Sensitive parameter determination method, device, computer equipment and storage medium

Abstract

The present application provides a sensitive parameter determination method, apparatus, computer equipment, and storage medium, belonging to the technical field of oil and gas exploration and development. The method includes: combining multiple elastic parameters based on the sensitivity of multiple elastic parameters of the target reservoir to reservoir parameters to obtain multiple elastic parameter combinations; for any elastic parameter combination, predicting the elastic parameter curves of multiple elastic parameters in the elastic parameter combination based on a prediction model to obtain a prediction result, wherein the prediction model is used to predict reservoir parameters based on the input elastic parameter curve; determining a target elastic parameter combination based on the prediction error of the multiple elastic parameter combinations, wherein the prediction error is used to reflect the degree of fit between the prediction result of the corresponding elastic parameter combination and the actual reservoir parameter curve; and determining multiple elastic parameters in the target elastic parameter combination as sensitive parameters. This method can improve the accuracy of quantitative reservoir characterization.

Description

Technical Field

[0001] The present application relates to the technical field of oil and gas exploration and development, and in particular to a method, apparatus, computer equipment, and storage medium for determining sensitive parameters. Background Art

[0002] With the advancement of oil and gas exploration and development technologies, quantitative reservoir characterization is becoming increasingly important. This process utilizes seismic, well logging, and core data to quantitatively calculate reservoir parameters. This provides a basis for reservoir characterization, identifying favorable zones and sweet spots, and well placement, playing a crucial role in reservoir calculations and development plan formulation. However, since quantitative reservoir characterization requires the selection of parameters that are sensitive to the reservoir's lithology and physical properties—also known as sensitive parameters—the selection of these parameters remains a challenging technical challenge.

[0003] Related technologies typically use intersection analysis to select sensitive parameters. By intersecting different input and output parameters, highly correlated sensitive parameters are selected. Based on these sensitive parameters, a prediction model is then used to predict reservoir parameters, yielding prediction results. However, this approach simply analyzes the impact of individual sensitive parameters on the prediction results, failing to consider the interactions between sensitive parameters and the impact of combined sensitive parameters on the prediction results. This results in reduced accuracy in quantitative reservoir characterization. Summary of the Invention

[0004] The embodiments of the present application provide a sensitive parameter determination method, apparatus, computer equipment, and storage medium, which improve the accuracy of reservoir quantitative characterization. The technical solution is as follows:

[0005] In one aspect, a method for determining a sensitive parameter is provided, the method comprising:

[0006] Based on the sensitivity of multiple elastic parameters of the target reservoir to the reservoir parameters, the multiple elastic parameters are combined to obtain multiple elastic parameter combinations, the multiple elastic parameters are used to reflect the elastic characteristics of the rock in the target reservoir, and the reservoir parameters are used to reflect the characteristics of the target reservoir;

[0007] For any elastic parameter combination, based on a prediction model, predicting elastic parameter curves of multiple elastic parameters in the elastic parameter combination to obtain a prediction result, wherein the prediction model is used to predict the reservoir parameters based on the input elastic parameter curve, and the prediction result represents a reservoir parameter curve of multiple reservoir parameters predicted based on the elastic parameter curve of the multiple elastic parameters;

[0008] Determining a target elastic parameter combination based on prediction errors of the multiple elastic parameter combinations, wherein the prediction error is used to reflect the degree of fit between the prediction result of the corresponding elastic parameter combination and the actual reservoir parameter curve, and the degree of fit is inversely correlated with the prediction error;

[0009] A plurality of elastic parameters in the target elastic parameter combination are determined as sensitive parameters.

[0010] In another aspect, a sensitive parameter determination device is provided, the device comprising:

[0011] a combination module, configured to combine the multiple elastic parameters of the target reservoir based on their sensitivity to the reservoir parameters to obtain multiple elastic parameter combinations, wherein the multiple elastic parameters are used to reflect the elastic characteristics of the rock in the target reservoir, and the reservoir parameters are used to reflect the characteristics of the target reservoir;

[0012] a prediction module configured to predict, for any elastic parameter combination, elastic parameter curves of a plurality of elastic parameters in the elastic parameter combination based on a prediction model to obtain a prediction result, wherein the prediction model is configured to predict the reservoir parameters based on the input elastic parameter curve, and the prediction result represents a reservoir parameter curve of the plurality of reservoir parameters predicted based on the elastic parameter curve of the plurality of elastic parameters;

[0013] a combination determination module, configured to determine a target elastic parameter combination based on prediction errors of the plurality of elastic parameter combinations, wherein the prediction error is used to reflect a degree of fit between a prediction result of the corresponding elastic parameter combination and a true reservoir parameter curve, wherein the degree of fit is inversely correlated with the prediction error;

[0014] The parameter determination module is configured to determine multiple elastic parameters in the target elastic parameter combination as sensitive parameters.

[0015] In some embodiments, the prediction module includes:

[0016] a transformation unit configured to perform, for any elastic parameter combination, a mathematical transformation and a rotational transformation on elastic parameter curves of a plurality of elastic parameters in the elastic parameter combination to obtain characteristic curves of the plurality of elastic parameters in the elastic parameter combination, wherein the mathematical transformation comprises at least one of addition, subtraction, multiplication, division, squaring, and square root, and the rotational transformation is configured to rotate the elastic parameter curve based on a rotation angle;

[0017] The prediction unit is configured to predict the characteristic curves of the plurality of elastic parameters in the elastic parameter combination based on the prediction model to obtain the prediction result.

[0018] In some embodiments, the combined module includes:

[0019] a sorting unit, configured to sort the plurality of elastic parameters from large to small based on the sensitivity;

[0020] The combination unit is used to select, for any selection number among multiple selection numbers, the elastic parameters of the selection number that are sorted first as an elastic parameter combination based on the sorting result, and the selection number is a positive integer not less than 2.

[0021] In some embodiments, the combination determination module includes:

[0022] a first determining unit, configured to determine a first cross-plot based on the prediction errors of the plurality of elastic parameter combinations and the plurality of elastic parameter combinations, the first cross-plot being configured to indicate a correspondence between the prediction errors and the number of elastic parameters in the plurality of elastic parameter combinations;

[0023] a second determining unit, configured to determine an inflection point of the prediction error in the first intersection graph, wherein the inflection point is a demarcation point where the prediction error transitions from gradually decreasing to becoming constant;

[0024] The third determining unit is configured to determine the target elastic parameter combination including the target number of elastic parameters based on the target number represented by the abscissa of the inflection point.

[0025] In some embodiments, the apparatus further comprises:

[0026] a selection module configured to randomly select a segment of the elastic parameter curve of any elastic parameter in the target elastic parameter combination based on the data distribution of the elastic parameter curve of the elastic parameter by using Monte Carlo simulation to obtain a simulated elastic parameter curve of the elastic parameter;

[0027] a simulation prediction module, configured to predict, based on the prediction model, simulated elastic parameter curves of a plurality of elastic parameters in the target elastic parameter combination, and obtain a simulation prediction result of the target elastic parameter combination;

[0028] The analysis module is used to perform statistical analysis on the multiple simulation prediction results of the target elastic parameter combination to determine a second cross-plot, wherein the second cross-plot is used to indicate the corresponding relationship between the multiple simulation prediction results and the frequency of occurrence of the multiple simulation prediction results.

[0029] In some embodiments, the apparatus further comprises:

[0030] The weight determination module is used to determine the parameter weight of any elastic parameter based on the prediction model, wherein the parameter weight is used to indicate the sensitivity of the elastic parameter to the reservoir parameter, and the parameter weight is positively correlated with the sensitivity.

[0031] On the other hand, a computer device is provided, which includes a processor and a memory, wherein the memory is used to store at least one computer program, and the at least one computer program is loaded and executed by the processor to implement the sensitive parameter determination method in the embodiment of the present application.

[0032] On the other hand, a computer-readable storage medium is provided, in which at least one computer program is stored. The at least one computer program is loaded and executed by a processor to implement the sensitive parameter determination method in the embodiment of the present application.

[0033] On the other hand, a computer program product is provided, including a computer program, which is stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the computer device executes the sensitive parameter determination method provided in the above-mentioned various aspects or various optional implementations of various aspects.

[0034] The embodiment of the present application provides a method for determining sensitive parameters. Since the prediction model is used to predict reservoir parameters based on the input elastic parameter curve, the prediction error is used to reflect the degree of fit between the prediction result of the input elastic parameter combination and the real reservoir parameter curve, and the prediction error is inversely correlated with the degree of fit. As the number of elastic parameters in the input elastic parameter combination increases, the prediction error gradually decreases, and the prediction error tends to be constant when it decreases to a certain extent. Therefore, the multiple elastic parameters in the elastic parameter combination corresponding to the dividing point when the prediction error transitions from gradually decreasing to tending to be constant are determined as sensitive parameters. Since the degree of fit between the prediction result obtained by the input elastic parameter combination at this time and the real reservoir parameter curve is the highest, the multiple sensitive parameters determined at this time can take into account the sensitivity of the interaction between the sensitive parameters to the prediction result, thereby improving the accuracy of quantitative reservoir characterization. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0036] Figure 1This is an implementation environment of a sensitive parameter determination method provided in an embodiment of the present application;

[0037] Figure 2 This is a flow chart of a sensitive parameter determination method provided in an embodiment of the present application;

[0038] Figure 3 is a flow chart of another sensitive parameter determination method provided in an embodiment of the present application;

[0039] Figure 4 is a schematic diagram of parameter weights of an elastic parameter provided according to an embodiment of the present application;

[0040] Figure 5 is a schematic diagram of a method for calculating a distribution error provided in an embodiment of the present application;

[0041] Figure 6 is a schematic diagram of a method for obtaining data distribution of an elastic parameter curve provided in an embodiment of the present application;

[0042] Figure 7 is a schematic diagram of a second intersection graph provided according to an embodiment of the present application;

[0043] Figure 8 is a schematic diagram of an operation process provided according to an embodiment of the present application;

[0044] Figure 9 is a block diagram of a sensitive parameter determination device provided according to an embodiment of the present application;

[0045] Figure 10 is a block diagram of another sensitive parameter determination device provided according to an embodiment of the present application;

[0046] Figure 11 is a schematic structural diagram of a terminal provided according to an embodiment of the present application;

[0047] Figure 12 It is a structural diagram of a server provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0049] In this application, the terms "first", "second", etc. are used to distinguish identical or similar items with substantially the same effects and functions. It should be understood that there is no logical or temporal dependency between "first", "second", and "nth", nor is there any limitation on the quantity and execution order.

[0050] In the present application, the term "at least one" means one or more, and the term "plurality" means two or more.

[0051] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the elasticity parameters involved in this application are all obtained with full authorization.

[0052] The sensitive parameter determination method provided in the embodiment of the present application can be applied to a computer device. In some embodiments, the computer device is a terminal or a server. The following first takes the computer device as an example to introduce the implementation environment of the sensitive parameter determination method provided in the embodiment of the present application. Figure 1 Schematic diagram of an implementation environment of a sensitive parameter determination method provided in an embodiment of the present application. Figure 1 The implementation environment includes a terminal 101 and a server 102. The terminal 101 and the server 102 can be directly or indirectly connected via wired or wireless communication, which is not limited in this application.

[0053] In some embodiments, terminal 101 is a smartphone, tablet computer, laptop computer, desktop computer, smart speaker, smartwatch, etc., but is not limited thereto. An application may be installed and running on terminal 101, and the application is used to display elastic parameter curves for multiple elastic parameters of a target reservoir and reservoir parameter curves for reservoir parameters. A user can log in to the application through terminal 101 to view the elastic parameter curves for multiple elastic parameters and reservoir parameter curves. The application is associated with server 102, and server 102 provides backend services.

[0054] Terminal 101 may generally refer to one of multiple terminals. This embodiment uses terminal 101 as an example. Those skilled in the art will appreciate that the number of terminals may be greater or lesser. For example, there may be a few terminals, or dozens, hundreds, or even more. This embodiment of the application does not limit the number or device type of terminals.

[0055] In some embodiments, server 102 is a standalone physical server, but it can also be a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. In some embodiments, server 102 receives multiple elastic parameters and reservoir parameters of a target reservoir uploaded by terminal 101 via an application. Based on the sensitivity of the multiple elastic parameters to the reservoir parameters, server 102 combines the multiple elastic parameters to obtain multiple elastic parameter combinations. For each elastic parameter combination, server 102 invokes a prediction model to predict elastic parameter curves for the multiple elastic parameters of the elastic parameter combination, obtaining a prediction result. Server 102 returns the prediction result to terminal 101, which then displays the reservoir parameter curve for the reservoir parameter via the application. Server 102 can also determine sensitive parameters from the multiple elastic parameters of the target reservoir based on the prediction result.

[0056] In some embodiments, server 102 performs primary computing tasks, and terminal 101 performs secondary computing tasks; alternatively, server 102 performs secondary computing tasks, and terminal 101 performs primary computing tasks; alternatively, server 102 and terminal 101 utilize a distributed computing architecture for collaborative computing. Optionally, the number of servers described above may be greater or less, and this is not limited in this embodiment of the present application. Of course, server 102 may also include other functional servers to provide more comprehensive and diverse services.

[0057] Figure 2 This is a flow chart of a sensitive parameter determination method provided in an embodiment of the present application. Figure 2 As shown, in the embodiment of the present application, the server is used as an example for explanation. The method includes the following steps:

[0058] 201. The server combines the multiple elastic parameters of the target reservoir based on their sensitivity to the reservoir parameters to obtain multiple elastic parameter combinations. The multiple elastic parameters are used to reflect the elastic characteristics of the rock in the target reservoir, and the reservoir parameters are used to reflect the characteristics of the target reservoir.

[0059] In the embodiments of the present application, the target reservoir is a rock formation with interconnected pores that allows oil and gas to be stored and permeated, that is, an area of ​​underground rock formation where oil and gas accumulate. Multiple elastic parameters of the target reservoir are used to characterize the elastic properties of the rock in the target reservoir. Common elastic parameters include compressional wave velocity, shear wave velocity, density, Lame parameter, shear modulus, bulk modulus, elastic impedance, gradient impedance, and extended elastic impedance. Characteristics of the target reservoir include lithology, physical properties, and hydrocarbon content. The lithology of the target reservoir describes the primary characteristics of the mineral composition of the target reservoir and reflects the storage performance and reservoir characteristics of the target reservoir. The physical properties of the target reservoir describe the physical properties of the target reservoir. The hydrocarbon content of the target reservoir indicates characteristics such as the properties and type of fluids within the target reservoir. Common reservoir parameters include porosity, mud content, water saturation, permeability, and rock layer thickness of the target reservoir rock.

[0060] Because different elastic parameters may have varying or equal sensitivities to reservoir parameters, some may be highly sensitive to reservoir parameters, while others may be less sensitive. Therefore, based on the sensitivity of these multiple elastic parameters to the target reservoir parameters, the server combines them in order of their sensitivity, generating multiple elastic parameter combinations. Each elastic parameter combination includes multiple elastic parameters. Different elastic parameter combinations may have varying or equal sensitivities to reservoir parameters. The server then determines multiple elastic parameters in the elastic parameter combination with the highest sensitivity to the reservoir parameter as sensitive parameters. Furthermore, the more sensitive the elastic parameter combination is to the reservoir parameter, the more the sensitive parameter can reflect changes in the reservoir parameter.

[0061] 202. For any elastic parameter combination, the server predicts the elastic parameter curves of multiple elastic parameters in the elastic parameter combination based on the prediction model to obtain a prediction result. The prediction model is used to predict reservoir parameters based on the input elastic parameter curves, and the prediction result represents the reservoir parameter curves of multiple reservoir parameters obtained by predicting the elastic parameter curves of multiple elastic parameters.

[0062] In the embodiment of the present application, since the elastic parameters of the target reservoir can reflect changes in reservoir parameters, and the prediction model can make predictions based on the relationship between the elastic parameters and the reservoir parameters, for any multiple elastic parameters in any elastic parameter combination, the server can input the elastic parameter curves of the multiple elastic parameters into the prediction model, and use the prediction model to predict the multiple reservoir parameters to obtain reservoir parameter curves for the multiple reservoir parameters. The abscissa of a point on the elastic parameter curve is the numerical value of the elastic parameter, and the ordinate is the depth of the target reservoir. The elastic parameter curve is used to indicate the corresponding relationship between the elastic parameter and the depth of the target reservoir. The abscissa of a point on the target reservoir parameter curve is the numerical value of the target reservoir parameter, and the ordinate is the depth of the target reservoir. The target reservoir parameter curve is used to indicate the corresponding relationship between the target reservoir parameter and the depth of the target reservoir parameter.

[0063] 203. The server determines a target elastic parameter combination based on prediction errors of multiple elastic parameter combinations. The prediction error is used to reflect the degree of fit between the prediction result of the corresponding elastic parameter combination and the actual reservoir parameter curve. The degree of fit is inversely correlated with the prediction error.

[0064] In an embodiment of the present application, the server can determine the prediction errors for multiple elastic parameter combinations based on the difference between the predicted target reservoir parameter curve and the actual target reservoir curve. Since the prediction error is inversely correlated with the degree of fit, smaller prediction errors indicate a higher degree of fit, while larger prediction errors indicate a lower degree of fit. Therefore, for any elastic parameter combination, the degree of fit between the predicted result of that elastic parameter combination and the actual reservoir parameter curve can be determined based on the prediction error of that elastic parameter combination. Then, by comparing the degrees of fit of the multiple elastic parameter combinations, the elastic parameter combination with the highest degree of fit is determined from among the multiple elastic parameter combinations, i.e., the target elastic parameter combination.

[0065] 204. The server determines multiple elastic parameters in the target elastic parameter combination as sensitive parameters.

[0066] In the embodiment of the present application, since the prediction error of the target elastic parameter is minimal, the target reservoir parameter curves of the multiple target reservoir parameters predicted based on the elastic parameter curves of the multiple elastic parameters in the target elastic parameter combination have the highest degree of fit with the actual target reservoir parameter curves. Therefore, the server determines the multiple elastic parameters in the target elastic parameter combination as sensitive parameters. These sensitive parameters are parameters that are sensitive to the lithology and physical properties of the target reservoir, and since the target elastic parameter combination is highly sensitive to the reservoir parameters, the multiple elastic parameters in the target elastic parameter combination are determined as sensitive parameters, making these sensitive parameters more sensitive to the reservoir parameters and more able to reflect changes in the reservoir parameters.

[0067] The embodiment of the present application provides a method for determining sensitive parameters. Since the prediction model is used to predict reservoir parameters based on the input elastic parameter curve, the prediction error is used to reflect the degree of fit between the prediction result of the input elastic parameter combination and the real reservoir parameter curve, and the prediction error is inversely correlated with the degree of fit. As the number of elastic parameters in the input elastic parameter combination increases, the prediction error gradually decreases, and the prediction error tends to be constant when it decreases to a certain extent. Therefore, the multiple elastic parameters in the elastic parameter combination corresponding to the dividing point when the prediction error transitions from gradually decreasing to tending to be constant are determined as sensitive parameters. Since the degree of fit between the prediction result obtained by the input elastic parameter combination at this time and the real reservoir parameter curve is the highest, the multiple sensitive parameters determined at this time can take into account the sensitivity of the interaction between the sensitive parameters to the prediction result, thereby improving the accuracy of quantitative reservoir characterization.

[0068] Figure 3 is a flow chart of another sensitive parameter determination method provided in an embodiment of the present application, such as Figure 3 As shown, in the embodiment of the present application, the server is used as an example for explanation. The method includes the following steps:

[0069] 301. The server obtains multiple elastic parameters and reservoir parameters of the target reservoir based on multiple well logging curves of the target reservoir. The multiple elastic parameters are used to reflect the elastic characteristics of the rock in the target reservoir, and the reservoir parameters are used to reflect the characteristics of the target reservoir.

[0070] In an embodiment of the present application, the multiple logging curves include multiple types of logging curves, and commonly used logging curves include sonic logging curves, density logging curves, natural gamma logging curves, induction logging curves, etc. Among them, the functions of different types of logging curves are also different. For example, sonic logging curves and density logging curves are used to determine the lithology and porosity of the target reservoir, natural gamma logging curves are used to determine the mud content of the target reservoir, and induction logging curves are used to determine the water saturation of the target reservoir. The server can obtain multiple logging curves from a local database, or obtain multiple logging curves from other servers, and can also use logging curves uploaded by multiple terminals as multiple logging curves.

[0071] In some embodiments, the server interprets multiple well logging curves to obtain multiple elastic parameters and reservoir parameters. Well logging interpretation is a method of processing well logging information into geological information. Well logging information refers to physical parameters derived from well logging curves. For example, resistivity, natural potential, acoustic wave velocity, and rock bulk density can be collectively referred to as well logging information. Geological information refers to information used to characterize the motion and existence of the lithosphere, including the crust. For example, reservoir parameters such as lithology, porosity, permeability, mud content, water saturation, and permeability can all be collectively referred to as geological information.

[0072] In some embodiments, raw log curves obtained through geophysical logging are often affected by environmental factors. Therefore, to obtain log curves that are specific to reservoir properties, environmental correction is required. Accordingly, the server performs log curve quality control on the log curves, removing outliers and ensuring their quality.

[0073] In some embodiments, the server can calculate other elastic parameters based on the partial elastic parameters. The partial elastic parameters include P-wave velocity, S-wave velocity, and density. Since P-wave velocity, S-wave velocity, and density are fundamental parameters describing the elasticity of rock in the target reservoir, elastic parameters such as the P-wave velocity ratio, Poisson's ratio, Lame parameter, shear modulus, bulk modulus, elastic impedance, gradient impedance, and extended elastic impedance can be calculated based on these three fundamental parameters.

[0074] 302. The server performs mathematical transformation and rotational transformation on elastic parameter curves of multiple elastic parameters to obtain characteristic curves of multiple elastic parameters. The mathematical transformation includes at least one of addition, subtraction, multiplication, division, square, and square root. The rotational transformation is used to rotate the elastic parameter curve based on a rotation angle.

[0075] In an embodiment of the present application, in order to increase the diversity of training samples, the server can perform mathematical transformation and rotation changes on the elastic parameter curves of multiple elastic parameters to obtain new characteristic curves. Among them, the server can perform one or more mathematical transformations on the elastic parameter curve, and can also perform rotation transformation on the elastic parameter curve based on different rotation angles, and the range of the rotation angle is 0-90 degrees. For example, the elastic parameter curve is multiplied by cosine (0-90 degrees) to obtain a rotated elastic parameter curve. Moreover, based on the rotation transformation of the elastic parameter curve at different rotation angles, mathematical transformations such as addition, subtraction, multiplication, division, square and square root can be performed. The elastic parameter curves of multiple elastic parameters can first be mathematically transformed and then subjected to rotation transformation; or they can be rotationally transformed and then subjected to mathematical transformation.

[0076] 303. The server trains a prediction model based on the characteristic curves of the multiple elastic parameters and the reservoir parameter curve of the reservoir parameters. The prediction model is used to predict the reservoir parameters based on the input characteristic curves of the multiple elastic parameters.

[0077] In an embodiment of the present application, the server can predict the characteristic curves of multiple elastic parameters through a prediction model to obtain a prediction result, which represents the reservoir parameter curves of multiple reservoir parameters predicted based on the characteristic curves of the multiple elastic parameters. The server determines the error based on the prediction result and the true reservoir parameter curve. The error is the loss value of the prediction model, which is used to reflect the degree of fit between the prediction result and the true reservoir parameter curve. The smaller the error, the higher the degree of fit between the prediction result and the true reservoir parameter curve, indicating that the prediction model predicts more accurately. Based on the error, the server updates the parameters of the prediction model to reduce the error of the prediction model, and trains to obtain an initial model, which is the prediction model.

[0078] In some embodiments, the server uses a grid-based automated search to determine the optimal parameters for the prediction model. The grid-based automated search selects a series of parameters from a set of candidate parameters and combines them to obtain multiple candidate parameter combinations. The server then iterates through the multiple candidate parameter combinations, places any candidate parameter combination in the model, and calculates a score for the candidate parameter combination. The candidate parameter combination with the highest score is selected as the optimal parameter for the model.

[0079] 304. For any elastic parameter, the server determines a parameter weight of the elastic parameter based on the prediction model. The parameter weight is used to indicate the sensitivity of the elastic parameter to the reservoir parameter. The parameter weight is positively correlated with the sensitivity.

[0080] In the present embodiment, the prediction model uses an elastic parameter curve for the elastic parameter as input and a reservoir parameter curve for the reservoir parameter as output. Therefore, the sensitivity of the elastic parameter to the reservoir parameter can be determined based on the parameter weight of the elastic parameter. The parameter weight is positively correlated with the sensitivity; the larger the parameter weight, the more sensitive the elastic parameter to the reservoir parameter. The smaller the parameter weight, the less sensitive the elastic parameter to the reservoir parameter.

[0081] For example, Figure 4 is a schematic diagram of parameter weights of elastic parameters provided in accordance with an embodiment of the present application, see Figure 4 The figure lists the six elastic parameters that are most sensitive to reservoir parameters. Among them, the parameter weight of the first elastic parameter is about 1.9, the parameter weight of the second elastic parameter is about 1.6, the parameter weight of the third elastic parameter is about 1.5, the parameter weight of the fourth elastic parameter is about 1.1, the parameter weight of the fifth elastic parameter is about 0.3, and the parameter weight of the sixth elastic parameter is about 0.2.

[0082] It should be noted that the embodiment of the present application is only described by taking the case where the prediction model is an unknown model as an example, and in another embodiment, the prediction model can be an unknown model or a known model, that is, the mathematical expression of the prediction model has been determined. In the case where the prediction model is an unknown model, the server executes the above steps 302-304. In the case where the prediction model is a known model, the above steps 302-303 are not executed, and the above step 304 can be replaced by the following steps: the server analyzes the sensitivity of multiple elastic parameters to reservoir parameters based on the prediction model using a global sensitivity analysis method based on variance. Among them, the Sobol method (a global sensitivity analysis method based on variance) analyzes the sensitivity of the elastic parameter to the reservoir parameter by calculating the influence of the variance of the input elastic parameter on the total output variance.

[0083] 305. The server combines the multiple elastic parameters based on the sensitivity of the multiple elastic parameters of the target reservoir to the reservoir parameter to obtain multiple elastic parameter combinations.

[0084] In the embodiment of the present application, when the value of the elastic parameter changes, the value of the reservoir parameter also changes due to the sensitivity of the elastic parameter. Furthermore, different elastic parameters may have different or equal sensitivities to the reservoir parameter. Therefore, based on the sensitivity of the multiple elastic parameters to the target reservoir parameter, the server combines the multiple elastic parameters in order of their sensitivities to obtain multiple elastic parameter combinations.

[0085] In some embodiments, the server can sort multiple elastic parameters based on the degree of sensitivity and obtain multiple elastic parameter combinations based on the sorting results. Accordingly, the server sorts the multiple elastic parameters from large to small based on the degree of sensitivity; for any of the multiple selection quantities, the server selects the elastic parameters with the highest selection quantity as an elastic parameter combination based on the sorting results, where the selection quantity is a positive integer not less than 2. The server is provided with multiple selection quantities, and based on the sorting results, the server can select the elastic parameters with the highest selection quantity multiple times to obtain multiple elastic parameter combinations. The number of elastic parameters in each elastic parameter combination is different.

[0086] For example, the selection quantities include 2, 3, 4, and 5. When the selection quantity is 2, the server selects the first two elastic parameters as a pop-up parameter combination based on the sorting result. When the selection quantity is 3, the server selects the first three elastic parameters as a pop-up parameter combination based on the sorting result. And so on, the server obtains a total of four elastic parameter combinations.

[0087] 306. For any elastic parameter combination, the server predicts elastic parameter curves of multiple elastic parameters in the elastic parameter combination based on the prediction model to obtain a prediction result, where the prediction result represents reservoir parameter curves of multiple reservoir parameters predicted based on the elastic parameter curves of the multiple elastic parameters.

[0088] In the embodiment of the present application, since the elastic parameters of the target reservoir can reflect changes in reservoir parameters, and the prediction model can perform predictions based on the relationship between the elastic parameters and the reservoir parameters, for multiple elastic parameters in any elastic parameter combination, the server can input the elastic parameter curves of the multiple elastic parameters into the prediction model, and use the prediction model to predict the multiple reservoir parameters to obtain reservoir parameter curves for the multiple reservoir parameters.

[0089] In some embodiments, the server transforms the input elastic parameter curve and predicts the characteristic curve obtained by the transformation to obtain a prediction result. Accordingly, for any elastic parameter combination, the server performs mathematical transformation and rotational transformation on the elastic parameter curves of multiple elastic parameters in the elastic parameter combination to obtain the characteristic curves of the multiple elastic parameters in the elastic parameter combination. The mathematical transformation includes at least one of addition, subtraction, multiplication, division, squaring, and square root. The rotational transformation is used to rotate the elastic parameter curve based on a rotation angle. The server predicts the characteristic curves of the multiple elastic parameters in the elastic parameter combination based on the prediction model to obtain a prediction result. The server can perform one or more mathematical transformations on the input elastic parameter curve and can also perform rotational transformations on the elastic parameter curve based on different rotation angles, with the rotation angle range being 0-90 degrees. The server can also predict the characteristic curves of the multiple elastic parameters in the elastic parameter combination using the prediction model to obtain a prediction result, which represents the reservoir parameter curves of the multiple reservoir parameters predicted based on the characteristic curves of the multiple elastic parameters.

[0090] 307. The server determines a target elastic parameter combination based on prediction errors of multiple elastic parameter combinations. The prediction error is used to reflect the degree of fit between the prediction result of the corresponding elastic parameter combination and the actual reservoir parameter curve. The degree of fit is inversely correlated with the prediction error.

[0091] In the present embodiment, since the prediction error is inversely correlated with the degree of fit, smaller prediction errors indicate a higher degree of fit, while larger prediction errors indicate a lower degree of fit. Therefore, for any elastic parameter combination, the degree of fit between the prediction result of that elastic parameter combination and the actual reservoir parameter curve can be determined based on the prediction error of that elastic parameter combination. Then, by comparing the degrees of fit of multiple elastic parameter combinations, the elastic parameter combination with the highest degree of fit is determined from among the multiple elastic parameter combinations, which is also known as the target elastic parameter combination.

[0092] In some embodiments, the following formula is used to determine the prediction error based on the prediction distribution error and the prediction mean square error. The prediction distribution error can better consider the overall effect of the prediction result, while the prediction mean square error considers the prediction error of each local point.

[0093] Error=ω*err1+(1-ω)*err2

[0094] Among them, Error is the prediction error between the predicted result and the true result, errr1 is the prediction distribution error between the predicted result and the true result, errr2 is the prediction mean square error between the predicted result and the true result, and ω is the weight, which ranges from [0, 1].

[0095] In some embodiments, the distribution error between the predicted result and the actual result can be obtained by calculating the difference between the probability value corresponding to each reservoir parameter value in the predicted result and the probability value corresponding to the actual result, and then summing each difference.

[0096] For example, see Figure 5 The diagram of the calculation method of the distribution error is shown in FIG. By intersecting the parameter value of the reservoir parameter with the number of times the parameter value occurs, the following can be obtained: Figure 5 The reservoir parameter distribution diagram shown in . Among them, the horizontal axis is the parameter value of the reservoir parameter, and the vertical axis is the probability of the parameter value. By dividing the number of times each parameter value appears by the maximum number of times, the probability of each parameter value appearing can be obtained. That is, by normalizing the vertical axis, the value range of the vertical axis is between 0 and 1. Then, the difference between the area of ​​the predicted reservoir parameter distribution and the actual measured reservoir parameter distribution is obtained by calculation, that is, Figure 5 The black area shown can obtain the distribution error between the predicted results and the true results.

[0097] In some embodiments, the server determines the elasticity parameter combination corresponding to the cutoff point when the prediction error transitions from gradually decreasing to becoming constant as the target elasticity parameter combination. Accordingly, the server determines the target elasticity parameter combination through the following steps (1)-(3).

[0098] (1) The server determines a first cross-graph based on the prediction errors of the multiple elastic parameter combinations and the multiple elastic parameter combinations, where the first cross-graph is used to indicate a corresponding relationship between the prediction errors and the number of elastic parameters in the multiple elastic parameter combinations.

[0099] In the embodiment of the present application, the abscissa of the points in the first crossplot represents the number of elastic parameters in the elastic parameter combination, and the ordinate represents the prediction error of the elastic parameter combination. Since the prediction error reflects the degree of fit between the prediction result of the elastic parameter combination and the true reservoir parameter curve, and the first crossplot can reflect the changing trend of the prediction error of the elastic parameter combination as the number of elastic parameters increases, based on the first crossplot, by comparing the magnitudes of the prediction errors of multiple elastic parameter combinations, the degree of fit between the prediction results of the multiple elastic parameter combinations and the true reservoir parameter curve can be compared.

[0100] (2) The server determines the inflection point of the prediction error in the first intersection graph. The inflection point is the dividing point where the prediction error transitions from gradually decreasing to becoming constant.

[0101] In the embodiment of the present application, as the number of elastic parameters in the elastic parameter combination increases in the first cross-plot, the prediction error of the elastic parameter combination gradually decreases, and the prediction error of the elastic parameter combination tends to be constant after decreasing to a certain extent. Therefore, the dividing point where the prediction error transitions from gradually decreasing to tending to be constant is determined as the inflection point.

[0102] (3) The server determines a target elastic parameter combination including a target number of elastic parameters based on the target number represented by the horizontal coordinate of the inflection point.

[0103] In the embodiment of the present application, the prediction error of the elastic parameter combination gradually decreases before the inflection point. And after reaching this inflection point, the prediction error of the elastic parameter combination tends to remain unchanged. This shows that among the prediction errors of multiple elastic parameter combinations, the prediction error represented by the ordinate of the inflection point is the smallest. And because the number of elastic parameters in the elastic parameter combination is different, based on the target number represented by the abscissa of the inflection point, it is possible to uniquely determine a target elastic parameter combination including a target number of elastic parameters, wherein the prediction error of the target elastic parameter combination is the smallest. Since the prediction error is used to reflect the degree of fit between the prediction result of the input elastic parameter combination and the true reservoir parameter curve, and the prediction error is inversely correlated with the degree of fit. Therefore, based on the inflection point, the prediction result of the target elastic parameter combination determined has the highest degree of fit with the true reservoir parameter curve.

[0104] 308. The server determines multiple elastic parameters in the target elastic parameter combination as sensitive parameters.

[0105] In the embodiment of the present application, since the prediction error of the target elastic parameter is minimal, the target reservoir parameter curves of the multiple target reservoir parameters predicted based on the elastic parameter curves of the multiple elastic parameters in the target elastic parameter combination have the highest degree of fit with the actual target reservoir parameter curves. Therefore, the server determines the multiple elastic parameters in the target elastic parameter combination as sensitive parameters. Among them, the sensitive parameters are parameters that are sensitive to the lithology and physical properties of the target reservoir, and since the target elastic parameter combination is highly sensitive to the reservoir parameters, the multiple elastic parameters in the target elastic parameter combination are determined as sensitive parameters, making these sensitive parameters both highly sensitive to the reservoir parameters and more able to reflect changes in the reservoir parameters.

[0106] 309. For any elastic parameter in the target elastic parameter combination, the server randomly selects a curve segment from the elastic parameter curve of the elastic parameter using Monte Carlo simulation based on data distribution of the elastic parameter curve to obtain a simulated elastic parameter curve of the elastic parameter.

[0107] In an embodiment of the present application, Monte Carlo simulation is a simulation technique based on repeated random sampling methods, which is used to simulate the probability of different results in a random process. Therefore, based on the data distribution of the elastic parameter curve, Monte Carlo simulation is used to randomly select a curve from the elastic parameter curve as the simulated elastic parameter curve of the elastic parameter. Among them, the data distribution of the elastic parameter curves of different elastic parameters may be the same or different. The data distribution of the elastic parameter curve includes uniform distribution, exponential distribution, triangular distribution and Gaussian distribution, etc. Since the selection of the elastic parameter curve by the Monte Carlo simulation is random, the simulated elastic parameter curve obtained by each random selection may be the same or different.

[0108] For example, Table 1 shows the data distribution and interval of the elastic parameter curves of multiple elastic parameters in the target elastic parameter combination, where the number of elastic parameters in the target elastic parameter combination is 4, that is, the number of sensitive parameters is 4. The data distribution of parameter 1 is uniform, and the depth trend of the uniform distribution is ±5. The data distribution of parameter 2 is normal, and the variance of the normal distribution is 0.05. The data distribution of parameter 3 is normal, and the variance of the normal distribution is 0.05. The data distribution of parameter 4 is normal, and the variance of the normal distribution is 0.1.

[0109] Table 1

[0110] Serial number Sensitive parameters distributed interval 1 Parameter 1 Uniform Depth trend ±5 2 Parameter 2 Normal Measured value, variance 0.05 3 Parameter 3 Normal Measured value, variance 0.05 4 Parameter 4 Normal Measured value, variance 0.1

[0111] In some embodiments, the server can automatically obtain the data distribution of the elastic parameter curve of the elastic parameter through the model. Taking lithofacies as an example, the specific implementation steps include: respectively counting the response values ​​of the input parameters for different lithofacies drilled in the area, obtaining a distribution map for each lithofacies corresponding to each input parameter; normalizing the distribution of each lithofacies; and then summing the distributions corresponding to each lithofacies that may occur in the formation to obtain the data distribution of the elastic parameter curve.

[0112] For example, see Figure 6 The schematic diagram of the method for obtaining the data distribution of the elastic parameter curve shown is shown in FIG. 1 , taking the input parameter as lithofacies as an example. Figure 6 (1) is the cross-plot of the parameter values ​​and the number of times the parameter values ​​appear for the three lithofacies. The horizontal axis is the parameter value, and the vertical axis is the number of times the parameter value appears. Figure 6 (2) is the intersection diagram of the parameter values ​​and the probability of occurrence of the parameter values ​​of the three lithofacies obtained by normalizing the vertical coordinates in (1). The horizontal coordinate is the parameter value and the vertical coordinate is the probability of occurrence of the parameter value. Figure 6 In (3), the probability of occurrence of each parameter value in the three parameter distributions in (2) is summed to obtain a comprehensive parameter distribution, and the vertical coordinate after the summation is normalized.

[0113] 310. The server predicts simulated elastic parameter curves of multiple elastic parameters in the target elastic parameter combination based on the prediction model to obtain a simulation prediction result of the target elastic parameter combination.

[0114] In this embodiment of the present application, since the multiple elastic parameters of the target elastic combination are sensitive to reservoir parameters, and the prediction model can perform predictions based on the relationship between the elastic parameters and the reservoir parameters, the server can input the simulated elastic parameter curves of the multiple elastic parameters in the target elastic parameter combination into the prediction model, and use the prediction model to predict the multiple reservoir parameters to obtain a simulated prediction result for the target elastic parameter combination. The simulated prediction result represents the reservoir parameter curves of the multiple reservoir parameters predicted based on the simulated elastic parameter curves of the multiple elastic parameters in the target elastic parameter combination.

[0115] 311. The server performs statistical analysis on multiple simulation prediction results of the target elastic parameter combination to determine a second cross-plot, where the second cross-plot is used to indicate a corresponding relationship between the multiple simulation prediction results and the frequencies of occurrence of the multiple simulation prediction results.

[0116] In an embodiment of the present application, the simulated elastic parameter curves of the multiple elastic parameters in the target elastic parameter combination are predicted multiple times to obtain multiple simulated prediction results. Among them, among the multiple simulated prediction results, some simulated prediction results may be the same or different. Therefore, a statistical analysis is performed on the multiple simulated prediction results to determine the second intersection diagram. Since the horizontal coordinates of the points in the second intersection diagram are the multiple simulated prediction results of the target elastic parameter combination, and the vertical coordinates are the probabilities of the occurrence of the multiple simulated prediction results of the target elastic parameter combination. Therefore, the second intersection diagram can reflect the probability distribution of the multiple simulated prediction results of the target elastic parameter combination, thereby realizing the uncertainty analysis of the prediction results of the multiple elastic parameters in the target elastic parameter combination, that is, the sensitive parameters, and providing a basis for evaluating the risks of oil and gas exploration and development.

[0117] It should be noted that this prediction model can be used to predict reservoir parameters based on an input elastic parameter curve, or it can be used to predict elastic parameters based on an input reservoir parameter curve. When predicting reservoir parameters, the server executes steps 302-311 above. When predicting elastic parameters, the elastic parameters in steps 302-311 are replaced with reservoir parameters, and the reservoir parameters are replaced with elastic parameters. The specific implementation is similar to that for predicting reservoir parameters based on elastic parameters and will not be further described here.

[0118] For example, in the case of predicting elastic parameters based on reservoir parameters, a statistical analysis is performed on multiple simulation prediction results of target reservoir parameter combinations to determine a second cross-plot. Figure 7 In the second crossplot shown, the predicted elastic parameter is the P-wave velocity. The abscissa of this second crossplot represents multiple simulated prediction results for the P-wave velocity, while the ordinate represents the probability of occurrence of these multiple simulated prediction results. The P-wave velocity range is 2000-3700 m / s, with the probability of occurrence being the highest at 2800 m / s, approximately 0.78.

[0119] Figure 8This is a schematic diagram of an operation process provided by an embodiment of the present application, which includes: obtaining multiple elastic parameters and reservoir parameters of the target reservoir based on multiple well logging curves. Through joint well-seismic analysis, the data distribution of the parameter curve of the input parameters can be determined. When the model is known, the server uses the Sobol method (a global sensitivity analysis method based on variance) to analyze the sensitivity of multiple elastic parameters to the reservoir parameters based on the prediction model, obtains the Sobol index of each elastic parameter, and then ranks the sensitivity of the multiple elastic parameters based on the size of the Sobol index. When the model is unknown, the server performs mathematical transformation and rotation transformation on the elastic parameter curves of the multiple elastic parameters to obtain characteristic curves of the multiple elastic parameters, and then trains the prediction model based on the characteristic curves of the multiple elastic parameters and the reservoir parameter curves of the reservoir parameters. The prediction model is a random forest model. Based on the trained random forest model, the server determines the contribution of the multiple elastic parameters to the reservoir parameters, that is, the sensitivity. Then, based on the sensitivity of the multiple elastic parameters to the reservoir parameters, the multiple elastic parameters are combined to obtain multiple elastic parameter combinations. Based on the prediction model, the elastic parameter curves of multiple elastic parameters in the multiple elastic parameter combinations are predicted to obtain prediction results. Then, based on the prediction errors of the multiple elastic parameter combinations, a target elastic parameter combination is determined from the multiple elastic parameter combinations, and the multiple elastic parameters in the target elastic parameter combination are determined as sensitive parameters. Then, based on the data distribution of the elastic parameter curves of the multiple elastic parameters in the target elastic parameter combination, a Monte Carlo simulation is used to randomly select a curve segment from the elastic parameter curve as a simulated elastic parameter curve for the elastic parameter. Based on the prediction model, the model elastic parameter curve is predicted to obtain multiple simulated prediction results. Statistical analysis is performed on the multiple simulated prediction results to obtain a probability distribution of the multiple simulated prediction results for the target elastic parameter combination, i.e., the output distribution of the prediction model.

[0120] The embodiment of the present application provides a method for determining sensitive parameters. Since the prediction model is used to predict reservoir parameters based on the input elastic parameter curve, the prediction error is used to reflect the degree of fit between the prediction result of the input elastic parameter combination and the real reservoir parameter curve, and the prediction error is inversely correlated with the degree of fit. As the number of elastic parameters in the input elastic parameter combination increases, the prediction error gradually decreases, and the prediction error tends to be constant when it decreases to a certain extent. Therefore, the multiple elastic parameters in the elastic parameter combination corresponding to the dividing point when the prediction error transitions from gradually decreasing to tending to be constant are determined as sensitive parameters. Since the degree of fit between the prediction result obtained by the input elastic parameter combination at this time and the real reservoir parameter curve is the highest, the multiple sensitive parameters determined at this time can take into account the sensitivity of the interaction between the sensitive parameters to the prediction result, thereby improving the accuracy of quantitative reservoir characterization.

[0121] Figure 9 This is a block diagram of a sensitive parameter determination device provided according to an embodiment of the present application. The device is used to perform the steps of the above sensitive parameter determination method. Figure 9 The sensitive parameter determination device includes: a combination module 901, a prediction module 902, a combination determination module 903 and a parameter determination module 904.

[0122] A combination module 901 is configured to combine multiple elastic parameters of the target reservoir based on their sensitivity to the reservoir parameters to obtain multiple elastic parameter combinations, wherein the multiple elastic parameters are used to reflect the elastic characteristics of the rock in the target reservoir, and the reservoir parameters are used to reflect the characteristics of the target reservoir;

[0123] A prediction module 902 is configured to predict elastic parameter curves of multiple elastic parameters in any elastic parameter combination based on a prediction model to obtain a prediction result. The prediction model is configured to predict reservoir parameters based on the input elastic parameter curves. The prediction result represents a reservoir parameter curve of multiple reservoir parameters predicted based on the elastic parameter curves of the multiple elastic parameters.

[0124] A combination determination module 903 is configured to determine a target elastic parameter combination based on prediction errors of multiple elastic parameter combinations, wherein the prediction error reflects the degree of fit between the prediction result of the corresponding elastic parameter combination and the actual reservoir parameter curve, and the degree of fit is inversely correlated with the prediction error.

[0125] The parameter determination module 904 is configured to determine multiple elastic parameters in the target elastic parameter combination as sensitive parameters.

[0126] The embodiment of the present application provides a sensitive parameter determination device. Since the prediction model is used to predict reservoir parameters based on the input elastic parameter curve, the prediction error is used to reflect the degree of fit between the prediction result of the input elastic parameter combination and the real reservoir parameter curve, and the prediction error is inversely correlated with the degree of fit. As the number of elastic parameters in the input elastic parameter combination increases, the prediction error gradually decreases, and the prediction error tends to be constant when it decreases to a certain extent. Therefore, the multiple elastic parameters in the elastic parameter combination corresponding to the dividing point when the prediction error transitions from gradually decreasing to tending to be constant are determined as sensitive parameters. Since the degree of fit between the prediction result obtained by the input elastic parameter combination at this time and the real reservoir parameter curve is the highest, the multiple sensitive parameters determined at this time can take into account the sensitivity of the interaction between the sensitive parameters to the prediction result, thereby improving the accuracy of quantitative reservoir characterization.

[0127] In some embodiments, Figure 10 A block diagram of a sensitive parameter determination device provided according to an embodiment of the present application. Figure 10 , prediction module 902, including:

[0128] a transformation unit 1001 configured to perform a mathematical transformation and a rotational transformation on elastic parameter curves of multiple elastic parameters in any elastic parameter combination to obtain characteristic curves of the multiple elastic parameters in the elastic parameter combination, wherein the mathematical transformation includes at least one of addition, subtraction, multiplication, division, squaring, and square root, and the rotational transformation is configured to rotate the elastic parameter curve based on a rotation angle;

[0129] The prediction unit 1002 is configured to predict characteristic curves of multiple elastic parameters in the elastic parameter combination based on the prediction model to obtain a prediction result.

[0130] In some embodiments, see Figure 10 , the combination module 901 includes:

[0131] A sorting unit 1003 is configured to sort the multiple elastic parameters from large to small based on sensitivity;

[0132] The combination unit 1004 is configured to select, for any selection number from the multiple selection numbers, a selection number of elastic parameters that is ranked first as an elastic parameter combination based on the sorting result, where the selection number is a positive integer not less than 2.

[0133] In some embodiments, see Figure 10 The combination determination module 903 includes:

[0134] A first determining unit 1005 is configured to determine a first cross-plot based on the prediction errors of the plurality of elastic parameter combinations and the plurality of elastic parameter combinations, wherein the first cross-plot is configured to indicate a corresponding relationship between the prediction errors and the number of elastic parameters in the plurality of elastic parameter combinations;

[0135] The second determining unit 1006 is configured to determine an inflection point of the prediction error in the first intersection graph, where the inflection point is a demarcation point where the prediction error transitions from gradually decreasing to becoming constant.

[0136] The third determining unit 1007 is configured to determine a target elastic parameter combination including a target number of elastic parameters based on the target number represented by the abscissa of the inflection point.

[0137] In some embodiments, see Figure 10 , the device further comprises:

[0138] A selection module 905 is configured to randomly select a segment of the elastic parameter curve of the elastic parameter based on the data distribution of the elastic parameter curve of the elastic parameter using Monte Carlo simulation for any elastic parameter in the target elastic parameter combination to obtain a simulated elastic parameter curve of the elastic parameter;

[0139] A simulation prediction module 906 is used to predict the simulated elastic parameter curves of multiple elastic parameters in the target elastic parameter combination based on the prediction model to obtain a simulation prediction result of the target elastic parameter combination;

[0140] The analysis module 907 is configured to perform statistical analysis on multiple simulation prediction results of the target elastic parameter combination to determine a second cross-plot, where the second cross-plot is configured to indicate a correspondence between the multiple simulation prediction results and the frequencies of occurrence of the multiple simulation prediction results.

[0141] In some embodiments, see Figure 10 , the device further comprises:

[0142] The weight determination module 908 is used to determine the parameter weight of any elastic parameter based on the prediction model. The parameter weight is used to indicate the sensitivity of the elastic parameter to the reservoir parameter. The parameter weight is positively correlated with the sensitivity.

[0143] It should be noted that the sensitive parameter determination device provided in the above embodiment only uses the division of the above functional modules as an example when running an application. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the sensitive parameter determination device provided in the above embodiment and the sensitive parameter determination method embodiment are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0144] In the embodiments of the present application, the computer device can be configured as a terminal or a server. When the computer device is configured as a terminal, the terminal can be used as the execution subject to implement the technical solution provided in the embodiments of the present application. When the computer device is configured as a server, the server can be used as the execution subject to implement the technical solution provided in the embodiments of the present application. The technical solution provided in the present application can also be implemented through interaction between the terminal and the server. The embodiments of the present application do not limit this.

[0145] Figure 11The figure is a schematic diagram of the structure of a terminal provided according to an embodiment of the present application. Terminal 1100 may be a portable mobile terminal, such as a smartphone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), a laptop computer, or a desktop computer. Terminal 1100 may also be referred to as user equipment, a portable terminal, a laptop terminal, a desktop terminal, or other similar names.

[0146] Typically, the terminal 1100 includes a processor 1101 and a memory 1102 .

[0147] The processor 1101 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 1101 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array). The processor 1101 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 1101 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 1101 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0148] The memory 1102 may include one or more computer-readable storage media, which may be non-transitory. The memory 1102 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 1102 is used to store at least one computer program, which is executed by the processor 1101 to implement the sensitive parameter determination method provided in the method embodiment of the present application.

[0149] In some embodiments, terminal 1100 may optionally include a peripheral device interface 1103 and at least one peripheral device. Processor 1101, memory 1102, and peripheral device interface 1103 may be connected via a bus or signal lines. Each peripheral device may be connected to peripheral device interface 1103 via a bus, signal lines, or circuit boards. Specifically, the peripheral device may include at least one of a radio frequency circuit 1104, a display screen 1105, a camera assembly 1106, an audio circuit 1107, and a power supply 1108.

[0150] The peripheral device interface 1103 can be used to connect at least one I / O (Input / Output)-related peripheral device to the processor 1101 and the memory 1102. In some embodiments, the processor 1101, the memory 1102, and the peripheral device interface 1103 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 1101, the memory 1102, and the peripheral device interface 1103 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0151] The RF circuit 1104 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 1104 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 1104 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. In some embodiments, the RF circuit 1104 includes an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The RF circuit 1104 can communicate with other terminals via at least one wireless communication protocol. Such wireless communication protocols include, but are not limited to, the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 1104 may also include circuitry related to Near Field Communication (NFC), although this application does not limit this.

[0152] The display screen 1105 is used to display a UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 1105 is a touch screen display, the display screen 1105 also has the ability to collect touch signals on the surface or above the surface of the display screen 1105. The touch signal can be input as a control signal to the processor 1101 for processing. At this time, the display screen 1105 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, there can be one display screen 1105, which is set on the front panel of the terminal 1100; in other embodiments, there can be at least two display screens 1105, which are respectively set on different surfaces of the terminal 1100 or in a folding design; in other embodiments, the display screen 1105 can be a flexible display screen, which is set on the curved surface or folding surface of the terminal 1100. Even more, the display screen 1105 can be set to a non-rectangular irregular shape, that is, a special-shaped screen. The display screen 1105 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0153] The camera assembly 1106 is used to capture images or videos. In some embodiments, the camera assembly 1106 includes a front camera and a rear camera. Typically, the front camera is arranged on the front panel of the terminal, and the rear camera is arranged on the back of the terminal. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, the fusion of the main camera and the wide-angle camera to realize panoramic shooting and VR (Virtual Reality) shooting function or other fusion shooting functions. In some embodiments, the camera assembly 1106 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0154] The audio circuit 1107 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals that are input into the processor 1101 for processing, or input into the radio frequency circuit 1104 to achieve voice communication. For the purpose of stereo sound collection or noise reduction, there may be multiple microphones, each located in different parts of the terminal 1100. The microphone may also be an array microphone or an omnidirectional collection microphone. The speaker is used to convert electrical signals from the processor 1101 or the radio frequency circuit 1104 into sound waves. The speaker may be a traditional thin film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert electrical signals into sound waves audible to humans, but also convert electrical signals into sound waves inaudible to humans for purposes such as distance measurement. In some embodiments, the audio circuit 1107 may also include a headphone jack.

[0155] Power supply 1108 is used to power various components in terminal 1100. Power supply 1108 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 1108 includes a rechargeable battery, the rechargeable battery can support wired charging or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0156] In some embodiments, the terminal 1100 further includes one or more sensors 1109 , including but not limited to: an acceleration sensor 1110 , a gyroscope sensor 1111 , a pressure sensor 1112 , an optical sensor 1113 , and a proximity sensor 1114 .

[0157] The accelerometer 1110 can detect the magnitude of acceleration along the three coordinate axes of the coordinate system established by the terminal 1100. For example, the accelerometer 1110 can be used to detect the components of gravity acceleration along the three coordinate axes. The processor 1101 can control the display screen 1105 to display the user interface in either a landscape or portrait view based on the gravity acceleration signal collected by the accelerometer 1110. The accelerometer 1110 can also be used to collect game or user motion data.

[0158] The gyroscope sensor 1111 can detect the orientation and rotation angle of the terminal 1100. The gyroscope sensor 1111 can work with the accelerometer 1110 to collect the user's 3D movements on the terminal 1100. Based on the data collected by the gyroscope sensor 1111, the processor 1101 can implement the following functions: motion sensing (such as changing the UI based on the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.

[0159] The pressure sensor 1112 can be provided on the side frame of the terminal 1100 and / or below the display screen 1105. When the pressure sensor 1112 is provided on the side frame of the terminal 1100, it can detect the user's gripping signal of the terminal 1100, and the processor 1101 can perform left-hand or right-hand recognition or shortcut operations based on the gripping signal collected by the pressure sensor 1112. When the pressure sensor 1112 is provided below the display screen 1105, the processor 1101 controls the operable controls on the UI interface based on the user's pressure operation on the display screen 1105. Operable controls include at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0160] Optical sensor 1113 is used to detect ambient light intensity. In one embodiment, processor 1101 can control the display brightness of display screen 1105 based on the ambient light intensity detected by optical sensor 1113. Optionally, when the ambient light intensity is high, the display brightness of display screen 1105 is increased; when the ambient light intensity is low, the display brightness of display screen 1105 is decreased. In another embodiment, processor 1101 can also dynamically adjust the shooting parameters of camera assembly 1106 based on the ambient light intensity detected by optical sensor 1113.

[0161] Proximity sensor 1114, also known as a distance sensor, is disposed on the front panel of terminal 1100. Proximity sensor 1114 is used to detect the distance between the user and the front of terminal 1100. In one embodiment, when proximity sensor 1114 detects that the distance between the user and the front of terminal 1100 is gradually decreasing, processor 1101 controls display screen 1105 to switch from the screen-on state to the screen-off state. When proximity sensor 1114 detects that the distance between the user and the front of terminal 1100 is gradually increasing, processor 1101 controls display screen 1105 to switch from the screen-off state to the screen-on state.

[0162] Those skilled in the art will understand that Figure 11 The structure shown in the figure does not constitute a limitation on the terminal 1100, and the terminal 1100 may include more or fewer components than shown in the figure, or combine certain components, or adopt a different component arrangement.

[0163] Figure 12This is a structural diagram of a server provided in accordance with an embodiment of the present application. The server 1200 may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) 1201 and one or more memories 1202, wherein the memory 1202 stores at least one computer program, and the at least one computer program is loaded and executed by the processor 1201 to implement the sensitive parameter determination method provided in each of the above method embodiments. Of course, the server may also have components such as a wired or wireless network interface, a keyboard, and an input / output interface for input and output. The server may also include other components for implementing device functions, which will not be described in detail here.

[0164] The present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one computer program, which is loaded and executed by a processor of a computer device to implement the operations performed by the computer device in the sensitive parameter determination method of the above embodiment. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0165] The present application also provides a computer program product, including a computer program stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium and executes the computer program, causing the computer device to perform the sensitive parameter determination method provided in the various optional implementations described above.

[0166] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or by a program to instruct the relevant hardware, and the program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk, etc.

[0167] The above description is merely an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for determining sensitive parameters, characterized in that: The method comprises: sorting the multiple elastic parameters of the target reservoir from largest to smallest based on their sensitivity to the reservoir parameters, the multiple elastic parameters being used to reflect the elastic characteristics of the rock in the target reservoir, and the reservoir parameters being used to reflect the characteristics of the target reservoir; For any selected number from the plurality of selected numbers, based on the sorting result, selecting the selected number of elastic parameters that are sorted first as an elastic parameter combination to obtain a plurality of elastic parameter combinations, wherein the selected number is a positive integer not less than 2; For any elastic parameter combination, based on a prediction model, predicting elastic parameter curves of multiple elastic parameters in the elastic parameter combination to obtain a prediction result, wherein the prediction model is used to predict the reservoir parameters based on the input elastic parameter curve, and the prediction result represents a reservoir parameter curve of multiple reservoir parameters predicted based on the elastic parameter curve of the multiple elastic parameters; Determining a first cross-plot based on the prediction errors of the multiple elastic parameter combinations and the multiple elastic parameter combinations, the first cross-plot being used to indicate a corresponding relationship between the prediction errors and the number of elastic parameters in the multiple elastic parameter combinations, the prediction errors being used to reflect a degree of fit between a prediction result of the corresponding elastic parameter combination and a true reservoir parameter curve, the degree of fit being inversely correlated with the prediction error; Determining an inflection point of the prediction error in the first intersection graph, where the inflection point is a demarcation point where the prediction error transitions from gradually decreasing to becoming constant; determining, based on a target number represented by the abscissa of the inflection point, a target elastic parameter combination including the target number of elastic parameters; A plurality of elastic parameters in the target elastic parameter combination are determined as sensitive parameters.

2. The method according to claim 1, characterized in that For any elastic parameter combination, based on the prediction model, elastic parameter curves of multiple elastic parameters in the elastic parameter combination are predicted to obtain a prediction result, including: For any elastic parameter combination, performing mathematical transformation and rotational transformation on elastic parameter curves of multiple elastic parameters in the elastic parameter combination to obtain characteristic curves of the multiple elastic parameters in the elastic parameter combination, wherein the mathematical transformation includes at least one of addition, subtraction, multiplication, division, squaring, and square root, and the rotational transformation is used to rotate the elastic parameter curve based on a rotation angle; Based on the prediction model, characteristic curves of multiple elastic parameters in the elastic parameter combination are predicted to obtain the prediction result.

3. The method according to claim 1, characterized in that After determining the multiple elastic parameters in the target elastic parameter combination as sensitive parameters, the method further includes: For any elastic parameter in the target elastic parameter combination, based on the data distribution of the elastic parameter curve of the elastic parameter, a section of the curve is randomly selected from the elastic parameter curve of the elastic parameter using Monte Carlo simulation to obtain a simulated elastic parameter curve of the elastic parameter; Based on the prediction model, predicting simulated elastic parameter curves of multiple elastic parameters in the target elastic parameter combination to obtain a simulation prediction result of the target elastic parameter combination; Statistical analysis is performed on the multiple simulation prediction results of the target elastic parameter combination to determine a second cross-plot, where the second cross-plot is used to indicate a corresponding relationship between the multiple simulation prediction results and the frequencies of occurrence of the multiple simulation prediction results.

4. The method according to claim 1, wherein Before selecting the selected number of elastic parameters ranked first as an elastic parameter combination based on the sorting result to obtain multiple elastic parameter combinations, the method further includes: For any elastic parameter, a parameter weight of the elastic parameter is determined based on the prediction model, and the parameter weight is used to indicate the sensitivity of the elastic parameter to the reservoir parameter, and the parameter weight is positively correlated with the sensitivity.

5. A sensitive parameter determination device, characterized in that: The device comprises: a combination module, configured to sort the multiple elastic parameters of the target reservoir from largest to smallest based on their sensitivity to the reservoir parameters, the multiple elastic parameters being used to reflect the elastic characteristics of the rock in the target reservoir, and the reservoir parameters being used to reflect the characteristics of the target reservoir; for any of the multiple selected quantities, based on the sorting result, selecting the selected quantity of elastic parameters that are ranked first as an elastic parameter combination to obtain multiple elastic parameter combinations, the selected quantity being a positive integer not less than 2; a prediction module configured to predict, for any elastic parameter combination, elastic parameter curves of a plurality of elastic parameters in the elastic parameter combination based on a prediction model to obtain a prediction result, wherein the prediction model is configured to predict the reservoir parameters based on the input elastic parameter curve, and the prediction result represents a reservoir parameter curve of the plurality of reservoir parameters predicted based on the elastic parameter curve of the plurality of elastic parameters; A combination determination module is configured to determine a first cross-plot based on the prediction errors of the multiple elastic parameter combinations and the multiple elastic parameter combinations, wherein the first cross-plot is configured to indicate a corresponding relationship between the prediction errors and the number of elastic parameters in the multiple elastic parameter combinations, wherein the prediction errors are configured to reflect a degree of fit between a prediction result of the corresponding elastic parameter combination and a true reservoir parameter curve, wherein the degree of fit is inversely correlated with the prediction errors; determine an inflection point of the prediction error in the first cross-plot, wherein the inflection point is a demarcation point where the prediction error transitions from a gradual decrease to a constant state; and determine a target elastic parameter combination including the target number of elastic parameters based on a target number represented by a horizontal coordinate of the inflection point; The parameter determination module is configured to determine multiple elastic parameters in the target elastic parameter combination as sensitive parameters.

6. A computer device, characterized in that: The computer device includes a processor and a memory, the memory is used to store at least one computer program, and the at least one computer program is loaded by the processor to execute the sensitive parameter determination method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store at least one computer program, and the at least one computer program is used to execute the sensitive parameter determination method according to any one of claims 1 to 4.

8. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the sensitive parameter determination method according to any one of claims 1 to 4 is implemented.

Images