Potential layer selection method and apparatus, computer device, and storage medium

Abstract

A potential layer selection method and apparatus, a computer device, and a storage medium. The method comprises: on the basis of indicator values of candidate layers under a plurality of logging indicators, determining indicator mean values and dispersion degrees of the candidate layers (S202); determining target ranking indicators of the candidate layers on the basis of the indicator mean values and the dispersion degrees (S204); and selecting a potential layer from among the candidate layers on the basis of the target ranking indicators of the candidate layers (S206).

Description

Methods, apparatus, computer equipment and storage media for selecting potential layers

[0001] This application claims priority to Chinese Patent Application No. 2024115266961, filed on October 30, 2024, entitled "Method, Apparatus, Computer Equipment and Storage Medium for Selecting Potential Layers", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of oil exploration, and more particularly to a method, apparatus, computer equipment, and storage medium for selecting potential layers. Background Technology

[0003] Potential layers are strata with potential oil or gas reserves. In the field of oil exploration, it is usually necessary to identify potential layers from among many strata.

[0004] In related technologies, after obtaining the logging index data, logging engineers usually need to select potential layers based on experience. This process involves data from multiple formations and multiple logging indices, resulting in a large amount of data and high computational difficulty, which leads to low efficiency in selecting potential layers. Summary of the Invention

[0005] This application provides a method, apparatus, computer device, and storage medium for selecting potential layers.

[0006] In a first aspect, this application provides a method for selecting potential layers, executed by a computer device, comprising: determining the mean and dispersion of the indicators of the candidate layers based on the indicator values ​​of the candidate layers under multiple logging indicators; determining the target ranking indicators of the candidate layers based on the mean and dispersion of the indicators; and selecting potential layers from the candidate layers according to the target ranking indicators of the candidate layers.

[0007] Secondly, this application provides a potential layer selection device, comprising:

[0008] The index value processing module is used to determine the index mean and dispersion of the candidate layer based on the index values ​​of the candidate layer under multiple logging indices.

[0009] The ranking metric determination module is used to determine the target ranking metric for the candidate layer based on the metric's mean and dispersion; and

[0010] The selection module is used to select potential layers from the candidate layers based on the target ranking index of the candidate layers.

[0011] Thirdly, this application also provides a computer device, the computer comprising: a processor, and a memory communicatively connected to the processor;

[0012] The memory stores computer-executed instructions;

[0013] The processor implements the above method when executing computer execution instructions stored in the memory.

[0014] Fourthly, this application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the above-described method.

[0015] Fifthly, this application also provides a computer program product, including computer execution instructions, which, when executed by a processor, implement the above-described method.

[0016] Details of one or more embodiments of this application are set forth in the following drawings and description. Other features, objects, and advantages of this application will become apparent from the specification, drawings, and claims. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] Figure 1 is a schematic diagram of an application scenario of the potential layer selection method provided in one embodiment;

[0019] Figure 2 is a flowchart of a potential layer selection method provided in one embodiment;

[0020] Figure 3 is a schematic diagram of the indicator values ​​when the production potential indicator is large in one embodiment;

[0021] Figure 4(a) is a schematic diagram showing the relationship between the scatter curves corresponding to the candidate ranking index sequence, the upper envelope, the lower envelope, and the mean envelope corresponding to the production potential index sequence in one embodiment.

[0022] Figure 4(b) is a schematic diagram showing the relationship between the scatter curves corresponding to the candidate ranking index sequence, the upper envelope, the lower envelope, and the mean envelope corresponding to the production potential index sequence in one embodiment.

[0023] Figure 4(c) is a schematic diagram showing the relationship between the scatter curves corresponding to the candidate ranking index sequence, the upper envelope, the lower envelope, and the mean envelope corresponding to the production potential index sequence in one embodiment.

[0024] Figure 4(d) is a schematic diagram illustrating the relationship between the scatter plots corresponding to the candidate ranking index sequence, the upper envelope, the lower envelope, and the mean envelope corresponding to the production potential index sequence in one embodiment.

[0025] Figure 4(e) is a schematic diagram showing the relationship between the scatter curves corresponding to the candidate ranking index sequence, the upper envelope, the lower envelope, and the mean envelope corresponding to the production potential index sequence in one embodiment.

[0026] Figure 4(f) is a schematic diagram showing the relationship between the scatter curves corresponding to the candidate ranking index sequence, the upper envelope, the lower envelope, and the mean envelope corresponding to the production potential index sequence in one embodiment.

[0027] Figure 5 is a schematic diagram showing the residuals corresponding to different adjustment factors in one embodiment;

[0028] Figure 6 is a flowchart of a potential layer selection method provided in one embodiment;

[0029] Figure 7 is a comparison chart showing the target ranking index according to multiple candidate layers in one embodiment;

[0030] Figure 8 is a schematic diagram of the potential layer selection device in one embodiment;

[0031] Figure 9 is a hardware structure diagram of a computer device provided in one embodiment.

[0032] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0033] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0034] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0035] First, let me explain the terms used in this application:

[0036] Potential layer: refers to a stratum with potential oil or natural gas reserves.

[0037] Candidate layer: A stratum that may have potential oil or gas reserves; This application embodiment is used to select potential layers from among the candidate layers.

[0038] Well logging parameters are important indicators for assessing formation characteristics and reservoir quality. Well logging parameters may include, but are not limited to, thickness, permeability, saturation and porosity. Among them, thickness is the physical thickness of the formation; permeability is used to reflect the ease with which fluids pass through pores in the formation; saturation is used to reflect the content of oil, gas or water in the formation; and porosity is used to reflect the volume fraction of pore space in the formation.

[0039] In related technologies, after obtaining the logging index data, logging engineers usually need to select potential layers based on experience. This process involves data from multiple formations and multiple logging indices, resulting in a large amount of data and high computational difficulty, which leads to low efficiency in selecting potential layers.

[0040] The potential layer selection method provided in this application determines the mean and dispersion of candidate layers based on their index values ​​under multiple logging indicators; it then determines the target ranking index for the candidate layers based on the mean and dispersion; and finally, it selects potential layers from the candidate layers according to the target ranking index. This process is manual and can automatically process complex index values ​​to select potential layers from the candidate layers, effectively improving the efficiency of potential layer selection. Furthermore, determining the target ranking index through the mean and dispersion ensures that the index values ​​under multiple logging indicators have a balanced effect on the target ranking index, improving the quality of the target ranking index. Selecting potential layers based on the target ranking index, which has a balanced effect from multiple logging indicators, improves the accuracy and reliability of the selected potential layers.

[0041] The potential layer selection method provided in this application embodiment can be applied to the application environment shown in Figure 1. In this environment, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on another network server.

[0042] The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle systems. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0043] In some embodiments, as shown in FIG2, a potential layer selection method is provided. Taking the application of this method to a computer device as an example, the computer device can be a terminal or server as shown in FIG1. ​​The method includes:

[0044] S202, based on the index values ​​of the candidate layer under multiple logging indices, determines the index mean and dispersion of the candidate layer.

[0045] Among them, the index mean is used to reflect the average value of the index values ​​under multiple logging indices; the dispersion is used to reflect the degree of dispersion of the distribution of multiple index values.

[0046] Specifically, the computer equipment acquires the index values ​​of the candidate layer under multiple logging indicators, calculates the average of the multiple index values, uses the number of multiple logging indicators as the exponent of the average, determines the exponent power of the average, and obtains the index mean; the computer equipment determines the difference between the multiple index values ​​and the index mean, and determines the dispersion based on the difference between the multiple index values ​​and the index mean.

[0047] In one possible approach, different logging indicators may have different dimensions. In order to convert logging indicators with different dimensions to a unified scale, the indicator values ​​of each logging indicator can be normalized, and then the indicator mean and dispersion can be determined based on the normalized indicator values.

[0048] It should be noted that there are multiple candidate layers. For each candidate layer, the mean and dispersion of the candidate layer are determined based on the index values ​​of the candidate layer under multiple logging indices.

[0049] S204, based on the mean and dispersion of the index, determines the target ranking index of the candidate layer.

[0050] Among them, the target ranking index can reflect the energy storage situation of the candidate layer; when comparing two target ranking indices, the larger target ranking index may correspond to better energy storage situation; it should be noted that the target ranking index is calculated based on the index value. In some scenarios, the candidate layer with better energy storage situation can be determined by comparing the target ranking index. The target ranking index is not the actual storage of the candidate layer.

[0051] Specifically, the computer device can use the difference between the index mean and dispersion as the target ranking index of the candidate layer; it can also adjust the dispersion through adjustment factors to reduce or increase the impact of dispersion on the target ranking index, and then calculate the target ranking index of the candidate layer based on the adjusted dispersion and index mean; or it can calculate candidate ranking indices under multiple adjustment factors based on the index mean and dispersion, and select one of the candidate ranking indices under multiple adjustment factors as the target ranking index.

[0052] In some embodiments, determining the target ranking index of the candidate layer based on the index mean and dispersion includes: determining the candidate ranking index of the candidate layer under multiple adjustment factors based on the index mean and dispersion; determining the production potential index of the candidate layer based on the multiple index values ​​of the candidate layer; selecting a target adjustment factor from the multiple adjustment factors based on the production potential index of the candidate layer and the candidate ranking index of the candidate layer under multiple adjustment factors; and using the candidate ranking index of the candidate layer under the target adjustment factor as the target ranking index of the candidate layer.

[0053] Among them, the adjustment factor is used to adjust the degree of influence of dispersion on the candidate ranking index. The larger the adjustment factor, the greater the influence of dispersion on the candidate ranking index. The candidate energy storage index can also reflect the energy storage status of the candidate layer.

[0054] Multiple adjustment factors are preset; before determining the candidate ranking index of the candidate layer under multiple adjustment factors based on the index mean and the dispersion, it also includes selecting multiple values ​​in a preset value range at preset intervals; the multiple values ​​are used as multiple adjustment factors; for example, if the preset value range is [0,1] and the preset interval is 0.01, then the multiple adjustment factors may include: 0, 0.01, 0.02, ..., 0.99, 1.

[0055] Multiple adjustment factors can also be multiple values ​​that belong to a preset value range; multiple adjustment factors can also be multiple values ​​randomly selected from the preset value range; the specific values ​​of multiple adjustment factors can be set according to actual needs, and the embodiments of this application do not limit the specific values ​​of multiple adjustment factors.

[0056] Among them, the production potential indicator is the actual reserves of the candidate layer.

[0057] Specifically, for each adjustment factor, the computer device determines the product between the adjustment factor and the dispersion, and then determines the candidate ranking index based on the index mean and the product. It should be noted that there are multiple candidate layers, and for each candidate layer, the candidate ranking index of the candidate layer under multiple adjustment factors can be calculated.

[0058] In some embodiments, the candidate ranking index of the candidate layer under multiple adjustment factors is determined based on the index mean and dispersion, including: for each adjustment factor, determining the product between the dispersion and the targeted adjustment factor to obtain the adjusted dispersion; and using the difference between the index mean and the adjusted dispersion as the candidate ranking index of the candidate layer under the targeted adjustment factor.

[0059] Specifically, the computer equipment can calculate the candidate ranking index according to formula (1).

[0060] Formula (1):

[0061] Where, γ c1 It is the candidate ranking index of candidate layer c1. The index mean of candidate layer c1 is given by α, which is a modulating factor, and σ is the mean index of candidate layer c1. c1 It is the discreteness of candidate layer c1.

[0062] In the above embodiments, candidate ranking indicators are determined by the mean and dispersion of the indicators, so that the indicator values ​​under multiple logging indicators have a balanced effect on the candidate ranking indicators, thereby improving the quality of the candidate ranking indicators.

[0063] In some embodiments, determining the production potential index of the candidate layer based on multiple index values ​​of the candidate layer includes: determining the product of multiple index values ​​of the candidate layer to obtain the production potential index of the candidate layer.

[0064] Specifically, for each candidate layer, the computer device determines the product of multiple index values ​​of the candidate layer to obtain the production potential index of the candidate layer, as shown in formula (2).

[0065] Formula (2):

[0066] Among them, S n X is the production potential index of the nth candidate layer, M is the number of logging indices, and X is the production potential index of the nth candidate layer. n,m It is the index value of the nth candidate layer under the mth logging index.

[0067] There are multiple candidate layers. The computer equipment obtains the candidate ranking index of each candidate layer under multiple adjustment factors, that is, it obtains the candidate ranking index of multiple candidate layers under each adjustment factor. For each adjustment factor, the order of multiple candidate layers is determined according to the candidate ranking index of multiple candidate layers under that adjustment factor, and a candidate ranking index sequence is obtained. The production potential index of multiple candidate layers is ranked according to this order, and a production potential index sequence is obtained. The energy storage difference under that adjustment factor is determined according to the candidate ranking index sequence and the production potential index sequence. In this way, the energy storage difference corresponding to each of the multiple adjustment factors can be obtained. The adjustment factor corresponding to the smallest energy storage difference can be used as the target adjustment factor, and the candidate ranking index of multiple candidate layers calculated based on the target adjustment factor can be used as the target ranking index of multiple candidate layers.

[0068] The principle of the method proposed in the embodiments of this application will be explained next.

[0069] The larger the values ​​of multiple indicators of a candidate layer, the better the energy storage of the candidate layer; therefore, the larger the production potential index, the better the energy storage of the candidate layer. In related technologies, potential layers are selected through the production potential index. However, a large production potential index does not necessarily mean that all multiple index values ​​are large. It may be that some index values ​​are large while others are small, resulting in a large production potential index for the candidate layer. Such candidate layers may be difficult to mine.

[0070] For example, multiple logging indicators may include thickness H, permeability K, saturation S, and porosity F. The production potential index of a candidate layer is the product of thickness H, permeability K, saturation S, and porosity F. When the production potential index is large, there may be a situation as shown in Figure 3, that is, a large production potential index of a candidate layer does not mean that the thickness H, permeability K, saturation S, and porosity F of the candidate layer are all large.

[0071] To address the issue that selecting potential layers using production potential indicators makes it difficult to apply them to real-world scenarios, this application embodiment determines the mean and dispersion of multiple indicator values, and determines candidate ranking indicators based on the mean and dispersion of the indicators.

[0072] The production potential index of the candidate layer can be calculated by referring to formula (2); formula (3) can be obtained according to Cauchy inequality.

[0073] Formula (3):

[0074] in, It is the mean of the indicators, and the condition for equality is X. n,1 =X n,2 =…=X n,m =…=X n,M-1 =X n,M .

[0075] In other words, Cauchy's inequality can be used to express the relationship between the product of multiple index values ​​and the index mean, in each X... n,m When the difference between them is 0, formula (3) can be considered equal.

[0076] Each X n,m A difference of 0 indicates that the candidate layer has the same index value under different logging parameters. In practical applications, this difference may not exist. n,mWhen the difference between the two is 0, in order to improve the accuracy of the candidate ranking index, an adjustment factor and dispersion (characterizing the difference) can be added to the index mean to make the candidate ranking index as close as possible to the production potential index. Therefore, the candidate ranking index is determined according to the index mean, dispersion and adjustment factor, and the candidate ranking index under multiple adjustment factors is calculated to select the target ranking index that is close to the production potential index from multiple candidate ranking indices. In this way, the target ranking index is calculated under the balanced effect of multiple logging indices and can reflect the actual energy storage of the candidate layer, thus improving the quality of the target ranking index.

[0077] S206. Based on the target ranking index of the candidate layers, select the potential layer from the candidate layers.

[0078] Specifically, the computer device can select the candidate layer with the largest target ranking index as the potential layer from multiple candidate layers, or sort multiple candidate layers according to the target ranking index in ascending order (or descending order) to obtain a candidate layer sequence, and select one or more potential layers from the candidate layer sequence.

[0079] In one possible scenario, after obtaining the candidate layer sequence, a scatter plot can be drawn according to the order of the candidate layer sequence, based on multiple candidate layers and their respective target ranking indicators. The scatter plot can provide an intuitive understanding of the energy storage status of multiple candidate layers.

[0080] The aforementioned potential layer selection method determines the mean and dispersion of candidate layer indicators based on the indicator values ​​of candidate layers under multiple logging indices; it then determines the target ranking index for candidate layers based on the indicator mean and dispersion; and finally, it selects potential layers from the candidate layers according to the target ranking index. This process is manual and can automatically process complex indicator values ​​to select potential layers from the candidate layers, effectively improving the efficiency of potential layer selection. Furthermore, determining the target ranking index through the indicator mean and dispersion ensures that the indicator values ​​under multiple logging indices have a balanced effect on the target ranking index, improving the quality of the target ranking index. Selecting potential layers based on the target ranking index, which plays a balanced role in multiple logging indices, improves the accuracy and reliability of the selected potential layers.

[0081] In some embodiments, the number of candidate layers is multiple; based on the index values ​​of the candidate layers under multiple logging indices, the index mean and dispersion of the candidate layers are determined, including: for each logging indices, obtaining the index values ​​of multiple candidate layers under the corresponding logging indices; normalizing the index values ​​of multiple candidate layers under the corresponding logging indices to obtain normalized index values ​​of multiple candidate layers under the corresponding logging indices; for each candidate layer, determining the index mean of the corresponding candidate layer based on the normalized index values ​​of the corresponding candidate layer under multiple logging indices; and determining the dispersion of the corresponding candidate layer based on the multiple normalized index values ​​and the index mean of the corresponding candidate layer.

[0082] Specifically, since there are multiple candidate layers, each candidate layer has index values ​​under multiple logging indicators. The index values ​​of multiple candidate layers under multiple logging indicators can be represented by a matrix. For example, the index values ​​of N candidate layers under M logging indicators can be represented as follows:

[0083] Among them, X 11 X is the index value of the first candidate layer under the first logging index. NM The index value of the Nth candidate layer under the Mth logging index.

[0084] For each logging index, the computer device obtains the index values ​​of multiple candidate layers under the target logging index, that is, obtains a column vector in matrix X. All index values ​​in this column vector correspond to the same logging index. Therefore, all index values ​​(index values ​​under the target logging index) in this column vector have the same dimensions. The computer device obtains the maximum index value and the minimum index value among the index values ​​under the target logging index. Based on the maximum index value and the minimum index value, the computer device performs normalization processing on each index value under the target logging index to obtain the normalized index value under the target logging index, as shown in formula (4).

[0085] Formula (4):

[0086] Among them, X n,m It is the index value of the nth candidate layer under the mth logging index. It is X n,m The corresponding normalized index value, max(X) .,m ) represents the maximum value among the index values ​​of multiple candidate layers under the m-th logging index, min(X) ·,m ) is the minimum value among the index values ​​of multiple candidate layers under the m-th logging index.

[0087] For each candidate layer, the normalized index value under multiple logging indices is determined, the mean value among multiple normalized index values ​​is determined, the number of multiple logging indices is used as the exponent, the exponent power of the mean value is determined, and the index mean value of the candidate layer is obtained, as shown in formula (5).

[0088] Formula (5):

[0089] in, It is the mean value of the index of the nth candidate layer. It is the normalized index of the nth candidate layer under the mth logging index, where M is the number of logging indices.

[0090] For each candidate layer, the computer device can calculate the variance based on the mean of the index of the candidate layer and multiple normalized index values, and use the variance as the dispersion; as shown in formula (6).

[0091] Formula (6):

[0092] Where, σ n It is the discreteness of the nth candidate layer. is the average index of the nth candidate layer, and M is the number of logging indices.

[0093] In the above embodiments, normalization can eliminate the obstacle of different dimensions between different logging indicators, so as to determine the indicator mean and dispersion on a unified scale, thereby improving the accuracy of the candidate ranking indicators determined based on the indicator mean and dispersion.

[0094] In some embodiments, determining the mean index of a candidate layer based on the normalized index values ​​of the candidate layer under multiple logging indices includes: obtaining the weights of multiple logging indices; determining the weighted mean of the candidate layer based on the weights of the multiple logging indices and the normalized index values ​​of the candidate layer under multiple logging indices; and using the weighted mean of the candidate layer as the mean index of the candidate layer.

[0095] The weights are used to reflect the importance of different logging indicators; the weights are preset and can be preset by experts in the field; the sum of the weights of multiple logging indicators can be 1.

[0096] Specifically, the mean index of the candidate layer can be determined by formula (7).

[0097] Formula (7): stw1+w2+…+w M =1;

[0098] Among them, w m It is the weight of the m-th logging index. It is the mean value of the index of the nth candidate layer. It is the normalized index value of the nth candidate layer under the mth logging index, where M is the number of logging indices.

[0099] It should be noted that, when the mean value of the candidate layer is determined by formula (7), the process of determining the dispersion can be as follows: for each candidate layer, calculate the normalized index value under each logging index, calculate the product of the normalized index value and the weight of the corresponding logging index to obtain the index value to be processed, and calculate the dispersion of the candidate layer based on the index value to be processed and the mean value of the index under multiple logging indices, as shown in formula (8).

[0100] Formula (8): stw1+w2+…+w M =1;

[0101] in, It is the value of the index to be processed for the nth candidate layer under the first logging index. It is the indicator mean, σ n,w It is the discreteness of the nth candidate layer.

[0102] Accordingly, the candidate ranking index for the target candidate layer can be determined according to formula (9).

[0103] Formula (9):

[0104] In the above embodiments, the weights of multiple logging indicators are considered when calculating the average value of the indicators, so as to adjust the contribution of the indicator values ​​of multiple logging indicators to the candidate energy storage indicators, making the candidate ranking indicators closer to actual applications, improving the quality of the candidate ranking indicators, and thus improving the accuracy and reliability of potential layer selection.

[0105] In some embodiments, the number of candidate layers is multiple; selecting a target adjustment factor from multiple adjustment factors based on the production potential index of the candidate layers and the candidate ranking index of the candidate layers under multiple adjustment factors includes: for each adjustment factor, ranking the candidate ranking index of multiple candidate layers under the targeted adjustment factor to obtain a candidate ranking index sequence corresponding to the targeted adjustment factor; ranking the production potential index of multiple candidate layers according to the order of the candidate ranking index sequence to obtain a production potential index sequence corresponding to the targeted adjustment factor; determining the residual corresponding to the targeted adjustment factor based on the candidate ranking index sequence and the production potential index sequence corresponding to the targeted adjustment factor; and selecting a target adjustment factor from multiple adjustment factors based on the residuals corresponding to each of the multiple adjustment factors.

[0106] Specifically, for each adjustment factor, the candidate ranking indicators of multiple candidate layers are sorted in descending order to obtain the candidate ranking indicator sequence corresponding to the targeted adjustment factor. The candidate layer order in the candidate ranking indicator sequence is obtained, and the production potential indicators of multiple candidate layers are sorted according to the candidate layer order to obtain the production potential indicator sequence corresponding to the targeted adjustment factor. Based on the candidate ranking indicator sequence and the production potential indicator sequence corresponding to the targeted adjustment factor, the residual corresponding to the targeted adjustment factor is determined, and the adjustment factor corresponding to the smallest residual is taken as the target adjustment factor.

[0107] In some embodiments, determining the residual corresponding to the targeted adjustment factor based on the candidate ranking index sequence and the production potential index sequence corresponding to the targeted adjustment factor includes: determining the mean envelope based on the production potential index sequence corresponding to the targeted adjustment factor; determining the production potential mean index sequence of multiple candidate layers based on the mean envelope; determining the difference value of multiple candidate layers based on the production potential mean index sequence and the candidate ranking index sequence; and determining the sum of squares of the difference values ​​of multiple candidate layers to obtain the residual corresponding to the targeted adjustment factor.

[0108] The mean envelope is used to reflect the average value of the production potential index of multiple candidate layers.

[0109] In some embodiments, determining the mean envelope based on the production potential index sequence corresponding to the targeted adjustment factor includes: determining the upper envelope and the lower envelope based on the production potential index sequence corresponding to the targeted adjustment factor; and determining the mean envelope based on the upper envelope and the lower envelope.

[0110] Specifically, the computer equipment obtains the maximum and minimum values ​​in the production potential index sequence corresponding to the targeted adjustment factor, determines the upper envelope based on the maximum value, determines the lower envelope based on the minimum value, and determines the mean envelope based on the upper and lower envelopes.

[0111] There are multiple maxima and multiple minima. The upper envelope can be obtained from the multiple maxima, and the lower envelope can be obtained from the multiple minima. For each production potential indicator, the average value of the corresponding value of the production potential indicator in the upper and lower envelopes is calculated to obtain the average value of the corresponding production potential indicator. The mean envelope is determined based on the average value of the corresponding production potential indicator.

[0112] In some embodiments, determining the upper and lower envelopes based on the production potential index sequence corresponding to the targeted adjustment factor includes: selecting a maximum and a minimum value in the production potential index sequence corresponding to the targeted adjustment factor; interpolating the maximum value to obtain a first interpolation result; determining the upper envelope based on the first interpolation result; interpolating the minimum value to obtain a second interpolation result; and determining the lower envelope based on the second interpolation result.

[0113] Specifically, there are multiple maxima. For each maxima, cubic spline interpolation is performed to obtain the first interpolation result, and the upper envelope is determined based on the first interpolation result. There are multiple minima. For each minima, cubic spline interpolation is performed to obtain the second interpolation result, and the lower envelope is determined based on the second interpolation result.

[0114] The computer equipment obtains the production potential mean index of multiple candidate layers from the mean envelope, and then determines the production potential mean index sequence corresponding to the target adjustment factor based on the mean envelope. Based on the production potential mean index sequence and the candidate ranking index sequence corresponding to the target adjustment factor, the difference value between the production potential mean index and the candidate ranking index of multiple candidate layers is determined respectively. The square of the difference value of multiple candidate layers is calculated respectively, and then the sum of the squares of the difference values ​​of multiple candidate layers is determined to obtain the residual corresponding to the target adjustment factor.

[0115] In one possible implementation, after determining the difference between the mean production potential index and the candidate ranking index of multiple candidate layers, the average of the difference values ​​of each of the multiple candidate layers can also be used as the residual corresponding to the targeted adjustment factor.

[0116] For example, the horizontal axis of Figures 4(a) to 4(f) is the ranking index of multiple candidate layers under different adjustment factors. The ranking index is used to indicate the order of multiple candidate layers in the candidate ranking index sequence; the vertical axis of Figures 4(a) to 4(f) is the production potential index.

[0117] It should be noted that since the candidate ranking index sequences may be different under different adjustment factors, the ranking indices of multiple candidate layers may be different under different adjustment factors. In other words, although the labels of the horizontal axes in Figures 4(a) to 4(f) are the same, the ranking indices of multiple candidate layers in Figures 4(a) to 4(f) may be different. That is, the same ranking index in Figures 4(a) to 4(f) may correspond to different candidate layers.

[0118] Figure 4(a) shows the relationship between the scatter plots of the candidate ranking index sequence, the upper envelope, lower envelope, and mean envelope of the production potential index sequence when the adjustment factor is equal to 0. Figure 4(a) only ranks the indicators based on their mean values ​​and does not consider the dispersion between the indicator values. Figure 4(b) shows the relationship between the scatter plots of the candidate ranking index sequence, the upper envelope, lower envelope, and mean envelope of the production potential index sequence when the adjustment factor is equal to 0.004. Figure 4(c) shows the relationship between the scatter plots of the candidate ranking index sequence, the upper envelope, lower envelope, and mean envelope of the production potential index sequence when the adjustment factor is equal to 0.008. Figure 4(d) shows the relationship between the scatter plots of the candidate ranking index sequence, the upper envelope, lower envelope, and mean envelope of the production potential index sequence when the adjustment factor is equal to 0.0012; Figure 4(e) shows the relationship between the scatter plots of the candidate ranking index sequence, the upper envelope, lower envelope, and mean envelope of the production potential index sequence when the adjustment factor is equal to 0.0020; Figure 4(f) shows the relationship between the scatter plots of the candidate ranking index sequence, the upper envelope, lower envelope, and mean envelope of the production potential index sequence when the adjustment factor is equal to 0.0100; In Figure 4(f), the dispersion has the greatest impact on the candidate ranking index.

[0119] As can be seen from Figures 4(a) to 4(f), when the adjustment factor is equal to 0, 0.0004, and 0.0100, the differences between the scatter plots corresponding to the candidate ranking index sequence, the upper envelope, lower envelope, and mean envelope corresponding to the production potential index sequence are relatively large. When the adjustment factor is equal to 0.0008, 0.0012, and 0.0020, the differences between the scatter plots corresponding to the candidate ranking index sequence, the upper envelope, lower envelope, and mean envelope corresponding to the production potential index sequence are relatively small. Therefore, the target adjustment factor can be selected from 0.0008, 0.0012, and 0.0020.

[0120] For example, as shown in Figure 5, the horizontal axis represents the value of the adjustment factor, and the vertical axis represents the residual. It can be seen that the residual is the smallest when the adjustment factor is 0.0008. Therefore, 0.0008 can be used as the target adjustment factor.

[0121] In the above embodiments, after calculating the candidate ranking index of the candidate layer under multiple adjustment factors, the target adjustment factor is selected from multiple adjustment factors based on the residual between the production potential index and the candidate ranking index, and the candidate ranking index corresponding to the target adjustment factor is used as the target ranking index. Thus, the difference between the target ranking index and the production potential index is small, that is, the target ranking index can reflect the actual energy storage situation of the candidate layer. Moreover, the target ranking index is calculated under the balanced effect of multiple logging indices, making the potential layer selected based on the target ranking index usable in real application scenarios and improving the practicality of potential layer selection.

[0122] In some embodiments, the potential layer selection method can be used in oil exploration scenarios. As shown in Figure 6, multiple logging indicators may include thickness H, permeability K, saturation S, and porosity F. The computer device obtains the index values ​​of each candidate layer in multiple logging indicators (thickness H, permeability K, saturation S, and porosity F). These index values ​​can be preprocessed, which may include noise reduction and interpolation operations. Then, the preprocessed index values ​​are normalized to obtain normalized index values. The weights of multiple logging indicators are obtained. Based on the normalized index values ​​and weights, the index mean and dispersion are determined.

[0123] The computer equipment determines the candidate ranking index for each candidate layer under multiple adjustment factors based on the index mean and dispersion; and calculates the product of the normalized index values ​​for each candidate layer to obtain the production potential index for each candidate layer.

[0124] Based on the production potential index, a target ranking index is selected from the candidate ranking indices of the candidate layers under multiple adjustment factors. Potential layers are then selected according to the target ranking indices of multiple candidate layers. This can be done by selecting the candidate layer with the largest target ranking index, or by selecting several candidate layers with relatively large target ranking indices (e.g., the top 3 candidate layers). Furthermore, a comparison chart can be displayed based on the target ranking indices of multiple candidate layers, as shown in Figure 7. In the comparison chart shown in Figure 7, the horizontal axis represents the candidate layer number, and the vertical axis represents the target ranking index of the candidate layer. The comparison chart provides a visualization method to intuitively understand the differences in energy storage conditions among multiple candidate layers.

[0125] The aforementioned potential layer selection method determines the mean and dispersion of candidate layer indicators based on the indicator values ​​of candidate layers under multiple logging indicators; it then determines candidate ranking indicators for candidate layers under multiple adjustment factors based on the indicator mean and dispersion; finally, it determines the production potential indicators of candidate layers based on the multiple indicator values ​​of candidate layers; based on the production potential indicators of candidate layers, it selects the target ranking indicator for candidate layers from the candidate ranking indicators for candidate layers under multiple adjustment factors; and finally, it selects potential layers from the candidate layers based on the target ranking indicator. This process is manual and can automatically process complex indicator values ​​to select potential layers from the candidate layers, effectively improving the efficiency of potential layer selection. Furthermore, determining the candidate ranking indicator through the indicator mean and dispersion ensures that the indicator values ​​under multiple logging indicators have a balanced effect on the candidate ranking indicator, improving the quality of the candidate ranking indicator. Selecting the target ranking indicator from the candidate ranking indicators based on the production potential indicator ensures that the target ranking indicator is as close as possible to the production potential indicator. In other words, selecting potential layers based on a target ranking indicator that has a balanced effect from multiple logging indicators and is close to the production potential indicator improves the accuracy and reliability of the selected potential layers.

[0126] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0127] Based on the same inventive concept, this application also provides a potential layer selection device. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more potential layer selection device embodiments provided below can be found in the limitations of the potential layer selection method above, and will not be repeated here.

[0128] In some embodiments, as shown in FIG8, a potential layer selection device is provided, including:

[0129] The index value processing module 801 is used to determine the index mean and dispersion of the candidate layer based on the index values ​​of the candidate layer under multiple logging indices.

[0130] The ranking index determination module 802 is used to determine the candidate ranking indices for the candidate layer under multiple adjustment factors based on the index mean and dispersion; and

[0131] The selection module 803 is used to select potential layers from the candidate layers based on the target ranking index of the candidate layers.

[0132] In some embodiments, the number of candidate layers is multiple; the index value processing module 801 is further configured to, for each logging index, obtain the index values ​​of multiple candidate layers under the corresponding logging index; normalize the index values ​​of multiple candidate layers under the corresponding logging index to obtain normalized index values ​​of multiple candidate layers under the corresponding logging index; for each candidate layer, determine the index mean of the corresponding candidate layer based on the normalized index values ​​of the corresponding candidate layer under the multiple logging indexes; and determine the dispersion of the corresponding candidate layer based on the multiple normalized index values ​​and the index mean of the corresponding candidate layer.

[0133] In some embodiments, the index value processing module 801 is further configured to obtain the weights of multiple logging indices; determine the weighted average of the candidate layer based on the weights of the multiple logging indices and the index values ​​of the candidate layer under the multiple logging indices; and use the weighted average of the candidate layer as the index average of the candidate layer.

[0134] In some embodiments, the ranking index determination module 802 is further configured to determine the candidate ranking index of the candidate layer under multiple adjustment factors based on the index mean and dispersion; determine the production potential index of the candidate layer based on the multiple index values ​​of the candidate layer; select a target adjustment factor from multiple adjustment factors based on the production potential index of the candidate layer and the candidate ranking index of the candidate layer under multiple adjustment factors; and use the candidate ranking index of the candidate layer under the target adjustment factor as the target ranking index of the candidate layer.

[0135] In some embodiments, the candidate ranking index determination module 802 is further configured to determine the product between the dispersion and the targeted adjustment factor for each adjustment factor to obtain the adjusted dispersion; and to use the difference between the index mean and the adjusted dispersion as the candidate ranking index of the candidate layer under the targeted adjustment factor.

[0136] In some embodiments, the number of candidate layers is multiple; the ranking index determination module 802 is further configured to, for each regulation factor, rank the candidate ranking indices of the multiple candidate layers under the regulation factor to obtain a candidate ranking index sequence corresponding to the regulation factor; rank the production potential indices of the multiple candidate layers according to the order of the multiple candidate layers in the candidate ranking index sequence to obtain a production potential index sequence corresponding to the regulation factor; determine the residual corresponding to the regulation factor based on the candidate ranking index sequence and the production potential index sequence corresponding to the regulation factor; and select the target regulation factor from the multiple regulation factors based on the residuals corresponding to each of the multiple regulation factors.

[0137] In some embodiments, the ranking index determination module 802 is further configured to: determine the mean envelope based on the production potential index sequence corresponding to the target adjustment factor; determine the production potential mean index sequence of multiple candidate layers based on the mean envelope; determine the difference value of multiple candidate layers based on the production potential mean index sequence and the candidate ranking index sequence; and determine the sum of squares of the difference values ​​of multiple candidate layers to obtain the residual corresponding to the target adjustment factor.

[0138] In some embodiments, the ranking index determination module 802 is further configured to determine the upper envelope and the lower envelope based on the production potential index sequence corresponding to the targeted adjustment factor; and to determine the mean envelope based on the upper envelope and the lower envelope.

[0139] In some embodiments, the sorting index determination module 802 is further configured to select a maximum value and a minimum value in the production potential index sequence corresponding to the targeted adjustment factor; interpolate the maximum value to obtain a first interpolation result; determine an upper envelope based on the first interpolation result; interpolate the minimum value to obtain a second interpolation result; and determine a lower envelope based on the second interpolation result.

[0140] In some embodiments, the ranking index determination module 802 is further configured to determine the product of multiple index values ​​of the candidate layer to obtain the production potential index of the candidate layer.

[0141] In some embodiments, the sorting index determination module 802 is further configured to select multiple values ​​in a preset value range according to a preset interval; and to use the multiple values ​​as multiple adjustment factors.

[0142] Each module in the aforementioned potential layer selection device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0143] Figure 9 is a schematic diagram of the structure of the computer device provided in this application. As shown in Figure 9, the computer device 90 provided in this embodiment includes at least one processor 901 and a memory 902. Optionally, the device 90 further includes a communication component 903. The processor 901, memory 902, and communication component 903 are connected via a bus.

[0144] In a specific implementation, at least one processor 901 executes computer execution instructions stored in memory 902, causing at least one processor 901 to perform the above-described method.

[0145] The specific implementation process of processor 901 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0146] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this application can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0147] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0148] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0149] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the methods described above.

[0150] This application also provides a computer program product, including computer execution instructions, which, when executed by a processor, implement the various steps in the methods described above.

[0151] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0152] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0153] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0154] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0155] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0156] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0157] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0158] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0159] Finally, it should be noted that other embodiments of this application will readily conceive of by those skilled in the art upon consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and alterations may be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for selecting potential layers, wherein, Performed by computer devices, including: Based on the index values ​​of the candidate layer under multiple logging indices, the mean and dispersion of the index of the candidate layer are determined. Based on the mean and dispersion of the aforementioned indicators, the target ranking index for the candidate layer is determined; and Based on the target ranking index of the candidate layer, a potential layer is selected from the candidate layer.

2. The method according to claim 1, wherein, The number of candidate layers is multiple; The determination of the mean and dispersion of the candidate layer's indicators based on the indicator values ​​of the candidate layer under multiple logging indicators includes: For each logging index, obtain the index values ​​of multiple candidate layers under the targeted logging index; The index values ​​of the multiple candidate layers under the target logging index are normalized to obtain the normalized index values ​​of the multiple candidate layers under the target logging index. For each candidate layer, the mean index of the candidate layer is determined based on the normalized index values ​​of the candidate layer under multiple logging indices; and The dispersion of the target candidate layer is determined based on multiple normalized index values ​​and the mean of the index.

3. The method according to claim 2, wherein, The step of determining the mean index of the target candidate layer based on the normalized index values ​​of the target candidate layer under multiple logging indices includes: Obtain the weights of multiple logging indicators; Based on the weights of the multiple logging indicators and the normalization of the target candidate layer under the multiple logging indicators, the weighted mean of the target candidate layer is determined; and The weighted average of the candidate layers is used as the index average of the candidate layers.

4. The method according to any one of claims 1 to 3, wherein, The step of determining the target ranking index of the candidate layer based on the index mean and the dispersion includes: Based on the mean and dispersion of the index, the candidate ranking index of the candidate layer under multiple adjustment factors is determined; The production potential index of the candidate layer is determined based on multiple index values ​​of the candidate layer; Based on the production potential index of the candidate layer and the candidate ranking index of the candidate layer under multiple adjustment factors, a target adjustment factor is selected from the multiple adjustment factors; and The candidate ranking index of the candidate layer under the target adjustment factor is used as the target ranking index of the candidate layer.

5. The method according to claim 4, wherein, The step of determining the candidate ranking index of the candidate layer under multiple adjustment factors based on the index mean and the dispersion includes: For each adjustment factor, the product between the dispersion and the applied adjustment factor is determined to obtain the adjusted dispersion; and The difference between the mean of the index and the adjusted dispersion is used as the candidate ranking index of the candidate layer under the targeted adjustment factor.

6. The method according to claim 4 or 5, wherein, The number of candidate layers is multiple; the selection of a target adjustment factor from among the multiple adjustment factors, based on the production potential index of the candidate layers and the candidate ranking index of the candidate layers under multiple adjustment factors, includes: For each regulation factor, the candidate ranking indices of multiple candidate layers are ranked under the regulation factor to obtain the candidate ranking index sequence corresponding to the regulation factor. According to the order of the multiple candidate layers in the candidate ranking index sequence, the production potential indicators of the multiple candidate layers are sorted to obtain the production potential index sequence corresponding to the targeted adjustment factor. Based on the candidate ranking index sequence and the production potential index sequence corresponding to the targeted adjustment factor, determine the residual corresponding to the targeted adjustment factor; and Based on the residuals corresponding to each of the multiple adjustment factors, a target adjustment factor is selected from the multiple adjustment factors.

7. The method according to claim 6, wherein, The step of determining the residual corresponding to the targeted adjustment factor based on the candidate ranking index sequence and the production potential index sequence includes: Determine the mean envelope based on the production potential index sequence corresponding to the targeted adjustment factor; Based on the mean envelope, determine the production potential mean index sequence of the multiple candidate layers; Based on the production potential mean index sequence and the candidate ranking index sequence, the difference values ​​of the multiple candidate layers are determined respectively; and The sum of squares of the differences among the multiple candidate layers is determined to obtain the residual corresponding to the targeted adjustment factor.

8. The method according to claim 7, wherein, The determination of the mean envelope based on the production potential index sequence corresponding to the targeted adjustment factor includes: The upper and lower envelopes are determined based on the production potential index sequence corresponding to the targeted regulating factor; and The mean envelope is determined based on the upper envelope and the lower envelope.

9. The method according to claim 8, wherein, The step of determining the upper and lower envelope lines based on the production potential index sequence corresponding to the targeted adjustment factor includes: Select the maximum and minimum values ​​from the production potential index sequence corresponding to the targeted adjustment factor; Interpolating the maximum value yields the first interpolation result; The upper envelope is determined based on the first interpolation result; Interpolating the minimum value yields a second interpolation result; and The lower envelope is determined based on the second interpolation result.

10. The method according to any one of claims 4 to 9, wherein, The step of determining the production potential index of the candidate layer based on multiple index values ​​of the candidate layer includes: The production potential index of the candidate layer is obtained by multiplying the multiple index values ​​of the candidate layer.

11. The method according to any one of claims 4 to 10, wherein, Before determining the candidate ranking index of the candidate layer under multiple adjustment factors based on the index mean and the dispersion, the method further includes: Within a preset range of values, select multiple values ​​at preset intervals; and These multiple values ​​are used as multiple adjustment factors.

12. A potential layer selection device, wherein, The device includes: The index value processing module is used to determine the index mean and dispersion of the candidate layer based on the index values ​​of the candidate layer under multiple logging indices. A ranking index determination module is used to determine the target ranking index of the candidate layer based on the index mean and the dispersion; and The selection module is used to select potential layers from the candidate layers based on the target ranking index of the candidate layers.

13. A computer device, wherein, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 11.

14. A computer-readable storage medium, wherein, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 11.

15. A computer program product comprising computer-executable instructions that, when executed by a processor, implement the steps of the method according to any one of claims 1-11.

Images