Oil reservoir data processing method and device, electronic equipment and storage medium

Abstract

The invention discloses an oil reservoir data processing method and device, electronic equipment and a storage medium. The method comprises the following steps: determining at least one target oil reservoir characteristic index according to characteristic index data of a plurality of to-be-divided oil reservoir samples under a plurality of candidate oil reservoir characteristic indexes; determining a first feature matrix corresponding to the to-be-divided oil reservoir samples and a second feature matrix corresponding to the target oil reservoir feature indexes according to the target index data of the plurality of to-be-divided oil reservoir samples under each target oil reservoir feature index; and determining an oil reservoir classification result corresponding to the to-be-divided oil reservoir sample based on the first feature matrix, and analyzing the oil reservoir classification result based on the first feature matrix and the second feature matrix. According to the technical scheme, the effect of improving the classification accuracy and classification efficiency of the oil reservoir types is achieved, the oil reservoir samples and the target oil reservoir characteristic indexes are combined and analyzed, and the effects of revealing the real internal cause of the difference between the oil reservoirs of different types and improving the credibility of the oil reservoir type classification result are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas field development engineering, and in particular to an oil reservoir data processing method, device, electronic equipment and storage medium. Background Art

[0002] Reservoir classification is of great significance for understanding oilfield development and formulating classified development plans. In my country, the basic classification criteria for reservoirs are crude oil properties, structural conditions, reservoir permeability, and reservoir rock types. However, these methods do not fully consider the development geological factors that control and affect the development process, and some geological factors are difficult to quantify, so they have little guiding significance at the reservoir development level.

[0003] Among the related technologies, multivariate statistical analysis methods have been increasingly used in reservoir type classification, such as principal component analysis, factor analysis, cluster analysis, discriminant analysis, etc.

[0004] However, current research methods focus on studying the relationship between characteristic parameters within a certain reservoir, which makes it difficult to quantitatively reflect the correlation between different reservoirs and reservoir characteristic parameters, and therefore it is difficult to deeply reveal the true internal causes of the differences between different types of reservoirs. Summary of the invention

[0005] The present invention provides a reservoir data processing method, device, electronic device and storage medium to achieve the effect of improving the classification accuracy and classification efficiency of reservoir types, and combines reservoir samples with multiple target reservoir characteristic indicators for analysis, thereby achieving the effect of revealing the true internal causes of the differences between different types of reservoirs and improving the credibility of the reservoir type classification results.

[0006] According to a first aspect of the present invention, a method for processing reservoir data is provided, the method comprising:

[0007] Determine at least one target reservoir characteristic index according to characteristic index data of a plurality of reservoir samples to be divided under a plurality of candidate reservoir characteristic indexes;

[0008] Determine, according to the target index data of the plurality of reservoir samples to be divided under each target reservoir characteristic index, a first characteristic matrix corresponding to the reservoir samples to be divided and a second characteristic matrix corresponding to the target reservoir characteristic index;

[0009] The reservoir classification result corresponding to the reservoir sample to be divided is determined based on the first characteristic matrix, and the reservoir classification result is analyzed based on the first characteristic matrix and the second characteristic matrix.

[0010] According to a second aspect of the present invention, there is provided a reservoir data processing device, the device comprising:

[0011] A characteristic index determination module, used to determine at least one target reservoir characteristic index according to characteristic index data of multiple reservoirs to be divided under multiple candidate reservoir characteristic indexes;

[0012] A characteristic matrix determination module, used to determine a first characteristic matrix corresponding to the oil reservoir to be divided and a second characteristic matrix corresponding to the characteristic index of the target oil reservoir according to the target index data of each of the characteristic indexes of the target oil reservoirs under the plurality of oil reservoirs to be divided;

[0013] The reservoir classification result determination module is used to determine the reservoir classification result corresponding to the reservoir to be divided based on the first characteristic matrix, and analyze the reservoir classification result based on the first characteristic matrix and the second characteristic matrix.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the reservoir data processing method described in any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the reservoir data processing method described in any embodiment of the present invention when executed by a processor.

[0019] The technical solution of the embodiment of the present invention determines at least one target reservoir characteristic index according to characteristic index data of multiple reservoir samples to be divided under multiple candidate reservoir characteristic indexes, further determines a first characteristic matrix corresponding to the reservoir samples to be divided and a second characteristic matrix corresponding to the target reservoir characteristic index according to the target index data of the multiple reservoir samples to be divided under each target reservoir characteristic index, finally, determines the reservoir classification result corresponding to the reservoir samples to be divided based on the first characteristic matrix, and analyzes the reservoir classification result based on the first characteristic matrix and the second characteristic matrix, thereby solving the problem that the related technology focuses on studying the relationship between characteristic parameters inside a certain reservoir, and it is difficult to quantitatively reflect the mutual correlation between different reservoirs and reservoir characteristic parameters, and thus it is difficult to deeply reveal the real internal cause of the differences between different types of reservoirs, and the effect of improving the classification accuracy and classification efficiency of reservoir types is achieved, and the reservoir samples and multiple target reservoir characteristic indexes are combined for analysis, so as to achieve the effect of revealing the real internal cause of the differences between different types of reservoirs, and improve the credibility of the reservoir type classification result.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a flow chart of a reservoir data processing method provided according to the first embodiment of the present invention;

[0023] Figure 2 is a schematic diagram of an oil reservoir classification result provided according to the first embodiment of the present invention;

[0024] Figure 3 is a schematic diagram of a basic dual information graphic board provided according to the first embodiment of the present invention;

[0025] Figure 4 is a schematic diagram of a chart representing the relationship between characteristic indicators of a target reservoir provided according to the first embodiment of the present invention;

[0026] Figure 5 is a schematic structural diagram of an oil reservoir data processing device provided according to Embodiment 2 of the present invention;

[0027] Figure 6 It is a schematic diagram of the structure of an electronic device for implementing the reservoir data processing method according to an embodiment of the present invention. DETAILED DESCRIPTION

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

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

[0030] Embodiment 1

[0031] Figure 1 This is a flow chart of a reservoir data processing method provided by the first embodiment of the present invention. This embodiment is applicable to the case of classifying and analyzing the characteristics of reservoir samples in any area. The method can be executed by a reservoir data processing device. The reservoir data processing device can be implemented in the form of hardware and / or software. The reservoir data processing device can be configured in a terminal and / or a server. Figure 1 As shown, the method includes:

[0032] S110, determining at least one target reservoir characteristic index according to characteristic index data of a plurality of reservoir samples to be divided under a plurality of candidate reservoir characteristic indexes.

[0033] Among them, the reservoir samples to be divided can be understood as the reservoir samples to be divided into reservoir types. The reservoir can be crude oil stored in the geological structure and closed in the reservoir. Generally, when the morphology or physical and chemical conditions of the underground reservoir structure are not suitable for the continued migration of oil during the migration of oil, the oil will gather at this location to form an oil reservoir. The indicators for evaluating the reservoir can include multiple, and optionally, they can include reservoir thickness, caprock thickness and effectiveness, oil-bearing area, oil-bearing thickness, closure, closure area, closure height, reservoir physical properties, effective thickness of the reservoir, etc. In practical applications, reservoir samples can be selected according to the geological characteristics of reservoir development to obtain multiple reservoir samples to be divided. The reservoir samples to be divided can be any samples, and optionally, they can be carbonate reservoir samples. The microscopic pore structure of carbonate reservoirs is complex, the heterogeneity is strong, and interlayers and thieves are widely developed. Efficient water injection development faces severe challenges, and the reservoir types are complex and diverse, and the geological characteristics and development methods of different types of reservoirs are different. The candidate reservoir characteristic index can be understood as an index that can perform characteristic analysis on the reservoir sample, or as a reservoir characteristic parameter, which can reflect the geological characteristics of the reservoir and determine whether to develop the reservoir. The candidate reservoir characteristic index can include multiple, optionally including pore structure parameters, formation thickness, effective thickness, net-to-gross ratio, porosity, permeability, water-oil mobility ratio, and Lorentz coefficient. Correspondingly, the characteristic index data can be understood as the data of the reservoir sample under the candidate reservoir characteristic index. The target reservoir characteristic index can be understood as the key reservoir characteristic index that affects the classification of reservoir types among multiple candidate reservoir characteristic indexes. Optionally, the target characteristic reservoir characteristic index can include effective thickness, permeability, formation thickness, and Lorentz coefficient.

[0034] In this embodiment, the characteristic index data may be obtained in a variety of ways. Optionally, when the reservoir sample to be divided and the candidate reservoir characteristic index are determined, the characteristic index data of the determined reservoir sample to be divided under the candidate reservoir characteristic index may be retrieved from a pre-constructed database; or, when the reservoir sample to be divided and the candidate characteristic index are determined, the characteristic index data of the reservoir sample to be divided under each candidate characteristic index may be determined according to the determination rule of each candidate characteristic index; or, the characteristic index data of the reservoir sample to be divided under the candidate reservoir characteristic index may be obtained in other ways, which are not specifically limited in this embodiment.

[0035] In practical applications, multiple reservoir samples to be divided can be first selected in any target area, and then multiple candidate reservoir characteristic indicators that reflect reservoir geological characteristics and determine reservoir development can be selected. Then, characteristic indicator data of each reservoir sample to be divided under each candidate reservoir characteristic indicator can be obtained. Furthermore, the characteristic indicator data under each candidate reservoir characteristic indicator can be processed to determine at least one target reservoir characteristic indicator among multiple candidate reservoir characteristic indicators.

[0036] Optionally, at least one target reservoir characteristic index is determined based on characteristic index data of multiple reservoir samples to be divided under multiple candidate reservoir characteristic indexes, including: normalizing the characteristic index data to obtain candidate index data of each reservoir sample to be divided under each candidate reservoir characteristic index; determining a weight value corresponding to each candidate reservoir characteristic index based on the candidate index data of each reservoir sample to be divided under each candidate reservoir characteristic index; and determining at least one target reservoir characteristic index based on the weight value of each candidate reservoir characteristic index.

[0037] The candidate indicator data may be understood as data obtained after normalizing the feature indicator data.

[0038] In this embodiment, when the characteristic index data is normalized, it can be first determined whether the candidate reservoir characteristic index is a positive index or a negative index, and then the corresponding characteristic index data can be processed according to the normalization processing function corresponding to the positive index or the negative index. Among them, the positive index can be understood as a positive correlation index, that is, the two variables change in the same direction, when one variable changes from large to small or from small to large, the other variable also changes from large to small or from small to large. Optionally, the positive index may include pore structure parameters, formation thickness, effective thickness, net-to-gross ratio, porosity and permeability. The negative index can be understood as a negative correlation index, that is, the two variables change in opposite directions, when one variable changes from large to small or from small to large, the other variable changes from small to large or from large to small. Optionally, the negative index may include the water-oil mobility ratio and the Lorentz coefficient.

[0039] In practical applications, when the candidate reservoir characteristic index is a positive index, for each reservoir sample to be divided, the characteristic index data of the current reservoir sample to be divided under the candidate reservoir characteristic index can be obtained. Then, the maximum and minimum values ​​of the characteristic index data of all reservoir samples to be divided under the candidate reservoir characteristic are determined. Then, the difference between the characteristic index data corresponding to the current reservoir sample to be divided and the minimum value can be determined to obtain a first value, and the difference between the maximum value and the minimum value can be determined to obtain a second value. Further, the ratio between the first value and the second value is determined, and the ratio can be used as the candidate index data of the current reservoir sample to be divided under the candidate reservoir characteristic index.

[0040] For example, the candidate index data of the reservoir sample to be divided under the positive index can be determined based on the following formula:

[0041]

[0042] Among them, x i ′ j It can represent the candidate index data of the reservoir sample to be divided under the positive index; X ij It can represent the characteristic index data of the reservoir samples to be divided under the positive index; n can represent the number of reservoir samples to be divided; i can represent the reservoir samples to be divided, i = 1, 2, ..., n; j can represent the characteristic index of the candidate reservoir, j = 1, 2, ..., m, m can represent the number of characteristic indexes of the candidate reservoir.

[0043] In practical applications, when the candidate reservoir characteristic index is a negative index, for each reservoir sample to be divided, the characteristic index data of the current reservoir sample to be divided under the candidate reservoir characteristic index can be obtained. Then, the maximum and minimum values ​​of the characteristic index data of all reservoir samples to be divided under the candidate reservoir characteristic index are determined. Then, the difference between the maximum value and the characteristic index data can be determined to obtain a third value, and the difference between the maximum value and the minimum value can be determined to obtain a fourth value. Furthermore, the ratio between the third value and the fourth value can be determined, and the ratio can be used as the candidate index data of the current reservoir sample to be divided under the candidate reservoir characteristic index.

[0044] For example, the candidate index data of the reservoir sample to be divided under the negative index can be determined based on the following formula:

[0045]

[0046] Furthermore, after obtaining the candidate index data of each reservoir sample to be divided under each candidate reservoir characteristic index, the weight value corresponding to each candidate reservoir characteristic index may be determined according to the candidate index data corresponding to these reservoir samples to be divided.

[0047] Optionally, the weight value corresponding to each reservoir characteristic indicator is determined according to the candidate indicator data of each reservoir to be divided sample under each candidate reservoir characteristic indicator, including: for each candidate reservoir characteristic indicator, according to the candidate indicator data of each reservoir to be divided under the candidate reservoir characteristic indicator, determining the proportion of indicator data corresponding to each reservoir to be divided under the candidate reservoir characteristic indicator; determining the information entropy value corresponding to each candidate reservoir characteristic indicator according to the proportion of indicator data corresponding to each reservoir to be divided under each candidate reservoir characteristic indicator; determining the information entropy redundancy corresponding to each candidate reservoir characteristic indicator according to the information entropy value corresponding to each candidate reservoir characteristic indicator; and determining the weight value corresponding to each reservoir characteristic indicator according to the information entropy redundancy corresponding to each candidate reservoir characteristic indicator.

[0048] Among them, the indicator data ratio can be understood as the proportion of candidate indicator data corresponding to each reservoir sample to be divided under the candidate reservoir characteristic index. The information entropy value can be understood as a numerical value that characterizes the uncertainty of the candidate reservoir characteristic index. Generally speaking, information entropy is a concept in information theory, which is used to describe the uncertainty and randomness of information. It is a measure of the average uncertainty of information, usually used to measure the uncertainty of the source and the efficiency of information transmission. Information entropy redundancy can be understood as the amount of redundant information present in the candidate reservoir characteristic index. In this embodiment, the information entropy redundancy can be the difference between the preset coefficient and the information entropy. The preset coefficient can be 1.

[0049] In practical applications, for each candidate reservoir characteristic index, the candidate index data of each reservoir sample to be divided under the current candidate reservoir characteristic index can be added to obtain the total candidate index data corresponding to the current candidate reservoir characteristic index. Afterwards, the ratio between the candidate index data of each reservoir sample to be divided under the current candidate reservoir characteristic index and the total candidate index data can be determined respectively, and the ratio can be used as the index data ratio corresponding to each reservoir sample to be divided under the current candidate reservoir characteristic index.

[0050] Exemplarily, the indicator data ratio may be determined based on the following formula:

[0051]

[0052] Among them, P ij It can represent the index data ratio corresponding to the reservoir samples to be divided under the candidate reservoir characteristic index; x i ′ j It can represent the candidate index data of the reservoir samples to be divided under the positive index; n can represent the number of reservoir samples to be divided.

[0053] Furthermore, for each candidate reservoir characteristic index, an information entropy function can be obtained, and the indicator data ratio corresponding to each reservoir to be divided under the candidate reservoir characteristic index is input into the information entropy function to obtain the information entropy value corresponding to the candidate reservoir characteristic index.

[0054] Exemplarily, the information entropy value may be determined based on the following formula:

[0055]

[0056] Among them, e j It can represent the information entropy value corresponding to the candidate reservoir characteristic index; P ij It can represent the index data ratio corresponding to the reservoir samples to be divided under the candidate reservoir characteristic index; n can represent the number of reservoir samples to be divided.

[0057] Furthermore, after obtaining the information entropy value corresponding to each candidate reservoir characteristic index, the difference between the preset coefficient and the information entropy value can be determined respectively, and these differences can be used as the information entropy redundancy corresponding to each candidate reservoir characteristic index.

[0058] Exemplarily, the information entropy redundancy may be determined based on the following formula:

[0059] d j =1-e j

[0060] Among them, d j It can represent the information entropy redundancy corresponding to the candidate reservoir characteristic indicators.

[0061] Finally, after determining the information entropy redundancy corresponding to each candidate reservoir characteristic index, the weight value corresponding to each candidate reservoir characteristic index can be determined according to the information entropy redundancy.

[0062] Optionally, a weight value corresponding to each candidate reservoir characteristic indicator is determined according to the information entropy redundancy corresponding to each candidate reservoir characteristic indicator, including: adding each information entropy redundancy to obtain a first value; for each candidate reservoir characteristic indicator, determining a ratio between the information entropy redundancy corresponding to the candidate reservoir characteristic indicator and the first value to obtain a second value, and using the second value as the weight value corresponding to the candidate reservoir characteristic indicator.

[0063] In practical applications, each information entropy redundancy can be added to obtain a total information entropy redundancy, and the total information entropy redundancy can be used as the first value. Afterwards, the ratio between each information entropy redundancy and the first value can be determined respectively, and the determined ratio can be used as the weight value corresponding to each candidate reservoir characteristic indicator.

[0064] For example, the weight value corresponding to the candidate reservoir characteristic index may be determined based on the following formula:

[0065]

[0066] Among them, w j It can represent the weight value corresponding to the candidate reservoir characteristic index; j can represent the candidate reservoir characteristic index, j=1,2,…,m, and m can represent the number of candidate reservoir characteristic indexes.

[0067] In practical applications, after determining the weight value corresponding to each candidate reservoir characteristic indicator, the importance of the candidate reservoir characteristic indicator can be judged according to the determined weight value. The larger the weight value, the higher the importance. A preset weight value threshold can be obtained, and then the weight value corresponding to each candidate reservoir characteristic indicator can be compared with the preset weight value threshold, and the candidate reservoir characteristic indicators with weight values ​​greater than the preset weight value threshold can be screened out, and the screened candidate reservoir characteristic indicators can be used as target reservoir characteristic indicators.

[0068] S120, determining a first characteristic matrix corresponding to the reservoir samples to be divided and a second characteristic matrix corresponding to the target reservoir characteristic index according to target index data of the plurality of reservoir samples to be divided under each target reservoir characteristic index.

[0069] The target index data can be understood as the data obtained after normalizing the characteristic index data. The first characteristic matrix can be understood as a matrix storing characteristic information of the reservoir samples to be divided, and each element in the matrix represents the score coefficient of the reservoir samples to be divided on the characteristic vector. The second characteristic matrix can be understood as a matrix storing characteristic information of the target reservoir characteristic index, and each element in the matrix represents the score coefficient of the target reservoir characteristic index on the characteristic vector.

[0070] In practical applications, after determining at least one target reservoir characteristic index, characteristic index data of the reservoir sample to be divided under each target reservoir characteristic index can be obtained. Afterwards, a normalization processing function corresponding to each target reservoir characteristic index can be determined. Furthermore, for each target reservoir characteristic index, the corresponding characteristic index data can be normalized according to the normalization processing function corresponding to the target reservoir characteristic index to obtain the target index data corresponding to the target reservoir characteristic index. Furthermore, after obtaining the target index data of each reservoir sample to be divided under each target reservoir characteristic index, the obtained target index data can be processed to obtain a first characteristic matrix corresponding to the reservoir sample to be divided and a second characteristic matrix corresponding to the target reservoir characteristic index.

[0071] Optionally, according to target indicator data of multiple samples of reservoirs to be divided under each target reservoir characteristic indicator, a first characteristic matrix corresponding to the samples of reservoirs to be divided and a second characteristic matrix corresponding to the target reservoir characteristic indicator are determined, including: obtaining target indicator data of multiple samples of reservoirs to be divided under each target reservoir characteristic indicator, and constructing a data matrix to be processed according to the target indicator data; processing the data matrix to be processed according to a pre-set feature extraction algorithm to obtain the first characteristic matrix and the second characteristic matrix.

[0072] Among them, the target indicator data is the data obtained after normalizing the characteristic indicator data. The feature extraction algorithm can be understood as an algorithm for extracting the main characteristic components of the data. The feature extraction algorithm can be any algorithm that performs dimensionality reduction processing on high-dimensional data. Optionally, the feature extraction algorithm can be a principal component analysis (PCA) algorithm. Those skilled in the art will understand that PCA is a commonly used data analysis method. PCA transforms the original data into a set of linearly independent representations of each dimension through linear transformation, which can be used to extract the main characteristic components of the data. It is often used for dimensionality reduction of high-dimensional data, and aims to use the idea of ​​dimensionality reduction to transform multiple indicators into a few comprehensive indicators.

[0073] In practical applications, when at least one target reservoir characteristic index is determined, the target index data of multiple reservoir samples to be divided under each target reservoir characteristic index can be obtained respectively. Furthermore, the reservoir samples to be divided can be used as row vectors, and the target reservoir characteristic index can be used as column vectors. A matrix can be constructed according to the target index data of the reservoir samples to be divided under the target reservoir characteristic index, and the constructed matrix can be used as the data matrix to be processed. The value of each element in the matrix can represent the target index data of the reservoir samples to be divided under the target reservoir characteristic index. Furthermore, feature extraction can be performed on the data matrix to be processed according to a pre-set feature extraction algorithm, so that a first feature matrix corresponding to the reservoir samples to be divided and a second feature matrix corresponding to the target reservoir characteristic index can be obtained.

[0074] Exemplarily, assuming that the feature extraction algorithm is a PCA algorithm, after obtaining the data matrix to be processed, a covariance matrix can be constructed based on the data matrix to be processed, and the data matrix to be processed is subjected to singular value decomposition to obtain the eigenvalues ​​of the covariance matrix, i.e., variance information, and the eigenvalues ​​are sorted from large to small to obtain an eigenvector matrix, see Table 1. It can be seen from the table that the eigenvalues ​​of the first two principal components are both greater than 1 and contain most of the information of the target indicator data, so it can be determined that the number of principal components is 2.

[0075] Table 1 Covariance matrix eigenvalue and eigenvector matrix

[0076]

[0077] Furthermore, the score coefficients of each reservoir sample to be divided and the characteristic index of the target reservoir on the two principal components are calculated. The score coefficient matrix of the reservoir samples to be divided on the two principal components can be used as the first characteristic matrix, see Table 2; the score coefficient matrix of the characteristic index of the target reservoir on the two principal components can be used as the second characteristic matrix, see Table 3.

[0078] Table 2 Score coefficients of reservoir samples to be divided on two principal components

[0079]

[0080]

[0081] Table 3 Score coefficients of target reservoir characteristic indicators on two principal components

[0082]

[0083] S130, determining the reservoir classification result corresponding to the reservoir sample to be divided based on the first characteristic matrix, and analyzing the reservoir classification result based on the first characteristic matrix and the second characteristic matrix.

[0084] The reservoir classification result may be understood as a reservoir type classification result obtained after clustering and classifying a plurality of reservoir samples to be classified. In this embodiment, the reservoir classification result may include at least one reservoir type corresponding to the plurality of reservoir samples to be classified.

[0085] In practical applications, after obtaining the first characteristic matrix corresponding to the reservoir samples to be divided and the second characteristic matrix corresponding to the target reservoir characteristic index, the first characteristic matrix can be clustered and classified, and then, multiple reservoir samples to be divided can be divided into at least one type, and the divided type can be used as the reservoir classification result.

[0086] Optionally, determining a reservoir classification result corresponding to the reservoir sample to be classified based on the first characteristic matrix includes: processing the first characteristic matrix according to a preset classification algorithm to obtain at least one reservoir type, and determining the reservoir classification result based on the at least one reservoir type.

[0087] Among them, the preset classification algorithm can be a pre-set algorithm used for clustering analysis of data. The preset classification algorithm can be any classification algorithm, and optionally, it can be a K-means clustering algorithm. The reservoir type can be understood as the grouping of reservoir samples obtained after clustering and classifying the reservoir samples to be divided. Those skilled in the art can understand that the naming of the reservoir type can be determined based on the cluster center data of the reservoir samples under the target reservoir characteristic index. In this embodiment, the reservoir type can include a thin layer low permeability homogeneous reservoir, a thick layer medium permeability reservoir, and a thick low permeability heterogeneous reservoir.

[0088] In practical applications, after obtaining the first characteristic matrix corresponding to the reservoir samples to be divided, the first characteristic matrix can be processed according to a preset classification algorithm, and then, multiple reservoir samples to be divided can be divided into at least one group, and the divided reservoir sample groups can be used as reservoir types. Furthermore, the reservoir classification results corresponding to the reservoir samples to be divided can be determined according to at least one reservoir type.

[0089] Exemplarily, assuming that the preset classification algorithm is a K-means clustering algorithm, after obtaining the first characteristic matrix, the first characteristic matrix can be processed according to the K-means clustering algorithm to divide all reservoir samples to be divided into k initial clusters, and the cluster center (mean) of each class is calculated as follows:

[0090]

[0091]

[0092] Among them, c i Can represent the horizontal coordinate of any cluster center; c j Can represent the ordinate of any cluster center; x i It can represent the abscissa of the reservoir sample to be divided in the cluster center, where the abscissa value represents the score coefficient of the reservoir sample to be divided on the principal component 1; j It can represent the ordinate of the reservoir sample to be divided in the cluster center, wherein the ordinate value represents the score coefficient of the reservoir sample to be divided on the principal component 2.

[0093] Furthermore, the number of clusters k is adjusted during the clustering process. The distance between the reservoir sample to be divided and the cluster center is determined, and the reservoir sample to be divided is assigned to the cluster whose cluster center is closest to it. The center coordinates of the two newly formed clusters are recalculated. ij and a cluster center c ij The distance between them is usually calculated using the Euclidean distance formula:

[0094]

[0095] Repeat the above steps until all reservoir samples to be divided are divided.

[0096] For example, Figure 2 It can be the reservoir classification result of the reservoir sample to be divided obtained by processing the first feature matrix based on the K-means clustering algorithm. Figure 2 It can be seen that the 16 reservoir samples to be classified can be clearly divided into three types, namely cluster I, cluster II and cluster III.

[0097] In practical applications, after obtaining the first characteristic matrix corresponding to the reservoir samples to be classified and the second characteristic matrix corresponding to the target reservoir characteristic indicators, the first characteristic matrix and the second characteristic matrix can be graphically processed to obtain a characteristic analysis diagram, and then the reservoir classification results can be analyzed based on the characteristic analysis diagram.

[0098] Optionally, the reservoir classification results are analyzed based on the first characteristic matrix and the second characteristic matrix, including: graphically processing the first characteristic matrix and the second characteristic matrix to obtain at least one dual information map; and analyzing the reservoir classification results based on the at least one dual information map.

[0099] Among them, the dual information map can be understood as a two-dimensional map that includes two kinds of characteristic information at the same time. In this embodiment, the dual information map can be a map that includes the characteristic information of the reservoir samples to be divided and the characteristic information of the target reservoir characteristic indicators at the same time. Optionally, the dual information map can include a basic dual information map and a map that characterizes the relationship between the characteristic indicators of the target reservoir. Exemplarily, it is assumed that the first characteristic matrix is ​​a score coefficient matrix of the reservoir samples to be divided on two principal components, and the second characteristic matrix is ​​a score coefficient matrix of the characteristic indicators of the target reservoir on two principal components. The score coefficients of each reservoir sample to be divided and each target reservoir characteristic indicator on principal component 1 in the first characteristic matrix and the second characteristic matrix can be used as the horizontal coordinate, and the score coefficients of each reservoir sample to be divided and each target reservoir characteristic indicator on principal component 2 can be used as the vertical coordinate, and then the dual information map is drawn.

[0100] For example, Figure 2 Can be a basic dual infographic, consisting of Figure 2It can be seen that the vector starting from the origin is determined by the coefficients of the target reservoir characteristic index on the two principal components, which approximately reflects the information of the target reservoir characteristic index in the second characteristic matrix; the coordinates of the data point are determined by the coefficients of the reservoir samples to be divided on the two principal components, which approximately reflects the information of the reservoir samples to be divided in the first characteristic matrix; the cosine value of the angle between vectors approximately reflects the correlation between the target reservoir characteristic indexes, and its value is positive if it is positively correlated, and its value is negative if it is negatively correlated. The size of its absolute value reflects the size of the correlation. The larger the absolute value, the stronger the correlation between the two, and vice versa; the length of the vector is approximately equal to the standard deviation of the column vector in the second characteristic matrix, reflecting the degree of dispersion between the target reservoir characteristic indexes. It can be seen that there is a positive correlation between most target reservoir characteristic indexes, such as formation thickness and effective thickness. Different reservoirs have large differences in effective thickness, permeability, formation thickness and Lorentz coefficient.

[0101] For example, Figure 3 It can be used as a chart to characterize the relationship between the characteristic indicators of the target reservoir. Figure 3 It can be seen that the straight line where the vector of a target reservoir characteristic index is located is the x' axis, and the straight line passing through the origin and perpendicular to the x' axis is the y' axis. A new coordinate system is established, and a vertical line is drawn from the data points of each reservoir sample to be divided to the x' axis. The origin represents the average value of each reservoir sample to be divided on a target reservoir characteristic index, and the coordinates of the projection point represent the relative values ​​of each reservoir sample to be divided on the target reservoir characteristic index. Based on this, the characteristic differences between different reservoir samples to be divided can be analyzed. Taking the Lorentz coefficient as an example, the B reservoir has the highest value on this parameter and the strongest heterogeneity, followed by the E reservoir, while the P reservoir has the lowest value and the weakest heterogeneity.

[0102] For example, in getting Figure 3 and Figure 4 After two dual information graphics, you can Figure 3 and Figure 4 right Figure 2The reservoir classification results in the analysis are analyzed, and the specific analysis results can be: the samples of the reservoirs to be classified in type I belong to thin-layer low-permeability homogeneous reservoirs, and the representative reservoirs are J, K, L, etc. The formation thickness of this type of reservoir is thin (15-49 meters), the permeability is low (2-19 millidarcy), the interlayer is not developed, the thief layer is widely distributed, the fractures are relatively developed, and the vertical permeability is high. The samples of the reservoirs to be classified in type II belong to thick-layer medium-permeability reservoirs, and the representative reservoirs are C, F, G, etc. The reservoir space type of this type of reservoir is relatively single, the formation thickness is large (50-175m), the porosity is medium-high (20%-28%), the permeability is medium (25-125 millidarcy), the net-to-gross ratio is low (0.66-0.72), the interlayer is relatively developed, the reservoir is anti-rhythmic and has layered characteristics, the plane connectivity is good, and the vertical heterogeneity is strong. The samples of the reservoirs to be classified in category III belong to the extremely thick low-permeability heterogeneous reservoirs, and the representative reservoirs are A, B, D, etc. This type of reservoir has a complex pore throat structure (mainly complex mode and multi-mode), extremely thick formations (162-210 meters), medium porosity (15%-21%), medium-low permeability (20-33 millidarcy), low net-to-gross ratio (0.71-0.89), development of unstable interlayers, widespread existence of thieves, and extremely strong reservoir heterogeneity.

[0103] The technical solution of the embodiment of the present invention determines at least one target reservoir characteristic index according to characteristic index data of multiple reservoir samples to be divided under multiple candidate reservoir characteristic indexes, further determines a first characteristic matrix corresponding to the reservoir samples to be divided and a second characteristic matrix corresponding to the target reservoir characteristic index according to the target index data of the multiple reservoir samples to be divided under each target reservoir characteristic index, finally, determines the reservoir classification result corresponding to the reservoir samples to be divided based on the first characteristic matrix, and analyzes the reservoir classification result based on the first characteristic matrix and the second characteristic matrix, thereby solving the problem that the related technology focuses on studying the relationship between characteristic parameters inside a certain reservoir, and it is difficult to quantitatively reflect the mutual correlation between different reservoirs and reservoir characteristic parameters, and thus it is difficult to deeply reveal the real internal cause of the differences between different types of reservoirs, and the effect of improving the classification accuracy and classification efficiency of reservoir types is achieved, and the reservoir samples and multiple target reservoir characteristic indexes are combined for analysis, so as to achieve the effect of revealing the real internal cause of the differences between different types of reservoirs, and improve the credibility of the reservoir type classification result.

[0104] Embodiment 2

[0105] Figure 5 Schematic diagram of the structure of a reservoir data processing device provided by the second embodiment of the present invention. Figure 5 As shown, the device includes: a characteristic index determination module 210, a characteristic matrix determination module 220 and an oil reservoir classification result determination module 230.

[0106] Among them, the characteristic index determination module 210 is used to determine at least one target reservoir characteristic index based on the characteristic index data of multiple reservoirs to be divided under multiple candidate reservoir characteristic indexes; the characteristic matrix determination module 220 is used to determine the first characteristic matrix corresponding to the reservoir to be divided and the second characteristic matrix corresponding to the target reservoir characteristic index based on the target index data of the multiple reservoirs to be divided under each of the target reservoir characteristic indexes; the reservoir classification result determination module 230 is used to determine the reservoir classification result corresponding to the reservoir to be divided based on the first characteristic matrix, and analyze the reservoir classification result based on the first characteristic matrix and the second characteristic matrix.

[0107] The technical solution of the embodiment of the present invention determines at least one target reservoir characteristic index according to characteristic index data of multiple reservoir samples to be divided under multiple candidate reservoir characteristic indexes, further determines a first characteristic matrix corresponding to the reservoir samples to be divided and a second characteristic matrix corresponding to the target reservoir characteristic index according to the target index data of the multiple reservoir samples to be divided under each target reservoir characteristic index, finally, determines the reservoir classification result corresponding to the reservoir samples to be divided based on the first characteristic matrix, and analyzes the reservoir classification result based on the first characteristic matrix and the second characteristic matrix, thereby solving the problem that the related technology focuses on studying the relationship between characteristic parameters inside a certain reservoir, and it is difficult to quantitatively reflect the mutual correlation between different reservoirs and reservoir characteristic parameters, and thus it is difficult to deeply reveal the real internal cause of the differences between different types of reservoirs, and the effect of improving the classification accuracy and classification efficiency of reservoir types is achieved, and the reservoir samples and multiple target reservoir characteristic indexes are combined for analysis, so as to achieve the effect of revealing the real internal cause of the differences between different types of reservoirs, and improve the credibility of the reservoir type classification result.

[0108] Optionally, the feature index determination module 210 includes: a candidate index data determination unit, a weight value determination unit and a feature index determination unit.

[0109] A candidate index data determination unit is used to perform normalization processing on the characteristic index data to obtain candidate index data of each of the reservoir samples to be divided under each of the candidate reservoir characteristic indexes;

[0110] A weight value determination unit, used for determining a weight value corresponding to each candidate reservoir characteristic index according to the candidate index data of each reservoir sample to be divided under each candidate reservoir characteristic index;

[0111] The characteristic index determining unit is used to determine at least one target reservoir characteristic index based on the weight value of each candidate reservoir characteristic index.

[0112] Optionally, the weight value determination unit includes: an indicator data ratio determination subunit, an information entropy value determination subunit, an information entropy redundancy determination subunit and a weight value determination subunit.

[0113] An indicator data ratio determination subunit is used to determine, for each of the candidate reservoir characteristic indicators, the indicator data ratio corresponding to each of the reservoir samples to be divided under the candidate reservoir characteristic indicator according to the candidate indicator data of each reservoir to be divided under the candidate reservoir characteristic indicator;

[0114] An information entropy value determination subunit is used to determine the information entropy value corresponding to each of the candidate oil reservoir characteristic indicators according to the indicator data ratio corresponding to each of the oil reservoirs to be divided under each of the candidate oil reservoir characteristic indicators;

[0115] An information entropy redundancy determination subunit is used to determine the information entropy redundancy corresponding to each of the candidate reservoir characteristic indicators according to the information entropy value corresponding to each of the candidate reservoir characteristic indicators;

[0116] The weight value determination subunit is used to determine the weight value corresponding to each of the candidate reservoir characteristic indicators according to the information entropy redundancy corresponding to each of the candidate reservoir characteristic indicators.

[0117] Optionally, a weight value determination subunit is specifically used to add each of the information entropy redundancies to obtain a first value; for each of the candidate reservoir characteristic indicators, determine the ratio between the information entropy redundancy corresponding to the candidate reservoir characteristic indicator and the first value, and use the ratio as the weight value corresponding to the candidate reservoir characteristic indicator.

[0118] Optionally, the feature matrix determination module 220 includes: a to-be-processed data matrix determination unit and a feature matrix determination unit.

[0119] A data matrix determination unit to be processed is used to obtain target index data of the plurality of reservoir samples to be divided under each target reservoir characteristic index, and to construct a data matrix to be processed according to the target index data, wherein the target index data is data obtained after normalization processing of the characteristic index data;

[0120] The feature matrix determination unit is used to process the to-be-processed data matrix according to a preset feature extraction algorithm to obtain the first feature matrix and the second feature matrix.

[0121] Optionally, the reservoir classification result determination module 230 includes: a feature matrix processing unit.

[0122] The characteristic matrix processing unit is used to process the first characteristic matrix according to a preset classification algorithm to obtain at least one reservoir type, and determine the reservoir classification result based on the at least one reservoir type.

[0123] Optionally, the reservoir classification result determination module 230 includes: an information plate determination unit and a classification result analysis unit.

[0124] An information plate determining unit, configured to perform graphical processing on the first characteristic matrix and the second characteristic matrix to obtain at least one dual information plate;

[0125] A classification result analysis unit is used to analyze the reservoir classification result based on the at least one dual information plate.

[0126] The reservoir data processing device provided in the embodiment of the present invention can execute the reservoir data processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0127] Embodiment 3

[0128] Figure 6 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0129] like Figure 6 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0130] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0131] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a reservoir data processing method.

[0132] In some embodiments, the reservoir data processing method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the reservoir data processing method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the reservoir data processing method in any other appropriate manner (e.g., by means of firmware).

[0133] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0134] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0135] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0136] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0137] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0138] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0139] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0140] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for processing reservoir data, characterized in that: include: Determine at least one target reservoir characteristic index according to characteristic index data of a plurality of reservoir samples to be divided under a plurality of candidate reservoir characteristic indexes; Determine, according to the target index data of the plurality of reservoir samples to be divided under each target reservoir characteristic index, a first characteristic matrix corresponding to the reservoir samples to be divided and a second characteristic matrix corresponding to the target reservoir characteristic index; The reservoir classification result corresponding to the reservoir sample to be divided is determined based on the first characteristic matrix, and the reservoir classification result is analyzed based on the first characteristic matrix and the second characteristic matrix.

2. The method according to claim 1, characterized in that The step of determining at least one target reservoir characteristic index according to the characteristic index data of the plurality of reservoir samples to be divided under the plurality of candidate reservoir characteristic indexes comprises: Normalizing the characteristic index data to obtain candidate index data of each of the reservoir samples to be divided under each of the candidate reservoir characteristic indexes; Determine a weight value corresponding to each candidate reservoir characteristic index according to the candidate index data of each of the reservoir samples to be divided under each candidate reservoir characteristic index; At least one target reservoir characteristic index is determined based on the weight value of each candidate reservoir characteristic index.

3. The method according to claim 2, characterized in that Determining the weight value corresponding to each reservoir characteristic index according to the candidate index data of each reservoir sample to be divided under each candidate reservoir characteristic index includes: For each of the candidate reservoir characteristic indicators, according to the candidate indicator data of each of the reservoirs to be divided under the candidate reservoir characteristic indicator, determine the indicator data ratio corresponding to each sample of the reservoirs to be divided under the candidate reservoir characteristic indicator; Determine the information entropy value corresponding to each of the candidate oil reservoir characteristic indicators according to the indicator data ratio corresponding to each of the oil reservoirs to be divided under each of the candidate oil reservoir characteristic indicators; Determine the information entropy redundancy corresponding to each of the candidate reservoir characteristic indicators according to the information entropy value corresponding to each of the candidate reservoir characteristic indicators; The weight value corresponding to each of the candidate reservoir characteristic indicators is determined according to the information entropy redundancy corresponding to each of the candidate reservoir characteristic indicators.

4. The method according to claim 3, characterized in that Determining the weight value corresponding to each candidate reservoir characteristic indicator according to the information entropy redundancy corresponding to each candidate reservoir characteristic indicator includes: Adding each of the information entropy redundancies to obtain a first value; For each of the candidate reservoir characteristic indicators, determine the ratio between the information entropy redundancy corresponding to the candidate reservoir characteristic indicator and the first value to obtain a second value, and use the second value as the weight value corresponding to the candidate reservoir characteristic indicator.

5. The method according to claim 1, characterized in that The step of determining a first characteristic matrix corresponding to the reservoir samples to be divided and a second characteristic matrix corresponding to the target reservoir characteristic index according to the target index data of each target reservoir characteristic index of the plurality of reservoir samples to be divided includes: Obtaining target indicator data of the plurality of reservoir samples to be divided under each target reservoir characteristic indicator, and constructing a data matrix to be processed according to the target indicator data, wherein the target indicator data is data obtained after normalization processing of the characteristic indicator data; The data matrix to be processed is processed according to a preset feature extraction algorithm to obtain the first feature matrix and the second feature matrix.

6. The method according to claim 1, characterized in that The step of determining the reservoir classification result corresponding to the reservoir sample to be classified based on the first characteristic matrix includes: The first characteristic matrix is ​​processed according to a preset classification algorithm to obtain at least one reservoir type, and the reservoir classification result is determined based on the at least one reservoir type.

7. The method according to claim 1, characterized in that The analyzing the reservoir classification result based on the first characteristic matrix and the second characteristic matrix includes: Performing graphical processing on the first characteristic matrix and the second characteristic matrix to obtain at least one dual information graphic plate; The reservoir classification result is analyzed based on the at least one dual information plate.

8. A reservoir data processing device, characterized in that: include: A characteristic index determination module, used to determine at least one target reservoir characteristic index according to characteristic index data of multiple reservoirs to be divided under multiple candidate reservoir characteristic indexes; A characteristic matrix determination module, used to determine a first characteristic matrix corresponding to the oil reservoir to be divided and a second characteristic matrix corresponding to the characteristic index of the target oil reservoir according to the target index data of each of the characteristic indexes of the target oil reservoirs under the plurality of oil reservoirs to be divided; The reservoir classification result determination module is used to determine the reservoir classification result corresponding to the reservoir to be divided based on the first characteristic matrix, and analyze the reservoir classification result based on the first characteristic matrix and the second characteristic matrix.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the reservoir data processing method according to any one of claims 1 to 7.

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

Images