A cementing solution recommendation method and device

Abstract

The application provides a cementing scheme recommendation method and device. The cementing scheme recommendation method comprises the following steps: in a plurality of cementing schemes of opened cementing, a cementing scheme of a newly opened cementing is selected according to the similarity of text type information and the similarity of numerical type information of attribute information of the newly opened cementing. The application relies on historical cementing data to complete similarity calculation of the newly opened cementing and the historical cementing design scheme, and provides a historical similar cementing scheme recommendation for the newly opened cementing, so that the design of the newly opened cementing scheme can be better and more efficiently completed.

Description

Technical Field

[0001] This application belongs to the field of oil and gas field development technology, particularly the field of cementing technology in oilfield engineering, and specifically relates to a cementing scheme recommendation method and apparatus. Background Technology

[0002] In the oil and gas extraction industry, cementing is a crucial step in the drilling process. Currently, cementing scheme design typically relies on engineers' experience to analyze the actual operating conditions of neighboring wells and their impact on the current well.

[0003] For example, a paper titled "A Remote Auxiliary Decision-Making System and Method for Cementing Operations" (publication number CN114091375A) provides a remote auxiliary decision-making system and method for cementing operations. The remote auxiliary decision-making system includes a cementing operation design module, a real-time cementing operation data acquisition and transmission module, an online cementing operation simulation module, and a data analysis, evaluation, and decision-making module. The cementing operation design module stores the basic data used in the cementing design; the real-time cementing operation data acquisition and transmission module acquires cementing operation data; the online cementing operation simulation module reads the basic data and cementing operation data to perform online simulation and obtain the dynamic equivalent density of the key well depth at the current cementing operation stage; and the data analysis, evaluation, and decision-making module compares the simulated dynamic equivalent density with the design value, provides well leakage / overflow warnings, and feeds back auxiliary decision-making suggestions.

[0004] The above methods do not effectively analyze and utilize the construction plans of adjacent wells to assist engineers in designing and referencing cementing operations. In other words, they do not provide reference guidance for cementing construction design and plans of subsequent wells of the same type in the same block based on the existing massive amount of data and rich practical experience, which is not conducive to improving cementing quality and work efficiency. Summary of the Invention

[0005] One objective of this invention is to provide a cementing scheme recommendation method, which aims to recommend similar cementing design schemes for new wells by analyzing historical data of neighboring wells, so as to complete the design of new cementing schemes better and more efficiently.

[0006] Another object of the present invention is to provide a cementing scheme recommendation device. A further object of the present invention is to provide an electronic device comprising a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the above-described cementing scheme recommendation method. A further object of the present invention is to provide a readable medium storing a computer program thereon, the computer program being executed by a processor to implement the steps of the above-described cementing scheme recommendation method.

[0007] To address the technical problems in the background section of this application, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a method for recommending cementing schemes, comprising:

[0009] Based on the length of the longest common subsequence of the textual information of the attribute information of the newly opened cementing well and the textual information of the attribute information of multiple opened cementing wells, the word order difference, the number of character edits required to achieve the same word order, and the first preset condition, the similarity between the textual information of the attribute information of the newly opened cementing well and the attribute information of the multiple opened cementing wells is determined.

[0010] The similarity between the numerical information of the attribute information of the newly opened cementing well and the numerical information of the attribute information of the multiple opened cementing wells is determined based on the length, type, size, distribution trend, and second preset conditions of the numerical information in the attribute information of the newly opened cementing well and the numerical information in the attribute information of the multiple opened cementing wells.

[0011] Among multiple cementing schemes that have already been opened, the cementing scheme for the newly opened well is selected based on the similarity of the textual information and the similarity of the numerical information.

[0012] In some embodiments of the present invention, the similarity between the attribute information of the newly opened cementing well and the textual information of the attribute information of the multiple opened cementing wells is determined based on the length of the longest common subsequence, the word order difference, the number of character edits required to achieve the same word order, and a first preset condition. This includes:

[0013] Based on the length of the longest common subsequence, the word order difference, and the number of character edits required to achieve the same word order in the textual information of the attribute information of the newly opened cementing well and the textual information of the attribute information of the multiple opened cementing wells, multiple first alternative similarities are determined between the textual information of the newly opened cementing well and the textual information of the multiple opened cementing wells.

[0014] The similarity of the text information is selected from the plurality of first candidate similarities according to the first preset condition; wherein, the first preset condition is that the number of different characters at corresponding positions between the string of the newly opened cementing well and the strings of the plurality of opened cementing wells is less than a first preset value.

[0015] In some embodiments of the present invention, determining the similarity between the numerical information of the attribute information of the newly opened cementing well and the numerical information of the attribute information of the plurality of opened cementing wells based on the length, type, size, and distribution trend of the numerical information in the attribute information of the newly opened cementing well and the numerical information in the attribute information of the plurality of opened cementing wells includes:

[0016] Based on the length, type, and size of the numerical information in the attribute information of the newly opened cementing well and the numerical information in the attribute information of the multiple opened cementing wells, determine multiple second alternative similarities between the numerical information corresponding to the newly opened cementing well and the numerical information corresponding to the multiple opened cementing wells.

[0017] The similarity of the numerical information is selected from the plurality of second alternative similarities according to a second preset condition; wherein, the second preset condition is that the similarity between the distribution trend corresponding to the newly opened cementing well and the distribution trend corresponding to the plurality of opened cementing wells is greater than the second preset value.

[0018] In some embodiments of the present invention, the word order of the greatest common subsequence is the position of the greatest common subsequence in the corresponding string;

[0019] The attribute information includes: well name, well type, well class, cementing type, current opening, oil field, casing type, casing size, drill bit size, drilling depth, funnel viscosity, well fluid density, well inclination, well diameter, block, geographical location, and formation characteristics.

[0020] In some embodiments of the present invention, when the attribute information corresponding to the well name and / or the geographical location is partially missing, a cementing scheme recommendation method further includes:

[0021] The well name corresponding to the newly opened cementing well, the geographical location, the well name corresponding to the multiple opened cementing wells, and the geographical location are split to generate multiple tuples;

[0022] Determine the similarity metric vector between the tuple corresponding to the newly opened cementing well and the tuple corresponding to the plurality of already opened cementing wells;

[0023] The similarity metric vector is used to assign scores to the parts of the attribute information that are partially missing.

[0024] Secondly, the present invention provides a cementing scheme recommendation device, the device comprising:

[0025] The text similarity determination module is used to determine the similarity between the text information of the attribute information of the newly opened cementing well and the text information of the attribute information of the multiple opened cementing wells based on the length of the longest common subsequence, the word order difference, the number of character edits required to achieve the same word order, and a first preset condition.

[0026] The numerical similarity determination module is used to determine the similarity between the numerical information of the attribute information of the newly opened cementing well and the numerical information of the attribute information of the multiple opened cementing wells based on the length, type, size, distribution trend, and second preset conditions of the numerical information in the attribute information of the newly opened cementing well and the numerical information in the attribute information of the multiple opened cementing wells.

[0027] The cementing scheme selection module is used to select the cementing scheme for the newly opened well from among multiple cementing schemes that have already been opened, based on the similarity of the textual information and the similarity of the numerical information.

[0028] In some embodiments of the present invention, the text similarity determination module includes:

[0029] The first similarity determination unit is used to determine multiple first candidate similarities between the text information corresponding to the newly opened cementing well and the text information corresponding to the multiple opened cementing wells based on the length of the longest common subsequence, the word order difference, and the number of character edits required to achieve the same word order in the text information of the attribute information of the newly opened cementing well and the text information of the attribute information of the multiple opened cementing wells.

[0030] A text similarity selection unit is used to select the similarity of the text information from a plurality of first candidate similarities according to the first preset condition; wherein, the first preset condition is that the number of different characters at corresponding positions between the string of the newly opened cementing well and the strings of the plurality of opened cementing wells is less than a first preset value.

[0031] In some embodiments of the present invention, the numerical similarity determination module includes:

[0032] The second similarity determination unit is used to determine multiple second alternative similarities between the numerical information corresponding to the newly opened cementing well and the numerical information corresponding to the multiple opened cementing wells based on the length, type and size of the numerical information in the attribute information of the newly opened cementing well and the numerical information in the attribute information of the multiple opened cementing wells.

[0033] A numerical similarity selection unit is used to select the similarity of the numerical information from a plurality of second candidate similarities according to a second preset condition; wherein, the second preset condition is that the similarity between the distribution trend corresponding to the newly opened cementing well and the distribution trend corresponding to the plurality of opened cementing wells is greater than a second preset value.

[0034] In some embodiments of the present invention, the word order of the greatest common subsequence is the position of the greatest common subsequence in the corresponding string;

[0035] The attribute information includes: well name, well type, well class, cementing type, current opening, oil field, casing type, casing size, drill bit size, drilling depth, funnel viscosity, well fluid density, well inclination, well diameter, block, geographical location, and formation characteristics.

[0036] In some embodiments of the present invention, when the attribute information corresponding to the well name and / or the geographical location is partially missing, a cementing scheme recommendation device further includes:

[0037] The tuple generation module is used to split the well name corresponding to the newly opened cementing well, the geographical location, the well names corresponding to the multiple opened cementing wells, and the geographical location to generate multiple tuples;

[0038] A similarity metric vector determination module is used to determine the similarity metric vector between the tuple corresponding to the newly opened cementing well and the tuple corresponding to the multiple opened cementing wells;

[0039] The missing score assignment module is used to assign scores to the parts of the attribute information that are partially missing based on the similarity metric vector.

[0040] Thirdly, the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of a cementing scheme recommendation method.

[0041] Fourthly, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of a recommended cementing scheme method.

[0042] Fifthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a recommended cementing scheme method.

[0043] As described above, embodiments of the present invention provide a cementing scheme recommendation method and apparatus. The corresponding cementing scheme recommendation method includes: firstly, determining the similarity between the textual information of the attribute information of the newly opened cementing well and the textual information of the attribute information of multiple opened cementing wells based on the length of the longest common subsequence, the difference in word order, the number of character edits required to achieve the same word order, and a first preset condition; nextly, determining the similarity between the numerical information of the attribute information of the newly opened cementing well and the numerical information of the attribute information of multiple opened cementing wells based on the length, type, size, distribution trend, and a second preset condition; finally, selecting the cementing scheme of the newly opened cementing well from among the cementing schemes of multiple opened cementing wells based on the similarity of the textual information and the similarity of the numerical information.

[0044] Based on historical cementing data, this invention calculates the similarity between cementing designs for new wells and historical cementing designs, providing recommendations for similar cementing schemes for new wells, thus enabling better and more efficient design of new cementing schemes. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart illustrating the cementing scheme recommendation method in an embodiment of the present invention. Figure 1 ;

[0047] Figure 2 This is a flowchart illustrating step 100 of the cementing scheme recommendation method in an embodiment of the present invention;

[0048] Figure 3 This is a flowchart illustrating step 200 of the cementing scheme recommendation method in an embodiment of the present invention;

[0049] Figure 4 This is a flowchart illustrating the cementing scheme recommendation method in an embodiment of the present invention. Figure 2 ;

[0050] Figure 5 This is a flowchart illustrating the implementation of the intelligent recommendation system for adjacent well cementing design in a specific embodiment of the present invention.

[0051] Figure 6This is a main framework diagram of the intelligent recommendation system for adjacent well cementing design in a specific embodiment of the present invention;

[0052] Figure 7 This is a flowchart illustrating a cementing scheme recommendation method according to a specific embodiment of the present invention;

[0053] Figure 8 A block representing a cementing scheme recommendation device in an embodiment of the present invention. Figure 1 ;

[0054] Figure 9 This is a block diagram of the text similarity determination module 10 in an embodiment of the present invention;

[0055] Figure 10 This is a block diagram of the numerical similarity determination module 20 in an embodiment of the present invention;

[0056] Figure 11 A block representing a cementing scheme recommendation device in an embodiment of the present invention. Figure 2 ;

[0057] Figure 12 This is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0059] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.

[0060] It should be noted that the terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or apparatuses. Without conflict, the embodiments and features in the embodiments of this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0061] The acquisition, storage, use, and processing of data in this application comply with relevant laws and regulations.

[0062] In recent years, with the development of big data and artificial intelligence technologies, more and more research has begun to explore how to utilize these advanced technologies to improve the accuracy and reliability of cementing design. By analyzing historical data, more valuable information can be extracted to help engineers better complete cementing design work. Based on this, and to solve at least some of the technical problems in the background section of this application, embodiments of the present invention provide a specific implementation of a cementing scheme recommendation method, see [link to relevant documentation]. Figure 1 The recommended cementing scheme methods specifically include the following:

[0063] Step 100: Based on the length of the longest common subsequence of the textual information of the attribute information of the newly opened cementing well and the textual information of the attribute information of multiple opened cementing wells, the word order difference, the number of character edits required to achieve the same word order, and the first preset condition, determine the similarity between the textual information of the attribute information of the newly opened cementing well and the attribute information of the multiple opened cementing wells.

[0064] Step 200: Determine the similarity between the numerical information of the attribute information of the newly opened cementing well and the numerical information of the attribute information of the multiple opened cementing wells based on the length, type, size, distribution trend, and second preset conditions of the numerical information in the attribute information of the newly opened cementing well and the numerical information in the attribute information of the multiple opened cementing wells.

[0065] Step 300: Among the multiple cementing schemes that have already been opened, select the cementing scheme for the newly opened well based on the similarity of the textual information and the similarity of the numerical information.

[0066] For steps 100 and 200, textual information is data existing in the form of natural language (such as Chinese or English) or symbols. It is typically represented as a sequence of characters and cannot be directly used for mathematical calculations, but it contains rich semantic information. Textual information has the following characteristics:

[0067] Unstructured: without a fixed format (such as free text, comments, articles).

[0068] Semanticity: relies on context and language rules to convey meaning (such as emotion and theme).

[0069] Diversity: May include punctuation, special characters, and multilingual content.

[0070] High dimensionality: The data needs to be converted into numerical form (such as word vectors) during processing, resulting in high dimensionality.

[0071] In contrast, numerical information is data represented in numerical form, which can be directly used in mathematical operations or statistical analysis, and usually has a clear quantitative meaning. Numerical information has the following characteristics:

[0072] Structured: Usually stored in the form of tables, matrices, etc. (such as Excel, database).

[0073] Computability: Supports operations such as addition, subtraction, multiplication, division, and statistical modeling.

[0074] Discrete / Continuous: Discrete: Values ​​are limited to a finite number (e.g., number of people, quantity of goods). Continuous: Values ​​are infinite and can be further subdivided (e.g., temperature, height).

[0075] Low dimensionality: can be used directly as algorithm input without complex transformation.

[0076] The greatest common subsequence (GCT) is a subsequence that appears in the same order across multiple strings (sequences), but they do not have to be consecutive. Additionally, character editing includes adding, shifting, and deleting.

[0077] For step 300, among the multiple cementing schemes that have already been cemented, the cementing scheme with the highest total score of similarity between textual information and numerical information is selected as the cementing scheme for the new cementing operation.

[0078] In some embodiments of the present invention, see Figure 2 Step 100 includes:

[0079] Step 101: Based on the length of the longest common subsequence, the word order difference, and the number of character edits required to achieve the same word order in the textual information of the attribute information of the newly opened cementing well and the textual information of the attribute information of the multiple opened cementing wells, determine multiple first alternative similarities between the textual information of the newly opened cementing well and the textual information of the multiple opened cementing wells.

[0080] Specifically, step 101 can be achieved through the following steps:

[0081] The longest common subsequence (LCS) is the longest sequence of identical characters in two strings, provided the characters are in the same order. The similarity between two strings can be measured by calculating the LCS length between the textual information of a newly cemented well and the textual information of each existing cemented well.

[0082] Word order differences can be measured by comparing the order of characters in two strings. If the character order of two strings differs significantly, it indicates a large difference in word order and a low degree of similarity.

[0083] Calculate the number of character edits (edit distance): Edit distance refers to the minimum number of editing operations (such as inserting, deleting, and replacing characters) required to transform one string into another. Understandably, the smaller the edit distance, the more similar the two strings are.

[0084] Finally, the similarity of the first candidate is calculated by combining LCS length, word order difference, and edit distance. For example, a weighted average can be used to take into account the effects of LCS length, word order difference, and edit distance to arrive at the final similarity score.

[0085] Step 102: Select the similarity of the text information from the plurality of first candidate similarities according to the first preset condition; wherein, the first preset condition is that the number of different characters at corresponding positions between the string of the newly opened cementing well and the strings of the plurality of opened cementing wells is less than a first preset value.

[0086] Preferably, the first preset value is 3.

[0087] In some embodiments of the present invention, see Figure 3 Step 200 includes:

[0088] Step 201: Based on the length, type, and size of the numerical information in the attribute information of the newly opened cementing well and the numerical information in the attribute information of the multiple opened cementing wells, determine multiple second alternative similarities between the numerical information corresponding to the newly opened cementing well and the numerical information corresponding to the multiple opened cementing wells.

[0089] Preferably, the type of numerical information in step 201 is discrete numerical information and continuous numerical information.

[0090] Understandably, the closer the lengths of numerical information are, the higher the similarity; the greater the difference in length, the lower the similarity. When the types of numerical information are the same, the similarity is high; when the types are different, the similarity is low. Regarding the magnitude of numerical information, for single-valued data, the differences in values ​​are directly compared. For multi-valued data (such as vectors or matrices), Euclidean distance, Manhattan distance, or cosine similarity can be calculated. The smaller the numerical difference, the higher the similarity; the greater the numerical difference, the lower the similarity.

[0091] Finally, assign different weights to length, type, and size according to actual needs. Calculate similarity scores for length, type, and size separately (e.g., normalized to between 0 and 1). Calculate the final similarity score using a weighted average or other comprehensive method.

[0092] Step 202: Select the similarity of the numerical information from the plurality of second alternative similarities according to the second preset condition; wherein, the second preset condition is that the similarity between the distribution trend corresponding to the newly opened cementing well and the distribution trend corresponding to the plurality of opened cementing wells is greater than the second preset value.

[0093] Preferably, the second preset value is 0.93.

[0094] In some embodiments of the present invention, the word order of the greatest common subsequence is the position of the greatest common subsequence in the corresponding string;

[0095] The attribute information includes: well name, well type, well class, cementing type, current opening, oil field, casing type, casing size, drill bit size, drilling depth, funnel viscosity, well fluid density, well inclination, well diameter, block, geographical location, and formation characteristics.

[0096] A well name is a unique identifier assigned to each well to distinguish different wells. It typically consists of letters and numbers and can reflect information such as the well's sequence and the region it belongs to. Well names are crucial identifiers for engineering and geological personnel for data management, recording, and retrieval.

[0097] Well type refers to the structural type of a well, which is related to the well design and drilling methods used during the drilling process. Common well types include: Vertical well: The wellbore is driven vertically into the formation. Horizontal well: The wellbore becomes horizontal or curved after a certain depth. Inclined well: The wellbore is inclined at a certain angle. Multi-branch well: A single wellbore branches into multiple branch wells.

[0098] Well type refers to the type or purpose of a well, including: Production wells: used for oil and gas production. Water injection wells: used to inject water to help improve oilfield recovery. Wastewater wells: used to discharge wastewater or other liquids. Monitoring wells: used to monitor geological conditions or fluid behavior.

[0099] Cementing type refers to the techniques or materials used in cementing operations in the annulus between the wellbore and the casing. Common cementing types include: Cement cementing: using cement slurry to fill the annulus. Resin cementing: using resin materials for cementing, suitable for high-temperature and high-pressure environments. Expandable cementing: utilizing expanding materials to expand during the cementing process and fill the annulus.

[0100] The current number of well openings refers to the total number of well openings performed during the entire development process of a particular well; that is, how many well opening operations have been carried out. The number of well openings is related to the well's operational history and maintenance cycle.

[0101] An oil field is a concentrated area of ​​natural oil and gas resources, either underground or on the seabed, and typically consists of multiple oil wells. The oil or natural gas resources within an oil field can be extracted through drilling, extraction, and other methods.

[0102] Casing types refer to the different types of casing used in wells. Casing is used to reinforce the wellbore and prevent wellbore collapse or well fluid leakage. These include: Surface casing: used to protect the wellhead and prevent surface water or other substances from entering the well. Production casing: used during the oil and gas production stage and installed when a certain formation is reached at the drilling depth. Formation casing: specifically used for extracting oil and gas formations.

[0103] Casing size refers to the outer and inner diameters of the casing, usually specified in inches. The choice of casing size directly affects well design and cementing success rates. Common casing sizes include 9.5 / 8 inches and 13.3 / 8 inches.

[0104] Drill bit size refers to the diameter of the drill bit, usually measured in inches. The choice of drill bit size depends on the target drilling depth, formation hardness, and required well diameter. Common drill bit sizes include 8 1 / 2 inches and 12 1 / 4 inches.

[0105] Drilling depth refers to the vertical distance from the wellhead to the deepest point of the well, usually measured in meters or feet. Drilling depth determines the working environment of the well, the required equipment, and the technical requirements.

[0106] Funnel viscosity is an indicator of drilling fluid fluidity. It describes the consistency of drilling fluids (such as drilling mud). Higher funnel viscosity indicates stronger viscosity and poorer fluidity; lower funnel viscosity indicates better fluidity.

[0107] Well fluid density refers to the ratio of the mass to the volume of drilling fluid, expressed in g / cm³. 3 (grams per cubic centimeter). Well fluid density directly affects downhole pressure control, and is especially crucial in deep wells and high-pressure, high-temperature wells. Higher well fluid density helps prevent blowouts, but can also increase drilling costs and difficulty.

[0108] Wellbore inclination refers to the angle of inclination of the wellbore relative to the vertical direction, usually expressed in degrees. Wellbore inclination control is particularly important during the drilling process of horizontal or deviated wells. Proper wellbore inclination control ensures the accuracy and safety of drilling.

[0109] Wellbore refers to the inner diameter of the wellbore, measured in inches or millimeters. The wellbore size determines the drill bit size, casing selection, and the size of the flow path for oil and gas. A wellbore that is too small may affect oil and gas production capacity, while one that is too large may increase costs.

[0110] A block refers to a designated oilfield development area, divided according to geological, geographical, or legal requirements. The scope and numbering of blocks help manage and develop oil and gas resources in different areas.

[0111] Geographic location refers to the specific geographical coordinates or area where a well is located, identified by latitude and longitude or administrative regions. Geographic location has a significant impact on the development of oil and gas resources, affecting well construction, equipment transportation, and environmental protection.

[0112] Formation characteristics refer to the properties and composition of underground strata, including rock type, hardness, porosity, permeability, pressure, and temperature. Formation characteristics have a significant impact on drilling design, well completion strategies, and oil and gas recovery. Accurate analysis of formation characteristics helps assess the difficulty of drilling and its production potential.

[0113] In some embodiments of the present invention, see Figure 4 When the attribute information corresponding to the well name and / or the geographical location is partially missing, a cementing scheme recommendation method further includes:

[0114] Step 400: Split the well name corresponding to the newly opened cementing well, the geographical location, the well names corresponding to the multiple opened cementing wells, and the geographical location to generate multiple tuples;

[0115] Step 500: Determine the similarity metric vector between the tuple corresponding to the newly opened cementing well and the tuple corresponding to the multiple opened cementing wells;

[0116] Step 600: Assign scores to the parts of the attribute information that are partially missing based on the similarity metric vector.

[0117] In steps 400 to 600, the well name (name) and geographical location (ghp) are split to obtain a series of values ​​in the form of (name) i ,ghp i The similarity measure vector (S(name)) is calculated between each pair of tuples. i ,name j ),S(ghp i ,ghpj ), where i ≠ j. Construct the following matrix:

[0118]

[0119] For any name score within the interval (α, β), the law of large numbers states that:

[0120]

[0121] Therefore, for any name, the score interval (α, β) of ghp can be assigned the following scores:

[0122]

[0123] To further illustrate the solution, in one specific embodiment, the present invention also provides a specific implementation of a cementing scheme recommendation method, which specifically includes the following:

[0124] First, see Figure 5 as well as Figure 6 This invention also provides an intelligent recommendation system for adjacent well cementing designs. This system is particularly suitable for automatically recommending cementing designs for historical adjacent wells based on relevant information about newly opened cementing wells. The system adopts a B / S architecture, providing convenient services to users. After logging into the system, users only need to input the relevant data for the newly opened cementing well and click the recommendation button; the system can then intelligently recommend cementing design schemes for historical adjacent wells. The specific implementation steps of this system are as follows:

[0125] The intelligent recommendation system for adjacent well cementing design mainly includes the following core functions: preprocessing of historical cementing data, intelligent correction of newly opened cementing data input, similarity calculation between newly opened cementing data and historical cementing data, and recommendation and optimization of cementing scheme design.

[0126] 1. Preprocessing of historical cementing data.

[0127] Historical cementing data preprocessing improves data quality through methods such as data completion and standardization, providing a fundamental guarantee for the accuracy of similarity calculations between new cementing data and historical cementing data. Historical cementing data preprocessing supports two modes: incremental processing within a time window and real-time processing, ensuring timely data updates.

[0128] Historical cementing data preprocessing employed methods such as word segmentation, stop word removal, standard data extraction, and text similarity calculation.

[0129] 2. Intelligent correction of newly opened cementing data input.

[0130] Intelligent correction for newly entered cementing data compares the text entered by the user with the text entered in historical cementing data to prompt the user for correction or completion, thus avoiding similarity calculation problems caused by typos. Correction content includes oilfield, geographical location, block, and formation.

[0131] The intelligent correction of newly opened cementing data input adopts methods such as Pinyin-Chinese character conversion and text similarity calculation.

[0132] 3. Calculation of similarity between newly opened cementing data and historical cementing data.

[0133] The similarity calculation between newly opened cementing data and historical cementing data first involves precise conditional data filtering, and then comparing the similarity between the user-input data and historical cementing data one by one. The calculation process implements scoring algorithms for cases where certain data items in the historical cementing data are empty, similarity algorithms for numerical data, and similarity algorithms for text data with different characteristics.

[0134] In the method for calculating the similarity between newly opened cementing data and historical cementing data, the common character ratio and the longest character substring ratio are used for textual information, the absolute error ratio is used for numerical information, and the similarity metric matrix interval scoring is used for empty value scoring.

[0135] 4. Recommendations and optimization of historical cementing schemes.

[0136] The intelligent recommendation system for adjacent well cementing design calculates the total similarity score for each historical cementing well based on the similarity scores and weights between new cementing wells and historical cementing well data. This score is then ranked, and the system recommends the most similar historical cementing well data and its design scheme to the user as a reference for designing new cementing wells. During the calculation process, the system updates the recommendation information weights for each user based on the optimal recommendation settings after each recommendation, continuously optimizing and adjusting the weights according to the user's choices.

[0137] In the process of updating and optimizing the weights of the recommendation information, the RankNet loss function was selected, and stochastic gradient descent was used to iteratively update the weights to achieve more accurate recommendations.

[0138] In addition, historical cementing data is supplemented, including oilfield name and geographical location. The supplementation logic is hierarchical supplementation, with oilfield supplementation at level 2 (oilfield, oil refinery) and geographical location supplementation at level 4 (province, city, (district / county), town).

[0139] The system standardizes historical cementing data, including oilfield names and formations. It standardizes inconsistent naming conventions for the same oilfield or formation into a single, consistent name.

[0140] The system performs intelligent text correction based on user input data, including oilfield name, geographical location, formation, and block. It intelligently suggests similar or standard data already existing in historical cementing records for any typos or pinyin errors entered by the user.

[0141] The system calculates and scores the similarity between the user-input information on newly opened cementing wells and historical cementing data, and recommends the top N.

[0142] See Figure 7 Based on the aforementioned intelligent recommendation system for adjacent well cementing design, the present invention also provides a cementing scheme recommendation method, the specific implementation of which includes the following steps:

[0143] S1: Preprocessing historical cementing data.

[0144] First, historical cementing data is preprocessed. This process includes initial preprocessing of historical cementing data and preprocessing of newly added historical data via scheduled tasks. The preprocessed data is saved by adding new data items to the original data to preserve its original appearance for display in the recommendation results. During the preprocessing stage, the system standardizes oilfield, geographical location, and formation data through data governance tasks, and adds standardized fields to the historical cementing data for use in subsequent recommendation models. The standardized historical cementing data is then used to generate standardized result data files, organized into libraries. Furthermore, the system is configured to periodically execute data governance programs to update the standardized result data files, ensuring that new historical cementing data can be updated and applied.

[0145] Examples of the remediation results are as follows:

[0146] Data completion: For example, if the oilfield name is Ciyutuo Oil Production Plant, complete it to Ciyutuo Oil Production Plant of Liaohe Oilfield. If the geographical location is Weiyuan County, complete it to Weiyuan County, Neijiang City, Sichuan Province.

[0147] Data standardization: For example, if the oilfield name is "Daqing", it is standardized as "Daqing Oilfield". If the formation is "S3", it is standardized as "Sha3".

[0148] S2: Configure user personalization.

[0149] In the intelligent recommendation system for adjacent well cementing design of this invention, users can personalize the recommendation parameters according to their specific needs before making intelligent recommendations for new cementing designs. This function aims to improve the relevance and practicality of the recommendation results, ensuring that the recommendations are closer to the user's actual needs. Users can also choose to directly use the default parameter values ​​provided by the system for recommendations, simplifying the operation process.

[0150] Detailed explanation of recommended parameters:

[0151] 1) Number of Recommendations: The system defaults to recommending 10 cementing design schemes, but users can adjust the number of recommendations from 1 to 10 according to their needs. This setting allows users to flexibly choose the number of recommended results based on their workload and decision-making habits.

[0152] 2) Recommendation Score Threshold: The system's default recommendation score threshold is 0. Users can set a threshold according to their needs. The system will first recommend items based on the number set by the user, and then filter from high to low scores based on the user-set score threshold. After setting a threshold, the number of recommended results may be less than the number of recommendations set by the user.

[0153] 3) Core Cementing Information Weight: The system assigns an average weight to all core cementing information by default, with a default weight score of 50. Users can adjust the weight score of a specific piece of information to control its importance in the recommendation algorithm; the weight score ranges from 0 to 100. This setting allows users to personalize the adjustment of the importance of different cementing information based on their professional judgment.

[0154] 4) Prioritize Wells with the Same Opening Number: The system defaults to selecting the "Prioritize Wells with the Same Opening Number" option. If the user selects this option, the system will prioritize recommending well plans with the same opening number and higher scores in the recommendation results. If the user does not select this option, the system will recommend wells based on their total scores.

[0155] 5) Prioritize data from the last two years: The system defaults to selecting the "Prioritize data from the last two years" option. If the user selects this option, the system will prioritize recommending oil well strategies with higher scores from the last two years of data. If the user does not select this option, the system will recommend strategies based on total scores.

[0156] 6) Highlight the best option: The "Highlight the best option" option is selected by default. If the user selects this option, the system will highlight the option with the highest similarity to the input information in the recommendation results. If the user does not select this option, the system will not highlight it.

[0157] 7) Hide duplicate information items: The system does not select the "Hide duplicate information items" option by default. If the user selects this option, the system will hide options that are identical to the input information in the final recommendation results. If the user does not select this option, the system will display all information.

[0158] 8) Recommendation Records: The system also provides a recommendation record function, allowing users to enter relevant information on the recommendation record page to retrieve and view previous search records and recommended oil well information. Users can click the "Recommend" button to view the recommendation details when a specific oil well is the best recommendation result, which helps users understand the logic and basis behind the recommendations. In addition, the system also provides a delete button, allowing users to delete unnecessary recommendation information from the historical recommendation records, keeping the recommendation records clean and relevant.

[0159] Through these meticulous and personalized settings, the intelligent recommendation system for adjacent well cementing design of this invention can provide users with more accurate and personalized recommendation services, greatly enhancing the user experience and the practical application value of the recommendation results. This flexibility and personalization is a major innovation of this system, enabling it to adapt to the needs of different users and provide more customized services.

[0160] S3: Enter information for newly opened cementing wells.

[0161] In the intelligent recommendation system for adjacent well cementing design of this invention, user input of new cementing information is a key step in the recommendation process. The system requires users to fill in nine mandatory fields, including oilfield, well number, number of wells, well type, well type, cementing method, casing type, and casing size, as well as optional fields such as block, corresponding formation of the casing, geographical location, construction unit, drill bit size, drilling depth, well inclination, well diameter, drilling fluid density, funnel viscosity, pass rate, construction process, and design date. This information collectively constitutes the basic information framework for cementing design, providing the system with the necessary data for accurate recommendations.

[0162] During the process of users inputting information for newly opened cementing wells, the system uses an intelligent correction function to help users ensure the accuracy of the information. For example, if the user inputs "Liaohe Oilfield," the system will use intelligent matching to prompt the user to select the correct "Liaohe Oilfield." This function also applies to information such as geographical location, formation, and block, to reduce input errors and improve the accuracy of recommended results.

[0163] The system was designed with both standard and exceptional aspects of cementing information in mind. For standard information, the system provides drop-down lists allowing users to select from preset standard data, such as casing type, casing size, drill bit size, well type, well shape, oil / gas well type, cementing method, and oilfield. This helps maintain data consistency and standardization. For information that may have exceptional variations, the system allows users to freely input information to support special cases not listed in the standard drop-down lists, thus ensuring the system can adapt to various cementing design requirements.

[0164] By combining standardized selection with free input, the intelligent recommendation system for adjacent well cementing design can flexibly adapt to various cementing design scenarios, providing users with a comprehensive, accurate, and user-friendly information input interface. This design not only improves the efficiency of data input but also provides a solid data foundation for subsequent recommendation algorithms, ensuring the relevance and practicality of the recommendation results.

[0165] S4: Recommend historical cementing design schemes.

[0166] The system first performs necessary filtering on historical cementing data to ensure business consistency based on the user-inputted new cementing information. Then, it calculates the similarity between the filtered historical cementing data and the user-inputted new cementing information, including pairwise similarity calculations between each core business data item. Different similarity calculation algorithms are used for textual and numerical data. Textual data uses different similarity calculation algorithms based on its text characteristics, while numerical data uses a unified similarity calculation algorithm. Additionally, a scoring algorithm is used to assign scores to some missing values ​​in the textual historical cementing data.

[0167] The numerical similarity calculation method is as follows:

[0168]

[0169] i represents the i-th data item, A is the user input information, and B is the historical cementing data information. `max` compares A and B and takes the larger value. `w` is the weight value of this data item after weighted averaging with other data items, with the weight value ranging from 0 to 1. Finally, the similarity score `S` for this data item is obtained, ranging from 0 to 1. The higher the score, the more similar the two data items are.

[0170] The text similarity calculation method is as follows:

[0171]

[0172] `i` represents the i-th data item. The user input information A is split into a continuous string set `a`, and the historical cementing data B is split into a continuous string set `b`. The total length of the intersecting substrings of the two sets is taken. `len` is the length of the user input information A. `w` is the weight value of this data item after weighted averaging with other data items, with a weight value ranging from 0 to 1. Finally, the similarity score `S` of this data item is obtained, ranging from 0 to 1. The higher the score, the more similar the two data items are.

[0173] The calculation method for assigning points to null values ​​is as follows:

[0174] Assigning scores to null values ​​for geographic locations: The well name (name) and geographic location (ghp) are split into a series of values ​​in the form of (name...). i,ghp i The similarity measure vector (S(name)) is calculated between each pair of tuples. i ,name j ),S(ghp i ,ghp j ), where i ≠ j. Construct the following matrix:

[0175]

[0176] For any name score within the interval (α, β), the law of large numbers states that:

[0177]

[0178] Therefore, for any name, the score interval (α, β) of ghp can be assigned the following scores:

[0179]

[0180] The method for assigning void values ​​to blocks can refer to the logic of geographical location. For assigning void values ​​to formations, drilling depth latitude can be added to the well name, and the rest is the same as the logic of geographical location.

[0181] S5: Display of recommendation results.

[0182] After the user completes the input of information for the new cementing well and clicks the "Recommend" button, the intelligent recommendation system for adjacent well cementing design of this invention will activate its core algorithm. The system will calculate the depth similarity between the user-input information for the new cementing well and historical cementing data, and score the results according to preset algorithm parameters. After the calculation is completed, the system will display the recommendation results in the user interface, highlighting the recommendation item that best matches the user's input information in a striking red color for easy identification and review by the user.

[0183] To provide more flexible viewing options, the system also allows users to filter the recommended data from the past two years or all historical data by checking or unchecking checkboxes. This feature enables users to choose to view recommended data within different time ranges according to their specific needs, enhancing the system's usability and user-friendliness.

[0184] S6: Adoption and optimization of recommendation results.

[0185] After the user reviews and selects the most suitable cementing design scheme, the intelligent recommendation system for adjacent well cementing designs of this invention will record and analyze each adoption behavior. This valuable data will be used to optimize the system's internal algorithms, especially adjusting the default weights of the data items involved in the calculation, to improve the accuracy and relevance of the recommendation results.

[0186] One of the system's core features is its self-learning ability. Based on a user's adoption history, the system can automatically adjust the weight of recommended information to better meet the user's actual needs. For each recommendation from each user, the system performs learning calculations to optimize weight allocation. For example, if a user does not choose the top recommended result but selects another option, the system will record this choice and adjust the weight accordingly to ensure that the user's optimal choice will be ranked top in future recommendations.

[0187] In the process of updating and optimizing the recommendation information weights, the system adopts the RankNet loss function and combines iterative updates of the weights using stochastic gradient descent to achieve more accurate recommendations. The RankNet loss function is defined as follows:

[0188]

[0189] Here, T(i,j) is an indicator function representing the relative order between two wells. If well i better meets the user's requirements, then T(i,j) = 1; if well j better meets the user's requirements, then T(i,j) = 0; if both meet the user's requirements (this situation rarely occurs), then T(i,j) = 0.5. i and S j The scores are for the target oil well and the non-target oil well, respectively.

[0190] The gradient function is used to iteratively update weights, and it is defined as follows:

[0191]

[0192] By iteratively updating weights using a gradient function, the system aims to minimize the loss function, iterating step by step until the target well ranks first. Through this intelligent learning and weight adjustment mechanism, the system can continuously evolve to better meet users' personalized needs, improving the intelligence level of the recommendation system and user satisfaction. This continuous optimization and learning process is a significant feature of this invention, not only improving the system's recommendation quality but also bringing innovative solutions to the cementing design field. In this way, the system can continuously adapt to and predict user needs, providing users with more accurate and personalized cementing design recommendations.

[0193] As described above, existing technologies cannot provide reference guidance for cementing construction design and schemes for subsequent wells of the same type and in the same block based on existing massive amounts of data and rich practical experience, which is detrimental to improving cementing quality and work efficiency. This invention addresses the technical pain point of relying on historical cementing data, conducting data preprocessing and data mining to achieve in-depth information mining and analysis throughout the entire cementing process. Finally, through scientific computational logic, it calculates the similarity between new well cementing and historical cementing design schemes, providing engineers with recommendations for historically similar cementing design schemes, helping them to design new well cementing schemes better and more efficiently.

[0194] This invention provides a visualized intelligent recommendation system and method for adjacent well cementing design, which effectively solves the problem of historical cementing data quality. It can receive user input of relevant information for newly opened cementing, such as well name, well type, well classification, cementing type, current opening, oil field, casing type, casing size, drill bit size, drilling depth, funnel viscosity, well fluid density, well inclination, well diameter, block, geographical location, formation, and other core factors, and complete the recommendation of historical adjacent well cementing designs, which effectively improves the efficiency and quality of new cementing design formulation.

[0195] Based on the same inventive concept, this application also provides a cementing scheme recommendation device, which can be used to implement the method described in the above embodiments, as shown in the following embodiments. Since the principle of the cementing scheme recommendation device in solving the problem is similar to that of the cementing scheme recommendation method, the implementation of the cementing scheme recommendation device can refer to the implementation of the cementing scheme recommendation method, and repeated details will not be elaborated further. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0196] Embodiments of the present invention provide a specific implementation of a cementing scheme recommendation device capable of implementing a cementing scheme recommendation method, wherein, see [link to specific implementation details]. Figure 8 A recommended cementing solution device includes:

[0197] The text similarity determination module 10 is used to determine the similarity between the text information of the attribute information of the newly opened cementing well and the text information of the attribute information of the multiple opened cementing wells based on the length of the longest common subsequence, the word order difference, the number of character edits required to achieve the same word order, and a first preset condition.

[0198] The numerical similarity determination module 20 is used to determine the similarity between the numerical information of the attribute information of the newly opened cementing well and the numerical information of the attribute information of the multiple opened cementing wells based on the length, type, size, distribution trend, and second preset conditions of the numerical information in the attribute information of the newly opened cementing well and the numerical information in the attribute information of the multiple opened cementing wells.

[0199] The cementing scheme selection module 30 is used to select the cementing scheme for the newly opened well from among multiple cementing schemes that have already been opened, based on the similarity of the textual information and the similarity of the numerical information.

[0200] In some embodiments of the present invention, see Figure 9 The text similarity determination module 10 includes:

[0201] The first similarity determination unit 10a is used to determine multiple first candidate similarities between the text information corresponding to the newly opened cementing well and the text information corresponding to the multiple opened cementing wells based on the length of the longest common subsequence, the word order difference, and the number of character edits required to achieve the same word order in the text information of the attribute information of the newly opened cementing well and the text information of the attribute information of the multiple opened cementing wells.

[0202] The text similarity selection unit 10b is used to select the similarity of the text information from the plurality of first candidate similarities according to the first preset condition; wherein, the first preset condition is that the number of different characters at corresponding positions between the string of the newly opened cementing well and the strings of the plurality of opened cementing wells is less than a first preset value.

[0203] In some embodiments of the present invention, see Figure 10 The numerical similarity determination module 20 includes:

[0204] The second similarity determination unit 20a is used to determine multiple second alternative similarities between the numerical information corresponding to the newly opened cementing well and the numerical information corresponding to the multiple opened cementing wells based on the length, type and size of the numerical information in the attribute information of the newly opened cementing well and the numerical information in the attribute information of the multiple opened cementing wells.

[0205] The numerical similarity selection unit 20b is used to select the similarity of the numerical information from the plurality of second candidate similarities according to a second preset condition; wherein, the second preset condition is that the similarity between the distribution trend corresponding to the newly opened cementing well and the distribution trend corresponding to the plurality of opened cementing wells is greater than the second preset value.

[0206] In some embodiments of the present invention, the word order of the greatest common subsequence is the position of the greatest common subsequence in the corresponding string;

[0207] The attribute information includes: well name, well type, well class, cementing type, current opening, oil field, casing type, casing size, drill bit size, drilling depth, funnel viscosity, well fluid density, well inclination, well diameter, block, geographical location, and formation characteristics.

[0208] In some embodiments of the present invention, see Figure 11 When the attribute information corresponding to the well name and / or the geographical location is partially missing, a cementing scheme recommendation device further includes:

[0209] The tuple generation module 40 is used to split the well name corresponding to the newly opened cementing well, the geographical location, the well names corresponding to the multiple opened cementing wells, and the geographical location to generate multiple tuples;

[0210] The similarity metric vector determination module 50 is used to determine the similarity metric vector between the tuple corresponding to the newly opened cementing well and the tuple corresponding to the multiple opened cementing wells.

[0211] The missing score assignment module 60 is used to assign scores to the parts of the attribute information that are partially missing based on the similarity metric vector.

[0212] As described above, embodiments of the present invention provide a cementing scheme recommendation device, comprising: a text similarity determination module, used to determine the similarity between the textual information of the attribute information of a newly opened cementing well and the textual information of the attribute information of multiple opened cementing wells based on the length of the longest common subsequence, the word order difference, the number of character edits required to achieve the same word order, and a first preset condition; a numerical similarity determination module, used to determine the similarity between the numerical information of the attribute information of a newly opened cementing well and the numerical information of the attribute information of multiple opened cementing wells based on the length, type, size, distribution trend, and a second preset condition; and a cementing scheme selection module, used to select a cementing scheme for a newly opened cementing well from among the cementing schemes of multiple opened cementing wells based on the similarity of the textual information and the similarity of the numerical information.

[0213] Based on historical cementing data, this invention calculates the similarity between cementing designs for new wells and historical cementing designs, and provides recommendations for similar cementing designs for new wells, thereby enabling better and more efficient design of new cementing schemes.

[0214] This application also provides a specific implementation of an electronic device capable of implementing all steps in the cementing scheme recommendation method described in the above embodiments. See [link to implementation details]. Figure 12 The electronic devices specifically include the following:

[0215] Electronic device 600 may also include: a communication module 110, an input unit 120, an audio processing unit 130, a display 160, and a power supply 170. It is worth noting that electronic device 600 does not necessarily need to include these components. Figure 12 All components shown; in addition, the electronic device 600 may also include Figure 12 For components not shown in the figure, refer to existing technologies. It is worth noting that this figure is exemplary; other types of structures can also be used to supplement or replace this structure to achieve telecommunications functions or other functions.

[0216] like Figure 12 As shown, the processor 100, sometimes also referred to as a controller or operating control, may include a microprocessor or other processor device and / or logic device. The processor 100 receives inputs and controls the operation of various components of the electronic device 600.

[0217] The memory 140 may be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It may store the aforementioned failure-related information, and also store a program for executing that information. The processor 100 may execute the program stored in the memory 140 to perform information storage or processing, etc.

[0218] Input unit 120 provides input to processor 100. Input unit 120 may be, for example, a keypad or touch input device. Power supply 170 provides power to electronic device 600. Display 160 displays images and text. Display 160 may be, for example, an LCD display, but is not limited thereto.

[0219] Memory 140 can be a solid-state memory, such as read-only memory (ROM), random access memory (RAM), SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and contains more data; examples of memory 140 are sometimes referred to as EPROM, etc. Memory 140 can also be some other type of device. Memory 140 includes a buffer 141 (sometimes referred to as buffer memory). Memory 140 may include an application / function storage unit 142 for storing application programs and function programs or processes for executing the operation of electronic device 600 by processor 100.

[0220] The memory 140 may also include a data storage unit 143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 144 of the memory 140 may include various drivers for the electronic device's communication functions and / or for performing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0221] The communication module 110 includes a transmitter / receiver that transmits and receives signals via antenna 111. The communication module 110 is coupled to processor 100 to provide input signals and receive output signals, which can be the same as in a conventional mobile communication terminal.

[0222] Based on different communication technologies, multiple communication modules 110 can be configured in the same electronic device, such as cellular network modules, Bluetooth modules, and / or wireless LAN modules. The communication module 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and receive audio input from the microphone 132, thereby realizing typical telecommunications functions. The audio processor 130 may include any suitable buffer, decoder, amplifier, etc. Additionally, the audio processor 130 is coupled to the processor 100, enabling on-device recording via the microphone 132 and on-device playback of stored sound via the speaker 131.

[0223] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, hardware + program embodiments are relatively simple in description because they are fundamentally similar to method embodiments; relevant parts can be referred to the descriptions in the method embodiments.

[0224] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0225] While this application provides method operation steps as shown in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual device or client product execution, the method can be executed sequentially as shown in the embodiments or drawings, or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0226] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing the embodiments of this specification, the functions of each module can be implemented in one or more software and / or hardware components, or a module that performs the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0227] Those skilled in the art will also know that, besides implementing the controller using purely computer-readable program code, the same functions can be achieved by logically programming the method steps, making the controller function as logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers (PLCs), and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the devices within it used to implement various functions can also be considered structures within that hardware component. Alternatively, the devices used to implement various functions can be considered as both software modules implementing the method and structures within a hardware component.

[0228] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0229] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0230] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, system embodiments are basically similar to method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. In the description of this specification, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the embodiments in this specification. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0231] The above description is merely an embodiment of the present specification and is not intended to limit the embodiments of the present specification. For those skilled in the art, various modifications and variations can be made to the embodiments of the present specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the embodiments of the present specification should be included within the scope of the claims of the embodiments of the present specification.

Claims

1. A method for recommending cementing schemes, characterized in that, include: Based on the length of the longest common subsequence of the textual information of the attribute information of the newly opened cementing well and the textual information of the attribute information of multiple opened cementing wells, the word order difference, the number of character edits required to achieve the same word order, and the first preset condition, the similarity between the textual information of the attribute information of the newly opened cementing well and the attribute information of the multiple opened cementing wells is determined. The similarity between the numerical information of the attribute information of the newly opened cementing well and the numerical information of the attribute information of the multiple opened cementing wells is determined based on the length, type, size, distribution trend, and second preset conditions of the numerical information in the attribute information of the newly opened cementing well and the numerical information in the attribute information of the multiple opened cementing wells. Among multiple cementing schemes that have already been opened, the cementing scheme for the newly opened well is selected based on the similarity of the textual information and the similarity of the numerical information.

2. The cementing scheme recommendation method according to claim 1, characterized in that, Based on the length of the longest common subsequence of the textual information of the attribute information of the newly opened cementing well and the textual information of the attribute information of the multiple opened cementing wells, the word order difference, the number of character edits required to achieve the same word order, and a first preset condition, the similarity between the textual information of the attribute information of the newly opened cementing well and the attribute information of the multiple opened cementing wells is determined, including: Based on the length of the longest common subsequence, the word order difference, and the number of character edits required to achieve the same word order in the textual information of the attribute information of the newly opened cementing well and the textual information of the attribute information of the multiple opened cementing wells, multiple first alternative similarities are determined between the textual information of the newly opened cementing well and the textual information of the multiple opened cementing wells. The similarity of the text information is selected from the plurality of first candidate similarities according to the first preset condition; wherein, the first preset condition is that the number of different characters at corresponding positions between the string of the newly opened cementing well and the strings of the plurality of opened cementing wells is less than a first preset value.

3. The cementing scheme recommendation method according to claim 1, characterized in that, The similarity between the numerical information of the attribute information of the newly opened cementing well and the numerical information of the attribute information of the multiple opened cementing wells is determined based on the length, type, size, and distribution trend of the numerical information in the attribute information of the newly opened cementing well and the numerical information in the attribute information of the multiple opened cementing wells, including: Based on the length, type, and size of the numerical information in the attribute information of the newly opened cementing well and the numerical information in the attribute information of the multiple opened cementing wells, determine multiple second alternative similarities between the numerical information corresponding to the newly opened cementing well and the numerical information corresponding to the multiple opened cementing wells. The similarity of the numerical information is selected from the plurality of second alternative similarities according to a second preset condition; wherein, the second preset condition is that the similarity between the distribution trend corresponding to the newly opened cementing well and the distribution trend corresponding to the plurality of opened cementing wells is greater than the second preset value.

4. The cementing scheme recommendation method according to any one of claims 1 to 3, characterized in that, The word order of the greatest common subsequence is the position of the greatest common subsequence in the corresponding string; The attribute information includes: well name, well type, well class, cementing type, current opening, oil field, casing type, casing size, drill bit size, drilling depth, funnel viscosity, well fluid density, well inclination, well diameter, block, geographical location, and formation characteristics.

5. The cementing scheme recommendation method according to claim 4, characterized in that, When the attribute information corresponding to the well name and / or the geographical location is partially missing, it also includes: The well name corresponding to the newly opened cementing well, the geographical location, the well name corresponding to the multiple opened cementing wells, and the geographical location are split to generate multiple tuples; Determine the similarity metric vector between the tuple corresponding to the newly opened cementing well and the tuple corresponding to the plurality of already opened cementing wells; The similarity metric vector is used to assign scores to the parts of the attribute information that are partially missing.

6. A cementing scheme recommendation device, characterized in that, include: The text similarity determination module is used to determine the similarity between the text information of the attribute information of the newly opened cementing well and the text information of the attribute information of the multiple opened cementing wells based on the length of the longest common subsequence, the word order difference, the number of character edits required to achieve the same word order, and a first preset condition. The numerical similarity determination module is used to determine the similarity between the numerical information of the attribute information of the newly opened cementing well and the numerical information of the attribute information of the multiple opened cementing wells based on the length, type, size, distribution trend, and second preset conditions of the numerical information in the attribute information of the newly opened cementing well and the numerical information in the attribute information of the multiple opened cementing wells. The cementing scheme selection module is used to select the cementing scheme for the newly opened well from among multiple cementing schemes that have already been opened, based on the similarity of the textual information and the similarity of the numerical information.

7. The cementing scheme recommendation device according to claim 6, characterized in that, The text similarity determination module includes: The first similarity determination unit is used to determine multiple first candidate similarities between the text information corresponding to the newly opened cementing well and the text information corresponding to the multiple opened cementing wells based on the length of the longest common subsequence, the word order difference, and the number of character edits required to achieve the same word order in the text information of the attribute information of the newly opened cementing well and the text information of the attribute information of the multiple opened cementing wells. A text similarity selection unit is used to select the similarity of the text information from a plurality of first candidate similarities according to the first preset condition; wherein, the first preset condition is that the number of different characters at corresponding positions between the string of the newly opened cementing well and the strings of the plurality of opened cementing wells is less than a first preset value.

8. The cementing scheme recommendation device according to claim 6, characterized in that, The numerical similarity determination module includes: The second similarity determination unit is used to determine multiple second alternative similarities between the numerical information corresponding to the newly opened cementing well and the numerical information corresponding to the multiple opened cementing wells based on the length, type and size of the numerical information in the attribute information of the newly opened cementing well and the numerical information in the attribute information of the multiple opened cementing wells. A numerical similarity selection unit is used to select the similarity of the numerical information from a plurality of second candidate similarities according to a second preset condition; wherein, the second preset condition is that the similarity between the distribution trend corresponding to the newly opened cementing well and the distribution trend corresponding to the plurality of opened cementing wells is greater than a second preset value.

9. The cementing scheme recommendation device according to any one of claims 6 to 8, characterized in that, The word order of the greatest common subsequence is the position of the greatest common subsequence in the corresponding string; The attribute information includes: well name, well type, well class, cementing type, current opening, oil field, casing type, casing size, drill bit size, drilling depth, funnel viscosity, well fluid density, well inclination, well diameter, block, geographical location, and formation characteristics.

10. The cementing scheme recommendation device according to claim 9, characterized in that, When the attribute information corresponding to the well name and / or the geographical location is partially missing, it also includes: The tuple generation module is used to split the well name corresponding to the newly opened cementing well, the geographical location, the well names corresponding to the multiple opened cementing wells, and the geographical location to generate multiple tuples; A similarity metric vector determination module is used to determine the similarity metric vector between the tuple corresponding to the newly opened cementing well and the tuple corresponding to the multiple opened cementing wells; The missing score assignment module is used to assign scores to the parts of the attribute information that are partially missing based on the similarity metric vector.

11. A computer program product, comprising a computer program / instructions, characterized in that, When executed by a processor, the computer program / instruction implements the steps of the cementing scheme recommendation method according to any one of claims 1 to 5.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the cementing scheme recommendation method according to any one of claims 1 to 5.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the cementing scheme recommendation method according to any one of claims 1 to 5.

Images