Method, device and equipment for constructing geological domain knowledge graph

Abstract

The embodiment of the invention discloses a geological domain knowledge graph construction method, device and equipment. The geological domain knowledge graph construction method comprises the steps of obtaining a to-be-processed geological text; performing entity information extraction on the to-be-processed geological text by adopting a preset geological triple extraction model to obtain triple data of the to-be-processed geological text; performing entity type prediction on the triple data of the to-be-processed geological text by adopting a preset entity type prediction model to obtain an entity type corresponding to the to-be-processed geological text; the entity type of the to-be-processed geological text is matched with a preset entity database, the entity type of the to-be-processed geological text is updated, updated triple data are obtained, and the updated triple data comprise entity data, relation data, attribute data and the entity type; and on the basis of a preset triple link model, performing triple connection on the updated triple data, and constructing the geological domain knowledge graph.

Description

Technical Field

[0001] This specification relates to the technical field of knowledge graphs, and particularly to a method, apparatus, and device for constructing a knowledge graph in the geological field. Background Art

[0002] A knowledge graph is a knowledge system that formally describes entities and their relationships. It organizes and stores structured knowledge and information through nodes and edges. The knowledge graph in the geological field can help better understand the structure and composition of geology, as well as the relationships between various geological phenomena. Therefore, constructing a knowledge graph in the geological field is of great significance for geological research.

[0003] In the prior art, the construction of a knowledge graph in the geological field often uses extensive and inaccurate data as the basis for constructing the knowledge graph, and the professionalism and complexity of constructing the knowledge graph in the geological field are not considered during the construction process of the knowledge graph. Therefore, the knowledge graph in the geological field constructed in the prior art has problems such as poor accuracy and inability to reflect real entity relationships.

[0004] Based on this, a method for constructing a knowledge graph in the geological field is needed. Summary of the Invention

[0005] Embodiments of this specification provide a method, apparatus, and device for constructing a knowledge graph in the geological field to solve the following technical problems: In the prior art, the construction of a knowledge graph in the geological field often uses extensive and inaccurate data as the basis for constructing the knowledge graph, and the professionalism and complexity of constructing the knowledge graph in the geological field are not considered during the construction process of the knowledge graph. Therefore, the knowledge graph in the geological field constructed in the prior art has problems such as poor accuracy and inability to reflect real entity relationships.

[0006] To solve the above technical problems, the embodiments of this specification are implemented as follows:

[0007] Embodiments of this specification provide a method for constructing a knowledge graph in the geological field, including:

[0008] Obtain the geological text to be processed;

[0009] Use a preset geological triple extraction model to extract entity information from the geological text to be processed, and obtain the triple data of the geological text to be processed, where the triple data includes entity data, relationship data, and attribute data;

[0010] Use a preset entity type prediction model to predict the entity type of the triple data of the geological text to be processed, and obtain the entity type corresponding to the geological text to be processed;

[0011] Match the entity types of the to-be-processed geological text with a preset entity database, update the entity types of the to-be-processed geological text, and obtain updated triple data, where the updated triple data includes: entity data, relationship data, attribute data, and entity types;

[0012] Based on a preset triple linking model, perform triple linking on the updated triple data to construct a geological domain knowledge graph.

[0013] This embodiment of the specification also provides a device for constructing a geological domain knowledge graph, including:

[0014] An acquisition module that acquires the to-be-processed geological text;

[0015] An extraction module that uses a preset geological triple extraction model to extract entity information from the to-be-processed geological text to obtain triple data of the to-be-processed geological text, where the triple data includes entity data, relationship data, and attribute data;

[0016] A prediction module that uses a preset entity type prediction model to predict the entity types of the triple data of the to-be-processed geological text to obtain the entity types corresponding to the to-be-processed geological text;

[0017] An update module that matches the entity types of the to-be-processed geological text with a preset entity database, updates the entity types of the to-be-processed geological text, and obtains updated triple data, where the updated triple data includes: entity data, relationship data, attribute data, and entity types;

[0018] A construction module that performs triple linking on the updated triple data based on a preset triple linking model to construct a geological domain knowledge graph.

[0019] This embodiment of the specification also provides an electronic device, including:

[0020] At least one processor; and,

[0021] A memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to:

[0023] Acquire the to-be-processed geological text;

[0024] Use a preset geological triple extraction model to extract entity information from the to-be-processed geological text to obtain triple data of the to-be-processed geological text, where the triple data includes entity data, relationship data, and attribute data;

[0025] Using a preset entity type prediction model, perform entity type prediction on the triple data of the to-be-processed geological text to obtain the entity type corresponding to the to-be-processed geological text;

[0026] Match the entity type of the to-be-processed geological text with a preset entity database to update the entity type of the to-be-processed geological text, and obtain updated triple data, where the updated triple data includes: entity data, relationship data, attribute data, and entity type;

[0027] Based on a preset triple linking model, perform triple linking on the updated triple data to construct a geological domain knowledge graph.

[0028] The method for constructing a geological domain knowledge graph provided in the embodiments of this specification includes obtaining a to-be-processed geological text; using a preset geological triple extraction model to extract entity information from the to-be-processed geological text to obtain triple data of the to-be-processed geological text, where the triple data includes entity data, relationship data, and attribute data; using a preset entity type prediction model to perform entity type prediction on the triple data of the to-be-processed geological text to obtain the entity type corresponding to the to-be-processed geological text; matching the entity type of the to-be-processed geological text with a preset entity database to update the entity type of the to-be-processed geological text, and obtaining updated triple data, where the updated triple data includes: entity data, relationship data, attribute data, and entity type; based on a preset triple linking model, performing triple linking on the updated triple data to construct a geological domain knowledge graph. The construction of the knowledge graph is processed in a standardized and consistent manner, and duplicate entity types are removed, thereby ensuring the accuracy of the knowledge graph construction, ensuring the quality of the knowledge graph, and providing a reliable guarantee for the subsequent application of the knowledge graph. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in this specification. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0030] Figure 1 It is a schematic diagram of the system architecture of a method for constructing a geological domain knowledge graph provided in the embodiments of this specification;

[0031] Figure 2Schematic flowchart of a method for constructing a geological domain knowledge graph provided by an embodiment of this specification;

[0032] Figure 3 Schematic diagram of the geological domain knowledge graph constructed according to an embodiment of this specification;

[0033] Figure 4 Schematic diagram of an apparatus for constructing a geological domain knowledge graph provided by an embodiment of this specification. Detailed implementation manners

[0034] In order to enable those skilled in the art to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in the embodiments of this specification with reference to the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0035] Figure 1 Schematic diagram of the system architecture of a method for constructing a geological domain knowledge graph provided by an embodiment of this specification. As Figure 1 shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0036] The terminal devices 101, 102, 103 interact with the server 105 through the network 104 to receive or send messages, etc. Various client applications may be installed on the terminal devices 101, 102, 103. For example, dedicated programs such as methods for constructing a geological domain knowledge graph.

[0037] The terminal devices 101, 102, 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various dedicated or general-purpose electronic devices, including but not limited to smartphones, tablets, laptop portable computers, and desktop computers, etc. When the terminal devices 101, 102, 103 are software, they may be installed in the above-listed electronic devices. It may be implemented as multiple software or software modules (such as multiple software or software modules for providing distributed services), or it may be implemented as a single software or software module.

[0038] Server 105 can be a server that provides various services, such as a backend server that provides services for client applications installed on terminal devices 101, 102, and 103. For example, the server can construct a geological domain knowledge graph so that the construction results of the geological domain knowledge graph are displayed on terminal devices 101, 102, and 103.

[0039] Server 105 can be hardware or software. When Server 105 is hardware, it can be implemented as a distributed server cluster composed of multiple servers or as a single server. When Server 105 is software, it can be implemented as multiple software or software modules (such as multiple software or software modules for providing distributed services), or as a single software or software module.

[0040] Figure 2 It is a schematic flowchart of a method for constructing a geological domain knowledge graph provided by an embodiment of this specification. From a program perspective, the execution subject of the process can be a program running on an application server or an application terminal. It can be understood that this method can be executed by any device, equipment, platform, or device cluster with computing and processing capabilities. As Figure 2 shown, this construction method includes:

[0041] Step S201: Obtain the geological text to be processed.

[0042] In the embodiments of this specification, the geological text to be processed includes: literature in the geological field, reports in the geological field, and geological databases. Specifically, the literature in the geological field is scientific and technological literature and papers related to geology; the reports in the geological field are geological-related reports; the geological database is a geological-related database. Specifically, it can be a classification code database for geological minerals, and further includes databases related to crystallography and mineralogy, petrology, ore deposit geology, general survey and exploration of solid minerals, and geological economics. Specifically in this embodiment, it can be classification codes for geological mineral terms - crystallography and mineralogy, classification codes for geological mineral terms - petrology, classification codes for geological mineral terms - ore deposit geology, classification codes for geological mineral terms - general survey and exploration of solid minerals, classification codes for geological mineral terms - geological economics.

[0043] In the embodiments of this specification, the geological data to be processed further includes: performing data preprocessing. Specifically, the data preprocessing includes: data cleaning and data integration. Among them, data cleaning refers to cleaning the data to remove noise and redundant information; data integration refers to integrating multi-source data to form a unified data format for constructing a geological knowledge graph. In the embodiments of this specification, the methods of data cleaning and data integration both adopt existing technologies and will not be elaborated here.

[0044] Step S203: Use a preset geological triple extraction model to extract entity information from the to-be-processed geological text, and obtain triple data of the to-be-processed geological text, where the triple data includes entity data, relationship data, and attribute data.

[0045] In the embodiments of this specification, the entity data includes: geological structure, rock type, mineral composition, geographical location, and stratigraphic name;

[0046] The relationship data represents the semantic relationship between the entity data;

[0047] The attribute data represents the attribute information of the entity data.

[0048] In the embodiments of this specification, the preset geological triple extraction model is a model based on a large language model. Further, in order to ensure that the large language model can adapt to the entity information extraction in the geological field, it is necessary to fine-tune the large language model to obtain the preset geological triple extraction model. It should be particularly noted that both the large language model and the fine-tuning of the large language model adopt existing technologies and will not be elaborated here.

[0049] Step S205: Use a preset entity type prediction model to perform entity type prediction on the triple data of the to-be-processed geological text, and obtain the entity type corresponding to the to-be-processed geological text.

[0050] In the embodiments of this specification, the preset entity type prediction model is a model trained based on a support vector machine model, specifically including:

[0051] Construct a training set based on historical data;

[0052] Use the training set to train the support vector machine model, select the Gaussian kernel function as the kernel function, and optimize the parameters of the support vector machine model through cross-validation technology.

[0053] In the embodiments of this specification, the support vector machine model includes a penalty coefficient and kernel function parameters;

[0054] The range of the penalty coefficient is [1, 1000], and the range of the kernel function parameters is [0.01, 1].

[0055] In the embodiments of this specification, the entity types include: mining area, ore, ore deposit, ore body, surrounding rock, stratum, and field work. Specifically, the mining area includes the project name, the mining area includes the mining area name and location, the ore includes the industrial type and natural type, the ore deposit includes the genetic type, the ore body includes the controlled length, controlled trench, average thickness, strike, and number, the surrounding rock includes the lithology and age, the stratum includes the lithology and age, and the field work includes geological mapping, electrical prospecting, magnetic prospecting, trenching, and drilling.

[0056] Use the triple data of the to-be-processed geological text obtained above as input, input it into a preset entity type prediction model for entity type prediction, and obtain the entity type corresponding to the to-be-processed geological text.

[0057] Step S207: Match the entity type of the to-be-processed geological text with a preset entity database, update the entity type of the to-be-processed geological text, and obtain updated triple data. The updated triple data includes: entity data, relationship data, attribute data, and entity type.

[0058] Since there may be duplicate entity types in the entity type of the to-be-processed geological text obtained, the subsequent constructed geological knowledge graph will be inaccurate. Therefore, in order to ensure the accuracy of the subsequent geological graph construction, in the embodiments of this specification, the triple data is updated to remove duplicate entity types.

[0059] In the embodiments of this specification, the entity types in the preset entity database include: mineralogy, petrology, ore deposit geology, geochemistry, paleontology, stratigraphy, structural geology, Quaternary geology, geodynamics, earth information science and technology, geophysics, resource exploration engineering, petroleum and natural gas geological engineering, mineral prospecting and exploration, geological engineering, engineering geology, hydrogeology, environmental geology, exploration technology and engineering, intelligent earth exploration, resource and environment big data engineering, groundwater science and engineering, tourism geology and planning engineering, geotechnical engineering, remote sensing geology, geological disaster prevention and control engineering.

[0060] In the embodiments of this specification, the matching of the entity type of the to-be-processed geological text with the preset entity database is performed in a synonymous matching manner. When the synonymous matching rate is greater than 80%, the entity type of the to-be-processed geological text is updated to the entity type in the preset entity database.

[0061] Step S209: Based on a preset triple link model, perform triple connection on the updated triple data to construct a geological domain knowledge graph.

[0062] In the embodiments of this specification, the preset triple link model is a model obtained by training based on bidirectional LSTM combined with an attention mechanism;

[0063] The input dimension of the input layer of the bidirectional LSTM is 300, and the time step is 10; the number of units in the LSTM layer of the bidirectional LSTM is 10, the boolean value of the returned sequence is False, the state return is not False, the activation function is tanh, and the recursive activation function is sigmoid; the regularization parameter is dropout; in the compilation parameters, the loss function is mean squared error, and the optimizer is Adam;

[0064] The attention mechanism is located in the output layer of the bidirectional LSTM.

[0065] In the embodiments of this specification, the updated triple data is used as the input of the bidirectional LSTM, encoded by the LSTM, and a hidden state sequence is generated;

[0066] The hidden state sequence is input into the attention mechanism to generate attention weights and a context vector;

[0067] Based on the attention weights and the context vector, triple linking is performed to generate the geological knowledge graph.

[0068] To further understand the method for constructing a geological domain knowledge graph provided in the embodiments of this specification, the constructed geological knowledge graph is further schematically shown below for easy understanding. Specifically, as Figure 3 shown,

[0069] The method for constructing a geological domain knowledge graph provided in the embodiments of this specification performs standardized and consistent processing on the construction of the knowledge graph, and removes duplicate entity types, thereby ensuring the accuracy of the construction of the knowledge graph, ensuring the quality of the knowledge graph, and providing a reliable guarantee for the subsequent application of the knowledge graph.

[0070] The above content details a method for constructing a geological domain knowledge graph. Correspondingly, this specification also provides a device for constructing a geological domain knowledge graph, as Figure 4 shown. Figure 4 The following is a schematic diagram of a device for constructing a geological domain knowledge graph provided in the embodiments of this specification. The construction device includes:

[0071] An acquisition module 401, which acquires the geological text to be processed;

[0072] The extraction module 403 uses a preset geological triple extraction model to extract entity information from the to-be-processed geological text, obtaining triple data of the to-be-processed geological text, where the triple data includes entity data, relationship data, and attribute data;

[0073] The prediction module 405 uses a preset entity type prediction model to perform entity type prediction on the triple data of the to-be-processed geological text, obtaining the entity type corresponding to the to-be-processed geological text;

[0074] The update module 407 matches the entity type of the to-be-processed geological text with a preset entity database to update the entity type of the to-be-processed geological text, obtaining updated triple data, where the updated triple data includes: entity data, relationship data, attribute data, and entity type;

[0075] The construction module 409 performs triple connection on the updated triple data based on a preset triple link model to construct a geological domain knowledge graph.

[0076] This embodiment of the specification also provides an electronic device, including:

[0077] At least one processor; and,

[0078] A memory communicatively connected to the at least one processor; wherein,

[0079] The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to:

[0080] Obtain the to-be-processed geological text;

[0081] Use a preset geological triple extraction model to extract entity information from the to-be-processed geological text, obtaining triple data of the to-be-processed geological text, where the triple data includes entity data, relationship data, and attribute data;

[0082] Use a preset entity type prediction model to perform entity type prediction on the triple data of the to-be-processed geological text, obtaining the entity type corresponding to the to-be-processed geological text;

[0083] Match the entity type of the to-be-processed geological text with a preset entity database to update the entity type of the to-be-processed geological text, obtaining updated triple data, where the updated triple data includes: entity data, relationship data, attribute data, and entity type;

[0084] Perform triple connection on the updated triple data based on a preset triple link model to construct a geological domain knowledge graph.

[0085] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0086] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the apparatus, electronic device, and non-volatile computer storage medium, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the partial description of the method embodiments.

[0087] The apparatus, electronic device, and non-volatile computer storage medium provided in the embodiments of this specification correspond to the method. Therefore, the apparatus, electronic device, and non-volatile computer storage medium also have beneficial technical effects similar to the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, electronic device, and non-volatile computer storage medium will not be elaborated here.

[0088] In the 1990s, it was obvious to distinguish whether an improvement in a technology was an improvement in hardware (e.g., improvement in circuit structures such as diodes, transistors, switches, etc.) or an improvement in software (improvement in method processes). However, with the development of technology, many improvements in method processes today can be regarded as direct improvements in hardware circuit structures. Almost all designers obtain the corresponding hardware circuit structures by programming the improved method processes into the hardware circuits. Therefore, it cannot be said that an improvement in a method process cannot be implemented with a hardware entity module. For example, a programmable logic device (PLD) (e.g., a field programmable gate array (FPGA)) is such an integrated circuit whose logic function is determined by the user's programming of the device. The designer can program by himself to "integrate" a digital system on a piece of PLD without having to ask a chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a hardware description language (HDL), and there is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. Currently, the most commonly used ones are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that by simply making a little logical programming of the method process with the above-mentioned several hardware description languages and programming it into the integrated circuit, it is easy to obtain the hardware circuit that implements the logical method process.

[0089] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to logically program the method steps to enable the controller to be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. to achieve the same function. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or structures within the hardware component.

[0090] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0091] For the convenience of description, when describing the above devices, they are described separately as various units according to their functions. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0092] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, the embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0093] This specification is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the specification. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to produce a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices generate means for implementing the functions specified in the flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks or multiple blocks.

[0094] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in the flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks or multiple blocks.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks or multiple blocks.

[0096] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0097] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0098] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0099] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0100] The specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media including storage devices.

[0101] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0102] The above description is only for the embodiments of this specification and is not intended to limit this application. For those skilled in the art, various modifications and variations can be made to this application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the scope of the claims of this application.

Claims

1. A method for constructing a knowledge graph in the geological field, characterized in that, The construction method includes: Obtain the geological text to be processed; Adopt a preset geological triple extraction model to extract entity information from the geological text to be processed, and obtain the triple data of the geological text to be processed, where the triple data includes entity data, relationship data, and attribute data; Adopt a preset entity type prediction model to predict the entity type of the triple data of the geological text to be processed, and obtain the entity type corresponding to the geological text to be processed; Match the entity type of the geological text to be processed with a preset entity database, update the entity type of the geological text to be processed, and obtain updated triple data, where the updated triple data includes: entity data, relationship data, attribute data, and entity type; Based on a preset triple link model, perform triple connection on the updated triple data to construct a geological domain knowledge graph.

2. The construction method according to claim 1, wherein The geological text to be processed includes: literature in the geological field, reports in the geological field, and geological databases.

3. The construction method according to claim 1, wherein The entity data includes: geological structure, rock type, mineral composition, geographical location, and stratigraphic name; The relationship data represents the semantic relationship between the entity data; The attribute data represents the attribute information of the entity data.

4. The construction method according to claim 1, wherein The entity types in the preset entity database include: mineralogy, petrology, ore deposit geology, geochemistry, paleontology, stratigraphy, structural geology, Quaternary geology, geodynamics, geoinformation science and technology, geophysics, resource exploration engineering, petroleum and natural gas geological engineering, mineral prospecting and exploration, geological engineering, engineering geology, hydrogeology, environmental geology, exploration technology and engineering, intelligent earth exploration, resource environment big data engineering, groundwater science and engineering, tourism geology and planning engineering, geotechnical engineering, remote sensing geology, geological disaster prevention and control engineering.

5. The construction method according to claim 1, wherein, The preset entity type prediction model is a model trained based on a support vector machine model, and specifically includes: Construct a training set based on historical data; Use the training set to train the support vector machine model, select the Gaussian kernel function as the kernel function, and optimize the parameters of the support vector machine model through cross-validation technology.

6. The construction method according to claim 5, characterized in that The support vector machine model includes a penalty coefficient and kernel function parameters; The range of the penalty coefficient is [1, 1000], and the range of the kernel function parameters is [0.01, 1].

7. The construction method according to claim 1, characterized in that, The preset triple link model is a model trained based on bidirectional LSTM combined with an attention mechanism; The input dimension of the input layer of the bidirectional LSTM is 300, and the time step is 10; the number of units in the LSTM layer of the bidirectional LSTM is 10, the boolean value of the returned sequence is False, the state return is not False, the activation function is tanh, and the recursive activation function is sigmoid; the regularization parameter is dropout; in the compilation parameters, the loss function is mean squared error, and the optimizer is Adam; The attention mechanism is located in the output layer of the bidirectional LSTM.

8. The construction method according to claim 7, wherein, The updated triple data is used as the input of the bidirectional LSTM, encoded by the LSTM, and a hidden state sequence is generated; The hidden state sequence is input into the attention mechanism to generate attention weights and context vectors; Based on the attention weights and context vectors, triple linking is performed to generate the geological knowledge graph.

9. A device for constructing a knowledge graph in the geological field, characterized in that, The construction device includes: An acquisition module that acquires the geological text to be processed; An extraction module that uses a preset geological triple extraction model to extract entity information from the geological text to be processed, obtaining triple data of the geological text to be processed, where the triple data includes entity data, relationship data, and attribute data; A prediction module that uses a preset entity type prediction model to perform entity type prediction on the triple data of the geological text to be processed, obtaining the entity type corresponding to the geological text to be processed; An update module that matches the entity type of the geological text to be processed with a preset entity database, updates the entity type of the geological text to be processed, and obtains updated triple data, where the updated triple data includes: entity data, relationship data, attribute data, and entity type; A construction module that performs triple connection on the updated triple data based on a preset triple linking model to construct a geological domain knowledge graph.

10. An electronic device, including: At least one processor; And, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: Acquire the geological text to be processed; Use a preset geological triple extraction model to extract entity information from the geological text to be processed, obtaining triple data of the geological text to be processed, where the triple data includes entity data, relationship data, and attribute data; Use a preset entity type prediction model to perform entity type prediction on the triple data of the geological text to be processed, obtaining the entity type corresponding to the geological text to be processed; Match the entity type of the geological text to be processed with a preset entity database, update the entity type of the geological text to be processed, and obtain updated triple data, where the updated triple data includes: entity data, relationship data, attribute data, and entity type; Perform triple connection on the updated triple data based on a preset triple linking model to construct a geological domain knowledge graph.

Images