Reservoir dessert prediction model weight distribution method, device and electronic equipment

Abstract

The present application provides a kind of reservoir dessert prediction model weight distribution method, device and electronic equipment, belong to oil and gas reservoir seismic exploration technical field.The method includes: obtaining the sample seismic attribute index set of multiple sample objects;Sample seismic attribute index of all sample objects is processed with index normalization, so that all sample seismic attribute indexes are positively correlated with evaluation;Sample seismic attribute index of all sample objects is processed with index normalization;Based on the improved information entropy of each sample seismic attribute index in all sample objects, the improved information entropy of each sample seismic attribute index is calculated based on the probability of occurrence of sample seismic attribute index;Based on the improved information entropy of each sample seismic attribute index, the weight of each sample seismic attribute index in the reservoir dessert prediction model for reservoir dessert is calculated.The present application is used to solve the subjectivity of the weight calculation of each index in the prior art, which is easily disturbed by human factors and cannot achieve more reasonable oil and gas reservoir dessert prediction.

Description

Technical Field

[0001] This invention relates to the field of seismic exploration technology for oil and gas reservoirs, specifically to a weight allocation method for a reservoir sweet spot prediction model, a weight allocation device for a reservoir sweet spot prediction model, an electronic device, a machine-readable storage medium, and a computer program product. Background Technology

[0002] Finding sweet spots is a crucial objective in seismic exploration and reservoir evaluation of oil and gas reservoirs, providing important references for further reservoir development design. Establishing predictive models using various seismic attributes as evaluation indicators presents a key challenge: selecting the appropriate indicator weights. Researchers have employed nonlinear methods such as D-S evidence theory, analytic hierarchy process (AHP), principal component analysis, combined cross-entropy, support vector machine, grey relational analysis, and fuzzy evaluation to analyze, screen, optimize, and integrate predictive indicators, thereby improving the accuracy of reservoir prediction and evaluation.

[0003] While the aforementioned studies achieved promising prediction results, there are still areas worthy of further research and discussion. The geological significance of some seismic attribute parameters used in these studies remains unclear. Furthermore, the methods employed in calculating the weights of various indicators are highly subjective and susceptible to human interference, making it difficult to achieve more reasonable predictions of oil and gas reservoir sweet spots. Summary of the Invention

[0004] The purpose of this invention is to provide a weight allocation method, apparatus, and electronic device for a reservoir sweet spot prediction model, in order to solve the shortcomings of existing methods in which the calculation of the weights of each indicator is highly subjective, easily affected by human factors, and unable to achieve more reasonable oil and gas reservoir sweet spot prediction.

[0005] To achieve the above objectives, embodiments of the present invention provide a weight allocation method for a reservoir sweet spot prediction model, comprising:

[0006] Obtain multiple earthquake attribute indicators to be predicted;

[0007] The multiple seismic attribute indicators are input into the reservoir sweet spot prediction model to obtain the reservoir sweet spot prediction result output by the reservoir sweet spot prediction model.

[0008] The weights of each seismic attribute index in the reservoir sweet spot prediction model are determined through the following steps:

[0009] Obtain a set of sample seismic attribute indicators for multiple sample objects, where each set of sample seismic attribute indicators includes multiple sample seismic attribute indicators corresponding to the sample object.

[0010] All sample seismic attribute indicators of all sample objects are positively correlated with the evaluation.

[0011] The seismic attribute indices of all sample objects are normalized.

[0012] The improved information entropy of each sample seismic attribute index is calculated based on the occurrence probability of the sample seismic attribute index.

[0013] The weight of each sample seismic attribute index is calculated based on the improved information entropy of each sample seismic attribute index.

[0014] Optionally, the sample seismic attribute indicators of all sample objects include positive sample seismic attribute indicators, negative sample seismic attribute indicators, and interval sample seismic attribute indicators; the positive sample seismic attribute indicators represent sample seismic attributes where the indicator and the evaluation are positively correlated; the negative sample seismic attribute indicators represent sample seismic attributes where the indicator and the evaluation are negatively correlated; the interval sample seismic attribute indicators represent sample seismic attributes where the evaluation of the indicator reaches its maximum value within a set interval, and where the evaluation of the indicator outside the set interval gradually increases or decreases with the distance from the set interval.

[0015] The step of positive-positiveing ​​the seismic attribute indices of all sample objects includes:

[0016] The inverse-type and interval-type sample seismic attribute indices of all sample objects are positiveized, while the positive-type sample seismic attribute indices of all sample objects are left unprocessed.

[0017] Optionally, the inverse-type sample seismic attribute indices of all sample objects are subjected to index forwarding processing, which is achieved by the following formula:

[0018] X :,j * =-X :,j or

[0019] Among them, X :,j * X represents the result after positive transformation of the indicator. :,j This represents any inverse sample seismic attribute index in the j-th column of the matrix composed of sample seismic attribute indices of all sample objects.

[0020] Optionally, the step of positively oriented the interval-type sample seismic attribute indices of all sample objects is achieved through the following formula:

[0021]

[0022] Where, x ijThis represents the j-th interval-type sample seismic attribute index of the i-th sample object in the matrix composed of sample seismic attribute indices of all sample objects, where [a,b] represents the set interval, min(X :,j ) represents the sample seismic attribute index with the smallest value in the j-th column of the matrix composed of sample seismic attribute indices of all sample objects, max(X :,j (x) represents the sample seismic attribute index with the largest value in the j-th column of the matrix composed of sample seismic attribute indices of all sample objects. ij * This indicates the result of positive index processing.

[0023] Optionally, the improved information entropy of each sample seismic attribute index in all sample objects is calculated based on the occurrence probability of the sample seismic attribute index, which is achieved by the following formula:

[0024]

[0025] Where, p ij For the sample earthquake attribute index x ij In X :,j The probability of occurrence in x ij X represents the j-th sample seismic attribute index of the i-th sample object in the matrix composed of sample seismic attribute indices of all sample objects. :,j This represents the sample seismic attribute index in the j-th column of the matrix composed of sample seismic attribute indices of all sample objects, where n represents the number of sample objects. j The improved information entropy represents the seismic attribute index of the j-th sample in the matrix.

[0026] Optionally, the weight of each sample seismic attribute index is calculated based on the improved information entropy of each sample seismic attribute index, using the following formula:

[0027]

[0028] Among them, IE j Let m represent the improved information entropy of the j-th sample seismic attribute index in the matrix composed of sample seismic attribute indices of all sample objects, and let h represent the number of sample seismic attribute indices in the matrix. j This represents the weight of the seismic attribute index of the j-th sample in the matrix.

[0029] On the other hand, embodiments of the present invention also provide a weight allocation device for a reservoir sweet spot prediction model, comprising:

[0030] The first acquisition module is used to acquire multiple earthquake attribute indicators to be predicted;

[0031] The prediction module is used to input the multiple seismic attribute indicators into the reservoir sweet spot prediction model to obtain the reservoir sweet spot prediction result output by the reservoir sweet spot prediction model.

[0032] The weights of each seismic attribute index in the reservoir sweet spot prediction model are determined by the following modules:

[0033] The second acquisition module is used to acquire a sample seismic attribute index set of multiple sample objects, and each sample seismic attribute index set includes multiple sample seismic attribute indices corresponding to the sample object.

[0034] The first processing module is used to perform positive index processing on the seismic attribute indicators of all sample objects so that all sample seismic attribute indicators are positively correlated with the evaluation.

[0035] The second processing module is used to normalize the sample seismic attribute indicators of all sample objects.

[0036] The first calculation module is used to calculate the improved information entropy of each sample seismic attribute index in all sample objects based on the occurrence probability of the sample seismic attribute index.

[0037] The second calculation module is used to calculate the weight of each sample seismic attribute index based on the improved information entropy of each sample seismic attribute index.

[0038] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the weight allocation method of the above-mentioned reservoir sweet spot prediction model.

[0039] On the other hand, the present invention also provides a machine-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the weight allocation method of the above-described reservoir sweet spot prediction model.

[0040] On the other hand, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the weight allocation method of the above-mentioned reservoir sweet spot prediction model.

[0041] Through the above technical solution, this embodiment of the invention calculates the improved information entropy of each sample seismic attribute index in all sample objects based on the occurrence probability of the sample seismic attribute index, and calculates the weight of each sample seismic attribute index in the reservoir sweet spot prediction model based on the improved information entropy of each sample seismic attribute index. Thus, this embodiment of the invention, based on the improved information entropy theory, objectively calculates the index variation value of the seismic attribute index, which can describe the ability of the seismic attribute index to distinguish reservoir sweet spots. This embodiment of the invention implements an objective weight allocation method based on the information entropy of the data itself, solving the problem that existing methods have strong subjectivity in calculating the weights of each index and are easily interfered with by human factors, thereby achieving a more reasonable prediction of oil and gas reservoir sweet spots.

[0042] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0043] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings:

[0044] Figure 1 This is a flowchart illustrating the weight allocation method of the reservoir sweet spot prediction model provided by the present invention.

[0045] Figure 2 This is a schematic diagram illustrating the weighting calculation of six different indicators (A to F) using the weighting allocation method of the reservoir sweet spot prediction model in this embodiment of the invention.

[0046] Figure 3 This is a schematic diagram of the test results of calculating the weights of six different indicators (A to F) using the weight allocation method of the reservoir sweet spot prediction model in this embodiment of the invention.

[0047] Figure 4 This is a schematic diagram illustrating the weight calculation of seven seismic attributes in a shale oil target area using the method of an embodiment of the present invention;

[0048] Figure 5 This is a schematic diagram of the test results of weighting seven seismic attributes of a shale oil target area using the method of an embodiment of the present invention;

[0049] Figure 6 This is a schematic diagram of the weight allocation device for the reservoir sweet spot prediction model provided by the present invention;

[0050] Figure 7 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0051] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.

[0052] Method Implementation Examples

[0053] Please refer to Figure 1 This invention provides a weight allocation method for a reservoir sweet spot prediction model, comprising: acquiring multiple seismic attribute indicators to be predicted; inputting the multiple seismic attribute indicators into the reservoir sweet spot prediction model to obtain the reservoir sweet spot prediction result output by the reservoir sweet spot prediction model. This invention uses a reservoir sweet spot prediction model to predict reservoir sweet spots. The reservoir sweet spot prediction model can be constructed based on various artificial intelligence models, such as convolutional neural networks or recurrent neural networks. Furthermore, the multiple seismic attribute indicators in this invention may include at least two of the following: gas content, porosity, lithological thickness, pressure coefficient, fracture density, total organic carbon (TOC), and automatic fault extract (AFE). In one embodiment, the multiple seismic attribute indicators in this invention may include gas content, porosity, lithological thickness, pressure coefficient, fracture density, TOC, and automatic fault extract.

[0054] This invention aims to address the issue of strong subjectivity in weight allocation in oil and gas reservoir sweet spot prediction models by using an improved information entropy-based weight allocation method. It seeks to achieve an objective weight allocation method based on the information entropy of the data itself, resulting in a more reasonable evaluation of oil and gas reservoir sweet spots. Therefore, this invention requires determining the weight of each seismic attribute index in the reservoir sweet spot prediction model based on improved information entropy. The weight of each seismic attribute index in the reservoir sweet spot prediction model is determined through the following steps:

[0055] Step 100: Obtain a set of sample seismic attribute indicators for multiple sample objects. Each set of sample seismic attribute indicators includes multiple sample seismic attribute indicators corresponding to the sample object.

[0056] The electronic device acquires a set of sample seismic attribute indicators for multiple sample objects. Each set of sample seismic attribute indicators includes multiple sample seismic attribute indicators corresponding to the sample object. The set of sample seismic attribute indicators for multiple sample objects can be a set of historical seismic attribute indicators for multiple known reservoir regions. The multiple sample seismic attribute indicators can be historical gas content, historical porosity, historical lithological thickness, historical pressure coefficient, historical fracture density, historical organic carbon content, and historical automatically extracted fracture attributes of the known reservoir regions.

[0057] Next, for each of the m sample seismic attribute indices of the n sample objects, they are organized into a matrix X with n rows and m columns.

[0058]

[0059] Where x ij The j-th index of the i-th sample object; the row vector X formed by the i-th row of the matrix. i,: Represents the various indicators of the i-th sample object; X is the column vector formed by the j-th column of the matrix. :,j This represents the j-th indicator for each sample object.

[0060] Step 200: Perform positive index processing on the seismic attribute indicators of all sample objects so that all sample seismic attribute indicators are positively correlated with the evaluation.

[0061] First, based on the relationship between the index values ​​and the evaluation, the indicators are divided into three types. That is, the sample seismic attribute indicators of all sample objects include positive sample seismic attribute indicators, negative sample seismic attribute indicators, and interval sample seismic attribute indicators.

[0062] The positive-type sample seismic attribute index represents sample seismic attributes where the index and evaluation are positively correlated; that is, the higher the index value, the higher the evaluation. The negative-type sample seismic attribute index represents sample seismic attributes where the index and evaluation are negatively correlated; that is, the lower the index value, the higher the evaluation. The interval-type sample seismic attribute index represents sample seismic attributes where the evaluation of the index reaches its maximum value within a set interval, and the evaluation of the index outside the set interval gradually increases or decreases with distance from the set interval. For example, if the evaluation is highest when the index value is within a certain set interval, and the evaluation gradually decreases with distance from the set interval when the index value is outside the set interval, the index type is considered a positive + interval composite type; when the evaluation is lowest within the set interval, and increases with distance outside the set interval, the index type is considered a negative + interval composite type.

[0063] Specifically, step 200 involves performing positive index processing on the seismic attribute indicators of all sample objects, including: performing positive index processing on the inverse-type and interval-type seismic attribute indicators of all sample objects, and leaving the positive-type seismic attribute indicators of all sample objects unprocessed. For the positive-type seismic attribute indicators, this embodiment of the invention does not require conversion.

[0064] For inverse-type sample seismic attribute indices, the inverse-type sample seismic attribute indices of all sample objects are forward-oriented, which is achieved by the following formula:

[0065] X :,j * =-X:,j or

[0066] Among them, X :,j * X represents the result after positive transformation of the indicator. :,j This represents any inverse sample seismic attribute index in the j-th column of the matrix composed of sample seismic attribute indices of all sample objects.

[0067] For interval-type sample seismic attribute indices, when the index value is optimal within the set interval [a, b], the interval-type sample seismic attribute indices of all sample objects are positively oriented, which is achieved through the following formula:

[0068]

[0069] Where, x ij This represents the j-th interval-type sample seismic attribute index of the i-th sample object in the matrix composed of sample seismic attribute indices of all sample objects, where [a,b] represents the set interval, min(X :,j ) represents the sample seismic attribute index with the smallest value in the j-th column of the matrix composed of sample seismic attribute indices of all sample objects, max(X :,j (x) represents the sample seismic attribute index with the largest value in the j-th column of the matrix composed of sample seismic attribute indices of all sample objects. ij * This indicates the result of positive index processing.

[0070] It should be noted that if the indicator is a composite type of inverse and interval, it should first be regarded as an inverse sample seismic attribute indicator, then converted into a forward sample seismic attribute indicator, and then interval-type forward conversion should be performed on this basis.

[0071] Therefore, in this embodiment of the invention, various indicators are transformed into positive sample seismic attribute indicators based on prior information, so that each indicator after transformation is positively correlated with the evaluation.

[0072] Step 300: Normalize the sample seismic attribute indices of all sample objects.

[0073] After the index positiveization process, the seismic attribute index of each sample needs to be normalized to the range of [0,1]. The purpose of normalization is to remove the dimensions and only evaluate and calculate the numerical relationship between the indicators. The seismic attribute index of each sample can be calculated using the following formula:

[0074]

[0075] Among them, X :,j *Let the j-th column of the matrix in formula (1) represent any sample seismic attribute index, min(X :,j * ) represents the sample seismic attribute index with the smallest value in the j-th column of the matrix in formula (1), max(X :,j * X represents the sample seismic attribute index with the largest value in the j-th column of the matrix in formula (1). :,j norm This represents the result of index normalization. For the index normalization of other sample seismic attribute indices in the matrix, formula (4) can be used for calculation.

[0076] Step 400: Calculate the improved information entropy of each sample seismic attribute index in all sample objects based on the occurrence probability of the sample seismic attribute index.

[0077] Based on the normalized index values, the improved information entropy of each seismic attribute index in all sample objects is calculated according to the occurrence probability of the sample seismic attribute index, using the following formula:

[0078]

[0079] Where, p ij For the sample earthquake attribute index x ij In X :,j The probability of x appearing in x can be obtained through probability density statistics. ij X represents the j-th sample seismic attribute index of the i-th sample object in the matrix composed of sample seismic attribute indices of all sample objects. :,j This represents the sample seismic attribute index in the j-th column of the matrix composed of sample seismic attribute indices of all sample objects, where n represents the number of sample objects. j Let represent the improved information entropy of the seismic attribute index of the j-th sample in the matrix. The smaller the improved information entropy of a certain sample seismic attribute index, the smaller the degree of variation of the index, and the smaller the contribution of the index to the comprehensive evaluation; conversely, the larger the improved information entropy of a certain sample seismic attribute index, the greater the degree of variation of the index, and the greater the contribution of the index to the comprehensive evaluation.

[0080] Step 500: Calculate the weight of each sample seismic attribute index based on the improved information entropy of each sample seismic attribute index.

[0081] Based on the improved information entropy of each sample seismic attribute index (each sample seismic attribute index) in the matrix of formula (1), the weight allocation based on each sample seismic attribute index can be further realized by using the improved information entropy.

[0082] In one embodiment, the weight of each sample seismic attribute index is calculated based on the improved information entropy of each sample seismic attribute index, using the following formula:

[0083]

[0084] Among them, IE j Let m represent the improved information entropy of the j-th sample seismic attribute index in the matrix composed of sample seismic attribute indices of all sample objects, and let h represent the number of sample seismic attribute indices in the matrix. j This represents the weight of the seismic attribute index of the j-th sample in the matrix.

[0085] Therefore, this embodiment of the invention uses a reservoir sweet spot prediction model based on the weights of the aforementioned sample seismic attribute indicators to predict reservoir sweet spots. This embodiment of the invention improves upon information entropy theory by objectively calculating the index variation values ​​of seismic attribute indicators; these index variation values ​​describe the ability of seismic attributes to distinguish sweet spots. This embodiment of the invention implements an objective weight allocation method based on the information entropy of the data itself, achieving more reasonable prediction of oil and gas reservoir sweet spots.

[0086] Please refer to Figure 2 As shown, to verify the ability of this embodiment of the invention to describe the information contained in the planar attributes, the weight allocation method of the reservoir sweet spot prediction model of this embodiment of the invention was applied to calculate the weights of six different indicators (A to F). The test results are as follows. Figure 3 As shown, the black curve represents the weights calculated using the traditional entropy weight method, which is not suitable for planar properties; the red line represents the weights calculated by the method of this embodiment. See also Figure 3 As can be seen, the improved entropy weight in this embodiment of the invention can effectively represent the ability of planar attributes to distinguish desserts.

[0087] Additionally, please refer to Figure 4 As shown in the figure, the method of this embodiment of the invention is used to calculate the weights of seven seismic attributes in a target shale oil area, and the obtained weights are used for sweet spot evaluation. The test results are as follows. Figure 5 As shown, Figure 5 Orange, yellow, cyan, and blue represent Class I, Class II, Class III, and Class IV sweet spots, respectively. Test results show a good correlation between sweet spots and high-yield wells, indicating that the method in this embodiment can achieve objective weight allocation based on the data's own information entropy, resulting in a more reasonable evaluation of oil and gas reservoir sweet spots.

[0088] This invention calculates the improved information entropy of each seismic attribute index in all sample objects based on the occurrence probability of the sample seismic attribute index, and calculates the weight of each sample seismic attribute index in the reservoir sweet spot prediction model based on the improved information entropy of each sample seismic attribute index. Thus, this invention objectively calculates the index variation value of seismic attribute indices based on the improved information entropy theory. The index variation value can describe the ability of seismic attribute indices to distinguish reservoir sweet spots. This invention implements an objective weight allocation method based on the information entropy of the data itself, solving the problem that existing methods have strong subjectivity in calculating the weights of each index and are easily interfered with by human factors, achieving a more reasonable prediction of oil and gas reservoir sweet spots.

[0089] Device Examples

[0090] Please refer to Figure 6 On the other hand, embodiments of the present invention also provide a weight allocation device for a reservoir sweet spot prediction model, comprising:

[0091] The first acquisition module is used to acquire multiple earthquake attribute indicators to be predicted;

[0092] The prediction module is used to input the multiple seismic attribute indicators into the reservoir sweet spot prediction model to obtain the reservoir sweet spot prediction result output by the reservoir sweet spot prediction model.

[0093] The weights of each seismic attribute index in the reservoir sweet spot prediction model are determined by the following modules:

[0094] The second acquisition module 601 is used to acquire a sample seismic attribute index set of multiple sample objects, and each sample seismic attribute index set includes multiple sample seismic attribute indices corresponding to the sample object.

[0095] The first processing module 602 is used to perform positive index processing on the sample seismic attribute indicators of all sample objects so that all sample seismic attribute indicators are positively correlated with the evaluation.

[0096] The second processing module 603 is used to perform index normalization processing on the sample seismic attribute indices of all sample objects.

[0097] The first calculation module 604 is used to calculate the improved information entropy of each sample seismic attribute index in all sample objects based on the occurrence probability of the sample seismic attribute index.

[0098] The second calculation module 605 is used to calculate the weight of each sample seismic attribute index based on the improved information entropy of each sample seismic attribute index.

[0099] Optionally, the sample seismic attribute indicators of all sample objects include positive sample seismic attribute indicators, negative sample seismic attribute indicators, and interval sample seismic attribute indicators; the positive sample seismic attribute indicators represent sample seismic attributes where the indicator and the evaluation are positively correlated; the negative sample seismic attribute indicators represent sample seismic attributes where the indicator and the evaluation are negatively correlated; the interval sample seismic attribute indicators represent sample seismic attributes where the evaluation of the indicator reaches its maximum value within a set interval, and where the evaluation of the indicator outside the set interval gradually increases or decreases with the distance from the set interval.

[0100] The step of positive-positiveing ​​the seismic attribute indices of all sample objects includes:

[0101] The inverse-type and interval-type sample seismic attribute indices of all sample objects are positiveized, while the positive-type sample seismic attribute indices of all sample objects are left unprocessed.

[0102] Optionally, the inverse-type sample seismic attribute indices of all sample objects are subjected to index forwarding processing, which is achieved by the following formula:

[0103] X :,j * =-X :,j or

[0104] Among them, X :,j * X represents the result after positive transformation of the indicator. :,j This represents any inverse sample seismic attribute index in the j-th column of the matrix composed of sample seismic attribute indices of all sample objects.

[0105] Optionally, the step of positively oriented the interval-type sample seismic attribute indices of all sample objects is achieved through the following formula:

[0106]

[0107] Where, x ij This represents the j-th interval-type sample seismic attribute index of the i-th sample object in the matrix composed of sample seismic attribute indices of all sample objects, where [a,b] represents the set interval, min(X :,j ) represents the sample seismic attribute index with the smallest value in the j-th column of the matrix composed of sample seismic attribute indices of all sample objects, max(X :,j (x) represents the sample seismic attribute index with the largest value in the j-th column of the matrix composed of sample seismic attribute indices of all sample objects. ij *This indicates the result of positive index processing.

[0108] Optionally, the improved information entropy of each sample seismic attribute index in all sample objects is calculated based on the occurrence probability of the sample seismic attribute index, which is achieved by the following formula:

[0109]

[0110] Where, p ij For the sample earthquake attribute index x ij In X :,j The probability of occurrence in x ij X represents the j-th sample seismic attribute index of the i-th sample object in the matrix composed of sample seismic attribute indices of all sample objects. :,j This represents the sample seismic attribute index in the j-th column of the matrix composed of sample seismic attribute indices of all sample objects, where n represents the number of sample objects. j The improved information entropy represents the seismic attribute index of the j-th sample in the matrix.

[0111] Optionally, the weight of each sample seismic attribute index is calculated based on the improved information entropy of each sample seismic attribute index, using the following formula:

[0112]

[0113] Among them, IE j Let m represent the improved information entropy of the j-th sample seismic attribute index in the matrix composed of sample seismic attribute indices of all sample objects, and let h represent the number of sample seismic attribute indices in the matrix. j This represents the weight of the seismic attribute index of the j-th sample in the matrix.

[0114] The weight allocation device of the reservoir sweet spot prediction model includes a processor and a memory. The second acquisition module 601, the first processing module 602, the second processing module 603, the first calculation module 604, and the second calculation module 605 are all stored in the memory as program units. The processor executes the program units stored in the memory to realize the corresponding functions.

[0115] A processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured.

[0116] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0117] Figure 7 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 7 As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730, and a communication bus 740, wherein the processor 710, the communication interface 720, and the memory 730 communicate with each other through the communication bus 740. The processor 710 can call logic instructions in the memory 730 to execute a weight allocation method for a reservoir sweet spot prediction model. This method includes: acquiring multiple seismic attribute indicators to be predicted; inputting the multiple seismic attribute indicators into the reservoir sweet spot prediction model to obtain a reservoir sweet spot prediction result output by the model; wherein the weight of each seismic attribute indicator in the reservoir sweet spot prediction model is determined through the following steps: acquiring a set of sample seismic attribute indicators for multiple sample objects, each set including multiple sample seismic attribute indicators corresponding to the sample object; performing positive index processing on the sample seismic attribute indicators of all sample objects to ensure that all sample seismic attribute indicators are positively correlated with the evaluation; performing index normalization processing on the sample seismic attribute indicators of all sample objects; calculating the improved information entropy of each sample seismic attribute indicator in all sample objects based on the occurrence probability of the sample seismic attribute indicators; and calculating the weight of each sample seismic attribute indicator based on the improved information entropy of each sample seismic attribute indicator.

[0118] Furthermore, the logical instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, 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 described in the various embodiments of the present invention. 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.

[0119] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a machine-readable storage medium. When the computer program is executed by a processor, the computer can execute a weight allocation method for a reservoir sweet spot prediction model. The method includes: acquiring multiple seismic attribute indicators to be predicted; inputting the multiple seismic attribute indicators into the reservoir sweet spot prediction model to obtain a reservoir sweet spot prediction result output by the reservoir sweet spot prediction model; wherein the weight of each seismic attribute indicator in the reservoir sweet spot prediction model is determined by the following steps: acquiring a sample seismic attribute indicator set for multiple sample objects, each sample seismic attribute indicator set including multiple sample seismic attribute indicators corresponding to the sample object; performing indicator positiveization processing on the sample seismic attribute indicators of all sample objects so that all sample seismic attribute indicators are positively correlated with the evaluation; performing indicator normalization processing on the sample seismic attribute indicators of all sample objects; calculating the improved information entropy of each sample seismic attribute indicator in all sample objects based on the occurrence probability of the sample seismic attribute indicators; and calculating the weight of each sample seismic attribute indicator based on the improved information entropy of each sample seismic attribute indicator.

[0120] In another aspect, the present invention also provides a machine-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a weight allocation method for a reservoir sweet spot prediction model. The method includes: acquiring multiple seismic attribute indicators to be predicted; inputting the multiple seismic attribute indicators into a reservoir sweet spot prediction model to obtain a reservoir sweet spot prediction result output by the model; wherein the weight of each seismic attribute indicator in the reservoir sweet spot prediction model is determined through the following steps: acquiring a set of sample seismic attribute indicators for multiple sample objects, each set including multiple sample seismic attribute indicators corresponding to the sample object; performing positive index processing on the sample seismic attribute indicators of all sample objects to ensure that all sample seismic attribute indicators are positively correlated with the evaluation; performing index normalization processing on the sample seismic attribute indicators of all sample objects; calculating the improved information entropy of each sample seismic attribute indicator in all sample objects based on the occurrence probability of the sample seismic attribute indicators; and calculating the weight of each sample seismic attribute indicator based on the improved information entropy of each sample seismic attribute indicator.

[0121] The device embodiments described above are merely illustrative. 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0122] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0123] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A weight allocation method for a reservoir sweet spot prediction model, characterized in that, include: Obtain multiple earthquake attribute indicators to be predicted; The multiple seismic attribute indicators are input into the reservoir sweet spot prediction model to obtain the reservoir sweet spot prediction result output by the reservoir sweet spot prediction model. The weights of each seismic attribute index in the reservoir sweet spot prediction model are determined through the following steps: Obtain a set of sample seismic attribute indicators for multiple sample objects, where each set of sample seismic attribute indicators includes multiple sample seismic attribute indicators corresponding to the sample object. All sample seismic attribute indicators of all sample objects are positively correlated with the evaluation. The seismic attribute indices of all sample objects are normalized. The improved information entropy of each sample seismic attribute index is calculated based on the occurrence probability of the sample seismic attribute index. The weight of each sample seismic attribute index is calculated based on the improved information entropy of each sample seismic attribute index.

2. The weight allocation method for the reservoir sweet spot prediction model according to claim 1, characterized in that, The sample seismic attribute indicators of all sample objects include positive sample seismic attribute indicators, negative sample seismic attribute indicators, and interval sample seismic attribute indicators; the positive sample seismic attribute indicators represent sample seismic attributes whose indicators are positively correlated with the evaluation; the negative sample seismic attribute indicators represent sample seismic attributes whose indicators are negatively correlated with the evaluation. The interval-type sample seismic attribute index represents the sample seismic attribute whose evaluation reaches its maximum value within a set interval, and whose evaluation of the index outside the set interval gradually increases or decreases with the distance from the set interval. The step of positive-positiveing ​​the seismic attribute indices of all sample objects includes: The inverse-type and interval-type sample seismic attribute indices of all sample objects are positiveized, while the positive-type sample seismic attribute indices of all sample objects are left unprocessed.

3. The weight allocation method for the reservoir sweet spot prediction model according to claim 2, characterized in that, The inverse-type sample seismic attribute indices of all sample objects are positiveized using the following formula: X :,j * =-X :,j or Among them, X :,j * X represents the result after positive transformation of the indicator. :,j This represents any inverse sample seismic attribute index in the j-th column of the matrix composed of sample seismic attribute indices of all sample objects.

4. The weight allocation method for the reservoir sweet spot prediction model according to claim 2, characterized in that, The process of positive-directing the interval-type sample seismic attribute indices of all sample objects is achieved through the following formula: Where, x ij This represents the j-th interval-type sample seismic attribute index of the i-th sample object in the matrix composed of sample seismic attribute indices of all sample objects, where [a,b] represents the set interval, min(X :,j ) represents the sample seismic attribute index with the smallest value in the j-th column of the matrix composed of sample seismic attribute indices of all sample objects, max(X :,j (x) represents the sample seismic attribute index with the largest value in the j-th column of the matrix composed of sample seismic attribute indices of all sample objects. ij * This indicates the result of positive index processing.

5. The weight allocation method for the reservoir sweet spot prediction model according to claim 1, characterized in that, The improved information entropy of each sample seismic attribute index in all sample objects is calculated based on the occurrence probability of the sample seismic attribute index, and is achieved by the following formula: Where, p ij For the sample earthquake attribute index x ij In X :,j The probability of occurrence in x ij X represents the j-th sample seismic attribute index of the i-th sample object in the matrix composed of sample seismic attribute indices of all sample objects. :,j This represents the sample seismic attribute index in the j-th column of the matrix composed of sample seismic attribute indices of all sample objects, where n represents the number of sample objects. j The improved information entropy represents the seismic attribute index of the j-th sample in the matrix.

6. The weight allocation method for the reservoir sweet spot prediction model according to claim 1, characterized in that, The weight of each sample seismic attribute index is calculated based on the improved information entropy of each sample seismic attribute index, using the following formula: Among them, IE j Let m represent the improved information entropy of the j-th sample seismic attribute index in the matrix composed of sample seismic attribute indices of all sample objects, and let h represent the number of sample seismic attribute indices in the matrix. j This represents the weight of the seismic attribute index of the j-th sample in the matrix.

7. A weight allocation device for a reservoir sweet spot prediction model, characterized in that, include: The first acquisition module is used to acquire multiple earthquake attribute indicators to be predicted; The prediction module is used to input the multiple seismic attribute indicators into the reservoir sweet spot prediction model to obtain the reservoir sweet spot prediction result output by the reservoir sweet spot prediction model. The weights of each seismic attribute index in the reservoir sweet spot prediction model are determined by the following modules: The second acquisition module is used to acquire a sample seismic attribute index set of multiple sample objects, and each sample seismic attribute index set includes multiple sample seismic attribute indices corresponding to the sample object. The first processing module is used to perform positive index processing on the seismic attribute indicators of all sample objects so that all sample seismic attribute indicators are positively correlated with the evaluation. The second processing module is used to normalize the sample seismic attribute indicators of all sample objects. The first calculation module is used to calculate the improved information entropy of each sample seismic attribute index in all sample objects based on the occurrence probability of the sample seismic attribute index. The second calculation module is used to calculate the weight of each sample seismic attribute index based on the improved information entropy of each sample seismic attribute index.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the weight allocation method of the reservoir sweet spot prediction model according to any one of claims 1 to 6.

9. A machine-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the weight allocation method of the reservoir sweet spot prediction model according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the weight allocation method of the reservoir sweet spot prediction model according to any one of claims 1 to 6.

Images