Exploration report generation method and device, storage medium and electronic device

Abstract

The application discloses a kind of exploration report generation method and device, storage medium and electronic device, wherein, above-mentioned method includes: in the case where receiving exploration report generation request, target exploration data is extracted from basic geological data by first model, wherein, the exploration report generation request is used to request to generate the exploration report corresponding to the basic geological data, and the first model is obtained according to the public data in public exploration report Training;From report structure set, the report structure corresponding to the exploration report generation request is determined, wherein, the report structure set is obtained by extracting the report template of the public exploration report by second model;According to the target exploration data and the report structure, the exploration report is generated.The problem that the efficiency of writing report is poor and the quality is low in related art is solved by using the manual template writing mode of rock and soil geological exploration report.

Description

Technical Field

[0001] This invention relates to the field of geological engineering, and more specifically, to a method and apparatus for generating exploration reports, a storage medium, and an electronic device. Background Technology

[0002] With the continuous development of rock and soil geological exploration, the use of manual templates to write geological exploration reports has also revealed some drawbacks. These are as follows:

[0003] 1) Various techniques and methods exist in rock and soil geological exploration, and each project may require different techniques and processes. However, using templates manually limits developers' flexibility in selecting and adjusting according to specific project needs, making the templates difficult to adapt to the technical differences of different projects. 2) Due to the special nature of rock and soil geological exploration and the variability of projects, templates often cannot cover all possible situations. Therefore, developers often need to manually modify and adjust when writing reports using templates, increasing maintenance costs and workload. 3) Using templates manually requires developers to be familiar with the template's structure and specifications, as well as possess relevant domain knowledge. For developers unfamiliar with the template, learning and understanding its usage requires additional time and effort, increasing learning costs. 4) In rock and soil geological exploration, different projects may have personalized needs and special data processing methods. Using fixed templates often fails to meet these personalized needs, affecting the quality and accuracy of the reports. 5) When the standards or specifications for rock and soil geological exploration reports change, the templates need to be updated. However, due to the template-based nature, each update requires manual modification of the content of each report, increasing the complexity and risk of the work.

[0004] In summary, the current method of manually applying templates to write geotechnical exploration reports suffers from drawbacks such as technical differences between different exploration projects, increased maintenance and learning costs due to manual template application, poor adaptability of the templates, and untimely updates. These drawbacks result in low efficiency and low quality in report writing.

[0005] Currently, there is no effective solution to the problem that the use of manual templates in rock and soil geological exploration reports leads to poor efficiency and low quality in report writing.

[0006] Therefore, it is necessary to improve the relevant technology to overcome the aforementioned defects. Summary of the Invention

[0007] This invention provides a method and apparatus for generating exploration reports, a storage medium, and an electronic device to at least solve the problem of low efficiency and low quality in writing rock and soil geological exploration reports due to the manual use of templates.

[0008] According to one aspect of the present invention, a method for generating an exploration report is provided, comprising: upon receiving an exploration report generation request, extracting target exploration data from basic geological data using a first model, wherein the exploration report generation request requests the generation of an exploration report corresponding to the basic geological data, and the first model is trained based on publicly available data in publicly available exploration reports; determining the report structure corresponding to the exploration report generation request from a set of report structures, wherein the set of report structures is obtained by extracting report templates from publicly available exploration reports using a second model; and generating the exploration report based on the target exploration data and the report structure.

[0009] In an exemplary embodiment, before extracting target exploration data from basic geological data using a first model, the method further includes: determining a first standard corresponding to the publicly available data used when training the first model; and obtaining a second standard, wherein the second standard is a data standard allowed to be used in generating exploration reports within the current time period; determining whether the first standard and the second standard are the same; and updating the first model using the publicly available data and the second standard if the first standard and the second standard are different.

[0010] In an exemplary embodiment, updating the first model using the publicly available data and the second standard includes: determining the standard deviations corresponding to the first standard and the second standard; performing a data adjustment operation on the publicly available data based on the standard deviations to obtain adjusted data, wherein the adjustment operation includes at least one of the following: a data scaling operation and a data analysis operation; and training the first model using the adjusted data to update the first model.

[0011] In an exemplary embodiment, generating the exploration report based on the target exploration data and the report structure includes: determining a first data source containing sub-exploration data in the target exploration data, and determining a second data source corresponding to the report structure, wherein the target exploration data includes multiple types of sub-exploration data; matching the first data source and the second data source to obtain a matching result; and, if the matching result indicates that the first data source and the second data source are successfully matched, filling the sub-exploration data into the report structure using a preset processing algorithm.

[0012] In an exemplary embodiment, after matching the first data source and the second data source to obtain a matching result, the method further includes: if the matching result indicates that the first data source and the second data source failed to match, obtaining all unfilled report structures in the report structures, and obtaining unfilled sub-exploration data in the target exploration data; determining the correspondence between the unfilled report structures and the unfilled sub-exploration data; if the correspondence indicates that the unfilled report structures and the unfilled sub-exploration data are associated, filling the unfilled sub-exploration data into the unfilled report structures using a preset processing algorithm.

[0013] In an exemplary embodiment, after matching the first data source and the second data source to obtain a matching result, the method further includes: if the matching result indicates that the first data source and the second data source failed to match, determining the third source address corresponding to the unfilled report structure in all the report structures, and determining the fourth source address of the unfilled sub-exploration data in the target exploration data; determining whether the similarity between the third source address and the fourth source address is higher than a preset threshold; if the similarity is higher than the preset threshold, modifying the target source address that contains an error in the third source address and the fourth source address.

[0014] In an exemplary embodiment, determining the report structure corresponding to the exploration report generation request from a set of report structures includes: determining the report requirements for the exploration report recorded in the exploration report generation request, wherein the report requirements include: project requirements and target object requirements; extracting filtering fields from the report requirements using a field extraction algorithm, wherein the field extraction algorithm is trained based on multiple report requirements and the available fields corresponding to the multiple report requirements; and filtering the report structure from the set of report structures using the filtering fields.

[0015] According to another aspect of the present invention, an exploration report generation apparatus is also provided, comprising: an extraction module, configured to extract target exploration data from basic geological data using a first model upon receiving an exploration report generation request, wherein the exploration report generation request requests the generation of an exploration report corresponding to the basic geological data, and the first model is trained based on publicly available data in publicly available exploration reports; a determination module, configured to determine the report structure corresponding to the exploration report generation request from a set of report structures, wherein the set of report structures is obtained by extracting report templates from publicly available exploration reports using a second model; and a generation module, configured to generate the exploration report based on the target exploration data and the report structure.

[0016] According to another aspect of the present invention, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer program, wherein the computer program is configured to execute the above-described method for generating an exploration report when it is run.

[0017] According to another aspect of the present invention, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above-described method for generating the exploration report through the computer program.

[0018] This invention, upon receiving an exploration report generation request, extracts target exploration data from basic geological data using a first model. The exploration report generation request generates an exploration report corresponding to the basic geological data. The first model is trained based on publicly available data from publicly available exploration reports. The report structure corresponding to the exploration report generation request is determined from a set of report structures, obtained by extracting report templates from publicly available exploration reports using a second model. The exploration report is then generated based on the target exploration data and the report structure. In other words, the first model extracts the target exploration data, and after determining the report structure to be used in the exploration report, the exploration report is directly generated based on the target exploration data and the report structure. This technical solution solves the problem of low efficiency and quality in writing geotechnical exploration reports due to the manual application of templates. By using a model to extract data, intelligently determine the report structure, and intelligently generate the exploration report, the efficiency and quality of report generation are improved. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with the description thereof, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0020] Figure 1 This is a hardware structure block diagram of a computer terminal for the method of generating exploration reports according to an embodiment of the present invention;

[0021] Figure 2 This is a flowchart (a) of a method for generating an exploration report according to an embodiment of the present invention;

[0022] Figure 3 This is a flowchart (II) of a method for generating an exploration report according to an embodiment of the present invention;

[0023] Figure 4 This is a schematic diagram illustrating the data entry process for generating an exploration report according to an embodiment of the present invention.

[0024] Figure 5 This is a schematic diagram illustrating the technical means of generating an exploration report according to an embodiment of the present invention;

[0025] Figure 6 This is a structural block diagram of an exploration report generation device according to an embodiment of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] The methods and embodiments provided in this application can be executed on a computer terminal or similar computing device. Taking running on a computer terminal as an example, Figure 1 This is a hardware structure block diagram of the computer terminal for the exploration report generation method according to an embodiment of the present invention. (See diagram below.) Figure 1 As shown, a computer terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor (MPU) or a programmable logic device (PLD)) and a memory 104 for storing data are also shown. In one exemplary embodiment, the computer terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the computer terminal described above. For example, the computer terminal may also include components that are more complex than those described above. Figure 1The more or fewer components shown, or having the same Figure 1 Equivalent functions or ratios shown Figure 1 The functions shown have more different configurations.

[0029] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the exploration report generation method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0030] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider for the computer terminal. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0031] To address the aforementioned problems, this embodiment provides a method for generating exploration reports, applied to the aforementioned computer terminal. Figure 2 This is a flowchart (a) of a method for generating an exploration report according to an embodiment of the present invention, which includes the following steps:

[0032] Step S202: Upon receiving an exploration report generation request, target exploration data is extracted from basic geological data using a first model. The exploration report generation request generates an exploration report corresponding to the basic geological data. The first model is trained based on publicly available data in publicly available exploration reports.

[0033] Step S204: Determine the report structure corresponding to the exploration report generation request from the report structure set, wherein the report structure set is obtained by extracting the report template of the public exploration report through the second model;

[0034] Understandably, the first model is a machine learning model for data extraction trained on publicly available data, while the second model is a text structure recognition model.

[0035] Step S206: Generate the exploration report based on the target exploration data and the report structure.

[0036] Through the above steps, upon receiving an exploration report generation request, the first model extracts target exploration data from the basic geological data. The exploration report generation request generates an exploration report corresponding to the basic geological data. The first model is trained based on publicly available data from publicly available exploration reports. The report structure corresponding to the exploration report generation request is determined from a set of report structures, which is obtained by extracting report templates from publicly available exploration reports using a second model. The exploration report is then generated based on the target exploration data and the report structure. In other words, the first model extracts the target exploration data, and after determining the report structure to be used in the exploration report, the exploration report is directly generated based on the target exploration data and the report structure. This technical solution solves the problem of low efficiency and quality in writing geotechnical exploration reports due to the manual application of templates. By using a model to extract data, intelligently determine the report structure, and intelligently generate the exploration report, the efficiency and quality of report generation are improved.

[0037] Optionally, in the event of changes in national and local standards, the first model in this application embodiment can be updated according to the specific changes in the standards. The specific update scheme is as follows: determine the first standard corresponding to the publicly available data used when training the first model; and obtain the second standard, wherein the second standard is the data standard allowed to be used in generating exploration reports within the current time period; determine whether the first standard and the second standard are the same; if the first standard and the second standard are different, update the first model using the publicly available data and the second standard.

[0038] Specifically, the timing of updating the first model is optional. It can be updated each time an exploration report generation request is received; alternatively, it can be updated by constantly monitoring changes in national and local standards and updating the first model as soon as changes occur. In this embodiment, the first standard is the national and local standard used when generating the publicly available data, and the second standard is the national and local standard used in the current time period.

[0039] Furthermore, updating the first model using the publicly available data and the second standard includes: determining the standard deviations corresponding to the first standard and the second standard; performing data adjustment operations on the publicly available data based on the standard deviations to obtain adjusted data, wherein the adjustment operations include at least one of the following: data scaling operations and data analysis operations; and training the first model using the adjusted data to update the first model.

[0040] Specifically, changes in national and local standards may lead to changes in the processing methods of basic geological data, such as requiring the use of new data processing methods or algorithms; they may also lead to changes in the interpretation and evaluation methods of basic geological data. In this case, the standard deviations of the first and second standards can be determined, and the publicly available data can be adjusted according to the standard deviations. Methods for obtaining the standard deviations include, but are not limited to: processing the same basic geological data using the processing methods required by the first and second standards respectively, and comparing the processing results, thus determining the standard deviation that should be used to adjust the publicly available data.

[0041] Step S206 can be implemented in various ways. In one optional implementation, generating the exploration report based on the target exploration data and the report structure includes: determining a first data source containing the sub-exploration data in the target exploration data, and determining a second data source corresponding to the report structure, wherein the target exploration data includes multiple types of the sub-exploration data; matching the first data source and the second data source to obtain a matching result; and, if the matching result indicates that the first data source and the second data source are successfully matched, filling the sub-exploration data into the report structure using a preset processing algorithm.

[0042] Optionally, the data source in this application can be understood as a data address. The target exploration data extracted by the first model includes various types of sub-exploration data, and different types of sub-exploration data will be stored at the data source location corresponding to that type of data. Furthermore, after the second model extracts the report structure set, the report structures in the report structure set will be specifically linked to the data source location where that report structure should be filled. Therefore, by matching the first data source and the second data source, the sub-exploration data can be filled into the corresponding report structure.

[0043] Optionally, before populating the report structure with sub-exploration data, at least one of the following determination steps may be performed: check whether the sub-exploration data contains all the fields required by the report structure, ensuring that no fields are missing; check whether the report structure can accommodate the size and format of the sub-exploration data, such as whether the report structure can accommodate the character length in the sub-exploration data, whether it supports special characters in the sub-exploration data, such as whether the report structure should be filled with image data, and whether the corresponding sub-exploration data is image data; check whether the values ​​of the sub-exploration data conform to the data type and constraints of the fields in the report structure, such as whether they conform to the date format and whether they conform to the numerical range.

[0044] In an exemplary embodiment, after matching the first data source and the second data source to obtain a matching result, the method further includes: if the matching result indicates that the first data source and the second data source failed to match, obtaining all unfilled report structures in the report structures, and obtaining unfilled sub-exploration data in the target exploration data; determining the correspondence between the unfilled report structures and the unfilled sub-exploration data; if the correspondence indicates that the unfilled report structures and the unfilled sub-exploration data are associated, filling the unfilled sub-exploration data into the unfilled report structures using a preset processing algorithm.

[0045] In cases where the data sources do not match, the unfilled report structure and the unfilled sub-exploration data can be directly obtained. A correspondence between the two can be determined through methods such as field mapping. Specifically, the report structure may have a report structure name and type, and the name and type may include relevant data filling indicator fields, such as "section view." If the unfilled sub-exploration data also contains a "section view" field, then the fields match, and the data can be matched and filled.

[0046] Furthermore, after matching the first data source and the second data source to obtain a matching result, the method further includes: if the matching result indicates that the first data source and the second data source failed to match, determining the third source address corresponding to the unfilled report structure in all the report structures, and determining the fourth source address of the unfilled sub-exploration data in the target exploration data; determining whether the similarity between the third source address and the fourth source address is higher than a preset threshold; if the similarity is higher than the preset threshold, modifying the target source address with errors in the third source address and the fourth source address.

[0047] It should be noted that in the event of a matching failure, the data source verification and the matching of the unfilled parts (i.e., the unfilled report structure and the unfilled sub-exploration data) can be performed simultaneously or sequentially, and this application embodiment does not limit this.

[0048] It is understandable that, when the data source corresponds to a specific data address, the reason for the matching failure may be that a certain byte in the data address is incorrect. Therefore, the similarity matching method can determine whether there is a byte error in the data address during transmission, storage, copying, etc.

[0049] Optionally, if the similarity is below a preset threshold, it is necessary to verify whether the report structure selection is reasonable and whether the target exploration data extracted by the first model failed to be saved, resulting in loss or incorrect saving. If the similarity is below the preset threshold, technical personnel can be instructed to verify the first model, the second model, the report structure set, the data sources linked to the report structure set, the target exploration data, and the data sources linked to the target exploration data. Specific verification can be performed using logs generated during the operation of this application's embodiments.

[0050] In an exemplary embodiment, determining the report structure corresponding to the exploration report generation request from a set of report structures includes: determining the report requirements for the exploration report recorded in the exploration report generation request, wherein the report requirements include: project requirements and target object requirements; extracting filtering fields from the report requirements using a field extraction algorithm, wherein the field extraction algorithm is trained based on multiple report requirements and the available fields corresponding to the multiple report requirements; and filtering the report structure from the set of report structures using the filtering fields.

[0051] Optionally, the report structure set in this application embodiment may also store a complete report template including a specific report structure for direct selection.

[0052] Obviously, the embodiments described above are merely some embodiments of the present invention, and not all embodiments. To better understand the above-described method for generating exploration reports, the process is described below with reference to optional embodiments, but this is not intended to limit the technical solutions of the embodiments of the present invention. Specifically:

[0053] To address the drawbacks of traditional manual template-based writing of geotechnical exploration reports, this application provides an optional embodiment of an artificial intelligence (AI) standardization method for geological engineering exploration information. The aim is to combine existing geological engineering exploration technologies with artificial intelligence, and through configuring relevant fields, achieve standardized processing of geological engineering exploration information, thereby reducing exploration costs and improving efficiency. The method provided by this optional embodiment eliminates the need for increased learning and project maintenance costs associated with using different geological engineering exploration technology systems. Compared to traditional single-technology systems, it eliminates redundant configurations, making geological engineering exploration information processing more efficient and reliable. It enables intelligent processing of geological engineering exploration information, providing accurate and consistent data results and reliable support for decision-making in geological engineering projects.

[0054] Specifically, optional embodiments of this application utilize technologies such as machine learning and natural language processing to automatically analyze and process rock and soil geological exploration data, and generate high-quality, personalized reports. For example... Figure 3 As shown, the optional embodiments of this application are implemented through the following steps:

[0055] Step S31: Intelligent Data Analysis: Intelligent analysis of rock and soil geological exploration data is performed using machine learning algorithms, such as deep learning and data mining techniques. This involves constructing suitable models to process the input data through feature extraction, data cleaning, and data transformation, specifically... Figure 4 As shown, this method aims to obtain information on geological conditions, geotechnical parameters, and geological structures, including geological exploration data, geotechnical parameters, and geological structures. Utilizing big data analytics and data mining techniques, valuable information is extracted from massive amounts of data, providing accurate and comprehensive data support for report generation.

[0056] Such as Figure 3 As shown, the data processing center processes the remote sensing mapping field point locations and soil layer experimental data. The processing includes, but is not limited to, mapping the points using a point processing engine and generating soil layer cross-sectional analysis maps through soil layer data processing. The processed data is then saved to the data warehouse.

[0057] Step S32: Report Structure Definition: Define the report structure and content according to the requirements and specifications for geotechnical geological exploration reports. Define the various parts of the report and set corresponding report templates. These templates include geological descriptions, data result analysis, recommendations, and predictions to meet the needs of different projects and industry standards.

[0058] The optional embodiments of this application can also be customized: the system provides a user interface that allows for customization based on user needs and specific project requirements. Users can set specific report requirements, specifications, and formats, and select report templates and styles suitable for specific projects. The system will then generate compliant reports based on the user's customized needs, combined with an automated report generation process, improving the adaptability and accuracy of the reports.

[0059] Furthermore, such as Figure 3 As shown, a basic report template can be obtained by creating a custom template or importing a template, and by annotating the template.

[0060] Step S33: Automatic Report Generation: Based on the analysis results and the preset report structure, using Natural Language Processing (NLP) and text generation technologies, the various parts of the geotechnical exploration report are automatically generated according to the data analysis results and the preset report structure. Through data transformation and language model generation, the analyzed data is transformed into clear and easy-to-read report content. During the generation process, techniques such as template filling, keyword extraction, and summary generation can be considered to ensure the accuracy and comprehensibility of the report.

[0061] Import the data from the data warehouse into the basic report template prepared in step S32, perform data matching, and determine whether the matching is successful. Matching can include overall template matching, or matching each structure in the template (equivalent to the report structure in the above embodiment) with the corresponding data (equivalent to the sub-exploration data in the above embodiment).

[0062] If a match is successful, the AI ​​recognition engine performs operations such as plane filling, profile filling, data filling, and specification referencing to populate the data into the basic report template, resulting in the final exploration report.

[0063] The technical means used in the implementation of the optional embodiments of this application are as follows: Figure 5 As shown.

[0064] Furthermore, through the optional embodiments of this application, users can quickly and accurately generate high-quality reports, reducing maintenance and learning costs. At the same time, the personalized customization functions provided by the optional embodiments of this application meet the needs of different projects and industries, improving the efficiency and quality of rock and soil geological exploration work.

[0065] Furthermore, optional embodiments of this application include: achieving efficient and accurate standardized processing of geological engineering exploration information through the flexible application of different geological data processing technologies and artificial intelligence technologies; adopting a universal configuration, combining the learning of national and local standards with differentiated data to produce standardized geological exploration reports; significantly avoiding human errors caused by repeated manual report modifications and reducing the time spent on repeated modifications of geological exploration reports; flexibly adapting to national and local standards and providing efficient standardized processing capabilities to meet the diverse needs of geological engineering exploration information processing; having a wide range of applications, including but not limited to the collection, cleaning, analysis, modeling, and visualization of geological exploration data; and providing innovative solutions for the standardized processing of geological engineering exploration information by fully utilizing artificial intelligence and data processing technologies, thereby improving efficiency, accuracy, and reliability.

[0066] In summary, the optional embodiments of this application employ key technologies such as machine learning, natural language processing, and text generation, combined with the characteristics of rock and soil geological exploration data and report requirements, to achieve an automated and intelligent report generation process. Through deep learning models and language models, the system can quickly and accurately analyze data and generate high-quality reports; users can customize the system to meet the needs of different projects. Therefore, the optional embodiments of this application provide an effective solution for rock and soil geological exploration work, improving work efficiency and report quality.

[0067] This embodiment also provides an exploration report generation apparatus, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0068] Figure 6 This is a structural block diagram of an exploration report generation apparatus according to an embodiment of the present invention, the apparatus comprising:

[0069] Extraction module 62 is used to extract target exploration data from basic geological data through a first model when an exploration report generation request is received. The exploration report generation request is used to generate an exploration report corresponding to the basic geological data. The first model is trained based on publicly available data in publicly available exploration reports.

[0070] The determination module 64 is used to determine the report structure corresponding to the exploration report generation request from the report structure set, wherein the report structure set is obtained by extracting the report template of the public exploration report through the second model;

[0071] The generation module 66 is used to generate the exploration report based on the target exploration data and the report structure.

[0072] Using the aforementioned device, upon receiving an exploration report generation request, target exploration data is extracted from basic geological data using a first model. The exploration report generation request generates an exploration report corresponding to the basic geological data. The first model is trained based on publicly available data from publicly available exploration reports. The report structure corresponding to the exploration report generation request is determined from a set of report structures, which is obtained by extracting report templates from publicly available exploration reports using a second model. The exploration report is then generated based on the target exploration data and the report structure. In other words, the first model extracts the target exploration data, and after determining the report structure to be used in the exploration report, the exploration report is directly generated based on the target exploration data and the report structure. This technical solution solves the problem of low efficiency and quality in writing geotechnical exploration reports due to the manual application of templates. By using a model to extract data, intelligently determining the report structure, and intelligently generating the exploration report, the efficiency and quality of report generation are improved.

[0073] In an exemplary embodiment, the apparatus further includes an update module, configured to determine a first standard corresponding to the publicly available data used when training the first model; and to obtain a second standard, wherein the second standard is a data standard permitted for generating exploration reports within the current time period; determine whether the first standard and the second standard are the same; and update the first model using the publicly available data and the second standard if the first standard and the second standard are different.

[0074] In an exemplary embodiment, the update module is further configured to determine the standard deviations corresponding to the first standard and the second standard; perform data adjustment operations on the publicly available data according to the standard deviations to obtain adjusted data, wherein the adjustment operations include at least one of the following: data scaling operations and data analysis operations; and train the first model using the adjusted data to update the first model.

[0075] In an exemplary embodiment, the generation module 66 is further configured to determine a first data source containing the sub-exploration data in the target exploration data, and to determine a second data source corresponding to the report structure, wherein the target exploration data includes multiple types of the sub-exploration data; match the first data source and the second data source to obtain a matching result; and, if the matching result indicates that the first data source and the second data source are successfully matched, fill the sub-exploration data into the report structure using a preset processing algorithm.

[0076] In an exemplary embodiment, the generation module 66 is further configured to: obtain all unfilled report structures in the report structures and obtain unfilled sub-exploration data in the target exploration data when the matching result indicates that the first data source and the second data source fail to match; determine the correspondence between the unfilled report structures and the unfilled sub-exploration data; and, when the correspondence indicates that the unfilled report structures and the unfilled sub-exploration data are associated, fill the unfilled sub-exploration data into the unfilled report structures using a preset processing algorithm.

[0077] In an exemplary embodiment, the generation module 66 is further configured to, when the matching result indicates that the first data source and the second data source fail to match, determine the third source address corresponding to the unfilled report structure in all the report structures, and determine the fourth source address of the unfilled sub-exploration data in the target exploration data; determine whether the similarity between the third source address and the fourth source address is higher than a preset threshold; and, if the similarity is higher than the preset threshold, modify the target source address that contains an error in the third source address and the fourth source address.

[0078] In an exemplary embodiment, the determining module 64 is further configured to determine the reporting requirements for the exploration report recorded in the exploration report generation request, wherein the reporting requirements include: project requirements and target object requirements; extract filtering fields from the reporting requirements using a field extraction algorithm, wherein the field extraction algorithm is trained based on multiple reporting requirements and the available fields corresponding to the multiple reporting requirements; and filter the report structure from the report structure set using the filtering fields.

[0079] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.

[0080] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0081] S1, Upon receiving an exploration report generation request, target exploration data is extracted from basic geological data using a first model. The exploration report generation request generates an exploration report corresponding to the basic geological data. The first model is trained based on publicly available data in publicly available exploration reports.

[0082] S2, determine the report structure corresponding to the exploration report generation request from the report structure set, wherein the report structure set is obtained by extracting the report template of the public exploration report through the second model;

[0083] S3, Generate the exploration report based on the target exploration data and the report structure.

[0084] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0085] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0086] Embodiments of the present invention also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0087] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0088] S1, Upon receiving an exploration report generation request, target exploration data is extracted from basic geological data using a first model. The exploration report generation request generates an exploration report corresponding to the basic geological data. The first model is trained based on publicly available data in publicly available exploration reports.

[0089] S2, determine the report structure corresponding to the exploration report generation request from the report structure set, wherein the report structure set is obtained by extracting the report template of the public exploration report through the second model;

[0090] S3, Generate the exploration report based on the target exploration data and the report structure.

[0091] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0092] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0093] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0094] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for generating an exploration report, characterized in that, include: Upon receiving an exploration report generation request, target exploration data is extracted from basic geological data using a first model. The exploration report generation request generates an exploration report corresponding to the basic geological data. The first model is trained based on publicly available data in publicly available exploration reports. The report structure corresponding to the exploration report generation request is determined from the report structure set, wherein the report structure set is obtained by extracting the report template of the public exploration report through the second model; The exploration report is generated based on the target exploration data and the report structure, wherein, before extracting the target exploration data from the basic geological data using the first model, the method further includes: Determine a first standard corresponding to the publicly available data used when training the first model; and obtain a second standard, wherein the second standard is the data standard allowed to be used in generating exploration reports within the current time period; Determine whether the first standard and the second standard are the same; In cases where the first standard and the second standard differ, the first model is updated using the publicly available data and the second standard. Updating the first model using the publicly available data and the second standard includes: Determine the standard deviations corresponding to the first standard and the second standard; The publicly available data is adjusted according to the standard deviation to obtain adjusted data, wherein the adjustment operation includes at least one of the following: data scaling operation, data analysis operation; The first model is trained using the adjusted data to update the first model.

2. The method according to claim 1, characterized in that, The exploration report is generated based on the target exploration data and the report structure, including: The first data source containing the sub-exploration data in the target exploration data is determined, and the second data source corresponding to the report structure is determined, wherein the target exploration data includes multiple types of the sub-exploration data; Match the first data source and the second data source to obtain the matching result; If the matching result indicates that the first data source and the second data source are successfully matched, the sub-exploration data is filled into the report structure using a preset processing algorithm.

3. The method according to claim 2, characterized in that, After matching the first data source and the second data source to obtain the matching result, the method further includes: If the matching result indicates that the first data source and the second data source fail to match, obtain all unfilled report structures in the report structures, and obtain the unfilled sub-exploration data in the target exploration data; Determine the correspondence between the unfilled report structure and the unfilled sub-exploration data; When the correspondence indicates that there is a relationship between the unfilled report structure and the unfilled sub-exploration data, the unfilled sub-exploration data is filled into the unfilled report structure using a preset processing algorithm.

4. The method according to claim 2, characterized in that, After matching the first data source and the second data source to obtain the matching result, the method further includes: If the matching result indicates that the first data source and the second data source fail to match, determine the third source address corresponding to the unfilled report structure in all the report structures, and determine the fourth source address of the unfilled sub-exploration data in the target exploration data; Determine whether the similarity between the third source address and the fourth source address is higher than a preset threshold; If the similarity is higher than a preset threshold, modify the target source address that contains an error in the third source address and the fourth source address.

5. The method according to claim 1, characterized in that, Determine the report structure corresponding to the exploration report generation request from the set of report structures, including: Determine the reporting requirements for the exploration report as recorded in the exploration report generation request, wherein the reporting requirements include: project requirements and target object requirements; The filtering fields are extracted from the report requirements using a field extraction algorithm, wherein the field extraction algorithm is trained based on multiple report requirements and the available fields corresponding to the multiple report requirements; The report structure is filtered from the set of report structures using the filter fields.

6. An apparatus for generating an exploration report, characterized in that, include: An extraction module is used to extract target exploration data from basic geological data using a first model when an exploration report generation request is received. The exploration report generation request is used to generate an exploration report corresponding to the basic geological data. The first model is trained based on publicly available data in publicly available exploration reports. The determination module is used to determine the report structure corresponding to the exploration report generation request from the report structure set, wherein the report structure set is obtained by extracting the report template of the public exploration report through the second model; The generation module is used to generate the exploration report based on the target exploration data and the report structure. The device further includes an update module, configured to: determine a first standard corresponding to the publicly available data used in training the first model; and obtain a second standard, wherein the second standard is a data standard permitted for generating exploration reports within the current time period; determine whether the first standard and the second standard are the same; and update the first model using the publicly available data and the second standard if the first standard and the second standard are different. The update module is further configured to determine the standard deviations corresponding to the first standard and the second standard; perform data adjustment operations on the publicly available data according to the standard deviations to obtain adjusted data, wherein the adjustment operations include at least one of the following: data scaling operation, data analysis operation; and train the first model using the adjusted data to update the first model.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method described in any one of claims 1 to 5.

8. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method described in any one of claims 1 to 5 through the computer program.

Images