data and a second result corresponding to the space data; and processing the first result and the second result by adopting the trained geological forecast model to generate a target geological forecast. The method is favorable for guiding production operation in advance. The model is combined with three-dimensional geology (space data), abnormal information is identified, extracted, generalized, tidied and complete geological forecast content is generated, and the accuracy of the content of geological forecast generated by the geological model can be evaluated according to actual mining conditions, so that the geological forecast model is fed back and optimized. The method can greatly improve the efficiency and accuracy of geological forecast.
Corresponding to the method, the embodiment of the application also provides a geological forecast generating device based on natural language processing, as shown in fig. 6, which comprises:
an acquisition unit 610 for acquiring geological data of a target region, the geological data including text data and spatial data;
a processing unit 620, configured to perform data preprocessing on the text data and the spatial data, respectively, to obtain a first result corresponding to the text data and a second result corresponding to the spatial data;
and processing the first result and the second result by adopting a trained geological forecast model to generate a target geological forecast.
The functions of each functional unit of the geological forecast generating device based on natural language processing provided in the foregoing embodiments of the present application may be implemented by the foregoing method steps, so specific working processes and beneficial effects of each unit in the geological forecast generating device based on natural language processing provided in the embodiments of the present application are not repeated herein.
The embodiment of the present application further provides an electronic device, as shown in fig. 7, including a processor 710, a communication interface 720, a memory 730, and a communication bus 740, where the processor 710, the communication interface 720, and the memory 730 complete communication with each other through the communication bus 740.
A memory 730 for storing a computer program;
processor 710, when executing the program stored on memory 730, performs the following steps:
obtaining geological data of a target area, wherein the geological data comprises text data and space data;
respectively carrying out data preprocessing on the text data and the space data to obtain a first result corresponding to the text data and a second result corresponding to the space data;
and processing the first result and the second result by adopting a trained geological forecast model to generate a target geological forecast.
The communication bus mentioned above may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, or the like. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
The communication interface is used for communication between the electronic device and other devices.
The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processing, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
Since the implementation manner and the beneficial effects of the solution to the problem of each device of the electronic apparatus in the foregoing embodiment may be implemented by referring to each step in the embodiment shown in fig. 2, the specific working process and the beneficial effects of the electronic apparatus provided in the embodiment of the present application are not repeated herein.
In yet another embodiment provided herein, a computer readable storage medium is provided, in which instructions are stored, which when run on a computer, cause the computer to perform a geological forecast generation method based on natural language processing as described in any of the above embodiments.
In yet another embodiment provided herein, there is also provided a computer program product containing instructions that, when run on a computer, cause the computer to perform a natural language processing based geological forecast generation method as described in any of the above embodiments.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, the present embodiments are intended to be construed as including the preferred embodiments and all such variations and modifications that fall within the scope of the embodiments herein.
It will be apparent to those skilled in the art that various modifications and variations can be made in the embodiments of the present application without departing from the spirit and scope of the embodiments of the present application. Thus, given that such modifications and variations of the embodiments in the present embodiments are within the scope of the embodiments and their equivalents, such modifications and variations are also intended to be included in the embodiments of the present application.
Claims (10)
1. A method for generating a geological forecast based on natural language processing, the method comprising:
obtaining geological data of a target area, wherein the geological data comprises text data and space data;
respectively carrying out data preprocessing on the text data and the space data to obtain a first result corresponding to the text data and a second result corresponding to the space data;
and processing the first result and the second result by adopting a trained geological forecast model to generate a target geological forecast.
2. The method of claim 1, wherein performing data preprocessing on the text data to obtain the first result comprises:
performing text cleaning on the text data to obtain a cleaning result;
performing word segmentation on the cleaning result to generate a word segmentation result;
determining target word segmentation with the same classification identifier as each target keyword in the word segmentation result based on the configured target keywords;
and determining the first result as a data set formed by each target keyword, the corresponding target word and the relation between the target keywords and the corresponding target word.
3. The method of claim 2, wherein the step of word segmentation of the cleaning result to obtain a word segmentation result comprises:
cutting the cleaning result to obtain a plurality of vocabulary sequences;
aiming at any vocabulary sequence, classifying and identifying the vocabulary sequence to obtain a target classifying and identifying, and identifying the word position of each character in the vocabulary sequence to obtain a target word position identification;
and determining a data set consisting of the vocabulary sequences, the target classification identifiers corresponding to the vocabulary sequences and the target word position identifiers of each character in the vocabulary sequences as a word segmentation result.
4. The method of claim 1, wherein performing data preprocessing on the spatial data to obtain the second result comprises:
extracting target data comprising comprehensive digging directions and reporting ranges from the space data according to a digging plan;
and vectorizing and converting the target data to obtain the second result.
5. The method of claim 1, wherein the training process of the geological forecast model comprises:
performing data preprocessing on the acquired historical geological data to obtain a historical first result and a historical second result; wherein the historical geological data comprises historical text data and historical space data;
training the deep learning model by taking the historical first result and the historical second result as training samples and taking the historical geological forecast as a training label to obtain an initial geological forecast model;
predicting a test sample by adopting the initial geological prediction model to obtain a test result;
calculating actual data corresponding to the test result and the test sample to obtain prediction accuracy;
and if the prediction precision reaches the expected precision, determining the initial geological prediction model as a geological prediction model.
6. The method of claim 5, wherein the actual data corresponding to the test result and the test sample are calculated to obtain a forecast accuracy;
converting the test result and the actual data into corresponding test result high-dimensional vectors and actual report high-dimensional vectors;
converting the high-dimensional vector of the test result and the actual reporting high-dimensional vector into a corresponding low-dimensional vector of the test result and an actual reporting low-dimensional vector;
and calculating cosine similarity between the low-dimensional vector of the test result and the actual report low-dimensional vector to obtain forecast accuracy.
7. A natural language processing-based geological forecast generation apparatus, the apparatus comprising:
the acquisition unit is used for acquiring geological data of the target area, wherein the geological data comprises text data and space data;
the processing unit is used for respectively carrying out data preprocessing on the text data and the space data to obtain a first result corresponding to the text data and a second result corresponding to the space data;
and processing the first result and the second result by adopting a trained geological forecast model to generate a target geological forecast.
8. The apparatus of claim 7, wherein the processing unit comprises a cleaning module, a word segmentation module, a determination module, and a composition module;
the cleaning module is used for cleaning the text of the text data to obtain a cleaning result;
the word segmentation module is used for carrying out word segmentation on the cleaning result to generate a word segmentation result;
the determining module is used for determining target word segmentation with the same classification identifier as each target keyword in the word segmentation result based on the configured target keywords;
the composition module is used for determining each target keyword, a corresponding target word and a data set formed by the relation between the target keywords and the corresponding target word as the first result.
9. An electronic device, characterized in that the electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are in communication with each other through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1-6 when executing a program stored on a memory.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored therein a computer program which, when executed by a processor, implements the method steps of any of claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311826368.9A CN117807220A (en) | 2023-12-27 | 2023-12-27 | Geological forecast generation method and device based on natural language processing and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311826368.9A CN117807220A (en) | 2023-12-27 | 2023-12-27 | Geological forecast generation method and device based on natural language processing and electronic equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117807220A true CN117807220A (en) | 2024-04-02 |
Family
ID=90419494
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311826368.9A Pending CN117807220A (en) | 2023-12-27 | 2023-12-27 | Geological forecast generation method and device based on natural language processing and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117807220A (en) |
-
2023
- 2023-12-27 CN CN202311826368.9A patent/CN117807220A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Demuzere et al. | LCZ Generator: a web application to create Local Climate Zone maps | |
Chen et al. | Landslide susceptibility mapping using feature fusion-based CPCNN-ML in Lantau Island, Hong Kong | |
Leng et al. | A hybrid data mining method for tunnel engineering based on real-time monitoring data from tunnel boring machines | |
CN110798805B (en) | Data processing method and device based on GPS track and storage medium | |
CN109242171A (en) | A kind of shield-tunneling construction Ground surface settlement method based on BIM and RS-SVR | |
CN106845496B (en) | Fine target identification method and system | |
CN114138923B (en) | Method for constructing geological map knowledge graph | |
CN112598192A (en) | Method and device for predicting vehicle entering logistics park, storage medium and terminal | |
CN113779880A (en) | Tunnel surrounding rock two-dimensional quality evaluation method based on advanced drilling data | |
Singh et al. | Roof bolt identification in underground coal mines from 3D point cloud data using local point descriptors and artificial neural network | |
CN116028499A (en) | Detection information generation method, electronic device, and computer-readable medium | |
CN117455237A (en) | Road traffic accident risk prediction method based on multi-source data | |
Tseng et al. | Scale and spatial distribution assessment of rainfall-induced landslides in a catchment with mountain roads | |
CN113326661B (en) | RS-XGboost-based tunnel advanced drilling quantitative interpretation method and device | |
CN114638300A (en) | Method, device and storage medium for identifying desserts of shale oil and gas reservoir | |
CN112802307B (en) | Geological monitoring and early warning method and system for geological investigation | |
CN113516060A (en) | Building space fusion discrimination method and device based on multi-temporal high-resolution data | |
CN117807220A (en) | Geological forecast generation method and device based on natural language processing and electronic equipment | |
CN110717618A (en) | Submarine hydrothermal sulfide resource evaluation and prediction method based on multi-index comprehensive elements | |
CN115758038A (en) | Stratum composite ratio calculation method, device, equipment and medium for shield construction | |
Lee et al. | Common patterns among different landslide susceptibility models of the same region | |
Zêzere et al. | Effects of landslide inventories uncertainty on landslide susceptibility modelling | |
Fengliang et al. | Updating Road Information in Open‐Pit Mines Using Truck Trajectories | |
Siljander et al. | Land use/land cover classification for the iron mining site of Kishushe, Kenya: A feasibility study of traditional and machine learning algorithms | |
CN117474340B (en) | Risk evaluation method and system for subway shield construction settlement |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |