Intelligent prospecting method based on multi-source information fusion and physical-data dual drive

Abstract

The invention relates to the technical field of prospecting, in particular to an intelligent prospecting method based on multi-source information fusion and physical-data dual-drive, and the method comprises the steps: obtaining a target multi-source information database based on the granularity and reliability of multi-source information data in the target multi-source information database; performing complementary fusion on the multi-source information data according to the matched fusion level to obtain a multi-source information complementary fusion result; extracting mineral resource distribution information of the target area according to a multi-source information complementary fusion result, and generating an earth crust mineral resource refined distribution diagram of the target area by using the mineral resource distribution information; and based on the target multi-source information database and the earth crust mineral resource refined distribution map, generating a mineral resource information inference result of the target area by using a target identification system. According to the method, the target identification system can be utilized to perform deep mining on the earth crust mineral resource refined distribution map drawn based on the multi-source information, the mineral resource information inference result is obtained, the earth crust mineral resource exploration efficiency can be effectively improved, the resource exploration cost can be reduced, and strategic mineral resources can be accurately locked.

Description

Technical Field

[0001] The present application relates to the field of mineral prospecting technology, and in particular to an intelligent mineral prospecting method based on multi-source information fusion and physical-data dual drive. Background Art

[0002] Mineral resources are an important foundation for supporting the economic development of human society and are widely used in energy, transportation, construction, electronics, environmental protection and other fields. With the rapid development of the global economy and the continuous growth of population, the demand for mineral resources continues to rise, resulting in the development and utilization of mineral resources becoming one of the major issues facing the world today.

[0003] Among the related technologies, traditional mineral exploration methods mainly rely on physical and chemical exploration methods, such as geophysical exploration (electrical, magnetic, gravity, etc.), geochemical exploration, and drilling exploration. Although these methods can provide information on the location and type of ore bodies to a certain extent, they often face defects such as limited exploration accuracy, high investment costs, and long time periods. In addition, the spatial distribution of mineral resources is affected by the complexity of the geological environment, and the formation process of mineral deposits is closely related to regional geological evolution, which makes it difficult for a single data source and traditional methods to fully and accurately reveal the potential distribution patterns of mineral deposits.

[0004] However, the mineral exploration methods in related technologies lack exploration accuracy when faced with complex geological conditions. In addition, the exploration costs are high and the efficiency is low. They are easily affected by various environmental factors and it is difficult to fully and accurately reveal the potential distribution patterns of mineral deposits. They cannot meet the mineral exploration needs under the continuous development of the economy and society, and this problem needs to be solved urgently. Summary of the invention

[0005] The present application provides an intelligent prospecting method based on multi-source information fusion and physical-data dual drive to solve the problems that the mineral exploration methods in related technologies lack exploration accuracy when facing complex geological conditions, and the exploration costs are high while the efficiency is low. It is easy to be affected by various environmental factors, and it is difficult to fully and accurately reveal the potential distribution patterns of mineral deposits, and it cannot meet the mineral exploration needs under the continuous development of the economy and society.

[0006] The first aspect of the present application provides an intelligent prospecting method based on multi-source information fusion and physical-data dual drive, comprising the following steps: based on the granularity and reliability of the multi-source information data in the target multi-source information database, matching the fusion level corresponding to the multi-source information data, and complementary fusion of the multi-source information data according to the fusion level to obtain a multi-source information complementary fusion result; extracting the mineral distribution information of the target area according to the multi-source information complementary fusion result, and using the mineral distribution information to generate a refined distribution map of the crustal mineral deposits in the target area; based on the target multi-source information database and the refined distribution map of the crustal mineral deposits, using a target recognition system based on physical-data dual drive to generate a mineral information inference result of the target area.

[0007] Optionally, in one embodiment of the present application, before matching the fusion level corresponding to the multi-source information data based on the granularity and reliability of the multi-source information data in the target multi-source information database, it also includes: collecting initial target multi-source information, and preprocessing the initial target multi-source information to obtain the target multi-source information that meets preset processing conditions; and constructing the target multi-source information database using the target multi-source information.

[0008] Optionally, in one embodiment of the present application, before using the target recognition system based on physical-data dual drive to generate the mineral information inference result, it also includes: obtaining knowledge rules that meet preset conditions based on target theoretical information and / or historical experience data, and constructing physical constraints based on the knowledge rules, so as to construct the physical drive in the target recognition system based on physical-data dual drive according to the knowledge rules and the physical constraints; using the target neural network and the multi-source information data to train the initial recognition system to construct the data drive in the target recognition system based on physical-data dual drive; and determining the target recognition system based on physical-data dual drive through the physical drive and the data drive.

[0009] Optionally, in one embodiment of the present application, based on the target multi-source information database and the refined distribution map of crustal mineral deposits, the target recognition system based on physical-data dual drive is used to generate the mineral deposit information inference result of the target area, including: based on the target multi-source information database, the target recognition system based on physical-data dual drive is used to obtain the spatial characteristics, ore body evolution information, mineral resource reserve estimation results, abnormal area information, and potential position prediction results of the target area; based on the spatial characteristics, the ore body evolution information, the mineral resource reserve estimation results, the abnormal area information, the potential position prediction results of the ore body and the refined distribution map of crustal mineral deposits, the target recognition system based on physical-data dual drive is used to generate the mineral deposit information inference result of the target area.

[0010] Optionally, in one embodiment of the present application, the fusion level includes at least one of data level fusion, feature level fusion, and decision level fusion.

[0011] Optionally, in one embodiment of the present application, the target recognition system based on physics-data dual drive is a target AI-assisted recognition system.

[0012] The second aspect of the present application provides an intelligent prospecting device based on multi-source information fusion and physical-data dual drive, including: a fusion module, which is used to match the fusion level corresponding to the multi-source information data based on the granularity and reliability of the multi-source information data in the target multi-source information database, and complementary fuse the multi-source information data according to the fusion level to obtain a multi-source information complementary fusion result; a first generation module, which is used to extract the mineral distribution information of the target area according to the multi-source information complementary fusion result, and use the mineral distribution information to generate a refined distribution map of the crustal mineral deposits in the target area; a second generation module, which is used to generate a mineral information inference result of the target area based on the target multi-source information database and the refined distribution map of the crustal mineral deposits using a target recognition system based on physical-data dual drive.

[0013] Optionally, in one embodiment of the present application, it also includes: a processing module, which is used to collect initial target multi-source information and pre-process the initial target multi-source information before matching the fusion level corresponding to the multi-source information data based on the granularity and reliability of the multi-source information data in the target multi-source information database, so as to obtain the target multi-source information that meets preset processing conditions; a first construction module, which is used to construct the target multi-source information database using the target multi-source information.

[0014] Optionally, in one embodiment of the present application, it also includes: a second construction module, which is used to obtain knowledge rules that meet preset conditions based on target theoretical information and / or historical experience data before generating the mineral information inference result using the target recognition system based on physical-data dual drive, and construct physical constraints based on the knowledge rules, so as to construct the physical drive in the target recognition system based on physical-data dual drive according to the knowledge rules and the physical constraints; a third construction module, which is used to train the initial recognition system using the target neural network and the multi-source information data, so as to construct the data drive in the target recognition system based on physical-data dual drive; a determination module, which is used to determine the target recognition system based on physical-data dual drive through the physical drive and the data drive.

[0015] Optionally, in one embodiment of the present application, the second generation module includes: an acquisition unit, which is used to acquire the spatial characteristics, ore body evolution information, mineral resource reserve estimation results, abnormal area information, and potential position prediction results of the target area based on the target multi-source information database and using the target identification system based on physical and data dual drive; a generation unit, which is used to generate the mineral information inference results of the target area based on the spatial characteristics, the ore body evolution information, the mineral resource reserve estimation results, the abnormal area information, the potential position prediction results of the ore body and the refined distribution map of crustal mineral deposits and using the target identification system based on physical and data dual drive.

[0016] Optionally, in one embodiment of the present application, the fusion level includes at least one of data level fusion, feature level fusion, and decision level fusion.

[0017] Optionally, in one embodiment of the present application, the target recognition system based on physics-data dual drive is a target AI-assisted recognition system.

[0018] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent prospecting method based on multi-source information fusion and physical-data dual drive as described in the above embodiment.

[0019] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above-mentioned intelligent prospecting method based on multi-source information fusion and physical-data dual drive.

[0020] The fifth aspect of the present application provides a computer program product, including a computer program, which, when executed, is used to implement the above-mentioned intelligent prospecting method based on multi-source information fusion and physical-data dual drive.

[0021] The embodiments of the present application can extract mineral distribution information from multi-source information data to draw a refined distribution map of crustal mineral deposits, and can use a target recognition system based on physical-data dual drive to deeply mine the refined distribution map of crustal mineral deposits to obtain mineral information inference results. As a result, it is possible to use multi-source information fusion technology to fuse massive multi-source information to obtain a detailed distribution map of crustal mineral deposits. Multi-source information fusion technology can use AI to effectively reduce exploration costs and time; the physical-expert learning module introduced by AI in the target recognition system can realize the effective learning of mineralization knowledge rules, and as a physical constraint, it realizes knowledge-driven, that is, physical-driven. Combined with data-driven means, through continuous training and optimization, the prediction accuracy of mineral information inference (prediction) results can be gradually improved, so that effective mineral deposit prediction and resource evaluation can be carried out in complex geological environments, and potential geological information can be extracted from multiple dimensions and different data sources, the spatial distribution pattern of mineral deposits can be identified, and the grade changes of ore bodies can be predicted, thereby providing theoretical support and technical guidance for the exploration, evaluation and development of mineral resources, improving the efficiency of crustal mineral resource exploration, reducing resource exploration costs, accurately locking in strategic mineral resources, and making strategic layouts for related tasks in advance. This solves the problems that the mineral exploration methods in related technologies lack exploration accuracy when faced with complex geological conditions, have high exploration costs and low efficiency, are easily affected by various environmental factors, find it difficult to fully and accurately reveal the potential distribution patterns of mineral deposits, and cannot meet the mineral exploration needs under the continuous development of the economy and society.

[0022] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which: Figure 1 A schematic diagram of the framework of an intelligent prospecting system according to an embodiment of the present application; Figure 2 A flowchart of an intelligent prospecting method based on multi-source information fusion and physical-data dual drive provided according to an embodiment of the present application; Figure 3 A schematic diagram of the structure of an intelligent prospecting device based on multi-source information fusion and physical-data dual drive according to an embodiment of the present application; Figure 4 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application.

[0024] Reference numerals: 10-Intelligent prospecting device based on multi-source information fusion and physical-data dual drive: 100-fusion module, 200-first generation module and 300-second generation module; 401-memory, 402-processor and 403-communication interface. DETAILED DESCRIPTION

[0025] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0026] The following describes the intelligent prospecting method based on multi-source information fusion and physical-data dual drive of the embodiment of the present application with reference to the accompanying drawings. In view of the fact that the mineral exploration method in the related art mentioned in the above background technology lacks exploration accuracy when facing complex geological conditions, and the exploration cost is high while the efficiency is low, it is easily affected by various environmental factors, and it is difficult to fully and accurately reveal the potential distribution law of the mineral deposit, and it is unable to meet the problem of mineral exploration needs under the continuous development of the economy and society, the present application provides an intelligent prospecting method based on multi-source information fusion and physical-data dual drive, in which the mineral distribution information can be extracted from the multi-source information data to draw a refined distribution map of the crustal mineral deposits, and the target recognition system based on physical-data dual drive can be used to deeply mine the refined distribution map of the crustal mineral deposits to obtain the mineral information inference result. As a result, it is possible to use multi-source information fusion technology to fuse massive multi-source information to obtain a detailed distribution map of crustal mineral deposits. Multi-source information fusion technology can use AI to effectively reduce exploration costs and time; the physical-expert learning module introduced by AI in the target recognition system can realize the effective learning of mineralization knowledge rules, and as a physical constraint, it realizes knowledge-driven, that is, physical-driven. Combined with data-driven means, through continuous training and optimization, the prediction accuracy of mineral information inference (prediction) results can be gradually improved, so that effective mineral deposit prediction and resource evaluation can be carried out in complex geological environments, and potential geological information can be extracted from multiple dimensions and different data sources, the spatial distribution pattern of mineral deposits can be identified, and the grade changes of ore bodies can be predicted, thereby providing theoretical support and technical guidance for the exploration, evaluation and development of mineral resources, improving the efficiency of crustal mineral resource exploration, reducing resource exploration costs, accurately locking in strategic mineral resources, and making strategic layouts for related tasks in advance. This solves the problems that the mineral exploration methods in related technologies lack exploration accuracy when faced with complex geological conditions, have high exploration costs and low efficiency, are easily affected by various environmental factors, find it difficult to fully and accurately reveal the potential distribution patterns of mineral deposits, and cannot meet the mineral exploration needs under the continuous development of the economy and society.

[0027] Before explaining the intelligent prospecting method based on multi-source information fusion and physical-data dual drive in the embodiment of the present application, the intelligent prospecting system involved in the embodiment of the present application is first explained.

[0028] In the embodiments of the present application, the intelligent prospecting system can be implemented (constructed) based on but not limited to AI (artificial intelligence) empowerment, that is, an intelligent prospecting system based on AI empowerment.

[0029] Figure 1 This is a schematic diagram of the framework of an intelligent prospecting system according to an embodiment of the present application. Figure 1 As shown, the intelligent prospecting system in the embodiment of the present application includes but is not limited to two parts: a multi-source information fusion system and an identification system.

[0030] In recent years, AI technology has shown significant advantages in processing large-scale, high-dimensional, and complex data, thus providing powerful assistance for tasks such as pattern recognition, feature extraction, and data prediction. The rapid development of AI technology in deep learning technology has provided a new breakthrough in the field of mineral exploration. The AI-based mineral exploration method in the embodiment of the present application includes a machine learning algorithm and a deep learning algorithm, which can automatically identify potential mineral deposit information in massive geological data, thereby improving the efficiency and accuracy of mineral resource exploration.

[0031] Based on this, in the embodiments of the present application, it is possible but not limited to construct an AI-enabled intelligent prospecting system, and the physical-data dual-driven recognition system contained in the intelligent prospecting system can be implemented using AI in the embodiments of the present application, such as constructing an AI-assisted identification system as a recognition system. In this way, it is possible to effectively integrate different types of data (such as geological images, remote sensing images, drilling records, seismic data, mineral chemical composition, etc.) through a multi-source information fusion method, and construct an AI-assisted identification system based on empirical knowledge learning and physical constraints to improve the accuracy and efficiency of exploration.

[0032] Specifically, the multi-source information fusion system in the embodiment of the present application includes but is not limited to a multi-source information database module and a data fusion module; the AI-assisted recognition system includes but is not limited to a physical-expert learning module and an AI inference module.

[0033] Among them, the multi-source information fusion system can collect multi-source information such as satellite remote sensing information, aerial remote sensing information, seismic exploration information, geological drilling information, geochemical detection information, gravity exploration information, magnetic exploration information and electrical exploration information to build a multi-source information database.

[0034] The multi-source information database module can pre-process the collected information to build a multi-source information database using the pre-processed multi-source information data. The data fusion module can also be used to perform complementary fusion of the multi-source information data in the multi-source information database at different levels to extract mineral information and build a refined distribution map of crustal minerals.

[0035] The physics-expert learning module can transform some physical theories or expert experience into knowledge rules suitable for AI learning, and construct them into physical constraints as loss functions to achieve physical drive (knowledge drive) for the AI-assisted recognition system.

[0036] The AI ​​inference module can identify the boundaries of mineral deposits, mineralized zones, structural features, etc.; predict the formation process of mineral deposits or the trend of mineral grade changes, help speculate the evolution of ore bodies; and estimate the reserves of mineral resources; it can also discover abnormal patterns in multi-source data, discover abnormal mineral deposits, mineralized zones, etc.; and help prospectors predict the potential location of ore bodies under complex conditions.

[0037] The AI-assisted identification system based on physical-data dual drive in the embodiment of the present application can form physical drive through the physical-expert learning module, and form data drive through the multi-source information database module and the AI ​​inference module. Through the physical-data dual drive, the refined distribution map of crustal mineral deposits is deeply mined to obtain the inference results of mineral deposit information, so as to comprehensively and accurately reveal the potential distribution law of mineral deposits, effectively improve the efficiency of crustal mineral resource exploration, reduce resource exploration costs, and accurately lock in strategic mineral resources.

[0038] Specifically, Figure 2 A flow chart of an intelligent prospecting method based on multi-source information fusion and physical-data dual drive provided in an embodiment of the present application.

[0039] like Figure 2 As shown, the intelligent prospecting method based on multi-source information fusion and physical-data dual drive includes the following steps: In step S201, based on the granularity and reliability of the multi-source information data in the target multi-source information database, the fusion level corresponding to the multi-source information data is matched, and the multi-source information data is complementary fused according to the fusion level to obtain a multi-source information complementary fusion result. The fusion level includes at least one of data level fusion, feature level fusion, and decision level fusion.

[0040] It is understandable that the target multi-source information database here refers to a database system that stores information collected from multiple different sources, wherein the collected information may be, but is not limited to, data information related to mineralization or prospecting.

[0041] In some embodiments, the present application can match the appropriate fusion level among the three different levels of fusion, namely, data-level fusion, feature-level fusion, and decision-level fusion, according to the granularity and reliability of the multi-source information data, to ensure that the multi-source information can be complementary and fused, thereby avoiding the problems of redundancy and contradiction in the multi-source information.

[0042] The granularity of multi-source information data here refers to the degree of detail or precision used by multi-source information data in describing a certain thing; reliability here refers to the accuracy, consistency and stability of multi-source information data in describing a certain thing.

[0043] In the embodiment of the present application, data-level fusion can be understood as fusion performed directly on the original data layer of the collected multi-source information data, which is the lowest level of fusion; feature-level fusion can be understood here as joint recognition of the feature layer, which can fuse the features of multiple multi-source information data from different feature extraction methods or feature representations to generate a more representative and rich feature vector, which belongs to the middle level fusion; decision-level fusion can be understood here as a high-level fusion after multiple transformations and processing or fusion.

[0044] For example, after acquiring multi-source information data, the present application may, but is not limited to, utilize some AI algorithms to perform data-level fusion on multi-source information data with lower granularity or lower reliability; perform feature-level fusion on multi-source information data with medium granularity or medium reliability; and perform decision-level fusion on multi-source information data with higher granularity or higher reliability, so as to obtain a complementary fusion result of multi-source information.

[0045] The embodiments of the present application can perform complementary fusion of multi-source information data at different levels, which can effectively improve the reliability and accuracy of the complementary fusion results of the multi-source information and provide strong data support for subsequent processing processes.

[0046] Optionally, in one embodiment of the present application, before matching the fusion level corresponding to the multi-source information data based on the granularity and reliability of the multi-source information data in the target multi-source information database, it also includes: collecting initial target multi-source information, and preprocessing the initial target multi-source information to obtain target multi-source information that meets preset processing conditions; and constructing a target multi-source information database using the target multi-source information.

[0047] In the actual implementation process, before complementary fusion of multi-source information data in the target multi-source information database is performed, it is necessary to first build the target multi-source information database.

[0048] When constructing a target multi-source information database, the embodiment of the present application may first collect initial target multi-source information. The initial target multi-source information may be understood as a variety of information obtained from a variety of information channels (sources) that is helpful for mineralization prediction and prospecting, such as satellite remote sensing information, aerial remote sensing information, seismic exploration information, geological drilling information, geochemical detection information, gravity exploration information, magnetic exploration information, electrical exploration information, and other related information.

[0049] In order to ensure the validity and data accuracy of the multi-source information data in the target multi-source information database, the embodiment of the present application can perform certain preprocessing on the initial target multi-source information, so as to ensure the reliability of the final multi-source information data.

[0050] For example, the embodiments of the present application can use outlier detection, data denoising, data alignment, data normalization and standardization, feature splicing technology and other related technologies to implement the preprocessing of the original multi-source heterogeneous data, i.e., the initial target multi-source information, so as to ensure that the preprocessed multi-source information data can meet the preset processing conditions. Among them, the preset processing conditions here can be understood as certain conditions that need to be met after the preprocessing of the initial target multi-source information data is completed, for example, the data values ​​are all valid values, the data accuracy is within the range required by the database, and the data type meets the requirements of the database, etc.

[0051] After obtaining target multi-source information that meets certain conditions, the embodiment of the present application can use the target multi-source information to construct a target multi-source information database.

[0052] It should be noted that the target multi-source information database and the multi-source information data contained therein in the embodiments of the present application are not static, but will be updated as the initial target multi-source information is updated. The initial target multi-source information can be updated accordingly based on data updates at the data source or new data sources. This is only an exemplary explanation and the present application does not impose any specific limitations.

[0053] The target multi-source information database in the embodiment of the present application integrates massive data from multiple sources and performs certain preprocessing to construct the target multi-source information database, which facilitates timely updating and management of multi-source information data, effectively reduces the time for data acquisition and processing, and improves the validity and reliability of the data.

[0054] Step S202, extracting mineral distribution information of the target area according to the complementary fusion result of multi-source information, and generating a refined distribution map of crustal minerals in the target area using the mineral distribution information.

[0055] In certain embodiments, after complementary fusion of multi-source information data is performed to obtain a multi-source information complementary fusion result, the present application can extract the mineral distribution information of the target area based on the multi-source information complementary fusion result, and use the mineral distribution information to generate a refined distribution map of the crustal minerals in the target area.

[0056] For example, the embodiments of the present application may, but are not limited to, target the possibility of mineral resource occurrence and draw a detailed distribution map of crustal mineral deposits in the target area based on the complementary fusion results of multi-source information.

[0057] The target area here refers to the area where mineral exploration (exploration) is required, which can be large or small and can be determined based on actual conditions. This application does not impose any specific restrictions.

[0058] The mineral distribution information here can be understood as a variety of mineral resource information determined by the embodiment of the present application based on the complementary fusion results of multi-source information. The refined distribution map of crustal mineral resources here refers to a certain image generated based on the mineral distribution information that can show the specific location and distribution characteristics of various mineral resources in the crust.

[0059] The embodiment of the present application can construct a refined distribution map of crustal mineral deposits based on the complementary fusion results of multi-source information, which is convenient for more detailed and intuitive understanding of the mineral information of each location in the target area, and can effectively reduce the cost and time of exploration and shorten the time period.

[0060] Step S203, based on the target multi-source information database and the refined distribution map of crustal mineral deposits, the target recognition system based on physics and data dual drive is used to generate the mineral deposit information inference result of the target area. Among them, the target recognition system based on physics and data dual drive can be but not limited to a target AI auxiliary identification system.

[0061] It can be understood that the target recognition system based on physical-data dual drive here refers to the relevant system based on physical-data drive to realize the identification of mineral information of the target area, and the target AI-assisted identification system here refers to the target recognition system that uses AI to identify the mineral information of the target area in the embodiment of the present application.

[0062] Based on the relevant descriptions of other embodiments, it can be understood that the target AI-assisted identification system in the embodiment of the present application can conduct in-depth mining of the refined distribution map of crustal mineral deposits through physical-data dual drive to obtain mineral information inference results.

[0063] In addition, the target AI-assisted identification system in the embodiment of the present application can perform unsupervised learning based on the processing of each task, that is, it will gradually improve its own applicability as the number of processed tasks increases, and the accuracy of mineral exploration will gradually increase.

[0064] In some embodiments, the target AI-assisted identification system can identify relevant information about mineral deposits based on the multi-source information data in the target multi-source information database and its own capabilities, and then use this information to conduct in-depth mining of the refined distribution map of crustal mineral deposits.

[0065] For example, the embodiment of the present application can infer more detailed mineral information based on the target AI-assisted identification system, such as the possible location of the ore body, and circle the corresponding location on the refined distribution map of crustal mineral deposits, etc., and then combine the distribution information of the mineral resources marked in the refined distribution map of crustal mineral deposits in the target area to determine the final mineral information inference result, such as the existence of mineral deposits at a certain location and the estimated reserves of the mineral resources at that location, etc., thereby effectively improving the efficiency of crustal mineral resource exploration, reducing resource exploration costs, and accurately locking in strategic mineral resources.

[0066] Optionally, in one embodiment of the present application, before using the target recognition system based on physical-data dual drive to generate mineral information inference results, it also includes: obtaining knowledge rules that meet preset conditions based on target theoretical information and / or historical experience data, and constructing physical constraints based on the knowledge rules, so as to construct physical drives in the target recognition system based on physical-data dual drive according to the knowledge rules and physical constraints; using the target neural network and multi-source information data to train the initial recognition system to construct data drives in the target recognition system based on physical-data dual drive; and determining the target recognition system based on physical-data dual drive through physical drives and data drives.

[0067] In the actual implementation process, before using the physical-data dual-driven target recognition system to generate mineral information inference results, this application will first build a physical-data dual-driven target recognition system to train and predict the system, so as to obtain a physical-data dual-driven target recognition system that can meet actual application needs.

[0068] Based on the relevant descriptions of other embodiments, it can be understood that the target recognition system based on physical-data dual drive in the present application (such as target AI-assisted identification system) can be but is not limited to deep mining of the refined distribution map of crustal mineral deposits through the physical-data dual drive it contains, wherein the physical-data dual drive can be but is not limited to being composed of two parts: physical drive and data drive.

[0069] For example, the physical drive in the target AI-assisted recognition system in the present application can be, but is not limited to, implemented by a physical-expert learning module. The physical-expert learning module can obtain knowledge rules that meet preset conditions based on target theoretical information and / or historical experience data, and construct physical constraints based on the knowledge rules, so as to construct the physical drive in the target recognition system based on physical-data dual drive based on the knowledge rules and physical constraints.

[0070] Among them, the preset conditions here can be understood as knowledge rules suitable for learning of target recognition systems based on physical-data dual-drive, such as knowledge rules suitable for AI learning in target AI-assisted identification systems.

[0071] For example, the present application can, but is not limited to, convert physical theories such as mineralization evolution theory, geological tectonics, ore deposits and mineralization, regional geology, metallogenic belts and mineral resources, mineralization and ore deposit models, and some expert experience into knowledge rules suitable for (AI) learning, and construct them into physical constraints as loss functions to achieve physical drive of the target recognition system (target AI-assisted identification system) based on physical-data dual-drive.

[0072] It should be noted that the knowledge rules in the embodiments of the present application will be increased or updated as physical theories and expert experience are increased or updated. Correspondingly, the knowledge drive in the physics-data dual-driven target recognition system (target AI-assisted recognition system) and the target recognition system will also be updated.

[0073] And, in an embodiment of the present application, the data drive in the target AI-assisted recognition system can be, but is not limited to, implemented by an inference module, and the inference module can be, but is not limited to, training the initial recognition system using a target neural network and multi-source information data. Among them, the target neural network here can be understood as a variety of neural networks that can be used to train the target recognition system, including but not limited to convolutional neural networks, recurrent neural networks, deep neural networks, autoencoders, and generative adversarial networks. The initial recognition system here refers to a target recognition system based on physical-data dual drive that has not been trained and predicted. And, the inference module in the embodiment of the present application can also be implemented using AI during training and prediction, which can effectively save costs and shorten construction time.

[0074] Similarly, the inference module in the embodiment of the present application can also perform unsupervised learning based on the processing of each task on the basis of AI implementation, that is, its applicability will gradually improve as the number of processing tasks increases, and its inference ability and accuracy will also gradually improve.

[0075] After completing the construction of physical drive and data drive, combining the two can form physical-data drive, thereby determining the final target recognition system based on physical-data dual drive.

[0076] The embodiment of the present application realizes the effective learning of mineralization knowledge rules by adding a physical-expert learning module, and realizes physical drive as a physical constraint. Combined with data-driven means, through continuous training and optimization, the prediction accuracy of the target recognition system based on physical-data dual drive will gradually improve, thereby realizing effective mineral deposit prediction and resource assessment in complex geological environments.

[0077] Optionally, in one embodiment of the present application, based on the target multi-source information database and the refined distribution map of crustal mineral deposits, a target recognition system based on dual physics and data drive is used to generate the mineral deposit information inference results of the target area, including: based on the target multi-source information database, using the target recognition system based on dual physics and data drive to obtain the spatial characteristics, ore body evolution information, mineral resource reserve estimation results, abnormal area information, and potential position prediction results of the ore body of the target area; based on the spatial characteristics, ore body evolution information, mineral resource reserve estimation results, abnormal area information, potential position prediction results of the ore body and the refined distribution map of crustal mineral deposits, using the target recognition system based on dual physics and data drive to generate the mineral deposit information inference results of the target area.

[0078] As a possible implementation method, when using a physical-data dual-driven target recognition system to conduct in-depth mining of the refined distribution map of mineral deposits, we can first use a physical-data dual-driven target recognition system based on the target multi-source information database to obtain the spatial characteristics of the target area, ore body evolution information, mineral resource reserve estimation results, abnormal area information, potential ore body location prediction results and other information, and then conduct in-depth mining of the refined distribution map of crustal mineral deposits based on this information to generate mineral information inference results of the target area.

[0079] For example, when the inference module in the present application is implemented using AI, an AI inference module is formed, which can, but is not limited to, use a convolutional neural network to extract features from image information such as satellite remote sensing information, aerial remote sensing information, etc. in the target multi-source information database, and automatically extract spatial features in the image through the convolution layer, so as to identify the boundaries of mineral deposits, mineralized zones, structural features, etc.

[0080] Furthermore, the embodiments of the present application may, but are not limited to, use a recurrent neural network to process the time-related dynamic evolution data of geological processes in a multi-source information database, simulate the temporal changes of hydrothermal fluids and mineralization processes, predict the formation process of a mineral deposit or the trend of mineral grade changes, and help infer the evolution of an ore body.

[0081] Furthermore, the embodiments of the present application may, but are not limited to, use deep neural networks to perform error back-propagation training and learning on multi-source heterogeneous data such as seismic exploration information, geological drilling information, geochemical detection information, gravity exploration information, magnetic exploration information, and electrical exploration information, train deep neural network models to predict ore grade and metal content, conduct comprehensive assessments of ore deposits, and help estimate mineral resource reserves.

[0082] Furthermore, the embodiments of the present application may, but are not limited to, use an autoencoder to extract important potential features from the high-dimensional information of a multi-source information database module, compress the representation of the input data (encoder), and then reconstruct the input data by decompression (decoder), thereby learning the effective representation of the data, helping to discover abnormal patterns in multi-source data, and discover abnormal mineral deposits, mineralized zones, etc.

[0083] Furthermore, the embodiments of the present application may, but are not limited to, use a generative adversarial network to generate simulation data, improve data quality, or simulate the generation process of a mineral deposit. The generative adversarial network uses adversarial training of the generator and the discriminator to enable the generator to generate exploration simulation data that is difficult to distinguish from real data, especially when sample data is insufficient, by generating virtual samples to increase the training data set. Virtual samples are used to simulate the formation and evolution process of mineral deposits under different conditions, helping prospectors predict the potential location of ore bodies under complex conditions.

[0084] It should be noted that the various neural networks used in the embodiments of the present application and their corresponding implemented functions can be adjusted according to actual conditions. They are only illustrative here without specific limitations.

[0085] After obtaining this information, the target recognition system based on physical and data dual drive can infer more detailed mineral information of each location in the target area, and then determine the final mineral information inference result by combining the distribution information of the marked mineral resources in the target area in the refined distribution map of crustal minerals.

[0086] According to the intelligent prospecting method proposed in the embodiment of the present application, mineral distribution information can be extracted from multi-source information data to draw a refined distribution map of crustal mineral deposits, and a target recognition system based on physical-data dual-drive can be used to deeply mine the refined distribution map of crustal mineral deposits to obtain mineral information inference results. As a result, it is possible to use multi-source information fusion technology to fuse massive multi-source information to obtain a detailed distribution map of crustal mineral deposits. Multi-source information fusion technology can use AI to effectively reduce exploration costs and time; the physical-expert learning module introduced by AI in the target recognition system can realize the effective learning of mineralization knowledge rules, and realize physical drive as a physical constraint. Combined with data-driven means, through continuous training and optimization, the prediction accuracy of mineral information inference (prediction) results can be gradually improved, so that effective mineral deposit prediction and resource evaluation can be carried out in complex geological environments, and potential geological information can be extracted from multiple dimensions and different data sources, the spatial distribution pattern of mineral deposits can be identified, and the grade changes of ore bodies can be predicted, thereby providing theoretical support and technical guidance for the exploration, evaluation and development of mineral resources, improving the efficiency of crustal mineral resource exploration, reducing resource exploration costs, accurately locking in strategic mineral resources, and making strategic layouts for related tasks in advance. This solves the problems that the mineral exploration methods in related technologies lack exploration accuracy when faced with complex geological conditions, have high exploration costs and low efficiency, are easily affected by various environmental factors, find it difficult to fully and accurately reveal the potential distribution patterns of mineral deposits, and cannot meet the mineral exploration needs under the continuous development of the economy and society.

[0087] Next, an intelligent prospecting device based on multi-source information fusion and physical-data dual drive proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0088] Figure 3 It is a structural schematic diagram of an intelligent prospecting device based on multi-source information fusion and physical-data dual drive in an embodiment of the present application.

[0089] like Figure 3 As shown, the intelligent prospecting device 10 based on multi-source information fusion and physical-data dual drive includes: a fusion module 100, a first generation module 200 and a second generation module 300.

[0090] Among them, the fusion module 100 is used to match the fusion level corresponding to the multi-source information data based on the granularity and reliability of the multi-source information data in the target multi-source information database, and to perform complementary fusion on the multi-source information data according to the fusion level to obtain a multi-source information complementary fusion result.

[0091] The first generation module 200 is used to extract mineral distribution information of the target area according to the complementary fusion result of multi-source information, and generate a refined distribution map of crustal minerals in the target area using the mineral distribution information.

[0092] The second generation module 300 is used to generate mineral information inference results of the target area based on the target multi-source information database and the refined distribution map of crustal mineral deposits by using a target recognition system based on physical-data dual drive.

[0093] Optionally, in one embodiment of the present application, it also includes: a processing module and a first building module.

[0094] Among them, the processing module is used to collect initial target multi-source information and pre-process the initial target multi-source information before matching the fusion level corresponding to the multi-source information data based on the granularity and reliability of the multi-source information data in the target multi-source information database, so as to obtain the target multi-source information that meets the preset processing conditions.

[0095] The first construction module is used to construct a target multi-source information database using target multi-source information.

[0096] Optionally, in one embodiment of the present application, it further includes: a second building module, a third building module and a determination module.

[0097] Among them, the second construction module is used to obtain knowledge rules that meet preset conditions based on target theoretical information and / or historical experience data before generating mineral information inference results using the target recognition system based on physical-data dual drive, and to construct physical constraints based on the knowledge rules, so as to construct the physical drive in the target recognition system based on physical-data dual drive based on the knowledge rules and physical constraints.

[0098] The third building module is used to train the initial recognition system using the target neural network and multi-source information data to build a data-driven target recognition system based on physical-data dual-driven.

[0099] The determination module is used to determine a target recognition system based on physical-data dual drive through physical drive and data drive.

[0100] Optionally, in one embodiment of the present application, the second generating module 300 includes: an acquiring unit and a generating unit.

[0101] Among them, the acquisition unit is used to obtain the spatial characteristics of the target area, ore body evolution information, mineral resource reserve estimation results, abnormal area information, and ore body potential location prediction results based on the target multi-source information database and the target recognition system based on physical and data dual drive.

[0102] The generation unit is used to generate the mineral information inference results of the target area based on the spatial characteristics, ore body evolution information, mineral resource reserve estimation results, abnormal area information, potential location prediction results of the ore body and the refined distribution map of crustal mineral deposits by using the target recognition system based on physical-data dual drive.

[0103] Optionally, in one embodiment of the present application, the fusion level includes at least one of data level fusion, feature level fusion, and decision level fusion.

[0104] Optionally, in one embodiment of the present application, the target recognition system based on dual physics-data drive is a target AI-assisted recognition system.

[0105] It should be noted that the aforementioned explanation of the embodiment of the intelligent prospecting method based on multi-source information fusion and physical-data dual drive is also applicable to the intelligent prospecting device based on multi-source information fusion and physical-data dual drive of this embodiment, and will not be repeated here.

[0106] According to the intelligent mineral prospecting device based on multi-source information fusion and physical-data dual drive proposed in the embodiment of the present application, mineral distribution information can be extracted from multi-source information data to draw a refined distribution map of crustal mineral deposits, and the refined distribution map of crustal mineral deposits can be deeply mined by using a target recognition system based on physical-data dual drive to obtain mineral information inference results. As a result, it is possible to use multi-source information fusion technology to fuse massive multi-source information to obtain a detailed distribution map of crustal mineral deposits. Multi-source information fusion technology can use AI to effectively reduce exploration costs and time; the physical-expert learning module introduced by AI in the target recognition system can realize the effective learning of mineralization knowledge rules, and realize physical drive as a physical constraint. Combined with data-driven means, through continuous training and optimization, the prediction accuracy of mineral information inference (prediction) results can be gradually improved, so that effective mineral deposit prediction and resource evaluation can be carried out in complex geological environments, and potential geological information can be extracted from multiple dimensions and different data sources, the spatial distribution pattern of mineral deposits can be identified, and the grade changes of ore bodies can be predicted, thereby providing theoretical support and technical guidance for the exploration, evaluation and development of mineral resources, improving the efficiency of crustal mineral resource exploration, reducing resource exploration costs, accurately locking in strategic mineral resources, and making strategic layouts for related tasks in advance. This solves the problems that the mineral exploration methods in related technologies lack exploration accuracy when faced with complex geological conditions, have high exploration costs and low efficiency, are easily affected by various environmental factors, find it difficult to fully and accurately reveal the potential distribution patterns of mineral deposits, and cannot meet the mineral exploration needs under the continuous development of the economy and society.

[0107] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include: Memory 401 , processor 402 , and a computer program stored in the memory 401 and executable on the processor 402 .

[0108] When the processor 402 executes the program, the intelligent prospecting method based on multi-source information fusion and physical-data dual drive provided in the above embodiment is implemented.

[0109] Furthermore, the electronic device further comprises: The communication interface 403 is used for communication between the memory 401 and the processor 402 .

[0110] The memory 401 is used to store computer programs that can be executed on the processor 402 .

[0111] The memory 401 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0112] If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0113] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can communicate with each other through an internal interface.

[0114] The processor 402 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0115] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned intelligent prospecting method based on multi-source information fusion and physical-data dual drive.

[0116] The embodiment of the present application also provides a computer program product, including a computer program, which can run computer instructions. When the computer instructions are executed by a processor, the intelligent prospecting method based on multi-source information fusion and physical-data dual drive provided by the embodiment of the present application is implemented.

[0117] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0118] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0119] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0120] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or N wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0121] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of multiple of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0122] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0123] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0124] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. An intelligent prospecting method based on multi-source information fusion and physical-data dual drive, characterized in that: The following steps are involved: Based on the granularity and reliability of the multi-source information data in the target multi-source information database, matching the fusion level corresponding to the multi-source information data, and performing complementary fusion on the multi-source information data according to the fusion level to obtain a multi-source information complementary fusion result; Extracting mineral distribution information of the target area according to the complementary fusion result of the multi-source information, and generating a refined distribution map of crustal minerals in the target area using the mineral distribution information; Based on the target multi-source information database and the refined distribution map of crustal mineral deposits, a target recognition system based on physics and data dual drive is used to generate mineral deposit information inference results of the target area.

2. The intelligent prospecting method based on multi-source information fusion and physical-data dual drive according to claim 1 is characterized in that: Before matching the fusion level corresponding to the multi-source information data based on the granularity and reliability of the multi-source information data in the target multi-source information database, the method further includes: Collecting initial target multi-source information, and preprocessing the initial target multi-source information to obtain the target multi-source information that meets preset processing conditions; The target multi-source information database is constructed using the target multi-source information.

3. The intelligent prospecting method based on multi-source information fusion and physical-data dual drive according to claim 1 is characterized in that: Before using the physical-data dual-driven target recognition system to generate the mineral deposit information inference result of the target area, it also includes: Obtaining knowledge rules that meet preset conditions according to target theoretical information and / or historical experience data, and constructing physical constraints according to the knowledge rules, so as to construct the physical drive in the target recognition system based on physical-data dual drive according to the knowledge rules and the physical constraints; Using the target neural network and the multi-source information data to train the initial recognition system, so as to construct the data drive in the target recognition system based on physical-data dual drive; The physical-data dual-driven target recognition system is determined by the physical drive and the data drive.

4. The intelligent prospecting method based on multi-source information fusion and physical-data dual drive according to claim 1 is characterized in that: The method of generating the mineral information inference result of the target area by using the target recognition system based on physical-data dual drive based on the target multi-source information database and the refined distribution map of crustal mineral deposits includes: Based on the target multi-source information database, the target recognition system based on physical-data dual drive is used to obtain the spatial characteristics of the target area, ore body evolution information, mineral resource reserve estimation results, abnormal area information, and ore body potential location prediction results; Based on the spatial characteristics, the ore body evolution information, the mineral resource reserve estimation results, the abnormal area information, the potential location prediction results of the ore body and the refined distribution map of crustal mineral deposits, the target recognition system based on physical-data dual drive is used to generate the mineral information inference results of the target area.

5. The intelligent prospecting method based on multi-source information fusion and physical-data dual drive according to claim 1 is characterized in that: The fusion level includes at least one of data level fusion, feature level fusion, and decision level fusion.

6. The intelligent prospecting method based on multi-source information fusion and physical-data dual drive according to claim 1 is characterized in that: The target recognition system based on physics-data dual drive is a target AI-assisted identification system.

7. An intelligent prospecting device based on multi-source information fusion and physical-data dual drive, characterized in that: include: A fusion module, for matching a fusion level corresponding to the multi-source information data based on the granularity and reliability of the multi-source information data in the target multi-source information database, and performing complementary fusion on the multi-source information data according to the fusion level to obtain a multi-source information complementary fusion result; A first generation module is used to extract mineral distribution information of the target area according to the complementary fusion result of the multi-source information, and generate a refined distribution map of crustal minerals in the target area using the mineral distribution information; The second generation module is used to generate the mineral information inference result of the target area based on the target multi-source information database and the refined distribution map of crustal mineral deposits by using the target recognition system based on physical-data dual drive.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent prospecting method based on multi-source information fusion and physical-data dual drive as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement an intelligent prospecting method based on multi-source information fusion and physical-data dual drive as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed, it is used to implement the intelligent prospecting method based on multi-source information fusion and physical-data dual drive as described in any one of claims 1-6.

Images