Yield prediction method and device based on single well yield time sequence data

Abstract

The invention discloses a yield prediction method and device based on single well yield time sequence data, and the method comprises the steps: calculating the similarity between a target well and all reference wells based on the time sequence data of the single well yield, selecting the reference well with the maximum similarity as a template well, and enabling the similarity to be cosine similarity based on an n-dimensional vector; and obtaining historical yield data of the template well, and predicting the future yield of the target well based on the historical yield data of the template well. According to the output prediction method based on the single well output time series data, mode recognition is carried out based on the production data by using the cosine similarity, the single well output of the target well is predicted through the actual production data of the reference well, the output prediction difficulty is reduced, the data prediction accuracy is improved, and the output prediction efficiency is improved. And the method has a wide application range and application scenarios.

Description

Technical Field

[0001] The present invention belongs to the technical field of oil and gas well production prediction, and particularly relates to a production prediction method and device based on single-well production time series data. Background Art

[0002] In the process of oil and gas field development, production prediction is a very necessary task, which is helpful for system monitoring, development plan optimization, reserve assessment, etc. With the continuous improvement of the digital level of the industry, the comprehensiveness and accuracy of production data have been further improved, making it possible to predict future production based on statistical analysis methods of production data.

[0003] And in this application, a reference well with a production trend similar to that of the well under study is found through time series data, and the production of the new well can be predicted based on the fluctuation of the historical data of the reference well. Summary of the Invention

[0004] In view of the above problems, the present invention is proposed to provide a production prediction method and device based on single-well production time series data that overcome the above problems or at least partially solve the above problems.

[0005] Other features and advantages of the present invention will become apparent through the following detailed description, or be learned in part through the practice of the present invention.

[0006] According to the first aspect of the embodiments of the present invention, a production prediction method based on single-well production time series data is provided, and the method includes:

[0007] Calculating the similarity between the target well and all reference wells based on the time series data of the single-well production, and selecting the reference well with the largest similarity as the template well, where the similarity is the cosine similarity based on the n-dimensional vector;

[0008] Obtaining the production historical data of the template well, and predicting the future production of the target well based on the production historical data of the template well.

[0009] In some embodiments of the present invention, the calculating the similarity between the target well and all reference wells based on the time series data of the single-well production, and selecting the reference well with the largest similarity as the template well specifically includes:

[0010] Obtaining the production data after the target well is put into production, and taking the production difference between any two adjacent days of production data of the target well as the first vector component, and obtaining the first eigenvector through the first vector components corresponding to the production differences of all adjacent two-day production data of the target well;

[0011] Obtain the production data after the reference well is put into production, and use the production difference between the production data of any two adjacent days of the reference well as the second vector component. Obtain the second eigenvector through the second vector components corresponding to the production differences of all adjacent two-day production data of the reference well;

[0012] Based on the vector cosine similarity method, calculate the vector cosine values between the first eigenvector of the target well and the second eigenvectors corresponding to each reference well respectively;

[0013] Sort all the obtained vector cosine values in descending order, and take the reference well with the largest vector cosine value as the template well.

[0014] In some embodiments of the present invention, the method further includes: obtaining the geological data stored in history of the well location to be selected as the historical geological data; collecting the geological data of the target well in real time as the real-time geological data; comparing the historical geological data of the well location to be selected with the real-time geological data respectively, and determining the historical geological data that matches the real-time geological data as the target historical geological data; selecting the well location to be selected corresponding to the target historical geological data as the reference well.

[0015] In some embodiments of the present invention, the geological data includes well depth, number of production layers, reservoir porosity, and reservoir permeability.

[0016] According to the second aspect of the embodiments of the present invention, there is provided a production prediction device based on single-well production time series data, and the device includes:

[0017] A similarity calculation module, configured to calculate the similarity between the target well and all reference wells based on the time series data of single-well production, and select the reference well with the largest similarity as the template well, where the similarity is the cosine similarity based on the n-dimensional vector;

[0018] A production prediction module, configured to obtain the production historical data of the template well, and predict the future production of the target well based on the production historical data of the template well.

[0019] In some embodiments of the present invention, the similarity calculation module is specifically configured to:

[0020] Obtain the production data after the target well is put into production, and use the production difference between the production data of any two adjacent days of the target well as the first vector component. Obtain the first eigenvector through the first vector components corresponding to the production differences of all adjacent two-day production data of the target well;

[0021] Obtain the production data after the reference well is put into production, and use the production difference between the production data of any two adjacent days of the reference well as the second vector component. Obtain the second eigenvector through the second vector components corresponding to the production differences of all adjacent two-day production data of the reference well;

[0022] Calculate the cosine values of the vectors between the first eigenvector of the target well and the second eigenvectors corresponding to each reference well respectively based on the vector cosine similarity method;

[0023] Sort all the obtained cosine values of the vectors in descending order, and use the reference well with the largest cosine value of the vector as the template well.

[0024] In some embodiments of the present invention, the device further includes:

[0025] A well location selection module, configured to obtain the geological data of the well location to be selected from the historically stored geological data as historical geological data; collect the geological data of the target well in real time as real-time geological data; compare the historical geological data of the well location to be selected with the real-time geological data respectively, determine the historical geological data that matches the real-time geological data as the target historical geological data; and select the well location to be selected corresponding to the target historical geological data as the reference well.

[0026] In some embodiments of the present invention, the geological data includes well depth, number of production layers, reservoir porosity, and reservoir permeability.

[0027] According to the third aspect of the embodiments of the present invention, there is provided a computer-readable storage medium, in which at least one computer program instruction is stored, and the at least one computer program instruction is loaded and executed by a processor to implement the operations performed by the method according to any one of the above first aspects.

[0028] According to the fourth aspect of the embodiments of the present invention, there is provided an electronic device, the electronic device includes one or more processors and one or more memories, and at least one computer program instruction is stored in the one or more memories, and the at least one computer program instruction is loaded and executed by the one or more processors to implement the method according to any one of the above first aspects.

[0029] The technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

[0030] A production prediction method and device based on single-well production time-series data provided in the embodiments of the present invention. The production prediction method based on single-well production time-series data in the embodiments of the present invention uses cosine similarity for pattern recognition based on production data, predicts the single-well production of the target well through the actual production data of the reference well, reduces the difficulty of production prediction, improves the accuracy of data prediction, is not only applicable to the production prediction of new wells with less historical production data, but also applicable to the production prediction of general oil and gas wells, and has good applicability to any production index with statistical laws, and has a wide range of application scopes and application scenarios.

[0031] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and do not limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present invention, and are used together with the specification to explain the principles of the present invention. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts. In the drawings:

[0033] Figure 1 is a schematic flow chart of a production prediction method based on single-well production time-series data provided by an embodiment of the present invention;

[0034] Figure 2 is a schematic flow chart of another embodiment of the present invention;

[0035] Figure 3 is a reference schematic diagram of a daily production report data table in an embodiment of the present invention;

[0036] Figure 4 is a reference schematic diagram of a comparison chart of actual production and predicted production in an embodiment of the present invention;

[0037] Figure 5 is a schematic flow chart of another embodiment of the present invention;

[0038] Figure 6 is a schematic diagram of the principle structure of a production prediction device based on single-well production time-series data provided by an embodiment of the present invention;

[0039] Figure 7 is a schematic diagram of the principle structure of another embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0041] In addition, the described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, numerous specific details are provided to give a thorough understanding of the embodiments of the present invention. However, those skilled in the art will realize that the technical solutions of the present invention may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the present invention.

[0042] The block diagrams shown in the drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0043] The flowcharts shown in the drawings are only illustrative and do not necessarily include all the content and operations / steps, nor are they necessarily executed in the described order. For example, some operations / steps can be decomposed, while some operations / steps can be combined or partially combined, so the actual execution order may change according to the actual situation.

[0044] It should be noted that the term "plurality" mentioned herein refers to two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after.

[0045] It should also be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above drawings are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the objects so used can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described.

[0046] To enable those skilled in the art to better understand the present invention, first, a simple description of the application scenarios related to the present invention is provided in conjunction with Figure 1 a simple explanation of the application scenarios related to the present invention is given.

[0047] Figure 1 is a schematic flowchart of a production prediction method based on single-well production time-series data provided for an embodiment of the present invention. Refer to Figure 1 As shown, the production prediction method based on single-well production time-series data includes:

[0048] S101. Calculate the similarity between the target well and all reference wells based on the time-series data of the single-well production, and select the reference well with the maximum similarity as the template well. The similarity is the cosine similarity based on the n-dimensional vector;

[0049] S102. Obtain the production history data of the template well, and predict the future production of the target well based on the production history data of the template well.

[0050] Refer to Figure 2 As shown, in the embodiment of the present invention, in step S101, the calculating the similarity between the target well and all reference wells based on the time-series data of the single-well production, and selecting the reference well with the maximum similarity as the template well specifically includes:

[0051] S201. Obtain the production data after the target well is put into production, and use the production difference between any two adjacent days of the production data of the target well as the first vector component. Obtain the first eigenvector through the first vector components corresponding to the production differences of all adjacent two-day production data of the target well;

[0052] For example, the production data X n = [x1, x2, x3... x n of the target well A in the first n days after it is put into production, where x is the production of the target well. Use the production difference between any two adjacent days of the production data of the target well as the first vector component. Then the first eigenvector A = (x2 - x1, x3 - x2, x4 - x3... x n - x (n-1) ).

[0053] S202. Obtain the production data after the reference well is put into production, and use the production difference between any two adjacent days of the production data of the reference well as the second vector component. Obtain the second eigenvector through the second vector components corresponding to the production differences of all adjacent two-day production data of the reference well;

[0054] For example, the data Y n = [y1, y2, y3... y n of the reference well B in the first n days after it is put into production, where y is the production of the reference well. Use the production difference between any two adjacent days of the production data of the reference well as the second vector component. Then the second eigenvector B = (y2 - y1, y3 - y2, y4 - y3... y n - y (n-1) );

[0055] S203. Calculate the vector cosine values between the first eigenvector of the target well and the second eigenvectors corresponding to each reference well respectively based on the vector cosine similarity method;

[0056] For example, for target well A and reference well B, the cosine value s of the vector between the first eigenvector of the two and the corresponding second eigenvector is calculated and obtained through the following formula:

[0057]

[0058] In the formula, A and B are the first eigenvector and the second eigenvector respectively, Ai and Bi are the first vector component and the second vector component respectively, n is the corresponding number of production days after production, and n is a positive integer.

[0059] S204. Sort all the obtained cosine values of the vectors in descending order, and use the reference well with the largest cosine value of the vector as the template well;

[0060] Set S = (s1, s2, s3…s m ), where s m is the cosine value of the vector between the m-th reference well and the target well. By sorting set S, the reference well with the largest cosine value of the vector has the highest similarity, that is, it is the closest to the pattern of the target well and can be used as the template well.

[0061] In the embodiment of the present invention, in step S102, the specific method for obtaining the historical production data of the template well and predicting the future production of the target well based on the historical production data of the template well is as follows:

[0062] For target well A, if the production on the (n + 1)-th day is x, then the production data from day 1 to the (n + 1)-th day is A (n+1) =[a1, a2, a3…a n , x], where a1…a n are known values, and the corresponding first eigenvector A = (a2 - a1, a3 - a2, a4 - a3…(x - a n ))

[0063] The production data of reference well B from day 1 to the (n + 1)-th day is B (n+1) =[b1, b2, b3…b n , b (n+1) , where b1…b (n+1) are known values, and the corresponding second eigenvector B = (b2 - b1, b3 - b2, b4 - b3…b (n+1) - b n )

[0064] Then the cosine value s of the vector corresponding to the first eigenvector A and the second eigenvector B is:

[0065]

[0066] In the formula, only x is the unknown term and it is a quadratic equation of one variable. Therefore, the actual value of x can be obtained according to the solution method of the quadratic equation of one variable, which can be used as the production of the target well on the (n + 1)-th day. By analogy, the production data at any time after the n-th day can be obtained, thus achieving the goal of production prediction.

[0067] Specifically, taking the reference well (which is the template well at this time) A and the target well B as examples, the daily data for 100 days are studied. Starting from the 101st day, the daily gas production of a single well is predicted and compared with the actual daily gas production data to verify the effectiveness of the predicted data.

[0068] Selecting 100 days of data as sample data, both the first vector component and the second vector component corresponding to the first eigenvector A and the second eigenvector B generated after taking the difference are 99.

[0069] For the sake of simplicity in calculation, the following parameters are set respectively:

[0070]

[0071]

[0072]

[0073] Then the vector cosine value formula can be correspondingly simplified to:

[0074]

[0075] Among them, q1 is the vector component of the daily gas production of the template well, and q2 is the vector component of the daily gas production of the new well of the research object (target well).

[0076] According to the above formula, it can be sorted out into a quadratic equation of one variable:

[0077]

[0078] At the same time, set:

[0079]

[0080] b = 2c0q1

[0081]

[0082] Then the above quadratic equation of one variable is simplified to:

[0083]

[0084] The corresponding solutions are:

[0085]

[0086] The criterion for judging the qualified solution in the embodiments of the present invention is to ensure that the change trend of the predicted data is the same as that of the template data and to ensure the stable change of the production volume. The specific judgment basis is as follows:

[0087] 1. The positive and negative signs of component B i are the same as those of template A i for the solution;

[0088] 2. If both solutions have the same positive and negative signs as template A i take the solution closer to the previous predicted value.

[0089] The q2 obtained above is the difference between the predicted daily gas production value and the daily gas production of the previous day. Adding q2 to the daily gas production or the predicted daily gas production of the previous day gives the predicted production volume for the current day.

[0090] The following takes the prediction of the daily gas production of the Daji-Ping 23-6H well with real data as a reference.

[0091] First, based on the time-series data of the single-well production volume, calculate the similarity between the data curves of the Daji-Ping 23-6H well and those of all other wells. The data used is the production daily report data from March 1, 2023 to June 8, 2023, as Figure 3 shown, which is a reference schematic diagram of the production daily report data table.

[0092] From Figure 3 the data, it can be confirmed that the similarity between the Daji-Ping 23-1H well and the Daji-Ping 23-6H well is the largest, which is 0.7931899971. Therefore, the production volume data of the Daji-Ping 23-1H well is used as the template to predict the Daji-Ping 23-6H well.

[0093] As shown in Table 1 below, it is the comparison data of the actual production volume and the predicted production volume of the Daji-Ping 23-6H well:

[0094] Hash sign Date Actual production Predicted production Daji-Ping 23-6H 2023-5-25 9185 Daji-Ping 23-6H 2023-5-26 8596 Daji-Ping 23-6H 2023-5-27 8497 Daji-Ping 23-6H 2023-5-28 8061 Daji-Ping 23-6H 2023-5-29 7200 Daji-Ping 23-6H 2023-5-30 7414 Daji-Ping 23-6H 2023-5-31 8360 Daji-Ping 23-6H 2023-6-1 10411 Daji-Ping 23-6H 2023-6-2 10517 Daji-Ping 23-6H 2023-6-3 11356 Daji-Ping 23-6H 2023-6-4 10851 Daji-Ping 23-6H 2023-6-5 10904 Daji-Ping 23-6H 2023-6-6 10751 Daji-Ping 23-6H 2023-6-7 10046 Daji-Ping 23-6H 2023-6-8 10133 Daji-Ping 23-6H 2023-6-9 9915 9955.76 Daji-Ping 23-6H 2023-6-10 7025 6888.35 Daji-Ping 23-6H 2023-6-11 7448 8696.16 Daji-Ping 23-6H 2023-6-12 8584 12431.87 Daji-Ping 23-6H 2023-6-13 11099 12663.48

[0095] Table 1 Comparison reference table of actual production volume and predicted production volume

[0096] At the same time, combined with Figure 4 as shown, which is a reference schematic diagram of the comparison chart of the actual production volume and the predicted production volume, it can be seen that the change trend of the predicted production volume is consistent with the actual situation, achieving the expected goal.

[0097] Referring to Figure 5 as shown, in some embodiments of the present invention, the method further includes:

[0098] S301. Obtain the geological data stored historically for the candidate well locations as historical geological data; collect the geological data of the target well in real time as real-time geological data; compare the historical geological data of the candidate well locations with the real-time geological data respectively, and determine the historical geological data that matches the real-time geological data as the target historical geological data; select the candidate well location corresponding to the target historical geological data as the reference well.

[0099] The geological data includes well depth, number of production layers, reservoir porosity, and reservoir permeability. By screening the reference wells in advance, the present invention can obtain the well location most similar to the target well as a reference, greatly improving the accuracy and feasibility of production prediction. Of course, it should be noted that in other embodiments of the present invention, classification can also be carried out according to reservoir characteristics and structural conditions, and the candidate well locations with similar theoretical patterns can be included in the reference range.

[0100] The production prediction method based on single-well production time-series data according to the embodiments of the present invention is based on the n-dimensional vector composed of production data, uses cosine similarity for pattern recognition, and predicts the single-well production of the target well through the actual production data of the reference well, reducing the difficulty of production prediction and improving the accuracy of data prediction. It is not only applicable to the production prediction of new wells with less historical production data, but also applicable to the production prediction of general oil and gas wells, and has good applicability to any production index with statistical laws, having a wide range of application scopes and application scenarios.

[0101] Based on the above embodiments, the present invention also provides a production prediction device based on single-well production time-series data. Refer to Figure 6 as shown, the device includes:

[0102] A similarity calculation module 100, configured to calculate the similarity between the target well and all reference wells based on the time-series data of single-well production, and select the reference well with the largest similarity as the template well, where the similarity is the cosine similarity based on the n-dimensional vector;

[0103] A production prediction module 200, configured to obtain the production history data of the template well and predict the future production of the target well based on the production history data of the template well.

[0104] In the embodiments of the present invention, the similarity calculation module 100 is specifically configured to:

[0105] Obtain the production data after the target well is put into production, and use the production difference between the production data of any two adjacent days of the target well as the first vector component, and obtain the first eigenvector through the first vector components corresponding to the production differences of all adjacent two-day production data of the target well;

[0106] Obtain the production data after the reference well is put into production, and use the production difference between the production data of any two adjacent days of the reference well as the second vector component. Obtain the second eigenvector through the second vector components corresponding to the production differences of all adjacent two-day production data of the reference well;

[0107] Based on the vector cosine similarity method, calculate the vector cosine values between the first eigenvector of the target well and the second eigenvectors corresponding to each reference well respectively;

[0108] Sort all the obtained vector cosine values according to their magnitudes, and select the reference well with the largest vector cosine value as the template well.

[0109] Refer to Figure 7 As shown, in the embodiment of the present invention, the device further includes:

[0110] A well location selection module 300, configured to obtain the geological data stored in history at the to-be-selected well location as historical geological data; collect the geological data of the target well in real time as real-time geological data; compare the historical geological data of the to-be-selected well location with the real-time geological data respectively, determine the historical geological data that matches the real-time geological data as the target historical geological data; select the to-be-selected well location corresponding to the target historical geological data as the reference well.

[0111] In the embodiment of the present invention, the geological data includes well depth, number of production layers, reservoir porosity, reservoir permeability, etc.

[0112] The production prediction device based on single-well production time-series data in the embodiment of the present invention can execute the production prediction method based on single-well production time-series data provided in the above embodiment. The production prediction device based on single-well production time-series data has the corresponding functional steps and beneficial effects of the production prediction method based on single-well production time-series data in the above embodiment. For details, please refer to the embodiment of the production prediction method based on single-well production time-series data. The embodiment of the present invention will not be elaborated here.

[0113] Based on the same inventive concept, an embodiment of the present invention further provides an electronic device, which may include a processor and a memory, where the processor and the memory may be connected through a bus or other means. The processor may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., or a combination of the above types of chips.

[0114] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the production prediction method based on the sequential data of single-well production in the embodiment of the present invention. By running the non-transitory software programs, instructions, and modules stored in the memory, the processor executes various functional applications and data processing of the processor, that is, implements the production prediction method based on the sequential data of single-well production in the above method embodiment.

[0115] The memory may include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. The one or more modules are stored in the memory and, when executed by the processor, execute the production prediction method based on the sequential data of single-well production in the Figure 1 embodiment shown. The specific details of the above electronic device can be referred to Figure 1For the relevant descriptions and effects corresponding to the embodiments shown, they can be understood and will not be elaborated here. Those skilled in the art can understand that to implement all or part of the processes in the methods of the above embodiments, it can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium can be a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory, a Hard Disk Drive (abbreviation: HDD), or a Solid-State Drive (SSD), etc.; the storage medium can also include a combination of the above types of memories.

[0116] In several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of the units can be a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of units or modules can be in an electrical or other form.

[0117] The units described as separate components may or may not be physically separated. The components serving as control devices may or may not be physical units, that is, they can be located in one place or distributed to multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0118] The above are only the embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the scope of the claims of the present invention.

Claims

1. A production prediction method based on single-well production time-series data, characterized in that The method includes: Calculating the similarity between the target well and all reference wells based on the time-series data of the single-well production, and selecting the reference well with the largest similarity as the template well, where the similarity is the cosine similarity based on the n-dimensional vector; Obtaining the production history data of the template well, and predicting the future production of the target well based on the production history data of the template well.

2. The production prediction method based on the sequential data of single well production according to claim 1, characterized in that The calculating the similarity between the target well and all reference wells based on the time-series data of the single-well production, and selecting the reference well with the largest similarity as the template well specifically includes: Obtaining the production data after the target well is put into production, and taking the production difference between any two adjacent days of production data of the target well as the first vector component, and obtaining the first eigenvector through the first vector components corresponding to the production differences of all adjacent two-day production data of the target well; Obtaining the production data after the reference well is put into production, and taking the production difference between any two adjacent days of production data of the reference well as the second vector component, and obtaining the second eigenvector through the second vector components corresponding to the production differences of all adjacent two-day production data of the reference well; Calculating the vector cosine values between the first eigenvector of the target well and the second eigenvectors corresponding to each reference well respectively based on the vector cosine similarity method; Sorting all the obtained vector cosine values in descending order, and taking the reference well with the largest vector cosine value as the template well.

3. The production prediction method based on the sequential data of the production of a single well according to claim 1, wherein, The method further includes: Obtaining the geological data stored in history of the well location to be selected as the historical geological data; Real-time collecting the geological data of the target well as the real-time geological data; Comparing the historical geological data of the well location to be selected with the real-time geological data respectively, and determining the historical geological data that matches the real-time geological data as the target historical geological data; Selecting the well location to be selected corresponding to the target historical geological data as the reference well.

4. The production prediction method based on the time series data of the single well production according to claim 3, wherein: The geological data includes well depth, number of production layers, reservoir porosity, and reservoir permeability.

5. A production prediction device based on single-well production time-series data, characterized in that The device includes: A similarity calculation module, configured to calculate the similarity between the target well and all reference wells based on the time-series data of the single-well production, and select the reference well with the largest similarity as the template well, where the similarity is the cosine similarity based on the n-dimensional vector; A production prediction module, configured to obtain the production history data of the template well, and predict the future production of the target well based on the production history data of the template well.

6. The production prediction device based on the single-well production time series data according to claim 5, wherein The similarity calculation module is specifically configured to: Obtain the production data after the target well is put into production, and take the production difference between any two adjacent days of production data of the target well as the first vector component, and obtain the first eigenvector through the first vector components corresponding to the production differences of all adjacent two-day production data of the target well; Obtain the production data after the reference well is put into production, and take the production difference between any two adjacent days of production data of the reference well as the second vector component, and obtain the second eigenvector through the second vector components corresponding to the production differences of all adjacent two-day production data of the reference well; Calculating the vector cosine values between the first eigenvector of the target well and the second eigenvectors corresponding to each reference well respectively based on the vector cosine similarity method; Sorting all the obtained vector cosine values in descending order, and taking the reference well with the largest vector cosine value as the template well.

7. The production prediction device based on the single-well production time series data according to claim 5, characterized in that The device further includes: The well location selection module is used to obtain the geological data of the candidate well locations stored in history as historical geological data; collect the geological data of the target well in real time as real-time geological data; compare the historical geological data of the candidate well locations with the real-time geological data respectively, determine the historical geological data that matches the real-time geological data as the target historical geological data; and select the candidate well location corresponding to the target historical geological data as the reference well.

8. The production prediction device based on the single-well production time series data according to claim 7, characterized in that: The geological data includes well depth, number of production layers, reservoir porosity, and reservoir permeability.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, and the computer program instructions are loaded and executed by a processor to implement the operations performed by the method according to any one of claims 1-4.

10. An electronic device, comprising a processor and a memory, characterized in that, The memory stores computer program instructions that can be executed by the processor. When the processor executes the computer program instructions, the instructions of the method according to any one of claims 1-4 are implemented.

Images