Method, device and equipment for determining total organic carbon content and medium

Abstract

The invention discloses a total organic carbon content determination method and device, equipment and a medium. According to the method, logging data, corresponding to different depths, of a target well are input into a pre-trained depth sequence model, and total organic carbon content prediction data of the target well are obtained; according to the logging data, the corresponding shale content of the target well at each depth is determined; and according to the shale content corresponding to each depth of the target well, correcting the total organic carbon content prediction data to obtain total organic carbon content correction data of the target well. According to the technical scheme, by considering the incidence relation among the logging data, the total organic carbon content and the depth and the influence degree of the shale content on the total organic carbon content, the total organic carbon content of the uncored well at each depth is accurately and effectively predicted, and data support is provided for oil-gas exploration evaluation.

Description

Technical Field

[0001] The present application relates to the technical field of geochemical analysis and oil and gas exploration potential evaluation, and in particular to a method, device, equipment and medium for determining total organic carbon content. Background Art

[0002] Source rock evaluation plays a key role in the study of oil and gas accumulation and resource potential. The determination of organic matter abundance is of great significance to the understanding of the hydrocarbon generation potential of various source rocks. The total organic carbon content is a key parameter for evaluating organic matter abundance, and it is also the basis for source rock evaluation and a key parameter affecting oil and gas resource evaluation. At present, oil and gas exploration in some oil fields in my country is gradually transforming from conventional to unconventional. The total organic carbon content has become one of the key parameters for the evaluation of the "seven properties" of unconventional shale reservoirs. It is necessary to establish an effective method for evaluating the total organic carbon of source rocks.

[0003] The total organic carbon content is usually obtained by geochemical sampling and analysis, and the total organic carbon content of rocks is measured by rock pyrolysis analyzer. However, due to the high cost of sampling and analysis, the total organic carbon content of each depth section in the well is usually not measured.

[0004] In recent years, with the vigorous exploration and development of unconventional oil and gas resources, estimating the distribution of total organic carbon content through geophysical technology has become an important means of predicting the distribution of effective source rocks. At present, there are mainly two ways to predict the total organic carbon content using geophysical methods:

[0005] 1) The ΔlogR method, multivariate regression analysis and other basic statistical analysis methods are mainly used. ΔlogR is to use the overlap of the acoustic time difference curve and the resistivity curve in the non-source rock layer as the baseline value of the total organic carbon content of 0, and the difference between the two curves reflects the abundance of organic matter; the multivariate regression analysis method is to predict by establishing a mathematical relationship between multiple independent variables and the dependent variable total organic carbon content. Both main statistical analysis methods have the problems of weak generalization ability, poor applicability and strong subjectivity.

[0006] 2) In recent years, with the development of machine learning methods, scholars have proposed two new methods for predicting total organic carbon content: conventional machine learning and neural networks. Conventional machine learning methods aim to establish a "point-to-point" mapping relationship between sensitive parameters and total organic carbon content, such as support vector machine method, Gaussian regression method, random forest method, etc. Neural network methods can adaptively establish complex mapping relationships between sensitive parameters and total organic carbon content, but are limited by the standardization of logging data between multiple wells, making it difficult to make regional predictions, and unable to reflect the influence of deep compaction trends and mud content on total organic carbon content. Only the mudstone section of some well sections is accurately predicted, and the prediction accuracy of the entire well section is low.

[0007] Therefore, how to provide a technical solution that can accurately and effectively predict the total organic carbon content is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0008] The present application provides a method, device, equipment and medium for determining the total organic carbon content. By considering the correlation between logging data, total organic carbon content and depth, and the influence of mud content on the total organic carbon content, the total organic carbon content at each depth of uncored wells is accurately and effectively predicted, providing data support for oil and gas exploration and evaluation.

[0009] According to one aspect of the present application, a method for determining total organic carbon content is provided, the method comprising:

[0010] Inputting the well logging data corresponding to the target well at different depths into the pre-trained depth sequence model to obtain the total organic carbon content prediction data of the target well;

[0011] Determining the shale content corresponding to each depth of the target well according to the well logging data;

[0012] According to the mud content corresponding to each depth of the target well, the total organic carbon content prediction data is corrected to obtain the total organic carbon content correction data of the target well.

[0013] According to another aspect of the present application, a device for determining total organic carbon content is provided, the device comprising:

[0014] A total organic carbon content prediction module is used to input the logging data corresponding to the target well at different depths into a pre-trained depth sequence model to obtain the total organic carbon content prediction data of the target well;

[0015] A shale content determination module, used to determine the shale content corresponding to each depth of the target well according to the well logging data;

[0016] The total organic carbon content correction module is used to correct the total organic carbon content prediction data according to the mud content corresponding to each depth of the target well to obtain the total organic carbon content correction data of the target well.

[0017] According to another aspect of the present application, there is provided a device for determining total organic carbon content, the device comprising:

[0018] At least one processor; and a memory communicatively connected to the at least one processor; wherein 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 method for determining the total organic carbon content described in any embodiment of the present application.

[0019] According to another aspect of the present application, 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 method for determining the total organic carbon content described in any embodiment of the present application when executed.

[0020] The technical solution provided by the present application obtains the total organic carbon content prediction data of the target well by inputting the well logging data corresponding to different depths into the pre-trained depth sequence model; determines the mud content corresponding to each depth of the target well according to the well logging data; and corrects the total organic carbon content prediction data according to the mud content corresponding to each depth of the target well to obtain the total organic carbon content correction data of the target well. The present technical solution accurately and effectively predicts the total organic carbon content of uncored wells at each depth by considering the correlation between well logging data, total organic carbon content and depth, and the influence of mud content on total organic carbon content, providing data support for oil and gas exploration and evaluation.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application 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 application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A flow chart of a method for determining total organic carbon content provided in Example 1 of the present application;

[0024] Figure 2 A flowchart of a training process of a deep sequence model provided in Example 2 of the present application;

[0025] Figure 3 A schematic diagram of the structure of a device for determining total organic carbon content provided in Example 3 of the present application;

[0026] Figure 4 It is a structural schematic diagram of a device for implementing a method for determining total organic carbon content in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0028] It should be noted that the terms "target", "candidate", "standard", "initial", "prediction", "measured", "correction", etc. in the specification and claims of the present application 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 interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations 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.

[0029] Embodiment 1

[0030] Figure 1 This is a flowchart of a method for determining total organic carbon content provided in Example 1 of the present application. This embodiment is applicable to the case of predicting the total organic carbon content of an uncored well. The method can be executed by a device for determining total organic carbon content. The device for determining total organic carbon content can be implemented in the form of hardware and / or software. The device for determining total organic carbon content can be configured in a device with data processing capabilities. Figure 1 As shown, the method includes:

[0031] S110, inputting the well logging data corresponding to the target well at different depths into a pre-trained depth sequence model to obtain the total organic carbon content prediction data of the target well.

[0032] The target well may be an uncored well. The logging data may be data obtained by electrical logging or non-electrical logging of the target well, such as logging curves. Specifically, when logging the target well, the logging data corresponding to each depth may be obtained at preset depth intervals in the target layer, such as acoustic wave, density, natural gamma, deep lateral resistivity, shallow lateral resistivity, natural potential, etc.

[0033] Among them, the deep sequence model can be a long short-term memory neural network model. By training the sequential sequence data, a nonlinear mapping relationship between the total organic carbon content with a depth-dependent change trend and multiple types of logging data is obtained. The total organic carbon content refers to the volume percentage of organic carbon per unit mass of rock at a certain depth, reflecting the hydrocarbon generation potential characteristics of the target well area.

[0034] Specifically, the logging data corresponding to the target well at different depths can be input into the depth sequence model, and the total organic carbon content of the target well at each depth can be predicted according to the trend and nonlinear mapping relationship trained by the depth sequence model.

[0035] S120: Determine the mud content corresponding to each depth of the target well according to the well logging data.

[0036] Among them, the mud content refers to the volume percentage of debris with a particle diameter of less than 0.01mm in a unit volume of rock at a certain depth. When the mud content is 100%, the rock here is pure mudstone; when the mud content is 0%, the rock here is pure sandstone.

[0037] Specifically, the shale content can be determined by natural potential logging, natural gamma logging or cross plot method. For example, the natural gamma method takes the difference between pure mudstone and pure sandstone as the change in logging reading caused by the shale content of 100%, and takes its relative value as the shale content; the natural potential logging method uses the different properties of the surface charge of sandstone minerals and clay minerals to determine the shale content.

[0038] Optionally, determining the mud content corresponding to each depth of the target well according to the logging data, including: determining the natural gamma value of each depth, the natural gamma value of pure sandstone, and the natural gamma value of pure mudstone according to the logging data; determining the mud content corresponding to the target well at each depth according to the natural gamma value of each depth, the natural gamma value of pure sandstone, and the natural gamma value of pure mudstone.

[0039] In this scheme, the natural gamma curve of the target well can be obtained by the natural gamma logging method, the natural gamma value at each depth can be obtained according to the natural gamma curve, and the natural gamma value of pure sandstone and the natural gamma value of pure mudstone can be determined.

[0040] Since the natural gamma value of sandstone is very low in theory and the clay adsorbed by mudstone has high radioactivity, the minimum value of the natural gamma curve can be taken as the natural gamma value of pure sandstone, and the maximum value of the natural gamma curve can be taken as the natural gamma value of pure mudstone.

[0041] Furthermore, the following formula can be used to determine the mud content corresponding to each depth of the target well:

[0042]

[0043] Where V_Shale i is the shale content of the target well at depth i, GR i is the natural gamma value of the target well at depth i, GR max is the natural gamma value of pure mudstone in the target well, GR min is the natural gamma value of pure sandstone in the target well.

[0044] S130, correcting the total organic carbon content prediction data according to the mud content corresponding to each depth of the target well to obtain the total organic carbon content correction data of the target well.

[0045] Generally speaking, only mudstone contains organic carbon, while sandstone does not contain organic carbon or has a low content of total organic carbon. Therefore, it is necessary to correct the predicted total organic carbon content data according to the mud content at different depths to obtain the corrected total organic carbon content data of the target well.

[0046] In this solution, the total organic carbon content correction data can be determined based on the mud content and total organic carbon content prediction data corresponding to each depth of the target well. For example, the product of the mud content and total organic carbon content prediction data at each depth can be used as the total organic carbon content correction data.

[0047] Optionally, the predicted data of total organic carbon content are corrected according to the mud content corresponding to each depth of the target well to obtain the corrected data of total organic carbon content of the target well, including: determining the correction coefficient corresponding to each depth according to the mud content corresponding to each depth of the target well; determining the corrected data of total organic carbon content corresponding to each depth of the target well according to the mud content corresponding to each depth of the target well, the predicted data of total organic carbon content corresponding to each depth of the target well, and the correction coefficient.

[0048] In this solution, the correction coefficient of the predicted total organic carbon content data can be determined according to the shale content, and then the predicted total organic carbon content data can be corrected according to the correction coefficient to obtain the corrected total organic carbon content data of the target well. The greater the shale content, the smaller the correction coefficient.

[0049] For example, the correction coefficient may be determined according to the average value of the shale content at each depth in the target layer, or may be determined according to the shale content at each depth, or may be determined according to actual conditions. The embodiment of the present invention does not limit this.

[0050] Optionally, according to the shale content corresponding to each depth of the target well, the predicted data of the total organic carbon content corresponding to each depth of the target well and the correction coefficient, the correction data of the total organic carbon content corresponding to each depth of the target well is determined, including: using the following formula to determine the correction data of the total organic carbon content corresponding to each depth of the target well: TOC i =V_Shale i ×TOC i ′ × i ; In the formula, TOC i V_Shale is the total organic carbon content correction data of the target well at depth i, i is the shale content of the target well at depth i, TOC i ′ is the predicted data of total organic carbon content at depth i of the target well, w i is the correction coefficient of the target well at depth i.

[0051] In this scheme, the total organic carbon content correction data can be determined based on the mud content at each depth, the correction coefficient and the total organic carbon content prediction data.

[0052] The beneficial effect of the above technical solution is that the prediction data of the total organic carbon content is constrained by the mud content, thereby improving the prediction accuracy of the total organic carbon content.

[0053] The embodiment of the present invention provides a method for determining the total organic carbon content. The method obtains the total organic carbon content prediction data of the target well by inputting the well logging data corresponding to different depths of the target well into a pre-trained depth sequence model; determines the mud content corresponding to each depth of the target well according to the well logging data; and corrects the total organic carbon content prediction data according to the mud content corresponding to each depth of the target well to obtain the total organic carbon content correction data of the target well. This technical solution accurately and effectively predicts the total organic carbon content of uncored wells at each depth by considering the correlation between well logging data, total organic carbon content and depth, and the influence of mud content on total organic carbon content, thereby providing data support for oil and gas exploration and evaluation.

[0054] Embodiment 2

[0055] Figure 2 This is a flowchart of a training process of a deep sequence model provided in the second embodiment of the present application. This embodiment is optimized based on the above embodiment. Figure 2 As shown, the method of this embodiment specifically includes the following steps:

[0056] S210. Collect logging data of at least two depths in at least one candidate well, and obtain the actual measured values ​​of total organic carbon content corresponding to the at least two depths, and use the logging data and the actual measured values ​​of total organic carbon content corresponding to each depth as sample data; wherein the candidate well and the target well are different wells in the same area to be studied.

[0057] The candidate wells may be cored wells. To ensure the validity of the sample data for training the depth sequence model, wells that belong to the same study area as the target well may be used as candidate wells.

[0058] In this scheme, the same logging method can be used to collect logging data of at least one candidate well, and the logging data of each candidate well in the same target layer section can be intercepted; at the same time, the cores of each candidate well in the same target layer section are collected and laboratory analyzed to obtain the actual measured values ​​of the total organic carbon content at each depth in the target layer section.

[0059] S220: normalize the sample data to obtain standard sample data.

[0060] Since the measurement scales of various types of well logging data and total organic carbon content are not uniform in the sample data, the subsequent model training process will require a large amount of calculation. Therefore, feature engineering can be performed on each data in the sample data set to eliminate the dimensional influence between data features, making different types of data computable and facilitating the subsequent model training process.

[0061] Specifically, the sample data can be normalized by the following formula to obtain standard sample data:

[0062] x ′ =(x-mean) / std;

[0063] In the formula, x ′ is the standard sample data, x is the sample data, mean is the mean of the sample data, and std is the standard deviation of the sample data.

[0064] S230: Input the standard sample data into an initial model, train the initial model, and obtain a deep sequence model.

[0065] The training method can be supervised training or unsupervised training.

[0066] The initial model may include an input layer, a hidden layer and an output layer. The input layer is used to process abnormal values ​​or missing values ​​of the normalized sample data, the hidden layer is used to train the sample data, and the output layer is used to output the prediction results of the total organic carbon content.

[0067] It is understandable that when collecting cores from candidate wells, core data at some depths may be missing or damaged, making it impossible to obtain the total organic carbon content at the corresponding depth, but this will not affect the training process of the depth sequence model.

[0068] Optionally, the standard sample data is input into an initial model, and the initial model is trained to obtain a deep sequence model, including: based on a preset sliding window, the standard sample data is intercepted to obtain at least two sub-standard sample data; according to each of the sub-standard sample data, the total organic carbon content of the target depth is predicted using the initial model to obtain a predicted value of the total organic carbon content; based on a preset loss function, the predicted value of the total organic carbon content and the measured value of the total organic carbon content are calculated to obtain a loss function value; based on the loss function value, the initial model is optimized to obtain a deep sequence model.

[0069] The preset sliding window may be determined according to the depth range. Specifically, based on the size of the preset sliding window, the standard sample data is intercepted according to the depth sequence to obtain sub-standard sample data.

[0070] Exemplarily, if the preset number of windows is 5, the sub-standard sample data corresponding to the first depth sequence may be sample data corresponding to the depth sampling points of {d1, d2, d3, d4, d5}, the sub-standard sample data corresponding to the second depth sequence may be sample data corresponding to the depth sampling points of {d2, d3, d4, d5, d6}, and the sub-standard sample data corresponding to the third depth sequence may be sample data corresponding to the depth sampling points of {d3, d4, d5, d6, d7}, and so on.

[0071] Furthermore, the total organic carbon content at the target depth is predicted based on the sub-standard sample data corresponding to each depth sequence to obtain a predicted value of the total organic carbon content.

[0072] During the training process, based on a preset loss function, the predicted value of the total organic carbon content and the measured value of the total organic carbon content are calculated to obtain a loss function value. Optionally, the loss of the training model can be represented by a root mean square error, the error can be represented by an absolute error, and the loss function can be represented by a linear integer tanh function.

[0073] Furthermore, the initial model is optimized based on the loss function value until the termination condition of the model training is met to obtain a deep sequence model. The termination condition of the model training may be the number of training times or the degree of convergence of the model.

[0074] Accordingly, the logging data corresponding to the target well at different depths are input into a pre-trained depth sequence model to obtain the total organic carbon content prediction data of the target well, including: inputting the logging data corresponding to the target well at different depths into a pre-trained depth sequence model to obtain the standard total organic carbon content prediction data of the target well; and performing denormalization processing on the standard total organic carbon content prediction curve to obtain the total organic carbon content prediction data.

[0075] Specifically, the following formula can be used to perform inverse normalization on the standard total organic carbon content prediction curve to obtain the total organic carbon content prediction data:

[0076] x″=std×x ′ +mean;

[0077] Where x″ is the predicted data of total organic carbon content.

[0078] It should be noted that after obtaining the depth sequence model, the logging data and the measured values ​​of the total organic carbon content of the candidate wells that did not participate in the model training can be used as test sample data to test and adjust the depth sequence model to ensure the accuracy of the depth sequence model's prediction of the total organic carbon content.

[0079] The embodiment of the present invention provides a training process for a depth sequence model, by collecting logging data of at least two depths in at least one candidate well, and obtaining the measured values ​​of the total organic carbon content corresponding to the at least two depths, the logging data corresponding to each depth and the measured values ​​of the total organic carbon content are used as sample data; wherein the candidate well and the target well are different wells in the same area to be studied; the sample data are normalized to obtain standard sample data; the standard sample data are input into the initial model, the initial model is trained, and the depth sequence model is obtained. This technical solution constructs a depth sequence model through the data of the cored wells in the same area, determines the trend of the logging data and the total organic carbon content with the depth, so as to achieve accurate and effective prediction of the total organic carbon content of the uncored wells.

[0080] Embodiment 3

[0081] Figure 3 This is a schematic diagram of a device for determining total organic carbon content provided in Example 4 of the present application. Figure 3 As shown, the device comprises:

[0082] The total organic carbon content prediction module 310 is used to input the well logging data corresponding to the target well at different depths into the pre-trained depth sequence model to obtain the total organic carbon content prediction data of the target well;

[0083] A shale content determination module 320 is used to determine the shale content corresponding to each depth of the target well according to the well logging data;

[0084] The total organic carbon content correction module 330 is used to correct the total organic carbon content prediction data according to the mud content corresponding to each depth of the target well to obtain the total organic carbon content correction data of the target well.

[0085] The embodiment of the present invention provides a device for determining the total organic carbon content, which obtains the total organic carbon content prediction data of the target well by inputting the well logging data corresponding to the target well at different depths into a pre-trained depth sequence model; determines the mud content corresponding to the target well at each depth according to the well logging data; and corrects the total organic carbon content prediction data according to the mud content corresponding to the target well at each depth to obtain the total organic carbon content correction data of the target well. This technical solution accurately and effectively predicts the total organic carbon content of uncored wells at each depth by considering the correlation between well logging data, total organic carbon content and depth, and the influence of mud content on total organic carbon content, thereby providing data support for oil and gas exploration and evaluation.

[0086] Furthermore, the training process of the deep sequence model includes:

[0087] Collecting well logging data of at least two depths in at least one candidate well, and obtaining measured values ​​of total organic carbon content corresponding to the at least two depths, and using the well logging data and measured values ​​of total organic carbon content corresponding to each depth as sample data; wherein the candidate well and the target well are different wells in the same area to be studied;

[0088] Normalizing the sample data to obtain standard sample data;

[0089] The standard sample data is input into the initial model, and the initial model is trained to obtain a deep sequence model.

[0090] Furthermore, the standard sample data is input into the initial model, and the initial model is trained to obtain a deep sequence model, including:

[0091] Based on a preset sliding window, the standard sample data is intercepted to obtain at least two sub-standard sample data;

[0092] According to each of the sub-standard sample data, the total organic carbon content of the target depth is predicted using the initial model to obtain a predicted value of the total organic carbon content;

[0093] Based on a preset loss function, the predicted value of the total organic carbon content and the measured value of the total organic carbon content are calculated to obtain a loss function value;

[0094] The initial model is optimized based on the loss function value to obtain a deep sequence model.

[0095] Furthermore, the well logging data corresponding to the target well at different depths are input into the pre-trained depth sequence model to obtain the total organic carbon content prediction data of the target well, including:

[0096] Inputting the well logging data corresponding to the target well at different depths into the pre-trained depth sequence model to obtain the standard total organic carbon content prediction data of the target well;

[0097] The standard total organic carbon content prediction curve is subjected to a reverse normalization process to obtain total organic carbon content prediction data.

[0098] Furthermore, the mud content determination module 320 includes:

[0099] A basic parameter determination unit, used to determine the natural gamma value at each depth, the natural gamma value of pure sandstone, and the natural gamma value of pure mudstone according to the well logging data;

[0100] The shale content determination unit is used to determine the shale content corresponding to each depth of the target well according to the natural gamma value of each depth, the natural gamma value of the pure sandstone and the natural gamma value of the pure mudstone.

[0101] Furthermore, the total organic carbon content correction module 330 includes:

[0102] A correction coefficient determination unit, used to determine the correction coefficient corresponding to each depth according to the shale content corresponding to each depth of the target well;

[0103] The total organic carbon content correction unit is used to determine the total organic carbon content correction data corresponding to each depth of the target well according to the mud content corresponding to each depth of the target well, the total organic carbon content prediction data corresponding to each depth of the target well and the correction coefficient.

[0104] Furthermore, the total organic carbon content correction unit is specifically used for:

[0105] The following formula is used to determine the total organic carbon content correction data corresponding to each depth of the target well:

[0106] TOC i =V_Shale i ×TOC′ i × i ;

[0107] In the formula, TOC i V_Shale is the total organic carbon content correction data of the target well at depth i,i is the shale content of the target well at depth i, TOC′ i is the predicted data of total organic carbon content at depth i of the target well, w i is the correction coefficient of the target well at depth i.

[0108] A device for determining total organic carbon content provided in an embodiment of the present application can execute a method for determining total organic carbon content provided in any embodiment of the present application, and has functional modules and beneficial effects corresponding to the execution method.

[0109] Embodiment 4

[0110] Figure 4 A schematic diagram of a device 10 that can be used to implement an embodiment of the present application is shown. The device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The device can also represent various forms of mobile devices, such as personal digital processing, 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 application described and / or required herein.

[0111] like Figure 4 As shown, the 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 device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0112] A number of components in the 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 device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0113] 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, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for determining the total organic carbon content.

[0114] In some embodiments, the method for determining the total organic carbon content 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 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 method for determining the total organic carbon content described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the method for determining the total organic carbon content in any other appropriate manner (e.g., by means of firmware).

[0115] 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), load 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.

[0116] The computer programs for implementing the methods of the present application 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 programs are executed by the processor, the functions / operations specified in the flow charts and / or block diagrams are implemented. The computer programs 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.

[0117] In the context of the present application, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction 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.

[0118] To provide interaction with a user, the systems and techniques described herein can be implemented on a 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 device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0119] 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.

[0120] 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.

[0121] 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 recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution of this application can be achieved, and this document is not limited here.

[0122] The above specific implementations do not constitute a limitation on the protection scope of this application. 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 modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for determining total organic carbon content, characterized in that: The method comprises: Inputting the well logging data corresponding to the target well at different depths into the pre-trained depth sequence model to obtain the total organic carbon content prediction data of the target well; Determining the shale content corresponding to each depth of the target well according to the well logging data; According to the mud content corresponding to each depth of the target well, the total organic carbon content prediction data is corrected to obtain the total organic carbon content correction data of the target well.

2. The method according to claim 1, characterized in that The training process of the deep sequence model includes: Collecting well logging data of at least two depths in at least one candidate well, and obtaining measured values ​​of total organic carbon content corresponding to the at least two depths, and using the well logging data and measured values ​​of total organic carbon content corresponding to each depth as sample data; wherein the candidate well and the target well are different wells in the same area to be studied; Normalizing the sample data to obtain standard sample data; The standard sample data is input into the initial model, and the initial model is trained to obtain a deep sequence model.

3. The method according to claim 2, characterized in that Inputting the standard sample data into the initial model, training the initial model, and obtaining a deep sequence model, including: Based on a preset sliding window, the standard sample data is intercepted to obtain at least two sub-standard sample data; According to each of the sub-standard sample data, the total organic carbon content of the target depth is predicted using the initial model to obtain a predicted value of the total organic carbon content; Based on a preset loss function, the predicted value of the total organic carbon content and the measured value of the total organic carbon content are calculated to obtain a loss function value; The initial model is optimized based on the loss function value to obtain a deep sequence model.

4. The method according to claim 2, characterized in that: The well logging data corresponding to the target well at different depths are input into the pre-trained depth sequence model to obtain the total organic carbon content prediction data of the target well, including: Inputting the well logging data corresponding to the target well at different depths into the pre-trained depth sequence model to obtain the standard total organic carbon content prediction data of the target well; The standard total organic carbon content prediction curve is subjected to a reverse normalization process to obtain total organic carbon content prediction data.

5. The method according to claim 1, characterized in that Determining the shale content corresponding to each depth of the target well according to the well logging data includes: Determine the natural gamma value at each depth, the natural gamma value of pure sandstone, and the natural gamma value of pure mudstone according to the logging data; The mud content corresponding to each depth of the target well is determined according to the natural gamma value at each depth, the natural gamma value of the pure sandstone and the natural gamma value of the pure mudstone.

6. The method according to claim 1, characterized in that According to the shale content corresponding to each depth of the target well, the total organic carbon content prediction data is corrected to obtain the total organic carbon content correction data of the target well, including: Determine the correction coefficient corresponding to each depth according to the mud content corresponding to each depth of the target well; According to the mud content corresponding to each depth of the target well, the predicted data of the total organic carbon content corresponding to each depth of the target well and the correction coefficient, the correction data of the total organic carbon content corresponding to each depth of the target well is determined.

7. The method according to claim 6, characterized in that According to the shale content corresponding to each depth of the target well, the predicted data of the total organic carbon content corresponding to each depth of the target well and the correction coefficient, the correction data of the total organic carbon content corresponding to each depth of the target well is determined, including: The following formula is used to determine the total organic carbon content correction data corresponding to each depth of the target well: TOC i =V_Shale i ×TOC′ i ×w i ; In the formula, TOC i V_Shale is the total organic carbon content correction data of the target well at depth i, i is the shale content of the target well at depth i, TOC′ i is the predicted data of total organic carbon content at depth i of the target well, w i is the correction coefficient of the target well at depth i.

8. A device for determining total organic carbon content, characterized in that: The device comprises: A total organic carbon content prediction module is used to input the logging data corresponding to the target well at different depths into a pre-trained depth sequence model to obtain the total organic carbon content prediction data of the target well; A shale content determination module, used to determine the shale content corresponding to each depth of the target well according to the well logging data; The total organic carbon content correction module is used to correct the total organic carbon content prediction data according to the mud content corresponding to each depth of the target well to obtain the total organic carbon content correction data of the target well.

9. An electronic device, characterized in that: The device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, 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 perform the method for determining the total organic carbon content according to 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 method for determining the total organic carbon content according to any one of claims 1 to 7 when executed.

Images