Model training method, fracturing parameter determination method, device and computer equipment

Abstract

The embodiments of this specification disclose a method for training an oil and gas production capacity prediction model, a method for determining fracturing parameters, an apparatus, and a computer device. The oil and gas production capacity prediction model training method includes: determining the main controlling factors affecting the oil and gas production capacity; constructing an objective function based on theoretical prior knowledge and empirical prior knowledge; wherein the theoretical prior knowledge is used to represent the theoretical value of the oil and gas production capacity under the main controlling factors, and the empirical prior knowledge is used to represent the change of the oil and gas production capacity with the main controlling factors; and using the objective function to train the oil and gas production capacity prediction model. The embodiments of this specification can improve the accuracy of oil and gas production capacity prediction, and can use the oil and gas production capacity prediction model to determine fracturing parameters.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of computer technology, and in particular to a method for training an oil and gas productivity prediction model, a method and device for determining fracturing parameters, and a computer device. Background Art

[0002] Unconventional oil and gas resources are the key development areas of oil and gas exploration and development in my country. Accurate prediction of oil and gas production capacity is the prerequisite for formulating and adjusting oil and gas well development plans and evaluating their production dynamics. Since the reservoir fracture network is difficult to accurately identify and characterize, there are many uncertainties in the traditional oil and gas production capacity calculation. Shale reservoirs have cross-scale pore structures (including micro-nano-scale organic pores, millimeter-scale natural fractures, and centimeter-scale artificial fractures, etc.). The simulation calculation of oil and gas production capacity is a typical time-consuming calculation problem with low calculation efficiency and unsatisfactory calculation results, resulting in low accuracy in oil and gas production capacity prediction. Summary of the invention

[0003] The embodiments of this specification provide an oil and gas productivity prediction model training method, a fracturing parameter determination method, an apparatus and a computer device to improve the accuracy of oil and gas productivity prediction. In addition, the oil and gas productivity prediction model can also be used to determine fracturing parameters.

[0004] In a first aspect of the embodiments of this specification, a method for training an oil and gas productivity prediction model is provided, comprising:

[0005] Identify the main controlling factors affecting oil and gas production capacity;

[0006] Constructing an objective function based on theoretical prior knowledge and empirical prior knowledge; wherein the theoretical prior knowledge is used to represent the theoretical value of oil and gas production capacity under the main control factors, and the empirical prior knowledge is used to represent the change of oil and gas production capacity with the main control factors;

[0007] The objective function is used to train the oil and gas production capacity prediction model.

[0008] A second aspect of the embodiments of this specification provides a method for determining fracturing parameters, comprising:

[0009] The fracturing parameters are determined according to an oil and gas productivity prediction model, wherein the oil and gas productivity prediction model is trained based on the method described in the first aspect.

[0010] A third aspect of the embodiments of this specification provides an oil and gas productivity prediction model training device, comprising:

[0011] A determination unit is used to determine the main controlling factors affecting oil and gas production capacity;

[0012] A construction unit, used to construct an objective function based on theoretical prior knowledge and empirical prior knowledge; wherein the theoretical prior knowledge is used to represent the theoretical value of oil and gas production capacity under the main control factors, and the empirical prior knowledge is used to represent the change of oil and gas production capacity with the main control factors;

[0013] The training unit is used to train the oil and gas production capacity prediction model using the objective function.

[0014] A fourth aspect of the embodiments of this specification provides a device for determining fracturing parameters, comprising:

[0015] A determination unit is used to determine fracturing parameters according to an oil and gas productivity prediction model, wherein the oil and gas productivity prediction model is trained based on the method described in the first aspect.

[0016] A fourth aspect of the embodiments of this specification provides a computer device, including:

[0017] at least one processor;

[0018] A memory storing program instructions, wherein the program instructions are configured to be suitable for being executed by the at least one processor, and the program instructions include instructions for executing the method as described in the first aspect or the second aspect.

[0019] The technical solution provided in the embodiments of this specification can determine the main controlling factors that affect oil and gas production capacity; can construct an objective function based on theoretical prior knowledge and empirical prior knowledge; wherein the theoretical prior knowledge is used to represent the theoretical value of oil and gas production capacity under the main controlling factors, and the empirical prior knowledge is used to represent the change of oil and gas production capacity with the main controlling factors; the objective function can be used to train the oil and gas production capacity prediction model. Since the objective function is constructed based on theoretical prior knowledge and empirical prior knowledge, it avoids the problems of repeated parameter adjustment and low parameter adjustment efficiency of traditional machine learning models and the complete dependence of traditional machine learning models on sample data, which is conducive to improving the training efficiency of the oil and gas production capacity prediction model and increasing the interpretability of the oil and gas production capacity prediction model. In addition, fracturing parameters can also be determined based on the oil and gas production capacity prediction model. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. The drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0021] Figure 1 This is a flow chart of the oil and gas production capacity prediction model training method in the embodiments of this specification;

[0022] Figure 2 It is a flow chart of the method for determining fracturing parameters in the embodiment of this specification;

[0023] Figure 3 This is a schematic diagram of the structure of the oil and gas production capacity prediction model training device in the embodiment of this specification;

[0024] Figure 4 This is a schematic diagram of the structure of a device for determining fracturing parameters in an embodiment of this specification;

[0025] Figure 5 Schematic diagram of the structure of a computer device in an embodiment of this specification. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0027] See also Figure 1 The embodiment of this specification provides a method for training an oil and gas production capacity prediction model. The method can be applied to a computer device, which may include a desktop computer, a laptop computer, a server, or a server cluster.

[0028] The oil and gas productivity prediction model training method may include the following steps.

[0029] Step S11: Determine the main controlling factors affecting oil and gas production capacity.

[0030] In some embodiments, the main controlling factors may include permeability, porosity, number of fracturing stages, etc.

[0031] The main controlling factors may be selected from geological parameters and engineering parameters. The geological parameters may include reservoir thickness, total carbon content (TOC), porosity, permeability, saturation, sweet spot distribution, maturity (Ro), gas content, etc. The engineering parameters may include horizontal section length, number of fracturing stages, stage spacing, number of single-stage clusters, cluster spacing, construction displacement, total liquid volume, total sand volume, sand addition intensity, etc. Considering that the number and types of geological parameters and engineering parameters are large, key parameters can be selected from geological parameters and engineering parameters as main controlling factors by principal component analysis method, thereby reducing the dimension of characteristic parameters.

[0032] In practical applications, the correlation between oil and gas production capacity and geological parameters and engineering parameters can be analyzed; the main controlling factors affecting oil and gas production capacity can be determined based on the analysis results. For example, the correlation between oil and gas production capacity and geological, engineering and other parameters can be analyzed to obtain the influence proportion of each parameter on oil and gas production capacity; the main components can be extracted based on the influence proportion to obtain the main controlling factors. Specifically, for example, a scatter plot of the change of oil and gas production capacity with each parameter can be determined; the scatter plot can be fitted to obtain a relationship curve and a degree of fit. Furthermore, parameters with a degree of fit greater than or equal to a predetermined value can be screened out.

[0033] The oil and gas production capacity may include liquid production, water content, oil recovery index, etc.

[0034] Step S13: construct an objective function based on theoretical prior knowledge and empirical prior knowledge.

[0035] In some embodiments, the theoretical prior knowledge can be used to represent the theoretical value of oil and gas production capacity under the main control factors. The theoretical prior knowledge can include an oil and gas production analysis model. For example, the oil and gas production analysis model can include the Bello and Wattenbarger model. The Bello and Wattenbarger model can be expressed as Among them, n F is the coefficient, s is the Laplace variable, h is the effective reservoir width, The geometry type representing the formation.

[0036] In some embodiments, the empirical prior knowledge may include empirical prior knowledge. The empirical prior knowledge is used to represent the change of oil and gas production capacity with the main controlling factors. For example, the empirical prior knowledge is used to represent the monotonic change of oil and gas production capacity with one or more of permeability, porosity and number of fracturing stages.

[0037] Taking a 3-layer neural network as an example, the empirical prior knowledge can be expressed as:

[0038] Among them, k represents permeability, α represents porosity, m represents the number of fracturing stages, w and b represent model parameters, and X represents the characteristic data in the sample data.

[0039] In some embodiments, the objective function is used to determine the model parameters of the oil and gas production capacity prediction model. The objective function can be constructed with theoretical prior knowledge and empirical prior knowledge as constraints. The objective function may include Among them, (QQ true ) 2 represents the initial constraints of the sample data, that is, the initial objective function. theory ) 2represents theoretical prior knowledge constraints, Represents empirical prior knowledge constraints. represents the monotonic variation of oil and gas production capacity with permeability, represents the monotonic variation of oil and gas production capacity with porosity, represents the monotonic change of oil and gas production capacity with the number of fracturing stages. w and b represent the model parameters of the oil and gas production capacity prediction model, λ is a hyperparameter, represents the penalty factor, Q true represents the label, Q represents the output of the oil and gas production capacity prediction model, and n represents the number of sample data.

[0040] In this way, the monotonically changing characteristics of oil and gas production capacity with permeability, porosity and the number of fracturing stages can be used as empirical prior knowledge and embedded in the oil and gas production capacity prediction model in the form of constraints; the oil and gas flow mechanism model can be used as physical prior knowledge and embedded in the oil and gas production capacity prediction model in the form of constraints. By coupling prior knowledge and the oil and gas production capacity prediction model, an oil and gas production capacity prediction model with a prior knowledge basis can be established, avoiding the problems of repeated parameter adjustment and low parameter adjustment efficiency of traditional machine learning models and the complete dependence of traditional machine learning models on sample data, which is conducive to improving the training efficiency of the oil and gas production capacity prediction model and increasing the interpretability of the oil and gas production capacity prediction model, thereby realizing real-time, accurate and rapid prediction of oil and gas production capacity, and providing a theoretical basis and scientific basis for production capacity evaluation and fine design of completion parameters.

[0041] Step S15: using the objective function to train the oil and gas productivity prediction model.

[0042] In some embodiments, the oil and gas production capacity prediction model can be obtained by superimposing a multi-layer perceptron and a long short-term memory neural network. In this way, in view of the multi-source heterogeneous characteristics of oil and gas fracturing production capacity data, by superimposing a multi-layer perceptron and a long short-term memory neural network, an oil and gas production capacity prediction model with different types of neural networks superimposed can be established, thereby optimizing the combination of oil and gas production capacity prediction models, allowing the two to play their respective advantages at the same time, and it is expected to enhance the prediction effect of oil and gas production capacity.

[0043] In some embodiments, the values ​​of the main control factors and the oil and gas production capacity data corresponding to the values ​​of the main control factors can be obtained from the production capacity database as sample data; the sample data and the objective function can be used to train the oil and gas production capacity prediction model. Among them, the values ​​of the main control factors can be used as feature data in the sample data, and the oil and gas production capacity data can be used as labels in the sample data. In practical applications, the sample data can be substituted into the objective function, and the objective function can be solved using the gradient descent method, the Newton method or the particle swarm algorithm to obtain the model parameters of the oil and gas production capacity prediction model.

[0044] In practical applications, geological parameters, engineering parameters and historical production data of production blocks are collected to establish a dynamic database of geology, engineering and production. The data in the database can be preprocessed. The preprocessing can include outlier cleaning and missing value completion. The values ​​of the main control factors and the corresponding oil and gas production capacity data can be obtained from the preprocessed database.

[0045] In some embodiments, a performance evaluation index may be selected to evaluate the training effect of the oil and gas production capacity prediction model.

[0046] The performance evaluation index may include mean absolute error (MAE) and the like.

[0047] For example, the mean absolute error can be expressed as Where n represents the number of sample data. represents the model prediction value, Represents the true value.

[0048] The oil and gas production capacity prediction model training method of the embodiment of this specification can determine the main controlling factors that affect the oil and gas production capacity; can construct an objective function based on theoretical prior knowledge and empirical prior knowledge; wherein the theoretical prior knowledge is used to represent the theoretical value of the oil and gas production capacity under the main controlling factors, and the empirical prior knowledge is used to represent the change of the oil and gas production capacity with the main controlling factors; the objective function can be used to train the oil and gas production capacity prediction model. Since the objective function is constructed based on theoretical prior knowledge and empirical prior knowledge, it avoids the problems of repeated parameter adjustment and low parameter adjustment efficiency of traditional machine learning models and the traditional machine learning models completely relying on sample data, which is conducive to improving the training efficiency of the oil and gas production capacity prediction model and increasing the interpretability of the oil and gas production capacity prediction model.

[0049] See also Figure 2 The embodiment of this specification also provides a method for determining fracturing parameters. The method can be applied to a computer device, which may include a desktop computer, a laptop computer, a server, or a server cluster.

[0050] The method for determining fracturing parameters may include the following steps.

[0051] Step S21: Determine fracturing parameters according to the oil and gas productivity prediction model.

[0052] In some embodiments, the oil and gas production capacity prediction model is based on Figure 1The corresponding embodiment is trained. By using the oil and gas production capacity prediction model, with the goal of maximizing oil and gas production capacity, the fracturing construction parameters under different reservoir conditions are formed, and the fracturing construction parameters under the condition of maximum oil and gas production capacity are optimized, thereby guiding the fracturing parameter design. Among them, the fracturing parameters may include one or more of the engineering parameters. For example, the fracturing parameters may include one or more of the horizontal section length, the number of fracturing sections, the section spacing, the number of single-section clusters, the cluster spacing, the construction displacement, the total liquid volume, the total sand volume, and the sand addition intensity. It is worth noting that the fracturing parameters may be engineering parameters that belong to the main controlling factors.

[0053] In some embodiments, the fracturing parameters under the condition of maximum oil and gas production capacity can be obtained according to the oil and gas production capacity prediction model. For example, in the target work area, the actual geological parameters are determined. The number of fracturing parameters can be one or more. Each fracturing parameter can have multiple values. The multiple values ​​of the one or more fracturing parameters can constitute multiple value combinations. The oil and gas production capacity corresponding to each value combination can be predicted according to the oil and gas production capacity prediction model. The value combination corresponding to the maximum oil and gas production capacity can be selected. For another example, in the target work area, the actual geological parameters are determined. The number of fracturing parameters can be one or more. Each fracturing parameter can have multiple values. According to the oil and gas production capacity prediction model, an optimization algorithm such as a particle swarm algorithm can be used to optimize the values ​​of the fracturing parameters under the condition of maximum oil and gas production capacity.

[0054] The fracturing parameter determination method of the embodiment of this specification can determine the fracturing parameters according to the oil and gas productivity prediction model, thereby realizing the fracturing parameter design driven by the combination of mechanism and data.

[0055] See also Figure 3 The embodiment of this specification provides an oil and gas productivity prediction model training device, including the following units.

[0056] A determination unit 31, used to determine the main control factors affecting oil and gas production capacity;

[0057] A construction unit 33 is used to construct an objective function based on theoretical prior knowledge and empirical prior knowledge; wherein the theoretical prior knowledge is used to represent the theoretical value of oil and gas production capacity under the main control factors, and the empirical prior knowledge is used to represent the change of oil and gas production capacity with the main control factors;

[0058] The training unit 35 is used to train the oil and gas productivity prediction model using the objective function.

[0059] See also Figure 4 The embodiment of this specification also provides a fracturing parameter determination device, which includes the following units.

[0060] The determination unit 41 is used to determine the fracturing parameters according to the oil and gas productivity prediction model, wherein the oil and gas productivity prediction model is based on Figure 1 The corresponding embodiment is trained.

[0061] An embodiment of the computer device of the present specification is introduced below. Figure 5 Schematic diagram of the hardware structure of the computer device in this embodiment. Figure 5 As shown, the computer device may include one or more (only one is shown in the figure) processors, memory and transmission modules. Of course, it can be understood by those skilled in the art that Figure 5 The hardware structure shown is only for illustration and does not limit the hardware structure of the above-mentioned computer device. In practice, the computer device may also include Figure 5 More or fewer component units as shown; or, Figure 5 Different configurations are shown.

[0062] The memory may include a high-speed random access memory; or, it may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory or other non-volatile solid-state memory. Of course, the memory may also include a remotely set network memory. The memory may be used to store program instructions or modules of application software, such as the instructions in this manual. Figure 1 or Figure 2 The program instructions or modules of the corresponding embodiment.

[0063] The processor may be implemented in any suitable manner. For example, the processor may take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, etc. The processor may read and execute program instructions or modules in the memory.

[0064] The transmission module can be used for transmitting data via a network, for example, via a network such as the Internet, an intranet, a local area network, a mobile communication network, etc.

[0065] This specification also provides an embodiment of a computer storage medium. The computer storage medium includes but is not limited to a random access memory (RAM), a read-only memory (ROM), a cache, a hard disk (HDD), a memory card, etc. The computer storage medium stores computer program instructions. When the computer program instructions are executed, the following are achieved: Figure 1 or Figure 2 The program instructions or modules of the corresponding embodiment.

[0066] It should be noted that each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, computer equipment embodiment, and computer storage medium embodiment, since they are basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. In addition, it is understandable that after reading this specification document, those skilled in the art can think of any combination of some or all of the embodiments listed in this specification without creative work, and these combinations are also within the scope of disclosure and protection of this specification.

[0067] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0068] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0069] It can be known from the above description of the implementation mode that the technicians in this field can clearly understand that the present specification can be implemented by means of software plus the necessary general hardware platform. Based on such an understanding, the technical solution of the present specification can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present specification or some parts of the embodiments.

[0070] This specification can be used in many general or special computer system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, and distributed computing environments that include any of the above systems or devices.

[0071] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0072] Although the present specification is described through embodiments, those skilled in the art will appreciate that there are many modifications and changes to the present specification without departing from the spirit of the present specification, and it is intended that the appended claims include these modifications and changes without departing from the spirit of the present specification.

Claims

1. A method for training an oil and gas production capacity prediction model, comprising: Identify the main controlling factors affecting oil and gas production capacity; According to theoretical prior knowledge and empirical prior knowledge, an objective function is constructed; wherein the theoretical prior knowledge is used to represent the theoretical value of oil and gas production capacity under the main control factors, and the theoretical prior knowledge includes n F is the coefficient, s is the Laplace variable, h is the effective reservoir width, Indicates the geometric type of the formation; the empirical prior knowledge is used to represent the monotonic change of oil and gas production capacity with permeability, porosity and number of fracturing stages; Using the objective function to train the oil and gas production capacity prediction model; The objective function construction includes: constructing the objective function with theoretical prior knowledge and empirical prior knowledge as constraints; the objective function includes: λ·(QQ theory ) 2 represents theoretical prior knowledge constraints, represents the monotonic variation of oil and gas production capacity with permeability, represents the monotonic variation of oil and gas production capacity with porosity, represents the monotonic change of oil and gas production capacity with the number of fracturing stages, w and b represent the model parameters of the oil and gas production capacity prediction model, λ represents the penalty factor, Q true represents the label, Q represents the output of the oil and gas production capacity prediction model, and n represents the number of sample data.

2. According to the method of claim 1, determining the main controlling factors affecting oil and gas production capacity comprises: Analyze the correlation between oil and gas production capacity and geological and engineering parameters; Based on the analysis results, determine the main controlling factors affecting oil and gas production capacity.

3. According to the method of claim 1, the oil and gas production capacity prediction model is obtained by superimposing a multi-layer perceptron and a long short-term memory neural network.

4. A method for determining fracturing parameters, comprising: The fracturing parameters are determined according to an oil and gas productivity prediction model, wherein the oil and gas productivity prediction model is trained based on any one of the methods of claims 1-3.

5. The method according to claim 4, wherein determining the fracturing parameters according to the oil and gas productivity prediction model comprises: According to the oil and gas production capacity prediction model, the fracturing parameters under the condition of maximum oil and gas production capacity are obtained.

6. An oil and gas productivity prediction model training device, comprising: A determination unit is used to determine the main controlling factors affecting oil and gas production capacity; A construction unit is used to construct an objective function based on theoretical prior knowledge and empirical prior knowledge; wherein the theoretical prior knowledge is used to represent the theoretical value of oil and gas production capacity under the main control factors, and the theoretical prior knowledge includes n F is the coefficient, s is the Laplace variable, h is the effective reservoir width, Indicates the geometric type of the formation; the empirical prior knowledge is used to represent the monotonic change of oil and gas production capacity with permeability, porosity and number of fracturing stages; A training unit, used for training the oil and gas production capacity prediction model using the objective function; The objective function construction includes: constructing the objective function with theoretical prior knowledge and empirical prior knowledge as constraints; the objective function includes: λ·(QQ theory ) 2 represents theoretical prior knowledge constraints, represents the monotonic variation of oil and gas production capacity with permeability, represents the monotonic variation of oil and gas production capacity with porosity, represents the monotonic change of oil and gas production capacity with the number of fracturing stages, w and b represent the model parameters of the oil and gas production capacity prediction model, λ represents the penalty factor, Q true represents the label, Q represents the output of the oil and gas production capacity prediction model, and n represents the number of sample data.

7. A device for determining fracturing parameters, comprising: A determination unit is used to determine fracturing parameters according to an oil and gas productivity prediction model, wherein the oil and gas productivity prediction model is trained based on any one of the methods in claims 1-3.

8. A computer device comprising: at least one processor; A memory storing program instructions, wherein the program instructions are configured to be executed by the at least one processor, and the program instructions include instructions for executing the method according to any one of claims 1-5.

Images