Method and device for dividing and processing oilfield development stages

Abstract

The present invention discloses a method and device for dividing and processing oilfield development stages, wherein the method comprises: obtaining development mode data, well network change data, stratum change data and production change data from oilfield development history data; drawing multiple curves of preset types according to the development mode data, well network change data, stratum change data and production change data; searching each curve and determining the turning point of each curve; clustering the turning points of all curves to obtain the center point of each cluster turning point as the defining point of the oilfield development stage; dividing and processing the oilfield development stage according to multiple defining points. The present invention can improve the efficiency and rationality of the division of oilfield development stages, and has a scientific guiding significance for the research on oil and gas development stages.

Description

Technical Field

[0001] The invention relates to the technical field of oilfield development, and in particular to a method and a device for dividing and processing oilfield development stages. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] Oilfield development is a long process, and its production, water content, pressure, gas-oil ratio, oil production rate and other indicators will change during the whole development process. And this change often has a phased characteristic, showing the natural development process of oilfield development from the early stage to the middle stage and then to the late stage. Obviously, it is an important task to divide the entire development process of the oilfield into several appropriate and reasonable development stages according to its own characteristics.

[0004] There are many ways to divide the oilfield development stage, and there is no unified standard so far. However, there are two common division methods: one is mainly based on the change of production; the other is mainly based on the change of water content. Regardless of which method is used, the factors considered are relatively simple, and it requires experienced reservoir engineers to divide according to indicators, which is both rational and inefficient. Summary of the invention

[0005] An embodiment of the present invention provides a method for dividing oilfield development stages, so as to improve the efficiency and rationality of dividing oilfield development stages. The method includes:

[0006] From the historical data of oilfield development, obtain the development mode data, well pattern change data, formation change data and production change data;

[0007] Draw multiple preset curves based on development method data, well pattern change data, layer change data and production change data;

[0008] Search each curve and determine the turning point of each curve;

[0009] Perform cluster analysis on the turning points of all curves, and obtain the center point of each cluster turning point as the defining point of the oilfield development stage;

[0010] The oilfield development phases are divided and processed based on multiple defining points.

[0011] The embodiment of the present invention further provides a device for processing the division of oilfield development stages, which is used to improve the efficiency and rationality of the division of oilfield development stages. The device includes:

[0012] An acquisition unit is used to obtain development mode data, well pattern change data, layer change data and production change data from the oilfield development history data;

[0013] A drawing unit, used to draw multiple preset curves according to development mode data, well pattern change data, layer change data and production change data;

[0014] A turning point determination unit, used for searching each curve and determining the turning point of each curve;

[0015] The defining point determination unit is used to perform cluster analysis on the turning points of all curves and obtain the center point of each cluster turning point as the defining point of the oilfield development stage;

[0016] The processing unit is used to divide the oil field development stages into processing stages according to a plurality of defined points.

[0017] An embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for dividing and processing oilfield development stages when executing the computer program.

[0018] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program for executing the above-mentioned method for dividing and processing oilfield development stages.

[0019] In the embodiment of the present invention, the division and processing scheme of the oilfield development stage is compared with the technical scheme in the prior art that considers relatively simple factors and requires experienced reservoir engineers to divide according to indicators. The scheme includes: obtaining development mode data, well network change data, formation change data and production change data from the historical data of oilfield development; drawing multiple curves of preset types according to the development mode data, well network change data, formation change data and production change data; searching each curve to determine the turning point of each curve; performing cluster analysis on the turning points of all curves to obtain the center point of each cluster turning point as the defining point of the oilfield development stage; and dividing and processing the oilfield development stage according to multiple defining points, thereby improving the efficiency and rationality of the oilfield development stage division and providing scientific guidance for the research on oil and gas development stages. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0021] Figure 1 Schematic diagram of a process for dividing and processing oilfield development stages in an embodiment of the present invention;

[0022] Figure 2-1 This is a schematic diagram of a monthly water injection volume variation curve in an embodiment of the present invention;

[0023] Figure 2-2 Schematic diagram of the total well number change curve in the embodiment of the present invention;

[0024] Figure 2-3 This is a schematic diagram of a monthly oil production variation curve in an embodiment of the present invention;

[0025] Figure 2-4 It is a schematic diagram of the layer system change curve in the embodiment of the present invention;

[0026] Figure 3-1 This is a schematic diagram of a monthly water injection volume variation curve (after two smoothings) in an embodiment of the present invention;

[0027] Figure 3-2 Schematic diagram of the total well number change curve (after smoothing) in an embodiment of the present invention;

[0028] Figure 3-3 This is a schematic diagram of the monthly oil production variation curve (after two smoothings) in the embodiment of the present invention;

[0029] Figure 3-4 Schematic diagram of layer change curve (after smoothing) in an embodiment of the present invention;

[0030] Figure 4-1 to Figure 4-6 is an illustration of the Douglas-Peucker algorithm in an embodiment of the present invention;

[0031] Figure 5-1 This is a cluster analysis diagram of turning points in an embodiment of the present invention (before analysis);

[0032] Figure 5-2 It is a cluster analysis diagram (analysis result) of turning points in an embodiment of the present invention;

[0033] Figure 6-1 to Figure 6-4 It is a schematic diagram of monthly water injection, total number of wells, monthly oil production, stratum change curve and final stage division in an embodiment of the present invention;

[0034] Figure 7 It is a structural schematic diagram of the oilfield development stage division processing device in an embodiment of the present invention. DETAILED DESCRIPTION

[0035] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0036] Taking into account the technical problems existing in the prior art, the inventor has proposed a solution for dividing the development stages of oil fields. The solution is a solution for automatically dividing the development stages of oil fields, including: according to the historical data of oil field development, the development methods, well network changes, formations and production changes are divided, and the corresponding curves are drawn; for each curve, necessary smoothing is performed, and then the turning points on the curve are searched; the turning points on all the curves are integrated, and these points are clustered and analyzed on the time axis; the center point of each cluster is the defining point of the development stage; the development stages are divided according to the defining points. The present invention comprehensively considers various factors for manually dividing the development stages of oil fields, automatically calculates the defining points of the development stages, and can greatly improve the efficiency of dividing the development stages of oil fields. The following is a detailed introduction to the solution for dividing the development stages of oil fields.

[0037] Figure 1 FIG. 1 is a flow chart of a method for dividing and processing oilfield development stages in an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0038] Step 101: obtaining development mode data, well pattern change data, layer change data and production change data from the oilfield development history data;

[0039] Step 102: Draw multiple curves of preset types according to the development mode data, well pattern change data, layer change data and production change data;

[0040] Step 103: Search each curve and determine the turning point of each curve;

[0041] Step 104: cluster analysis is performed on the turning points of all the curves, and the center point of each cluster turning point is obtained as the defining point of the oilfield development stage;

[0042] Step 105: Divide the oilfield development stages according to the multiple definition points.

[0043] In one embodiment, the above-mentioned method for dividing the oilfield development stages may further include: studying the oilfield development stages according to the results of dividing the oilfield development stages, and developing the oilfield according to the results of the study.

[0044] In one embodiment, the above-mentioned method for dividing the oilfield development stages may further include: smoothing the drawn multiple curves of preset types to obtain multiple smoothed curves;

[0045] Searching for each curve and determining the turning point of each curve may include: searching for multiple smoothed curves and determining the turning point of each curve.

[0046] In specific implementation, after smoothing the drawn curves of multiple preset types, the turning point of each curve is determined, and the accurate turning point can be obtained, laying the foundation for the precise division of subsequent oilfield development stages.

[0047] In one embodiment, performing smoothing on the drawn multiple preset types of curves to obtain multiple smoothed curves may include:

[0048] The moving average method MA is used to smooth the drawn multiple preset types of curves to obtain multiple smoothed curves.

[0049] In specific implementation, the moving average method MA is used to smooth the drawn multiple preset types of curves, which can obtain better balanced processing results and lay the foundation for the precise division of subsequent oilfield development stages.

[0050] In one embodiment, the above-mentioned method for dividing the oilfield development stages may further include: obtaining the stratum change data according to the following method:

[0051] According to the production situation of each small layer at a preset time, binary coded data is obtained;

[0052] The binary coded data is converted into decimal data to obtain time series data on the layer change as layer change data.

[0053] In specific implementation, the above-mentioned implementation method of obtaining the stratum change data can further improve the efficiency and rationality of the oilfield development stage division process. Specific implementation methods are described in the following embodiments.

[0054] In one embodiment, searching each curve and determining the turning point of each curve may include: using Douglas-Peucker algorithm to determine the turning point of each curve.

[0055] In specific implementation, the Douglas-Peucker algorithm is used to determine the turning point of each curve, and accurate turning points can be obtained, laying the foundation for the precise division of subsequent oilfield development stages.

[0056] In one embodiment, cluster analysis is performed on the turning points of all curves to obtain the center point of each type of turning point as the defining point of the oil field development stage, which can include: using a K-means clustering algorithm to cluster analysis the turning points of all curves to obtain the center point of each type of turning point as the defining point of the oil field development stage.

[0057] In the specific implementation, the K-means clustering algorithm is used to perform cluster analysis on the turning points of all curves, which can obtain the accurate center point, that is, the accurate definition point of the oil field development stage, and thus realize the accurate division of the oil field development stage.

[0058] In order to facilitate understanding of how the present invention is implemented, the following Figure 2-1 to Figure 6-4 , let me give you an example to illustrate this.

[0059] Depend on Figure 1 It can be seen that the division and processing methods of oil field development stages include:

[0060] Step 101: From the historical data of oilfield development, select data closely related to development methods, well pattern changes, formation changes, and production changes.

[0061] The historical data of oilfield development include: oil production, liquid production, water content, water injection, number of oil and water wells, stratum changes, etc. Among them, the data related to the development method include water injection, gas injection, polymer injection, etc.; the data related to the well network change include the number of oil wells, the number of water wells, the ratio of oil to water wells, etc.; the data related to the change of production include indicators such as oil production, liquid production, water content, etc.

[0062] In the embodiment of the present invention, since the oil field is developed by water injection, the data corresponding to the development method is the monthly water injection volume; the well network change is represented by the total number of wells; and the production change is represented by the monthly oil production.

[0063] The change of the layer system is different from other data. It cannot be used directly to draw curves. It needs to be processed and obtained through encoding. The present invention uses binary encoding to process the layer system changes. The encoding method is as follows: Assuming that there are n small layers, at time t, the small layer in production is marked as 1, and the small layer without production is marked as 0. In this way, at each time t, a string of binary coded data with n bits is obtained. The binary data is converted into decimal data to obtain the time series data about the layer system changes. For the layer system changes with 10 small layers, please refer to Table 1.

[0064] Table 1

[0065]

[0066] Step 102: Draw a curve based on various data and perform smoothing on the curve.

[0067] After the four types of data (monthly water injection volume, total number of wells, monthly oil production, and encoded formation data) are obtained in step 101, these data can be plotted into curves. The horizontal axes of these curves are all time.

[0068] Observe whether each curve is smooth, and smooth the curves with "burrs". The "burrs" of the curve refer to the jagged shape of the curve data due to fluctuations. Figure 2-1 to Figure 2-4 As can be seen from the figure, some curves are jagged due to data fluctuations. Therefore, before using them, such curves need to be smoothed. The present invention uses the simple moving average method (MA) for processing. The weights of each element of the simple moving average are equal. The calculation formula of the simple moving average is as follows:

[0069] F t =(A t-1 +A t-2 +A t-3 +…+A t-n ) / n

[0070] Where: F t represents the predicted value of the next period, n represents the number of periods of moving average, A t-1 Indicates the previous actual value, A t-2 , A t-3 and A t-n They represent the actual values ​​of the first two periods, the first three periods, and up to the first n periods respectively.

[0071] If the curve still has "burrs" after smoothing, you can continue to use the moving average method on the previous smoothing result until a satisfactory effect is achieved.

[0072] The moving average method used in the embodiment of the present invention adopts a period of 5, wherein the moving average method is used twice for the monthly water injection and monthly oil production curves. The final smoothed curve is as follows Figure 3-1 to Figure 3-4 shown.

[0073] Step 103: Search for the turning point of each curve and record it.

[0074] Searching for the turning point of a curve is actually to perform data thinning on the curve. A broken line formed by connecting the turning points of the curve in sequence can well replace the original curve. The embodiment of the present invention uses the Douglas-Peuker algorithm to obtain the turning point of the curve.

[0075] The steps of Douglas-Peucker algorithm are as follows:

[0076] Draw a straight line between the first and last points of the curve to be processed, calculate the distance between all the middle points and the straight line, and find the maximum distance value d max , use d max Compared with the thinning threshold:

[0077] If d max<threshold, all the middle points on this curve are discarded;

[0078] If d max ≥threshold, the curve is divided into two parts with this point as the boundary, and the above process is repeated for these two parts of the curve until all points are processed.

[0079] Figure 4-1 to Figure 4-6 This is a schematic diagram of the Douglas-Peucker algorithm. There are 10 points. First, Figure 4-1 As shown in the figure, connect the first and last points to make a straight line. Find the distance between other points and this straight line and find the point with the largest distance. The largest point in the figure is the 9th point. Then, connect the 1st point and the 9th point. Figure 4-2 As shown. Again, find the point with the largest distance from this straight line among points 2-8. The result is that point 7 has the largest distance from this straight line. Figure 4-3 As shown in , point 1 and point 7 and point 7 and point 9 are connected in sequence to form two straight lines. Find the point with the largest distance from these two straight lines. Since the distance between point 8 and the straight line is less than the threshold, point 8 is thinned out and directly replaced by the straight line between point 7 and point 9. Figure 4-4 Continue with the above steps, such as Figure 4-5 As shown. Finally, Figure 4-6 As shown, points 2, 4, 6, and 8 are discarded, and the turning points obtained are points 1, 3, 5, 7, 9, and 10.

[0080] The Douglas-Peucker algorithm is used to find turning points of the four smoothed curves in this embodiment, and the dates corresponding to the turning points are recorded.

[0081] Step 104: Perform cluster analysis on the turning points of all curves.

[0082] Since the turning points of the records are dates, in order to facilitate cluster analysis, the dates are converted to numbers. The first date is taken as 0, and the other dates are converted to the number of months from the first date. In this way, an integer sequence is obtained. After sorting this sequence from small to large, it is used for cluster analysis. The cluster analysis uses the K-means clustering algorithm.

[0083] The steps of the K-means clustering algorithm are to randomly select K objects as the initial cluster centers, then calculate the distance between each object and each seed cluster center, and assign each object to the cluster center closest to it. The cluster centers and the objects assigned to them represent a cluster. Each time a sample is assigned, the cluster center of the cluster will be recalculated based on the existing objects in the cluster. This process will be repeated until the cluster center no longer changes, at which time the error sum of squares is locally minimized.

[0084] For the convenience of display, the series itself is copied to the Y axis, so that it is a 45° straight line on the XY two-dimensional graph. In this embodiment, three clusters are taken, and the cluster analysis results are as follows Figure 5-1 and Figure 5-2 As shown. Figure 5-1 It is a two-dimensional graph of the turning points before cluster analysis. Figure 5-2 It is a two-dimensional graph of turning points after cluster analysis.

[0085] Step 105: Obtain the definition points of the oil field development stage.

[0086] Through the cluster analysis in step 104, the time corresponding to the turning points of all curves can be divided into K categories, and the center point of each cluster is taken. These center points (time points) can be used as the defining points of the oil field development stage.

[0087] For example, the centers of the three clusters are taken and the calculated means are 26.4, 178.5, and 321.625 respectively. Because they are to be converted into dates, they are rounded to 26, 179, and 322, which correspond to dates (years and months) of May 1987, February 2000, and January 2012 respectively. This is the defining point of the oilfield development stage in this embodiment.

[0088] Add the final development stage to the curve change diagram, see Figure 6-1 to Figure 6-4 It can be seen that this method of automatically dividing the development stages is basically accurate. Even if it is found to be unreasonable after manual inspection, only local fine-tuning is required.

[0089] In summary, the beneficial results of the present invention are: by comprehensively considering various factors for artificially dividing the development stages of oil fields, by encoding the changes in the strata, using the Douglas-Peucker algorithm to find the turning points of the curve, and by clustering analysis to classify the turning points, the defining points of the oil field development stages are obtained through the cluster centers. This method can greatly improve the efficiency of dividing the development stages of oil fields.

[0090] The present invention also provides a device for processing the division of oilfield development stage, as described in the following embodiments. Since the principle of solving the problem by the device is similar to the method for processing the division of oilfield development stage, the implementation of the device can refer to the implementation of the method for processing the division of oilfield development stage, and the repeated parts will not be repeated.

[0091] Figure 7 FIG. 1 is a schematic diagram of a structure of a device for dividing and processing oilfield development stages in an embodiment of the present invention. Figure 7 As shown, the device comprises:

[0092] The acquisition unit 01 is used to obtain development mode data, well pattern change data, layer change data and production change data from the oil field development history data;

[0093] The drawing unit 02 is used to draw multiple curves of preset types according to the development mode data, well pattern change data, layer change data and production change data;

[0094] A turning point determination unit 03, used for searching each curve and determining the turning point of each curve;

[0095] The defining point determination unit 04 is used to perform cluster analysis on the turning points of all curves, and obtain the center point of each cluster turning point as the defining point of the oilfield development stage;

[0096] The processing unit 05 is used to divide the oilfield development stages according to a plurality of defining points.

[0097] In one embodiment, the oilfield development stage division processing device may further include: a smoothing processing unit, used to smooth the drawn multiple curves of preset types to obtain multiple smoothed curves;

[0098] The turning point determination unit is specifically used for searching for multiple smoothed curves and determining the turning point of each curve.

[0099] In one embodiment, the smoothing processing unit is specifically used for:

[0100] The moving average method MA is used to smooth the drawn multiple preset types of curves to obtain multiple smoothed curves.

[0101] In one embodiment, the acquisition unit is specifically used to obtain the layer change data according to the following method:

[0102] According to the production situation of each small layer at a preset time, binary coded data is obtained;

[0103] The binary coded data is converted into decimal data to obtain time series data on the layer change as layer change data.

[0104] In one embodiment, the turning point determination unit is specifically used to: determine the turning point of each curve using the Douglas-Peucker algorithm.

[0105] In one embodiment, the defining point determination unit is specifically used to: use a K-means clustering algorithm to perform cluster analysis on the turning points of all curves, and obtain the center point of each type of turning point as the defining point of the oilfield development stage.

[0106] An embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for dividing and processing oilfield development stages when executing the computer program.

[0107] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program for executing the above-mentioned method for dividing and processing oilfield development stages.

[0108] In the embodiment of the present invention, the division and processing scheme of the oilfield development stage is compared with the technical scheme in the prior art that considers relatively simple factors and requires experienced reservoir engineers to divide according to indicators. The scheme includes: obtaining development mode data, well network change data, formation change data and production change data from the historical data of oilfield development; drawing multiple curves of preset types according to the development mode data, well network change data, formation change data and production change data; searching each curve to determine the turning point of each curve; performing cluster analysis on the turning points of all curves to obtain the center point of each cluster turning point as the defining point of the oilfield development stage; and dividing and processing the oilfield development stage according to multiple defining points, thereby improving the efficiency and rationality of the oilfield development stage division and providing scientific guidance for the research on oil and gas development stages.

[0109] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may 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.

[0110] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes 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 a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0113] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for dividing and processing oilfield development stages, characterized in that: include: From the historical data of oilfield development, obtain the development mode data, well pattern change data, formation change data and production change data; Development mode data include water injection volume, gas injection volume and polymer injection volume; well pattern change data include the number of oil wells, water wells and oil-water well ratio; production change data include oil production, liquid production and water content; Draw multiple preset curves based on monthly water injection volume, total number of wells, formation change data and monthly oil production; Searching each curve and determining the turning point of each curve, which includes: using Douglas-Peucker algorithm to determine the turning point of each curve; Perform cluster analysis on the turning points of all curves, and obtain the center point of each cluster turning point as the defining point of the oilfield development stage; The oilfield development phases are divided and processed according to multiple defining points; The turning points of all curves are clustered and analyzed, and the center point of each type of turning point is obtained as the defining point of the oilfield development stage, including: using a K-means clustering algorithm to cluster the turning points of all curves, and the center point of each type of turning point is obtained as the defining point of the oilfield development stage; The method for dividing and processing the oil field development stage also includes: obtaining stratum change data according to the following method: according to the production situation of each small layer at a preset time, the small layer in production is marked as 1, and the small layer not in production is marked as 0, to obtain binary coded data; converting the binary coded data into decimal data to obtain time series data about stratum changes as stratum change data.

2. The method for dividing the oil field development stages according to claim 1, characterized in that: Also includes: Smoothing the drawn multiple curves of preset types to obtain multiple smoothed curves; Searching each curve and determining the turning point of each curve, including: searching multiple smoothed curves and determining the turning point of each curve.

3. The method for dividing the oil field development stages according to claim 2, characterized in that: Smoothing is performed on multiple drawn curves of preset types to obtain multiple smoothed curves, including: The moving average method MA is used to smooth the drawn multiple preset types of curves to obtain multiple smoothed curves.

4. A division processing device for oil field development stage, characterized in that: include: An acquisition unit is used to obtain development mode data, well pattern change data, layer change data and production change data from the oilfield development history data; Development mode data include water injection volume, gas injection volume and polymer injection volume; well pattern change data include the number of oil wells, water wells and oil-water well ratio; production change data include oil production, liquid production and water content; A drawing unit is used to draw multiple preset curves according to the monthly water injection volume, the total number of wells, the formation change data and the monthly oil production; A turning point determination unit is used to search each curve and determine the turning point of each curve, which includes: using Douglas-Peucker algorithm to determine the turning point of each curve; The defining point determination unit is used to perform cluster analysis on the turning points of all curves and obtain the center point of each cluster turning point as the defining point of the oilfield development stage; A processing unit for dividing the oilfield development stages according to a plurality of defined points; The defining point determination unit is specifically used to: use K-means clustering algorithm to perform cluster analysis on the turning points of all curves, and obtain the center point of each type of turning point as the defining point of the oilfield development stage; The acquisition unit is specifically used to obtain the stratigraphic change data according to the following method: according to the production status of each small layer at a preset time, the small layer in production is marked as 1, and the small layer not in production is marked as 0, to obtain binary coded data; the binary coded data is converted into decimal data to obtain time series data about the stratigraphic change as the stratigraphic change data.

5. The oilfield development stage division processing device according to claim 4, characterized in that: Also includes: A smoothing processing unit, used for smoothing the drawn multiple curves of preset types to obtain multiple smoothed curves; The turning point determination unit is specifically used for searching for multiple smoothed curves and determining the turning point of each curve.

6. The oilfield development stage division processing device according to claim 5, characterized in that: The smoothing processing unit is specifically used for: The moving average method MA is used to smooth the drawn multiple preset types of curves to obtain multiple smoothed curves.

7. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 3 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program for executing the method according to any one of claims 1 to 3.

Images