Inversion mapping model training method and device, electronic equipment and storage medium

Abstract

The invention discloses an inversion mapping model training method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring to-be-trained seismic data and a wave impedance tag corresponding to the to-be-trained seismic data; training an initial learner based on the to-be-trained seismic data and the wave impedance tag corresponding to the to-be-trained seismic data to obtain an active learner model; obtaining non-labeled seismic data, and inputting the non-labeled seismic data into the active learning device model to obtain a wave impedance label of the non-labeled seismic data; and training a neural network model based on the unlabeled seismic data and the wave impedance tag of the unlabeled seismic data to obtain a trained inversion mapping model. According to the technical scheme, the wave impedance tag of the unlabeled seismic data is generated through active learning simulation, so that training of the inversion mapping model is completed under a small amount of labeled information, and the training precision of the inversion mapping model is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas exploration, and in particular to an inversion mapping model training method, device, electronic equipment and storage medium. Background Art

[0002] Seismic wave impedance inversion is one of the effective means of reservoir prediction. Wave impedance has a certain correlation with oil and gas reservoirs. Seismic wave impedance is actually the product of medium density and wave propagation speed in the medium. It can reflect the lithological properties of underground geology. Through inversion, seismic data reflecting stratum interface information can be converted into wave impedance information reflecting lithological changes. It is a key technology for reservoir prediction during seismic exploration.

[0003] With the development of artificial intelligence technology, deep learning methods are increasingly being used in the field of oil and gas exploration. At present, for wave impedance inversion based on supervised learning, a large number of high-quality labels are required to learn the inversion mapping model, which has the problems of limited number of labels and low model training accuracy. Summary of the invention

[0004] The present invention provides an inversion mapping model training method, device, electronic device and storage medium to realize automatic generation of wave impedance labels for unlabeled seismic data, solve the problem of limited number of labels, and then train a neural network model through unlabeled seismic data and the wave impedance labels corresponding to the unlabeled seismic data, so as to realize high-precision inversion mapping model training in the absence of labeled samples.

[0005] According to one aspect of the present invention, there is provided an inversion mapping model training method, comprising:

[0006] Acquire seismic data to be trained and wave impedance labels corresponding to the seismic data to be trained;

[0007] Training an initial learner based on the seismic data to be trained and the wave impedance labels of the seismic data to be trained to obtain an active learner model;

[0008] Acquire unlabeled seismic data, input the unlabeled seismic data into an active learner model, and obtain a wave impedance label of the unlabeled seismic data;

[0009] The neural network model is trained based on the unlabeled seismic data and the wave impedance labels of the unlabeled seismic data to obtain a trained inversion mapping model.

[0010] According to another aspect of the present invention, there is provided an inversion mapping model training device, comprising:

[0011] A training sample acquisition module, used to acquire seismic data to be trained and wave impedance labels corresponding to the seismic data to be trained;

[0012] An active learner training module, used for training an initial learner based on the seismic data to be trained and the wave impedance labels corresponding to the seismic data to be trained, to obtain an active learner model;

[0013] A wave impedance label determination module, used for acquiring unlabeled seismic data, inputting the unlabeled seismic data into an active learner model, and obtaining a wave impedance label of the unlabeled seismic data;

[0014] The inversion mapping model training module is used to train the neural network model based on the unlabeled seismic data and the wave impedance labels of the unlabeled seismic data to obtain a trained inversion mapping model.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor;

[0017] and a memory communicatively coupled to the at least one processor;

[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the inversion mapping model training method described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the inversion mapping model training method described in any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention realizes the automatic generation of wave impedance labels for unlabeled seismic data through active learning simulation, solves the problem of limited number of labels, and then trains the neural network model through the unlabeled seismic data and the wave impedance labels corresponding to the unlabeled seismic data, thereby realizing high-precision inversion mapping model training in the absence of labeled samples, thereby improving the training accuracy of the model.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 is a flow chart of an inversion mapping model training method provided according to Embodiment 1 of the present invention;

[0024] Figure 2 is a flow chart of an inversion mapping model training method provided according to Embodiment 2 of the present invention;

[0025] Figure 3 is a flow chart of an inversion mapping model training method provided according to Embodiment 3 of the present invention;

[0026] Figure 4 is a structural schematic diagram of an inversion mapping model training device provided according to Embodiment 4 of the present invention;

[0027] Figure 5 It is a structural schematic diagram of an electronic device for implementing the inversion mapping model training method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Embodiment 1

[0031] Figure 1 This is a flowchart of an inversion mapping model training method provided in the first embodiment of the present invention. This embodiment is applicable to the case where the inversion mapping model training is performed in the absence of sample label information. The method can be performed by an inversion mapping model training device. The inversion mapping model training device can be implemented in the form of hardware and / or software. The inversion mapping model training device can be configured in a terminal and / or a server. Figure 1 As shown, the method includes:

[0032] S110, obtaining seismic data to be trained and wave impedance labels corresponding to the seismic data to be trained.

[0033] In this embodiment, the seismic data to be trained and the wave impedance labels corresponding to the seismic data to be trained are training sample data of the active learner.

[0034] Specifically, the seismic data to be trained and the wave impedance labels corresponding to the seismic data to be trained can be read from a preset storage path of the electronic device, or the seismic data to be trained and the wave impedance labels corresponding to the seismic data to be trained can be obtained from other electronic devices or the cloud that communicate with the electronic device, without limitation here.

[0035] S120: Training an initial learner based on the seismic data to be trained and the wave impedance labels corresponding to the seismic data to be trained to obtain an active learner model.

[0036] In this embodiment, the active learner model can be obtained by training with a small amount of labeled data. In the trained initial learner, the seismic data to be trained will be pre-extracted with features, and the model parameters in the initial learner will be trained based on the extracted feature information, and by continuously adjusting the model parameters, the distance deviation between the output result of the model and the wave impedance label corresponding to the seismic data to be trained will gradually decrease and tend to be stable, thereby obtaining the active learner model.

[0037] S130, obtaining unlabeled seismic data, and inputting the unlabeled seismic data into an active learner model to obtain a wave impedance label of the unlabeled seismic data.

[0038] Specifically, the unlabeled seismic data is input into the active learner model, and the active learner model queries and predicts based on the unlabeled seismic data, thereby obtaining the wave impedance labels of the unlabeled seismic data and obtaining a large amount of labeled data to solve the problem of limited number of labels.

[0039] S140, training a neural network model based on the unlabeled seismic data and the wave impedance labels of the unlabeled seismic data to obtain a trained inversion mapping model.

[0040] In this embodiment, the inversion mapping model can be obtained by training the neural network model with a large amount of unlabeled seismic data and the wave impedance labels of the unlabeled seismic data. In the trained neural network model, the unlabeled seismic data will be feature extracted in advance, and the model parameters in the neural network model will be trained based on the extracted feature information, and by continuously adjusting the model parameters, the distance deviation between the output result of the model and the wave impedance label of the labeled seismic data to the neural network model is gradually reduced and stabilized, thereby obtaining the inversion mapping model.

[0041] In some optional embodiments, after obtaining the trained inversion mapping model, it also includes: acquiring actual seismic data; inputting the actual seismic data into the trained inversion mapping model to obtain the wave impedance corresponding to the actual seismic data.

[0042] Specifically, actual seismic data can be input as input data into a pre-trained inversion mapping model; the inversion mapping model extracts characteristic information from the actual seismic data, and predicts the wave impedance corresponding to the actual seismic data based on the extracted characteristic information, and outputs it to complete the seismic wave impedance inversion.

[0043] The technical solution of the embodiment of the present invention realizes the automatic generation of wave impedance labels for unlabeled seismic data through active learning simulation, solves the problem of limited number of labels, and then trains the neural network model through the unlabeled seismic data and the wave impedance labels corresponding to the unlabeled seismic data, thereby realizing high-precision inversion mapping model training in the absence of labeled samples, thereby improving the training accuracy of the model.

[0044] Embodiment 2

[0045] Figure 2 A flow chart of an inversion mapping model training method provided in the second embodiment of the present invention, the method of this embodiment can be combined with the various optional schemes in the inversion mapping model training method provided in the above embodiments. The inversion mapping model training method provided in this embodiment is further optimized. Optionally, the unlabeled seismic data is input into the active learner model to obtain the wave impedance label of the unlabeled seismic data, including: querying the unlabeled seismic data to obtain the target unlabeled seismic data; labeling the target unlabeled seismic data to obtain the target wave impedance label corresponding to the target unlabeled seismic data; iteratively replacing the target wave impedance label corresponding to the target unlabeled seismic data to obtain the wave impedance label of the unlabeled seismic data.

[0046] like Figure 2 As shown, the method includes:

[0047] S210: Acquire seismic data to be trained and wave impedance labels corresponding to the seismic data to be trained.

[0048] S220: Train the initial learner based on the seismic data to be trained and the wave impedance labels corresponding to the seismic data to be trained to obtain an active learner model.

[0049] S230: query the unlabeled seismic data to obtain target unlabeled seismic data.

[0050] Among them, the target unlabeled seismic data refers to sample data that is representative or has labeling value.

[0051] Specifically, feature extraction can be performed on unlabeled seismic data to obtain key seismic features corresponding to the unlabeled seismic data, and then the key seismic features corresponding to the unlabeled seismic data can be screened through a pre-set selection strategy to obtain target unlabeled seismic data.

[0052] The selection strategy includes at least one of a maximum entropy strategy, a minimum confidence strategy, a minimum interval strategy, and a classifier voting strategy, which is not limited here.

[0053] Optionally, the seismic key features corresponding to the unlabeled seismic data are screened through a pre-set selection strategy to obtain the target unlabeled seismic data, including: the seismic key features corresponding to the unlabeled seismic data are screened through a pre-set minimum confidence strategy to obtain the target unlabeled seismic data.

[0054] Exemplarily, the minimum confidence strategy formula is as follows:

[0055]

[0056] in, represents the target unlabeled earthquake data selected by the minimum confidence strategy, x represents the earthquake key features corresponding to the unlabeled earthquake data, represents the label with the highest probability predicted by the active learner model, P θ Represents the predicted probability output by the active learner model.

[0057] It should be noted that through the minimum confidence strategy, the earthquake data with the highest prediction probability and low credibility of the active learner model can be screened out and labeled as high-value samples.

[0058] S240: Label the target unlabeled seismic data to obtain a target wave impedance label corresponding to the target unlabeled seismic data.

[0059] In this embodiment, the marking method includes online marking or offline marking, which is not specifically limited here.

[0060] S250, performing iterative replacement processing according to the target wave impedance labels corresponding to the target unlabeled seismic data to obtain the wave impedance labels of the unlabeled seismic data.

[0061] Specifically, determine the random wave impedance labels of the unlabeled seismic data; replace the random wave impedance labels of the unlabeled seismic data according to the target wave impedance labels corresponding to the target unlabeled seismic data, and update the active learner model based on the target unlabeled seismic data and the target wave impedance labels corresponding to the target unlabeled seismic data until the active learner model meets the training stop condition, stop label replacement, and obtain the wave impedance labels of the unlabeled seismic data. It should be noted that through the above iterative replacement process, high-precision wave impedance labels of unlabeled seismic data can be obtained.

[0062] S260: Training a neural network model based on the unlabeled seismic data and the wave impedance labels of the unlabeled seismic data to obtain a trained inversion mapping model.

[0063] In some optional embodiments, after obtaining the trained inversion mapping model, it also includes: fine-tuning the inversion mapping model based on the seismic data to be trained and the wave impedance labels corresponding to the seismic data to be trained to obtain a target inversion mapping model to improve the performance of the inversion mapping model.

[0064] The technical solution of the embodiment of the present invention obtains target unlabeled seismic data by querying unlabeled seismic data, and then labels the target unlabeled seismic data to obtain target wave impedance labels corresponding to the target unlabeled seismic data, and then iteratively replaces the target wave impedance labels corresponding to the target unlabeled seismic data to obtain high-precision wave impedance labels for the unlabeled seismic data, thereby solving the problem of limited number of labels.

[0065] Embodiment 3

[0066] Figure 3A flow chart of an inversion mapping model training method provided in Embodiment 3 of the present invention, the method of this embodiment can be combined with the various optional schemes in the inversion mapping model training method provided in the above embodiments. The inversion mapping model training method provided in this embodiment is further optimized. Optionally, the neural network model is trained based on the unlabeled seismic data and the wave impedance labels of the unlabeled seismic data to obtain a trained inversion mapping model, including: training an encoder-decoder structure network model based on the unlabeled seismic data and the wave impedance labels of the unlabeled seismic data to obtain a trained inversion mapping model.

[0067] like Figure 3 As shown, the method includes:

[0068] S310: Obtain seismic data to be trained and wave impedance labels corresponding to the seismic data to be trained.

[0069] S320: Train the initial learner based on the seismic data to be trained and the wave impedance labels corresponding to the seismic data to be trained to obtain an active learner model.

[0070] S330, obtaining unlabeled seismic data, inputting the unlabeled seismic data into an active learner model, and obtaining a wave impedance label of the unlabeled seismic data.

[0071] S340: training an encoder-decoder structure network model based on the unlabeled seismic data and the wave impedance labels of the unlabeled seismic data to obtain a trained inversion mapping model.

[0072] In this embodiment, the encoder-decoder structure network model refers to a U-Net network model, which includes a feature extraction part and a feature fusion part. The feature extraction part is used to downsample the unlabeled seismic data to obtain multiple levels of feature information of the unlabeled seismic data; the feature fusion part is used to fuse the feature information of multiple levels of the unlabeled seismic data through jump connections, so that the network model can learn the shallow and deep features of the seismic data, thereby improving the training accuracy of the inversion mapping model.

[0073] The technical solution of the embodiment of the present invention is to train the encoder-decoder structure network model according to the unlabeled seismic data and the wave impedance labels of the unlabeled seismic data to obtain a trained inversion mapping model, so that the model can learn the shallow and deep features of the seismic data, thereby improving the training accuracy of the inversion mapping model.

[0074] Embodiment 4

[0075] Figure 4This is a schematic diagram of the structure of an inversion mapping model training device provided in Embodiment 4 of the present invention. Figure 4 As shown, the device comprises:

[0076] The training sample acquisition module 410 is used to acquire the seismic data to be trained and the wave impedance labels corresponding to the seismic data to be trained;

[0077] An active learner training module 420 is used to train an initial learner based on the seismic data to be trained and the wave impedance labels corresponding to the seismic data to be trained to obtain an active learner model;

[0078] The wave impedance label determination module 430 is used to obtain unlabeled seismic data, input the unlabeled seismic data into the active learner model, and obtain the wave impedance label of the unlabeled seismic data;

[0079] The inversion mapping model training module 440 is used to train the neural network model based on the unlabeled seismic data and the wave impedance labels of the unlabeled seismic data to obtain a trained inversion mapping model.

[0080] The technical solution of the embodiment of the present invention realizes the automatic generation of wave impedance labels for unlabeled seismic data through active learning simulation, solves the problem of limited number of labels, and then trains the neural network model through the unlabeled seismic data and the wave impedance labels corresponding to the unlabeled seismic data, thereby realizing high-precision inversion mapping model training in the absence of labeled samples, thereby improving the training accuracy of the model.

[0081] In some optional implementations, the wave impedance tag determination module 430 includes:

[0082] A seismic data query unit, used for querying the unlabeled seismic data to obtain target unlabeled seismic data;

[0083] A seismic data labeling unit, used for labeling the target unlabeled seismic data to obtain a target wave impedance label corresponding to the target unlabeled seismic data;

[0084] The wave impedance label replacement unit is used to perform iterative replacement processing according to the target wave impedance label corresponding to the target unlabeled seismic data to obtain the wave impedance label of the unlabeled seismic data.

[0085] In some optional implementations, the seismic data query unit includes:

[0086] A seismic key feature extraction subunit, used for extracting features from the unlabeled seismic data to obtain seismic key features corresponding to the unlabeled seismic data;

[0087] The target seismic data screening subunit is used to screen the seismic key features corresponding to the unlabeled seismic data through a preset selection strategy to obtain the target unlabeled seismic data.

[0088] In some optional implementations, the target seismic data screening subunit may also be used to:

[0089] The key seismic features corresponding to the unlabeled seismic data are screened using a preset minimum confidence strategy to obtain target unlabeled seismic data.

[0090] In some optional implementations, the wave impedance label replacement unit may also be specifically used for:

[0091] determining random wave impedance labels for the unlabeled seismic data;

[0092] According to the target wave impedance label corresponding to the target unlabeled seismic data, the random wave impedance label of the unlabeled seismic data is replaced, and the active learner model is updated based on the target unlabeled seismic data and the target wave impedance label corresponding to the target unlabeled seismic data until the active learner model meets the training stop condition, stops label replacement, and obtains the wave impedance label of the unlabeled seismic data.

[0093] In some optional implementations, the inversion mapping model training module 440 may also be used to:

[0094] The encoder-decoder structure network model is trained based on the unlabeled seismic data and the wave impedance labels of the unlabeled seismic data to obtain a trained inversion mapping model.

[0095] In some optional embodiments, the inversion mapping model training device further includes:

[0096] An actual earthquake data acquisition module, used for acquiring actual earthquake data;

[0097] The wave impedance prediction module is used to input the actual seismic data into the trained inversion mapping model to obtain the wave impedance corresponding to the actual seismic data.

[0098] The inversion mapping model training device provided in the embodiment of the present invention can execute the inversion mapping model training method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0099] Embodiment 5

[0100] Figure 5A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0101] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The I / O interface 15 is also connected to the bus 14.

[0102] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0103] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 performs the various methods and processes described above, such as the inversion mapping model training method, which includes:

[0104] Acquire seismic data to be trained and wave impedance labels corresponding to the seismic data to be trained;

[0105] Training an initial learner based on the seismic data to be trained and wave impedance labels corresponding to the seismic data to be trained to obtain an active learner model;

[0106] Acquire unlabeled seismic data, input the unlabeled seismic data into an active learner model, and obtain a wave impedance label of the unlabeled seismic data;

[0107] The neural network model is trained based on the unlabeled seismic data and the wave impedance labels of the unlabeled seismic data to obtain a trained inversion mapping model.

[0108] In some embodiments, the inversion mapping model training method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the inversion mapping model training method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the inversion mapping model training method in any other appropriate manner (e.g., by means of firmware).

[0109] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0110] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0111] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0112] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0113] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0114] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0115] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0116] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for training an inversion mapping model, characterized in that: include: Acquire seismic data to be trained and wave impedance labels corresponding to the seismic data to be trained; Training an initial learner based on the seismic data to be trained and wave impedance labels corresponding to the seismic data to be trained to obtain an active learner model; Acquire unlabeled seismic data, input the unlabeled seismic data into an active learner model, and obtain a wave impedance label of the unlabeled seismic data; The neural network model is trained based on the unlabeled seismic data and the wave impedance labels of the unlabeled seismic data to obtain a trained inversion mapping model.

2. The method according to claim 1, characterized in that: The step of inputting the unlabeled seismic data into an active learner model to obtain a wave impedance label of the unlabeled seismic data includes: Querying the unlabeled seismic data to obtain target unlabeled seismic data; Labeling the target unlabeled seismic data to obtain a target wave impedance label corresponding to the target unlabeled seismic data; An iterative replacement process is performed according to the target wave impedance labels corresponding to the target unlabeled seismic data to obtain the wave impedance labels of the unlabeled seismic data.

3. The method according to claim 2, characterized in that The querying of the unlabeled seismic data to obtain target unlabeled seismic data includes: Extracting features from the unlabeled seismic data to obtain key seismic features corresponding to the unlabeled seismic data; The key seismic features corresponding to the unlabeled seismic data are screened by a preset selection strategy to obtain target unlabeled seismic data.

4. The method according to claim 3, characterized in that The method of screening the seismic key features corresponding to the unlabeled seismic data by a preset selection strategy to obtain target unlabeled seismic data includes: The key seismic features corresponding to the unlabeled seismic data are screened using a preset minimum confidence strategy to obtain target unlabeled seismic data.

5. The method according to claim 2, characterized in that: The iterative replacement process is performed according to the target wave impedance label corresponding to the target unlabeled seismic data to obtain the wave impedance label of the unlabeled seismic data, including: determining random wave impedance labels for the unlabeled seismic data; According to the target wave impedance label corresponding to the target unlabeled seismic data, the random wave impedance label of the unlabeled seismic data is replaced, and the active learner model is updated based on the target unlabeled seismic data and the target wave impedance label corresponding to the target unlabeled seismic data until the active learner model meets the training stop condition, stops label replacement, and obtains the wave impedance label of the unlabeled seismic data.

6. The method according to claim 1, characterized in that The neural network model is trained based on the unlabeled seismic data and the wave impedance labels of the unlabeled seismic data to obtain a trained inversion mapping model, including: The encoder-decoder structure network model is trained based on the unlabeled seismic data and the wave impedance labels of the unlabeled seismic data to obtain a trained inversion mapping model.

7. The method according to any one of claims 1 to 6, characterized in that: After the trained inversion mapping model is obtained, the method further includes: Obtain actual earthquake data; The actual seismic data is input into the trained inversion mapping model to obtain the wave impedance corresponding to the actual seismic data.

8. An inversion mapping model training device, characterized in that: include: A training sample acquisition module, used to acquire seismic data to be trained and wave impedance labels corresponding to the seismic data to be trained; An active learner training module, used for training an initial learner based on the seismic data to be trained and the wave impedance labels corresponding to the seismic data to be trained, to obtain an active learner model; A wave impedance label determination module, used for acquiring unlabeled seismic data, inputting the unlabeled seismic data into an active learner model, and obtaining a wave impedance label of the unlabeled seismic data; The inversion mapping model training module is used to train the neural network model based on the unlabeled seismic data and the wave impedance labels of the unlabeled seismic data to obtain a trained inversion mapping model.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the inversion mapping model training method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the inversion mapping model training method according to any one of claims 1 to 7 when executed.

Images