Production data analysis method and device for oil reservoir and oil-water well

Abstract

The invention provides a production data analysis method and device for an oil reservoir and an oil-water well. The method comprises the steps that production data of each oil reservoir block is acquired; inputting the production data of each oil reservoir block into a first production data analysis model, and determining the development quality grade of each oil reservoir block; dividing the oil reservoir block of the target development quality grade into a plurality of main control factor units, and screening out production data of each main control factor unit; inputting the production data of each main control factor unit into a second production data analysis model, and determining the development quality grade of each main control factor unit; obtaining production data of each oil well in the main control factor unit of the target development quality grade and water injection data of the water well; inputting the production data of each oil well into a third production data analysis model, and determining the development quality grade of each oil well; and inputting the water injection data of each water well into the water injection data analysis model, and determining the development quality grade of each water well.

Description

Technical Field

[0001] The present invention relates to the technical field of reservoir development, and particularly to a method and device for analyzing production data of reservoirs and oil production and injection wells. Background Art

[0002] This section aims to provide background or context for the embodiments of the present invention described in the claims. The description herein is not admitted to be prior art merely because it is included in this section.

[0003] During the process of reservoir exploitation, the development effect of a reservoir or an oil production and injection well can be measured by the development quality grade; analyzing the production data of the reservoir and the oil production and injection wells to find out the reservoir blocks and oil production and injection wells that restrict the high-quality development of the reservoir plays an important role in the production management of the reservoir. However, there is no technical solution for analyzing the production data of reservoirs and oil production and injection wells in the prior art; therefore, how to analyze the production data of reservoirs and oil production and injection wells and find out the reservoirs and oil production and injection wells that do not meet the development quality requirements is an urgent problem to be solved. Summary of the Invention

[0004] In an embodiment of the present invention, a method for analyzing production data of a reservoir and oil production and injection wells is proposed, which can automatically analyze the production data of the reservoir and the oil production and injection wells, and timely determine the reservoir blocks and oil production and injection wells that do not meet the development quality grade, providing technical support for improving the production management of the reservoir and the oil production and injection wells, including:

[0005] Obtain the production data of each reservoir block; wherein, the reservoir block is obtained by dividing the reservoir according to a preset block;

[0006] Input the production data of each reservoir block into a first production data analysis model to determine the development quality grade of each reservoir block; wherein, the first production data analysis model is trained for a machine learning model based on the production data of historical reservoir blocks and the corresponding development quality grades; the development quality grade is an index for measuring the development effect of the reservoir and the oil production and injection wells;

[0007] Divide the reservoir blocks with the target development quality grade into multiple main control factor units, and screen out the production data of each main control factor unit from the production data of the reservoir blocks with the target development quality grade; wherein, the main control factor units include: one or any combination of a high-permeability layer, a fracture zone, a high-viscosity oil area, bottom water, edge water, and an asphalt mat;

[0008] Input the production data of each main control factor unit into a second production data analysis model to determine the development quality grade of each main control factor unit; wherein, the second production data analysis model is trained for a machine learning model based on the production data of historical main control factor units and the corresponding development quality grades;

[0009] Obtain the production data of each oil well and the water injection data of each water well in the main control factor unit with the target development quality level.

[0010] Input the production data of each oil well into the third production data analysis model to determine the development quality level of each oil well; input the water injection data of each water well into the water injection data analysis model to determine the development quality level of each water well; among them, the third production data analysis model is trained on a machine learning model based on the production data of historical oil wells and the corresponding development quality levels; the water injection data analysis model is trained on a machine learning model based on the water injection data of historical water wells and the corresponding development quality levels.

[0011] In an embodiment of the present invention, a production data analysis device for oil reservoirs and oil and water wells is proposed, which can automatically analyze the production data of oil reservoirs and oil and water wells, and timely determine the oil reservoir blocks and oil and water wells that do not meet the development quality level, providing technical support for improving the production management of oil reservoirs and oil and water wells, including:

[0012] The first data acquisition module is used to acquire the production data of each oil reservoir block; among them, the oil reservoir block is obtained by dividing the oil reservoir according to a preset block.

[0013] The first data analysis module is used to input the production data of each oil reservoir block into the first production data analysis model to determine the development quality level of each oil reservoir block; among them, the first production data analysis model is trained on a machine learning model based on the production data of historical oil reservoir blocks and the corresponding development quality levels; the development quality level is an index used to measure the development effect of oil reservoirs and oil and water wells.

[0014] The oil reservoir block division module is used to divide the oil reservoir block with the target development quality level into multiple main control factor units, and screen out the production data of each main control factor unit from the production data of the oil reservoir block with the target development quality level; among them, the main control factor unit includes: high permeability layer, fracture zone, high viscosity oil area, bottom water, edge water, asphalt pad, one or any combination thereof.

[0015] The second data analysis module is used to input the production data of each main control factor unit into the second production data analysis model to determine the development quality level of each main control factor unit; among them, the second production data analysis model is trained on a machine learning model based on the production data of historical main control factor units and the corresponding development quality levels.

[0016] The second data acquisition module is used to acquire the production data of each oil well and the water injection data of each water well in the main control factor unit with the target development quality level.

[0017] A third data analysis module, configured to input the production data of each oil well into a third production data analysis model to determine the development quality level of each oil well; and input the water injection data of each water well into a water injection data analysis model to determine the development quality level of each water well. Wherein, the third production data analysis model is obtained by training a machine learning model based on the production data of historical oil wells and their corresponding development quality levels; and the water injection data analysis model is obtained by training a machine learning model based on the water injection data of historical water wells and their corresponding development quality levels.

[0018] In an embodiment of the present invention, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, a production data analysis method for a reservoir and oil and water wells is implemented.

[0019] In an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, a production data analysis method for a reservoir and oil and water wells is implemented.

[0020] In an embodiment of the present invention, a computer program product is provided. The computer program product includes a computer program, and when the computer program is executed by a processor, a production data analysis method for a reservoir and oil and water wells is implemented.

[0021] In an embodiment of the present invention, production data of each reservoir block is obtained, where the reservoir block is obtained by dividing the reservoir according to a preset block; the production data of each reservoir block is input into a first production data analysis model to determine the development quality level of each reservoir block, where the first production data analysis model is obtained by training a machine learning model based on the production data of historical reservoir blocks and the corresponding development quality levels; the development quality level is an index for measuring the development effect of the reservoir and oil and water wells; the reservoir blocks with the target development quality level are divided into multiple main control factor units, and the production data of each main control factor unit is screened out from the production data of the reservoir blocks with the target development quality level, where the main control factor unit includes one or any combination of a high-permeability layer, a fracture zone, a high-viscosity oil area, bottom water, edge water, and an asphalt mat; the production data of each main control factor unit is input into a second production data analysis model to determine the development quality level of each main control factor unit, where the second production data analysis model is obtained by training a machine learning model based on the production data of historical main control factor units and the corresponding development quality levels; the production data of each oil well and the water injection data of water wells in the main control factor units with the target development quality level are obtained; the production data of each oil well is input into a third production data analysis model to determine the development quality level of each oil well; the water injection data of each water well is input into a water injection data analysis model to determine the development quality level of each water well, where the third production data analysis model is obtained by training a machine learning model based on the production data of historical oil wells and the corresponding development quality levels; the water injection data analysis model is obtained by training a machine learning model based on the water injection data of historical water wells and the corresponding development quality levels. The embodiment of the present invention can automatically analyze the production data of the reservoir and oil and water wells, timely determine the reservoir blocks and oil and water wells that do not meet the development quality level, enable production management personnel to timely master the development quality of the reservoir and oil and water wells, and provide technical support for improving the production management of the reservoir and oil and water wells. Description of the Drawings

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the accompanying drawings required for the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0023] Figure 1 It is a schematic flow chart of the production data analysis method for the reservoir and oil and water wells in the embodiment of the present invention;

[0024] Figure 2 It is a specific example diagram of the production data analysis method for the reservoir and oil and water wells in the embodiment of the present invention;

[0025] Figure 3 It is a specific example diagram of the production data analysis method for the reservoir and oil production wells in the embodiments of the present invention;

[0026] Figure 4 It is a specific example diagram of the production data analysis method for the reservoir and oil production wells in the embodiments of the present invention;

[0027] Figure 5 It is a specific example diagram of the production data analysis method for the reservoir and oil production wells in the embodiments of the present invention;

[0028] Figure 6 It is a specific example diagram of the production data analysis method for the reservoir and oil production wells in the embodiments of the present invention;

[0029] Figure 7 It is a specific example diagram of the production data analysis method for the reservoir and oil production wells in the embodiments of the present invention;

[0030] Figure 8 It is a schematic diagram of the production data analysis device for the reservoir and oil production wells in the embodiments of the present invention;

[0031] Figure 9 It is a schematic diagram of the computer device in the embodiments of the present invention. Detailed implementation manners

[0032] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer and more understandable, the following further elaborates on the embodiments of the present invention with reference to the accompanying drawings. Herein, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but not to limit the present invention.

[0033] The term "and / or" in this article merely describes an association relationship, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" in this article means any one of multiple types or any combination of at least two of multiple types. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set composed of A, B, and C.

[0034] In the description of this specification, terms such as "including", "comprising", "having", "containing", etc. are all open-ended terms, meaning including but not limited to. The description with reference to terms such as "one embodiment", "one specific embodiment", "some embodiments", "for example", etc. means that the specific features, structures or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. The order of steps involved in each embodiment is used to schematically illustrate the implementation of the present application, and the order of steps is not limited and can be adjusted appropriately as needed.

[0035] The principles and spirit of the present invention will be elaborated in detail below with reference to several representative embodiments of the present invention.

[0036] Figure 1 It is a schematic flow chart of the production data analysis method for oil reservoirs and oil and water wells in an embodiment of the present invention. As Figure 1 shown, the method includes:

[0037] Step 101, obtaining the production data of each oil reservoir block; wherein, the oil reservoir block is obtained by dividing the oil reservoir according to a preset block;

[0038] Step 102, inputting the production data of each oil reservoir block into the first production data analysis model to determine the development quality grade of each oil reservoir block; wherein, the first production data analysis model is obtained by training a machine learning model based on the production data of historical oil reservoir blocks and the corresponding development quality grades; the development quality grade is an index used to measure the development effect of oil reservoirs and oil and water wells;

[0039] Step 103, dividing the oil reservoir blocks with the target development quality grade into multiple main control factor units, and screening out the production data of each main control factor unit from the production data of the oil reservoir blocks with the target development quality grade; wherein, the main control factor unit includes: one or any combination of high permeability layer, fracture zone, high viscosity oil area, bottom water, edge water, asphalt mat;

[0040] Step 104, inputting the production data of each main control factor unit into the second production data analysis model to determine the development quality grade of each main control factor unit; wherein, the second production data analysis model is obtained by training a machine learning model based on the production data of historical main control factor units and the corresponding development quality grades;

[0041] Step 105, obtaining the production data of each oil well and the water injection data of the water well in the main control factor unit with the target development quality grade;

[0042] Step 106: Input the production data of each oil well into the third production data analysis model to determine the development quality grade of each oil well; input the water injection data of each water well into the water injection data analysis model to determine the development quality grade of each water well. Among them, the third production data analysis model is obtained by training a machine learning model based on the production data of historical oil wells and their corresponding development quality grades; the water injection data analysis model is obtained by training a machine learning model based on the water injection data of historical water wells and their corresponding development quality grades.

[0043] In the embodiment of the present invention, the production data of each reservoir block is obtained. Among them, the reservoir block is obtained by dividing the reservoir according to a preset block; the production data of each reservoir block is input into the first production data analysis model to determine the development quality grade of each reservoir block. The development quality grade is an index used to measure the development effect of the reservoir and oil and water wells; the reservoir block with the target development quality grade is divided into multiple main control factor units, and the production data of each main control factor unit is screened out from the production data of the reservoir block with the target development quality grade. Among them, the main control factor unit includes one or any combination of the following: high-permeability layer, fracture zone, high-viscosity oil area, bottom water, edge water, and asphalt mat; the production data of each main control factor unit is input into the second production data analysis model to determine the development quality grade of each main control factor unit; the production data of each oil well and the water injection data of the water well in the main control factor unit with the target development quality grade are obtained; the production data of each oil well is input into the third production data analysis model to determine the development quality grade of each oil well; the water injection data of each water well is input into the water injection data analysis model to determine the development quality grade of each water well. The embodiment of the present invention can automatically analyze the production data of the reservoir and oil and water wells, timely determine the reservoir blocks and oil and water wells that do not meet the development quality grade, enable production management personnel to timely master the development quality of the reservoir and oil and water wells, and provide technical support for improving the production management of the reservoir and oil and water wells.

[0044] For a clearer explanation of the above production data analysis method for the reservoir and oil and water wells, the following will be described in detail in combination with each step.

[0045] In one embodiment of the present invention, the production data of the reservoir can be analyzed to determine the development quality grade of the reservoir; the development quality grade is an index for measuring the development effect of the reservoir and oil production and injection wells, and in the present invention, it can be described as the health status grade; specifically, the development quality grade (health status grade) includes the following three grades, including: healthy (the first grade), sub-healthy (the second grade), and diseased (the third grade). After obtaining the production data of the reservoir, the production data of the reservoir is input into the reservoir production data analysis model to determine the development quality grade of the reservoir; among them, the reservoir production data analysis model is trained for a machine learning model based on the production data of historical reservoirs and the corresponding development quality grades; referring to Table 1, the production data of the reservoir includes: the recovery degree of recoverable reserves during the stable production period, the energy maintenance level data and the energy utilization degree data, the oil production rate of remaining recoverable reserves, the comprehensive decline rate of oil production, the water cut increase rate, the effective rate of measures for old wells, the comprehensive production time rate of oil production and injection wells, the water injection utilization rate, the water drive index, the injection allocation completion rate, etc., and the oil production rate of remaining recoverable reserves and the comprehensive decline rate of oil production can be further divided into three scenarios: the recovery degree of recoverable reserves is less than 50%, the recovery degree of recoverable reserves is between 50% and 80%, and the recovery degree of recoverable reserves is greater than 80%. According to Table 1, after obtaining the production data of the reservoir, the development quality grade corresponding to each production data of the reservoir can be determined.

[0046] In one embodiment of the present invention, the recovery degree of recoverable reserves during the stable production period, the energy maintenance level, the energy utilization degree, the oil production rate of remaining recoverable reserves, the comprehensive decline rate of (annual) oil production, the water cut increase rate, the effective rate of measures for old wells, the comprehensive production time rate of oil production and injection wells, the water injection utilization rate, the water drive index, and the injection allocation completion rate in Table 1 are all single production data indicators, which can be calculated and statistically analyzed through the production dynamic data of the reservoir. The specific values corresponding to healthy, sub-healthy, and diseased are used as the reference values of the production data indicators to divide the grades.

[0047] Table 1

[0048]

[0049] In one embodiment of the present invention, in the production data analysis at the reservoir scale, item 3 and item 4 in Table 1 are type 1 production data, item 6, item 7, and item 10 are type 2 production data, and the remaining items are type 3 production data. Among the type 1 production data, 2 items meeting the health standards can be used for health diagnosis, 1 item is sub-healthy, 1 item for health or disease determination is identified as sub-healthy, and 2 items for disease can be used for disease diagnosis; among the type 2 indicators, 2 items reaching the health level can be used for health diagnosis, 1 sub-healthy item can be used for sub-healthy diagnosis, and 2 disease-level items can be used for disease diagnosis; among the type 3 indicators, 3 items reaching the health level are for health diagnosis, 2 sub-healthy items are for sub-healthy diagnosis, and 3 disease items are for disease diagnosis. Through the overall analysis of the 3 types of production data and 10 production data indicators, referring to Table 2, for health diagnosis, it requires "2 + 2 + 3" and above, for sub-healthy diagnosis, it requires between "2 + 2 + 3 to 1 + 1 + 2" and between "1 + 2 + 2 to 2 + 2 + 3", and for disease diagnosis, it requires below "2 + 2 + 3". The development quality grade (health status grade) of the reservoir can be qualitatively diagnosed for the healthy, sub-healthy, and disease states of the reservoir. Table 2 also lists the quantitative calculation method of the specific development quality score (health status score). The score of a single data indicator is 100 points. The score of a health indicator is greater than or equal to 80 points, the score of a sub-healthy indicator is between 60 - 79 points, and the score of a disease indicator is less than or equal to 59 points. The calculation method is as follows:

[0050] When the single production data calculation meets the health indicators in Table 1:

[0051] Development quality score = 80 + (production data indicator - indicator reference value in Table 1) / indicator reference value in Table 1 × 20

[0052] When the single production data calculation meets the sub-healthy indicators in Table 1:

[0053] Development quality score = 60 + (production data indicator - indicator reference value in Table 1) / indicator reference value in Table 1 × 20

[0054] When the single development indicator calculation meets the disease indicators in Table 1:

[0055] Development quality score = 40 + (production data indicator - indicator reference value in Table 1) / indicator reference value in Table 1 × 20

[0056] The weight coefficient is given according to the importance of the production data. Referring to Table 2, the weight coefficient of type 1 production data is 60%, with n1 items, the weight coefficient of type 2 production data is 15%, with n2 items, and the weight coefficient of type 3 production data is 25%, with n3 items. The calculation formula is as follows:

[0057] The development quality score of Class 1 production data = the development quality score of Production Data 1 (comprehensive decline rate of oil production) × 60% / n1 + the development quality score of Production Data 2 (annual water cut increase rate) × 60% / n1;

[0058] The development quality score of Class 2 production data = the development quality score of Production Data 1 (effective rate of old well measures) × 15% / n2 + the development quality score of Production Data 2 (comprehensive production time rate of oil and water wells) × 15% / n2 + the development quality score of Production Data 3 (completion rate of injection allocation) × 15% / n2;

[0059] The development quality score of Class 3 production data = the development quality score of Production Data 1 (recovery degree of recoverable reserves during the stable production period) × 25% / n3 + the development quality score of Production Data 2 (energy maintenance level and energy utilization degree) × 25% / n3 + the development quality score of Production Data 3 (oil production rate of remaining recoverable reserves) × 25% / n3 + the development quality score of Production Data 4 (water injection utilization rate) × 25% / n3 + the development quality score of Production Data 5 (water drive index) × 25% / n3.

[0060] The calculation of the reservoir health index is shown in the following formula:

[0061] The development quality score of the reservoir = the development quality score of Class 1 production data + the development quality score of Class 2 production data + the development quality score of Class 3 production data;

[0062] In the formula: n1 represents the number of Class 1 production data; n2 represents the number of Class 2 production data, which is an integer; n3 represents the number of Class 3 production data.

[0063] Table 2

[0064]

[0065]

[0066] In an embodiment of the present invention, the production data of each reservoir block is input into the first production data analysis model to determine the development quality grade of each reservoir block; wherein, the first production data analysis model is trained on a machine learning model based on the production data of historical reservoir blocks and the corresponding development quality grades; the development quality grade is an index used to measure the development effect of the reservoir and oil and water wells.

[0067] In an embodiment of the present invention, before inputting the production data of each reservoir block into the first production data analysis model, it further includes:

[0068] Classifying the production data of each reservoir block according to a preset importance level; wherein, the preset importance level is set according to the influence degree of the production data of the reservoir block on the development quality grade of the reservoir block;

[0069] According to the classification results, determine the preset weight coefficients corresponding to the production data of each type of reservoir block.

[0070] Use the preset weight coefficients corresponding to the production data of each type of reservoir block to correct the production data of each reservoir block.

[0071] In an embodiment of the present invention, before inputting the production data of each reservoir block into the first production data analysis model, it further includes:

[0072] Perform normalization processing on the production data of each reservoir block.

[0073] In an embodiment of the present invention, the production data of each reservoir block includes at least two or more of the comprehensive production decline rate of oil production, the water cut rising rate, the comprehensive production time rate of oil and water wells, the injection allocation completion rate, the oil production rate value of remaining recoverable reserves, the water injection utilization rate, the water drive index, the energy maintenance level data, and the energy utilization degree data, and any combination thereof.

[0074] During specific implementation, the reservoir is also divided into blocks for management on the plane. After the health assessment and diagnosis of the reservoir, it is necessary to be specific to the blocks to screen out the health levels of each block in the reservoir development quality grade. Compared with determining the development quality grade of the reservoir, when determining the development quality grade of each reservoir block, the recoverable reserve production degree during the stable production period and the effective rate of old well measures are removed. Referring to Table 3, usually these two indicators are used as evaluation indicators at the oilfield or reservoir scale. In addition, due to the boundary flow and reserve splitting between blocks, these two indicators may not be used as indicators for determining the development quality grade of blocks.

[0075] Table 3

[0076]

[0077]

[0078] During specific implementation, when there are 2 healthy items in type 1 production data + 1 healthy item in type 2 production data + 2 healthy items in type 3 production data, it can be diagnosed as healthy. When there are 2 diseased items in type 1 production data + 2 diseased items in type 2 production data + 2 or less than 2 diseased items in type 3 production data, it can be diagnosed as a disease of the reservoir block. In other cases, it is in a sub - healthy state. Table 4 also lists the specific quantitative calculation method of the development quality score (health status score) of the reservoir block. The calculation method is the same as that of the development quality score of the reservoir. The calculation of the development quality score (health status score) of the block is shown in the following formula:

[0079] The development quality score of the reservoir block = the development quality score of type 1 production data + the development quality score of type 2 production data + the development quality score of type 3 production data.

[0080] Table 4

[0081]

[0082] The present invention can determine the development quality grade of the reservoir and clarify the indicators of the healthy, sub-healthy and diseased states. At the same time, it can quickly lock which reservoir block the indicators of the sub-healthy and diseased states come from. The reservoir blocks with different sub-healthy or diseased states can be ranked or the treatment priority levels can be considered according to the development quality scores of the reservoir blocks.

[0083] In an embodiment of the present invention, the reservoir blocks of the target development quality grade are divided into multiple main control factor units, and the production data of each main control factor unit is screened out from the production data of the reservoir blocks of the target development quality grade; wherein, the main control factor units include: high-permeability layer, fracture zone, high-viscosity oil area, bottom water, edge water, asphalt mat, one or any combination thereof; the production data of each main control factor unit is input into the second production data analysis model to determine the development quality grade of each main control factor unit; wherein, the second production data analysis model is obtained by training a machine learning model based on the production data of the historical main control factor units and the corresponding development quality grades.

[0084] During specific implementation, before inputting the production data of each main control factor unit into the second production data analysis model, it further includes:

[0085] According to the classification results, determine the preset weight coefficients corresponding to the production data of each type of main control factor unit;

[0086] Use the preset weight coefficients corresponding to the production data of each type of main control factor unit to correct the production data of each main control factor unit.

[0087] In one embodiment of the present invention, the sub-healthy and disease states of the development quality level are mainly restricted by the physical properties of the geological reservoir itself, the production methods and systems, and management factors. In the process of this data analysis, it is also necessary to clarify the reasons for the sub-health and diseases of the indicators. The present invention introduces a main control factor unit for analysis. Referring to Table 5, the main control factor unit includes: high-permeability layer, fracture zone, high-viscosity oil area, bottom water, edge water, asphalt pad, etc. For example, in the case of the fracture zone and bottom water, under this main control factor, the energy maintenance level, energy utilization degree, and water cut increase rate are not the production data focused on analysis; at the same time, the oil production rate of the remaining recoverable reserves is not used as an index for production data analysis either. The main reason is that there is oil-water flow between different well groups, which will lead to inaccurate data analysis of this main control factor unit. When the index ratio of type 1 production data + type 2 production data + type 3 production data of different main control factor units is greater than 62.5%, it is diagnosed that the main control factor unit is healthy; when the healthy production data index ratio is less than 62.5% and the sub-healthy production data index ratio is higher than 37.5%, it is diagnosed that the main control factor unit is sub-healthy; when the disease production data index ratio is greater than or equal to 75%, it is diagnosed that the main control factor unit has a disease. When calculating the development quality score of each main control factor unit, the calculation method is the same as that for calculating the development quality score (healthy state score) of the reservoir.

[0088] Table 5

[0089]

[0090]

[0091] In one embodiment of the present invention, the production data of each oil well and the water injection data of each water well in the main control factor unit of the target development quality level are obtained; the production data of each oil well is input into the third production data analysis model to determine the development quality level of each oil well; the water injection data of each water well is input into the water injection data analysis model to determine the development quality level of each water well; wherein, the third production data analysis model is obtained by training a machine learning model based on the production data of historical oil wells and the corresponding development quality levels; the water injection data analysis model is obtained by training a machine learning model based on the water injection data of historical water wells and the corresponding development quality levels.

[0092] In one embodiment of the present invention, the production data of each oil well includes: production dynamic characteristic data, development index data, and production change data; wherein, the production dynamic characteristic data includes: any one or any combination of the oil production decline rate, water cut increase rate, and pressure recovery speed value; the development index data includes: any one or any combination of the water injection utilization rate, water drive index, and recovery degree value; the production change data includes: any one or any combination of the liquid production change value, oil production change value, water cut change value, pressure change value, and injection-production ratio change value;

[0093] The water injection data of each well includes: one or any combination of injection allocation completion rate, wellhead pressure, and apparent water absorption index.

[0094] In specific implementation, a corresponding relationship is established between the main control factor units and oil and water wells. There will also be a small number of sub-healthy and disease well groups in the healthy main control factor units, more sub-healthy well groups in the sub-healthy main control factor units, and the most disease well groups in the disease main control factor units. In a sorted manner, priority is given to the oil and water wells classified into the main control factor units with diseases and low development quality scores, followed by the oil and water wells classified into the main control factor units in the sub-healthy area and the main control factor units with medium development quality scores, and finally the oil and water wells classified into the main control factor units in the healthy area and the main control factor units with high development quality scores. First, for oil wells, three levels of health, sub-health, and disease are diagnosed from the dynamic characteristic indicators and development index data, and compared with the production data changes of the previous month. Referring to Table 6, the production dynamic characteristic data includes: monthly production decline rate, monthly water cut increase rate, pressure recovery speed, and monthly injection-production ratio, and the development index data: recovery factor - water cut increase, water injection utilization rate, and water drive index; the production change data (i.e., the production data compared with the previous month) includes: monthly liquid production change, monthly oil production change, monthly water cut change, monthly pressure change, monthly injection-production ratio change, and pump condition change.

[0095] Table 6

[0096]

[0097]

[0098] In an embodiment of the present invention, the quantitative calculation weight coefficients of the development quality scores (health status scores) of oil wells are also listed in Table 6. The scores of individual data indicators are all 100 points. The score of the health indicator is greater than or equal to 80 points, the score of the sub-health indicator is between 60 - 79 points, and the score of the disease indicator is less than or equal to 59 points; the embodiment of the present invention can determine the development quality score of the oil well, that is, the health status score, according to the production dynamic characteristic data, development index data, production change data of the oil well, and the corresponding preset weight coefficients.

[0099] In the present invention, the water injection data of water wells is less than the production data of oil wells. Referring to Table 7, it includes: injection allocation completion rate, wellhead pressure, apparent water absorption index, and Hall curve (Hall-plot). In specific implementation, the development quality grade (i.e., the health status grade) of the water injection well is determined through 4 items of water injection data, and targeted suggestions and measures are proposed for the problem water wells. Among them, the Hall curve (Hall-plot) is the Hall curve method for evaluating water injection wells in water injection oilfields proposed by Hall, using the Hall integral term It has a linear relationship with the cumulative injection volume Wt on the rectangular coordinates, and the change in the slope of this curve can be used to judge the change in the injection capacity of the water well.

[0100] In specific implementation, according to the water injection data of the water well and the corresponding preset weight coefficients, the development quality score of the water well, that is, the health status score, is determined.

[0101] Table 7

[0102]

[0103]

[0104] Figure 2 It is a specific example diagram of the production data analysis method for the reservoir and oil and water wells in the embodiment of the present invention.

[0105] The embodiment of the present invention can implement the development quality analysis method process of reservoir - block - main control factor unit - oil and water wells. Refer to Figure 2 , and data analysis is carried out through three dimensions of production data and development quality grading (health status level). A preset weight value is assigned to the same data dimension, and the highest score in each data dimension is 100 points (healthy, sub - healthy, diseased), that is, in each dimension, the development quality score is calculated by comparing with the reference boundary value or the number of indicators to determine the development quality level of each production data, and the level in this production data can also be seen from the development quality score, so as to compare with other production data. After data analysis, a diagnosis report and score are given, and a health management file for the reservoir, block, main control factor unit and oil and water wells is established. For the healthy, sub - healthy and diseased states, they are respectively marked with green, orange and red. For the specific problems of diseased and sub - healthy oil and water wells, a comprehensive analysis of typical wells is carried out, and specific implementation suggestions in aspects such as injection - production system and technological measures are put forward. The oil and water wells are tracked and analyzed on a weekly basis, and the effectiveness of the treatment is evaluated by monthly updating and the entire process of return visit analysis. When the diseased and sub - healthy oil and water wells are treated, the proportion of wells with this development quality level will also decrease accordingly, and the proportion of wells in the healthy dimension will increase. The indicators of the main control factor unit, block and reservoir will show a trend of improvement, which will be reflected in the monthly assessment, and the score will increase in the short term. Medium - and long - term treatment will make adjustments in the dimension, such as recovering from diseased to sub - healthy and then to healthy, and the health score increasing from 60 points to 80 points, etc. The production data analysis method process for the reservoir and oil and water wells provided by the present invention is crucial for the health management and optimization adjustment of carbonate rocks, and can gradually improve the oilfield development effect, enhance the oil displacement efficiency and recovery rate.

[0106] Figure 3 、 Figure 4 It is a specific example diagram of the production data analysis method for the reservoir and oil and water wells in the embodiment of the present invention.

[0107] The production data analysis method for the reservoir and oil production and injection wells of the present invention can be applied to a carbonate reservoir in a certain oilfield. Figure 3 It represents the health assessment (development quality analysis) and treatment process of the carbonate reservoir. Figure 4 It represents the division of blocks and main control factor units on the plane of a reservoir. The main control factors are divided into 5 types, and the main control factor units are divided into 11 according to the region. Table 8 shows the actual values of various production data of a reservoir. Through production data analysis, among the type 1 production data, 2 are in a healthy level, among the type 2 production data, 2 are in a healthy level, and among the type 3 production data, only 1 is in a healthy level. The reservoir can be diagnosed as sub-healthy. Among them, the recovery degree of recoverable reserves during the stable production period, the energy maintenance level and energy utilization degree, the comprehensive production rate of oil production and injection wells, the water injection utilization rate, and the water drive index are all in a sub-healthy level. This also shows that the water injection development effect in the current development of this reservoir is still at a medium level. According to the calculation method of the development quality score, this reservoir is in a sub-healthy state with a value of 71.7 points.

[0108] Table 8

[0109]

[0110] The sum scores of the above-mentioned 3 blocks of the reservoir refer to Table 9. Blocks 1 and 2 are in a sub-healthy state, and the health state scores are 88.2 and 88.9 respectively. The main indicators of the disease state are: the energy maintenance level and energy utilization degree, and the comprehensive production rate of oil production and injection wells. The sub-healthy indicators are: the water injection utilization rate and the water drive index, indicating that there are still situations of low pressure maintenance degree and low well opening rate of oil production and injection wells in these two blocks. At the same time, there is still room for further improvement in the water drive development effect; Block 4 is in a healthy level, and the sub-healthy indicators are: the comprehensive production rate of oil production and injection wells, the water injection utilization rate, and the water drive index, indicating that the well opening rate of oil production and injection wells is not high, and the water injection utilization rate and the water drive index are on the low side, and the production management and water injection effect need to be further improved.

[0111] Table 9

[0112]

[0113]

[0114] Table 10 shows the development quality grades and scores of different main control factor units. The health of different main control factor units is closely related to the influence of the main control factors on water injection effectiveness. The high-permeability layer and the fracture zone in Block 2 are both healthy, the fracture zone in Block 4 is healthy, and other areas are all in a sub-healthy state. Classify and conduct a health diagnosis on the effects of the producing oil wells. The number of producing wells is 107, the number of healthy wells is 23, the number of sub-healthy wells is 51, and the number of diseased wells is 33. The 33 diseased wells are basically oil wells with a water cut exceeding 80%, mainly located in the main control factor areas of the high-permeability layer and the fracture zone, and the horizontal well trajectory passes through a relatively high proportion of the high-permeability layer, resulting in a longer flooded section.

[0115] Table 10

[0116]

[0117]

[0118] Figure 5 、 Figure 6 、 Figure 7 are specific example diagrams of the production data analysis method for the reservoir and oil production and injection wells in the embodiments of the present invention.

[0119] In an embodiment of the present invention, the development quality grade of the injection well is judged through the injection data of the well, referring to Figure 5 and Figure 6 , adding the Hall-plot curve (Hall curve), wellhead pressure and actual injection volume diagnosis. Figure 7 shows the change of the water cut rising rate of the reservoir, thereby giving Table 11 to determine the development quality grade (health status grade) of the injection well. The numbers of healthy injection wells include: AD4-6-2H, AD4-8-3H, AD4-10-2H, AD4-20-1H and AD4-20-2H. The numbers of sub-healthy injection wells include: AD4-10-5H. The numbers of diseased injection wells include: AD4-8-2H, AD4-16-3H.

[0120] Table 11

[0121]

[0122]

[0123] Table 12 shows the production data analysis results of a certain month of a reservoir. Table 12 gives the number of diseased oil production and injection wells. At the same time, corresponding adjustment and measure suggestions are put forward for these diseases. A healthy return visit system is established. The oil wells with a water cut greater than 80% are the 33 diseased wells screened out in Table 12. Through screening evaluation, treatment and return visits, the number of diseased wells is reduced to 15 by 2022, and the production data of the reservoir gradually improves, and the health level rises significantly.

[0124] Table 12

[0125]

[0126] It should be noted that although the operations of the method of the present invention are described in a specific order in the above embodiments and accompanying drawings, this does not require or imply that these operations must be performed in this specific order, or that all the shown operations must be performed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution.

[0127] The implementation of the production data analysis device for the reservoir and oil and water wells can refer to the implementation of the above method, and the repeated parts will not be elaborated here. The terms "module" or "unit" used hereinafter can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0128] Based on the same inventive concept, the present invention also provides a production data analysis device for a reservoir and oil and water wells, as Figure 8 shown, the device includes:

[0129] A first data acquisition module 801, configured to acquire production data of each reservoir block; wherein, the reservoir block is obtained by dividing the reservoir according to a preset block;

[0130] A first data analysis module 802, configured to input the production data of each reservoir block into a first production data analysis model to determine the development quality level of each reservoir block; wherein, the first production data analysis model is trained on a machine learning model according to the production data of historical reservoir blocks and the corresponding development quality levels; the development quality level is an index for measuring the development effect of the reservoir and oil and water wells;

[0131] A reservoir block division module 803, configured to divide the reservoir blocks with the target development quality level into multiple main control factor units, and screen out the production data of each main control factor unit from the production data of the reservoir blocks with the target development quality level; wherein, the main control factor unit includes one or any combination of: high permeability layer, fracture zone, high viscosity oil area, bottom water, edge water, asphalt pad;

[0132] A second data analysis module 804, configured to input the production data of each main control factor unit into a second production data analysis model to determine the development quality level of each main control factor unit; wherein, the second production data analysis model is trained on a machine learning model according to the production data of historical main control factor units and the corresponding development quality levels;

[0133] A second data acquisition module 805, configured to acquire the production data of each oil well and the water injection data of the water well in the main control factor unit with the target development quality level;

[0134] A third data analysis module 806 is configured to input the production data of each oil well into a third production data analysis model to determine the development quality grade of each oil well; and input the water injection data of each water well into a water injection data analysis model to determine the development quality grade of each water well. The third production data analysis model is obtained by training a machine learning model based on the production data of historical oil wells and their corresponding development quality grades. The water injection data analysis model is obtained by training a machine learning model based on the water injection data of historical water wells and their corresponding development quality grades.

[0135] In an embodiment of the present invention, it further includes:

[0136] A data classification module is configured to classify the production data of each reservoir block according to a preset importance level before inputting the production data of each reservoir block into a first production data analysis model. The preset importance level is set according to the influence of the production data of the reservoir block on the development quality grade of the reservoir block.

[0137] A first weight coefficient determination module is configured to determine a preset weight coefficient corresponding to the production data of each reservoir block according to the classification result.

[0138] A first data correction module is configured to correct the normalized production data of each reservoir block by using the preset weight coefficient corresponding to the production data of each reservoir block.

[0139] In an embodiment of the present invention, it further includes:

[0140] A second weight coefficient determination module is configured to determine a preset weight coefficient corresponding to the production data of each type of main control factor unit according to the classification result before inputting the production data of each main control factor unit into a second production data analysis model.

[0141] A second data correction module is configured to correct the production data of each main control factor unit by using the preset weight coefficient corresponding to the production data of each type of main control factor unit.

[0142] In an embodiment of the present invention, it further includes:

[0143] A normalization processing module is configured to perform normalization processing on the production data of each reservoir block before inputting the production data of each reservoir block into a first production data analysis model.

[0144] In an embodiment of the present invention, the production data of each reservoir block includes at least two or any combination of two or more of the comprehensive production decline rate of oil production, water cut increase rate, comprehensive production time rate of oil and water wells, injection completion rate, oil production rate value of remaining recoverable reserves, water injection utilization rate, water drive index, energy maintenance level data, and energy utilization degree data.

[0145] In an embodiment of the present invention, the production data of each oil well includes: production dynamic characteristic data, development index data, and production change data; wherein, the production dynamic characteristic data includes: any one or any combination of the production oil decline rate, the water cut rising rate, and the pressure recovery speed value; the development index data includes: any one or any combination of the water injection utilization rate, the water drive index, and the recovery degree value; the production change data includes: any one or any combination of the liquid production change value, the oil production change value, the water cut change value, the pressure change value, and the injection-production ratio change value;

[0146] The water injection data of each water well includes: any one or any combination of the injection allocation completion rate, the wellhead pressure, and the apparent water absorption index.

[0147] It should be noted that although several modules of the production data analysis device for the oil reservoir and oil and water wells are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present invention, the features and functions of two or more of the above-described modules can be embodied in one module. Conversely, the features and functions of one module described above can be further divided and embodied by multiple modules.

[0148] Based on the foregoing inventive concept, as Figure 9 shown, the present invention also proposes a computer device 900, including a memory 901, a processor 902, and a computer program 903 stored on the memory 901 and executable on the processor 902. When the processor 902 executes the computer program 903, the foregoing production data analysis method for the oil reservoir and oil and water wells is implemented.

[0149] Based on the foregoing inventive concept, the present invention proposes a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the foregoing production data analysis method for the oil reservoir and oil and water wells is implemented.

[0150] Based on the foregoing inventive concept, the present invention proposes a computer program product, which includes a computer program, and when the computer program is executed by a processor, the production data analysis method for the oil reservoir and oil and water wells is implemented.

[0151] In an embodiment of the present invention, production data of each reservoir block is obtained; wherein, the reservoir block is obtained by dividing the reservoir according to a preset block; the production data of each reservoir block is input into a first production data analysis model to determine the development quality level of each reservoir block; wherein, the first production data analysis model is obtained by training a machine learning model based on the production data of historical reservoir blocks and the corresponding development quality levels; the development quality level is an index for measuring the development effect of the reservoir and oil and water wells; the reservoir blocks with the target development quality level are divided into multiple main control factor units, and the production data of each main control factor unit is screened out from the production data of the reservoir blocks with the target development quality level; wherein, the main control factor unit includes one or any combination of the following: high permeability layer, fracture zone, high viscosity oil area, bottom water, edge water, asphalt mat; the production data of each main control factor unit is input into a second production data analysis model to determine the development quality level of each main control factor unit; wherein, the second production data analysis model is obtained by training a machine learning model based on the production data of historical main control factor units and the corresponding development quality levels; the production data of each oil well and the water injection data of each water well in the main control factor unit with the target development quality level are obtained; the production data of each oil well is input into a third production data analysis model to determine the development quality level of each oil well; the water injection data of each water well is input into a water injection data analysis model to determine the development quality level of each water well; wherein, the third production data analysis model is obtained by training a machine learning model based on the production data of historical oil wells and the corresponding development quality levels; the water injection data analysis model is obtained by training a machine learning model based on the water injection data of historical water wells and the corresponding development quality levels. The embodiment of the present invention can automatically analyze the production data of the reservoir and oil and water wells, timely determine the reservoir blocks and oil and water wells that do not meet the development quality level, enable production management personnel to timely master the development quality of the reservoir and oil and water wells, and provide technical support for improving the production management of the reservoir and oil and water wells.

[0152] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0153] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one or more flows Figure 1 one or more flows and / or blocks Figure 1 or means for implementing the functions specified in one or more blocks.

[0154] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means for implementing the functions specified in one or more flows Figure 1 one or more flows and / or blocks Figure 1 or means for implementing the functions specified in one or more blocks.

[0155] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more flows Figure 1 one or more flows and / or blocks Figure 1 or means for implementing the functions specified in one or more blocks.

[0156] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for analyzing production data of an oil reservoir and oil production and injection wells, characterized in that, Including: Obtain the production data of each reservoir block; wherein, the reservoir block is obtained by dividing the reservoir according to a preset block division; Input the production data of each reservoir block into the first production data analysis model to determine the development quality grade of each reservoir block; wherein, the first production data analysis model is obtained by training a machine learning model based on the production data of historical reservoir blocks and the corresponding development quality grades; the development quality grade is an index used to measure the development effect of the reservoir and oil and water wells; Divide the reservoir blocks with the target development quality grade into multiple main control factor units, and screen out the production data of each main control factor unit from the production data of the reservoir blocks with the target development quality grade; wherein, the main control factor units include: one or any combination of high permeability layers, fracture zones, high viscosity oil areas, bottom water, edge water, and asphalt pads; Input the production data of each main control factor unit into the second production data analysis model to determine the development quality grade of each main control factor unit; wherein, the second production data analysis model is obtained by training a machine learning model based on the production data of historical main control factor units and the corresponding development quality grades; Obtain the production data of each oil well and the water injection data of each water well in the main control factor units with the target development quality grade; Input the production data of each oil well into the third production data analysis model to determine the development quality grade of each oil well; input the water injection data of each water well into the water injection data analysis model to determine the development quality grade of each water well; wherein, the third production data analysis model is obtained by training a machine learning model based on the production data of historical oil wells and the corresponding development quality grades; the water injection data analysis model is obtained by training a machine learning model based on the water injection data of historical water wells and the corresponding development quality grades.

2. The method according to claim 1, characterized in that, Before inputting the production data of each reservoir block into the first production data analysis model, it further includes: Classify the production data of each reservoir block according to a preset importance level; wherein, the preset importance level is set according to the influence degree of the production data of the reservoir block on the development quality grade of the reservoir block; According to the classification result, determine the preset weight coefficient corresponding to the production data of each type of reservoir block; Use the preset weight coefficient corresponding to the production data of each type of reservoir block to correct the production data of each reservoir block.

3. The method according to claim 2, characterized in that, Before inputting the production data of each main control factor unit into the second production data analysis model, it further includes: According to the classification result, determine the preset weight coefficient corresponding to the production data of each type of main control factor unit; Use the preset weight coefficient corresponding to the production data of each type of main control factor unit to correct the production data of each main control factor unit.

4. The method according to claim 1, characterized in that, Before inputting the production data of each reservoir block into the first production data analysis model, it further includes: Normalize the production data of each reservoir block.

5. The method according to claim 1, characterized in that, The production data of each reservoir block includes at least two or more arbitrary combinations of the comprehensive production decline rate of oil production, the water cut rising rate, the comprehensive production time rate of oil and water wells, the injection completion rate, the oil production rate of remaining recoverable reserves, the water injection utilization rate, the water drive index, the energy maintenance level data, and the energy utilization degree data.

6. The method according to claim 1, characterized in that, The production data of each oil well includes: production dynamic characteristic data, development index data, and production change data; among them, the production dynamic characteristic data includes: any one or any combination of the production oil decline rate, water cut increase rate, and pressure recovery speed value; the development index data includes: any one or any combination of the water injection utilization rate, water drive index, and recovery degree value; the production change data includes: any one or any combination of the liquid production change value, production oil change value, water cut change value, pressure change value, and injection-production ratio change value; The water injection data of each water well includes: any one or any combination of the injection allocation completion rate, wellhead pressure, and apparent water absorption index.

7. An apparatus for analyzing production data of an oil reservoir and oil production and injection wells, characterized in that, Including: The first data acquisition module is used to acquire the production data of each reservoir block; among them, the reservoir block is obtained by dividing the reservoir according to a preset block. The first data analysis module is used to input the production data of each reservoir block into the first production data analysis model to determine the development quality grade of each reservoir block; among them, the first production data analysis model is trained on a machine learning model based on the production data of historical reservoir blocks and the corresponding development quality grades; the development quality grade is an index used to measure the development effect of the reservoir and oil and water wells. The reservoir block division module is used to divide the reservoir blocks of the target development quality grade into multiple main control factor units, and screen out the production data of each main control factor unit from the production data of the reservoir blocks of the target development quality grade; among them, the main control factor units include: any one or any combination of high permeability layers, fracture zones, high viscosity oil areas, bottom water, edge water, and asphalt pads. The second data analysis module is used to input the production data of each main control factor unit into the second production data analysis model to determine the development quality grade of each main control factor unit; among them, the second production data analysis model is trained on a machine learning model based on the production data of historical main control factor units and the corresponding development quality grades. The second data acquisition module is used to acquire the production data of each oil well and the water injection data of the water well in each main control factor unit of the target development quality grade. The third data analysis module is used to input the production data of each oil well into the third production data analysis model to determine the development quality grade of each oil well; input the water injection data of each water well into the water injection data analysis model to determine the development quality grade of each water well; among them, the third production data analysis model is trained on a machine learning model based on the production data of historical oil wells and the corresponding development quality grades; the water injection data analysis model is trained on a machine learning model based on the water injection data of historical water wells and the corresponding development quality grades.

8. The apparatus according to claim 7, characterized in that, It also includes: The data classification module is used to classify the production data of each reservoir block according to a preset importance level before inputting the production data of each reservoir block into the first production data analysis model; among them, the preset importance level is set according to the influence of the production data of the reservoir block on the development quality grade of the reservoir block. The first weight coefficient determination module is used to determine the preset weight coefficient corresponding to the production data of each reservoir block according to the classification result. The first data correction module is used to correct the normalized production data of each reservoir block by using the preset weight coefficients corresponding to the production data of each reservoir block.

9. The apparatus according to claim 8, characterized in that, It further includes: The second weight coefficient determination module is used to determine the preset weight coefficients corresponding to the production data of each type of main control factor unit according to the classification results before inputting the production data of each main control factor unit into the second production data analysis model; The second data correction module is used to correct the production data of each main control factor unit by using the preset weight coefficients corresponding to the production data of each type of main control factor unit.

10. The device according to claim 7, wherein, It further includes: The normalization processing module is used to perform normalization processing on the production data of each reservoir block before inputting the production data of each reservoir block into the first production data analysis model.

11. The device according to claim 7, wherein, The production data of each reservoir block includes at least two or more of the following: comprehensive production decline rate of oil production, water cut increase rate, comprehensive production time rate of oil and water wells, injection allocation completion rate, oil production rate of remaining recoverable reserves, water injection utilization rate, water drive index, energy maintenance level data, and energy utilization degree data, and any combination thereof.

12. The device according to claim 7, wherein, The production data of each oil well includes: production dynamic characteristic data, development index data, production change data; among them, the production dynamic characteristic data includes: any one or combination of oil production decline rate, water cut increase rate, and pressure recovery speed value; the development index data includes: any one or combination of water injection utilization rate, water drive index, and recovery degree value; the production change data includes: any one or combination of liquid production change value, oil production change value, water cut change value, pressure change value, and injection-production ratio change value. The water injection data of each water well includes: any one or combination of injection allocation completion rate, wellhead pressure, and apparent water absorption index.

13. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, When the processor executes the computer program, it implements the method according to any one of claims 1 to 6.

14. A computer-readable storage medium, wherein, The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, it implements the method according to any one of claims 1 to 6.

15. A computer program product, wherein, The computer program product includes a computer program, and when the computer program is executed by the processor, it implements the method according to any one of claims 1 to 6.

Images