Drilling scheme recommendation method and device, computer program product and electronic equipment

Abstract

The invention relates to the technical field of drilling control, and relates to a drilling scheme recommendation method and device, a computer program product and electronic equipment. The method comprises the steps that according to drilling environment characteristics, drilling scheme characteristics are matched from a drilling scheme database, scheme construction is conducted according to the drilling scheme characteristics, and a first candidate drilling scheme is obtained; encoding the first candidate drilling scheme to obtain a first encoding feature, and encoding the drilling environment feature to obtain a second encoding feature; calculating the second coding features and the first coding features to obtain similarity scores of the first candidate drilling schemes, and determining a second candidate drilling scheme from the first candidate drilling schemes according to the similarity scores; quantifying the drilling demand information into demand indexes, evaluating second candidate drilling schemes based on the demand indexes, and determining a reference drilling scheme from the second candidate drilling schemes according to evaluation scores; and carrying out correction and reliability rechecking on the reference drilling scheme. The present disclosure may recommend a drilling scheme.

Description

Technical Field

[0001] This disclosure relates to the field of drilling control technology, and more specifically, to a drilling scheme recommendation method, a drilling scheme recommendation device, a computer program product, and an electronic device. Background Technology

[0002] Offshore wind power drilling refers to specialized drilling projects conducted in the early stages and during the construction of offshore wind farms, targeting the seabed and shallow sea strata of the selected site area. It is a core component of offshore wind power engineering exploration, using specialized offshore drilling equipment (such as jack-up drilling platforms and drilling vessels) to drill holes into the seabed strata, obtaining rock cores, soil samples, and in-situ test data to provide geological evidence for the design, construction, and safe operation of the wind farm. Choosing the appropriate drilling scheme for offshore drilling plays a crucial role in improving drilling efficiency and effectiveness.

[0003] It should be noted that the information in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0004] The purpose of this disclosure is to provide a drilling scheme recommendation method, a drilling scheme recommendation device, a computer program product, and an electronic device, thereby providing suitable schemes for offshore wind power drilling and improving drilling efficiency and results.

[0005] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0006] According to one aspect of this disclosure, a drilling scheme recommendation method is provided, comprising: acquiring drilling demand information and multi-dimensional drilling environment features; matching multiple drilling scheme features from a pre-established drilling scheme database based on the multi-dimensional drilling environment features, and constructing schemes based on the multiple drilling scheme features to obtain multiple first candidate drilling schemes; encoding the multiple first candidate drilling schemes to obtain multiple first encoded features, and encoding the multi-dimensional drilling environment features to obtain second encoded features; and performing interactive calculations between the second encoded features and each first encoded feature to obtain the similarity corresponding to each first candidate drilling scheme. The drilling process involves scoring the drilling requirements and determining multiple second-candidate drilling schemes from among the first-candidate schemes based on similarity scores. Drilling demand information is quantified to obtain multiple demand indicators, which are then used to evaluate the second-candidate drilling schemes and obtain evaluation scores. Reference drilling schemes are then determined from among the second-candidate schemes based on these evaluation scores. Based on historical amendment data, drilling demand information, and drilling environment characteristics, the reference drilling schemes are revised to obtain target drilling schemes. The reliability of the target drilling schemes is then verified, and the target drilling schemes that pass the verification are determined as the recommended target drilling schemes.

[0007] In an exemplary embodiment of this disclosure, before matching multiple drilling scheme features from a pre-established drilling scheme database based on the multidimensional drilling environment features, and constructing a scheme based on the multiple drilling scheme features to obtain multiple first candidate drilling schemes, the method further includes: obtaining a set of historical successful drilling schemes; deconstructing each historical successful drilling scheme in the set to obtain atomized drilling feature elements; establishing a weighted mapping relationship between each atomized drilling feature element and drilling environment features to obtain the pre-established drilling scheme database; wherein the weighted mapping relationship includes the correspondence between atomized drilling feature elements and drilling environment features and the matching degree weight.

[0008] In an exemplary embodiment of this disclosure, the step of matching multiple drilling scheme features from a pre-established drilling scheme database based on the multidimensional drilling environment features, and constructing a scheme based on the multiple drilling scheme features to obtain multiple first candidate drilling schemes, includes: calculating the environment adaptability score of each atomized drilling feature element in the pre-established drilling scheme database based on the weighted mapping relationship and the multidimensional drilling environment features; filtering out the multiple drilling scheme features from the atomized drilling feature elements based on the environment adaptability score; performing compatibility and mutual exclusion judgment on the multiple drilling scheme features based on the engineering constraint rule base to filter out drilling scheme features that contradict each other; and constructing the multiple first candidate drilling schemes based on the remaining drilling scheme features.

[0009] In an exemplary embodiment of this disclosure, the step of interactively calculating the second encoded feature with each of the first encoded features to obtain a similarity score corresponding to each of the first candidate drilling schemes, and determining a plurality of second candidate drilling schemes from the plurality of first candidate drilling schemes based on the similarity score, includes: for each first encoded feature, interactively calculating the first encoded feature with the second encoded feature based on a cross-attention mechanism to obtain a target encoded feature, and processing the target encoded feature into the similarity score using a fully connected network; determining the mean and standard deviation of each of the similarity scores, and determining a target threshold based on the mean and standard deviation; and determining a plurality of second candidate drilling schemes from the plurality of first candidate drilling schemes based on the target threshold and each of the similarity scores.

[0010] In one exemplary embodiment of this disclosure, the second candidate drilling scheme includes at least equipment, platform, schedule, and process; the step of quantifying the drilling demand information to obtain multiple demand indicators, and evaluating the multiple second candidate drilling schemes based on the multiple demand indicators to obtain evaluation scores, and determining a reference drilling scheme from the multiple second candidate drilling schemes based on the evaluation scores, includes: for each second candidate drilling scheme, evaluating the cost-effectiveness ratio of the second candidate drilling scheme based on the multiple demand indicators and in combination with the equipment, platform, schedule, and process; predicting the failure probability of the second candidate drilling scheme using a large model based on the multidimensional drilling environment characteristics; determining the evaluation score of the second candidate drilling scheme based on the cost-effectiveness ratio and the failure probability; and determining the reference drilling scheme from the multiple second candidate drilling schemes based on the evaluation scores of each second candidate drilling scheme.

[0011] In one exemplary embodiment of this disclosure, each historical modification example data is a triple including drilling scenario information, original scheme data, and modified scheme data. The drilling scenario information includes drilling environment data and drilling demand data. The step of modifying the reference drilling scheme based on the historical modification example data, the drilling demand information, and the drilling environment characteristics to obtain a target drilling scheme includes: matching the drilling demand information and the drilling environment characteristics with the drilling environment data and drilling demand data in the historical modification example data to determine multiple target historical modification example data based on the matching results; for each target historical modification example data, determining modification difference data based on the original scheme data and the modified scheme data, the modification difference data reflecting the difference between the original scheme data and the modified scheme data; and modifying the reference drilling scheme based on the modification difference data corresponding to each target historical modification example data to obtain the target drilling scheme.

[0012] In one exemplary embodiment of this disclosure, the step of verifying the reliability of the target drilling scheme and determining the target drilling scheme that passes the verification as the target recommended drilling scheme includes: obtaining a pre-trained risk detection model, wherein the pre-trained risk detection model is trained based on historical abnormal drilling data and corresponding drilling environment characteristics; using the pre-trained risk detection model to perform a risk assessment on the target drilling scheme to obtain a risk probability; and if the risk probability is lower than a preset risk threshold, then determining the target drilling scheme as the target recommended drilling scheme.

[0013] According to one aspect of this disclosure, a drilling scheme recommendation device is provided, comprising: an information acquisition module for acquiring drilling demand information and multi-dimensional drilling environment features; a first scheme determination module for matching multiple drilling scheme features from a pre-established drilling scheme database based on the multi-dimensional drilling environment features, and constructing schemes based on the multiple drilling scheme features to obtain multiple first candidate drilling schemes; a feature encoding module for encoding the multiple first candidate drilling schemes respectively to obtain multiple first encoded features, and encoding the multi-dimensional drilling environment features to obtain second encoded features; and a second scheme determination module for interactively calculating the second encoded features with each of the first encoded features to obtain the similarity corresponding to each of the first candidate drilling schemes. The system firstly assigns a score and determines multiple second candidate drilling schemes from the multiple first candidate drilling schemes based on the similarity score; secondly, it quantifies the drilling demand information to obtain multiple demand indicators and evaluates the multiple second candidate drilling schemes based on the multiple demand indicators to obtain an evaluation score, and determines a reference drilling scheme from the multiple second candidate drilling schemes based on the evaluation score; thirdly, it modifies the reference drilling scheme based on historical amendment example data, the drilling demand information, and the drilling environment characteristics to obtain a target drilling scheme, and verifies the reliability of the target drilling scheme based on historical abnormal drilling data, and determines the target drilling scheme that passes the verification as the target recommended drilling scheme.

[0014] According to one aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements any of the above methods.

[0015] According to one aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any of the above methods by executing the executable instructions.

[0016] The drilling scheme recommendation method in the exemplary embodiments of this disclosure obtains drilling demand information and multi-dimensional drilling environment features; based on the multi-dimensional drilling environment features, it matches multiple drilling scheme features from a pre-established drilling scheme database, and constructs schemes based on the multiple drilling scheme features to obtain multiple first candidate drilling schemes; it encodes each of the multiple first candidate drilling schemes to obtain multiple first coded features, and encodes the multi-dimensional drilling environment features to obtain second coded features; it then performs interactive calculations between the second coded features and each of the first coded features to obtain a similarity score corresponding to each first candidate drilling scheme. Based on similarity scores, multiple second-candidate drilling schemes are determined from multiple first-candidate drilling schemes. Drilling demand information is quantified to obtain multiple demand indicators, and the multiple second-candidate drilling schemes are evaluated based on these indicators to obtain evaluation scores. Reference drilling schemes are then determined from the multiple second-candidate drilling schemes based on these evaluation scores. Based on historical amendment example data, drilling demand information, and drilling environment characteristics, the reference drilling schemes are revised to obtain target drilling schemes. The reliability of the target drilling schemes is then verified, and the target drilling schemes that pass the verification are determined as the target recommended drilling schemes.

[0017] On the one hand, the drilling scheme recommendation process, through the interactive calculation of multi-dimensional drilling environment feature encoding (second encoding feature) and drilling scheme encoding (first encoding feature), achieves deep, non-linear feature matching. This captures the inherent connection between the complexity of the offshore drilling environment and the drilling scheme, ensuring that the recommended second candidate drilling scheme has a higher degree of fit with the current environment, thereby improving the accuracy of the initial screening. On the other hand, through quantitative evaluation, drilling requirements are transformed into measurable indicators, enabling the selection of the reference drilling scheme with the highest comprehensive evaluation score and best suited to the client's actual interests from multiple technically feasible options. Furthermore, based on historical amendment data and reliability verification, the process demonstrates high feasibility and safety in practice, significantly reducing the risk of project failure and improving both drilling efficiency and results.

[0018] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0019] The above and other objects, features, and advantages of this disclosure will become readily apparent from the following detailed description of exemplary embodiments, taken in conjunction with the accompanying drawings. Several embodiments of this disclosure are illustrated in the drawings by way of example and not limitation.

[0020] Figure 1 A diagram illustrating an application environment related to a drilling scheme recommendation method of an exemplary embodiment of this disclosure is provided.

[0021] Figure 2 A flowchart of a drilling scheme recommendation method according to an exemplary embodiment of the present disclosure is shown.

[0022] Figure 3 A flowchart of a pre-established drilling scheme database according to an exemplary embodiment of the present disclosure is shown.

[0023] Figure 4 A flowchart illustrating an example of obtaining a first candidate drilling scheme according to an exemplary embodiment of the present disclosure is shown.

[0024] Figure 5 A flowchart illustrating an embodiment of the present disclosure for obtaining a second candidate drilling scheme is shown.

[0025] Figure 6 A flowchart illustrating the determination of a reference drilling scheme according to an exemplary embodiment of the present disclosure is shown.

[0026] Figure 7 A flowchart illustrating a target drilling scheme according to an exemplary embodiment of the present disclosure is shown.

[0027] Figure 8 A schematic diagram of the composition of a drilling scheme recommendation apparatus according to an exemplary embodiment of the present disclosure is shown.

[0028] Figure 9 A block diagram of an electronic device according to an exemplary embodiment of the present disclosure is shown.

[0029] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed Implementation

[0030] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore their detailed description will be omitted.

[0031] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced without one or more of the specific details described, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known structures, methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0032] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, or in one or more software-hardened modules, or in different network and / or processor devices and / or microcontroller devices.

[0033] Offshore wind power drilling refers to specialized drilling projects conducted in the early stages and during the construction of offshore wind farms, targeting the seabed and shallow sea strata of the selected site area. It is a core component of offshore wind power engineering exploration, using specialized offshore drilling equipment (such as jack-up drilling platforms and drilling vessels) to drill holes into the seabed strata, obtaining rock cores, soil samples, and in-situ test data to provide geological evidence for the design, construction, and safe operation of the wind farm. With numerous existing offshore drilling platforms, equipment, and methods, selecting a suitable drilling scheme is a pressing issue. However, currently, there are no recommended methods for offshore wind power drilling, resulting in low efficiency, high difficulty, and a certain degree of impact on drilling effectiveness.

[0034] Based on this, the exemplary embodiments of this disclosure provide a drilling scheme recommendation method, which solves the matching accuracy problem in complex environments through coding and interactive calculation, solves the multi-objective optimization decision-making problem through demand quantification assessment, solves the scheme reliability and risk control problem through case correction and review, and finally solves the efficiency and standardization problem through full-process automation. This method can provide cost-effective and safe drilling schemes, and improves the quality and efficiency of the early planning work of offshore wind power drilling to a certain extent.

[0035] The drilling scheme recommendation method provided in the exemplary embodiments of this disclosure can be applied to, for example, Figure 1 The application environment shown is illustrated. Terminal 101 communicates with server 102 via a network. A data storage system can store the data that server 102 needs to process. The data storage system can be integrated onto server 102, or it can be located in the cloud or on another network server.

[0036] In one exemplary embodiment, the drilling scheme recommendation method provided by the exemplary embodiment of this disclosure can be executed by server 102, and correspondingly, the drilling scheme recommendation is set in server 102. Correspondingly, in this manner executed by server 102, server 102 can begin executing the steps in the technical solution of the exemplary embodiment of this disclosure in response to a triggering command, wherein the triggering command can be sent by a terminal used by a user, or can be triggered locally by the server in response to some automated event.

[0037] Server 102 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. Server 102 can execute background tasks.

[0038] Furthermore, in another exemplary embodiment, terminal 101 may also have similar functions to server 102, thereby executing the drilling scheme recommendation method provided by the exemplary embodiments of this disclosure.

[0039] The terminal 101 can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, IoT device, or portable wearable device. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. The terminal 101 can also be referred to as a mobile terminal, terminal device, mobile device, etc. The exemplary embodiments of this disclosure do not limit the type of terminal 101.

[0040] Furthermore, the technical solutions of the exemplary embodiments of this disclosure can also be executed collaboratively by terminal 101 and server 102. In this collaborative execution method, some steps of the technical solutions provided by the exemplary embodiments of this disclosure are executed by terminal 101, while other steps are executed by server 102. It should be noted that in this collaborative execution method, the steps executed by terminal 101 and server 102 respectively can be dynamically adjusted according to actual circumstances, and no special restrictions are placed on this. Terminal 101 and server 102 can be directly or indirectly connected via wireless communication, and the exemplary embodiments of this disclosure do not impose any special restrictions here.

[0041] like Figure 2 The diagram shown is a flowchart of a drilling scheme recommendation method according to an exemplary embodiment of this disclosure, with reference to... Figure 2 As shown, the recommended drilling method includes steps S210 to S260: Step S210: Obtain drilling demand information and multi-dimensional drilling environment characteristics.

[0042] Step S220: Based on the multidimensional drilling environment characteristics, match multiple drilling scheme features from the pre-established drilling scheme database, and construct schemes based on the multiple drilling scheme features to obtain multiple first candidate drilling schemes.

[0043] Step S230: Encode the multiple first candidate drilling schemes to obtain multiple first coding features, and encode the multidimensional drilling environment features to obtain second coding features.

[0044] Step S240: Perform interactive calculations between the second coding feature and each first coding feature to obtain the similarity score corresponding to each first candidate drilling scheme, and determine multiple second candidate drilling schemes from multiple first candidate drilling schemes based on the similarity score.

[0045] Step S250: Quantify the drilling demand information to obtain multiple demand indicators, and evaluate multiple second candidate drilling schemes based on the multiple demand indicators to obtain evaluation scores, so as to determine the reference drilling scheme from the multiple second candidate drilling schemes according to the evaluation scores.

[0046] Step S260: Based on historical amendment example data, drilling demand information and drilling environment characteristics, the reference drilling plan is revised to obtain the target drilling plan, and the reliability of the target drilling plan is verified. The target drilling plan that passes the verification is determined as the target recommended drilling plan.

[0047] The drilling scheme recommendation method of this disclosure, through exemplary embodiments, achieves deep, non-linear feature matching by introducing interactive calculations of multi-dimensional drilling environment feature encoding (second encoding features) and drilling scheme encoding (first encoding features). This captures the inherent connection between the complexity of the offshore drilling environment and the drilling scheme, ensuring that the recommended second candidate drilling scheme has a higher degree of fit with the current environment, thereby improving the accuracy of the initial screening. Furthermore, through quantitative evaluation, drilling requirements are transformed into measurable indicators, enabling the selection of the reference drilling scheme with the highest comprehensive evaluation score and best suited to the client's actual interests from multiple technically feasible schemes. Moreover, the method is revised based on historical amendment data and undergoes reliability verification, demonstrating high feasibility and safety in practice, significantly reducing the risk of project failure, and improving drilling efficiency and effectiveness.

[0048] Steps S210 to S260 will be described in more detail below.

[0049] In step S210, drilling demand information and multi-dimensional drilling environment characteristics are obtained.

[0050] In the exemplary embodiments of this disclosure, drilling requirement information refers to the subjective, goal-oriented requirements and economic constraints proposed by users (such as owners or construction units) to complete a specific offshore wind power project, such as cost requirements and construction location requirements. This drilling requirement information can originate from the customer's tender documents, technical specifications, or direct communication, without specific limitations. Multidimensional drilling environment characteristics refer to objectively existing characteristics of the drilling operation area that can affect the drilling platform, equipment, methods, and safety. "Multidimensional" means that the data sources of the drilling environment characteristics are diverse, and their data types can be multiple, such as numerical values, categories, and text. It can also refer to comprehensive information obtained from different physical dimensions (such as sea surface waves, ocean currents, and seabed geology) and different data sources (such as remote sensing, field measurements, and geological models).

[0051] In step S220, based on the multidimensional drilling environment characteristics, multiple drilling scheme features are matched from the pre-established drilling scheme database, and schemes are constructed based on the multiple drilling scheme features to obtain multiple first candidate drilling schemes.

[0052] In the exemplary embodiments of this disclosure, the pre-established drilling scheme database can be understood as a structured, digital knowledge base that stores a large amount of core feature data of drilling schemes that have been successfully applied in the past or have been theoretically verified. The pre-established drilling scheme database can also be a weighted mapping relationship between atomized drilling feature elements and drilling environment features, where the weighted mapping relationship includes the correspondence and matching degree weight between the atomized drilling feature elements and drilling environment features.

[0053] Among them, drilling scheme characteristics refer to the set of key parameters used to describe the core technical capabilities and applicable conditions of a drilling scheme. These characteristics are matched and retrieved through a database. Specifically, drilling scheme characteristics may include platform characteristics, equipment characteristics, and method characteristics. For example, platform characteristics include platform type (jack-up, semi-submersible, ship-mounted), operating water depth, deck load, leg length, lifting speed, wind resistance rating, and positioning method (anchoring). Equipment characteristics include drilling rig type (rotary drill, percussion drill), maximum drilling depth, borehole diameter range, coring capability, drill pipe specifications, and mud system capacity. Method characteristics include drilling technology (coring, sampling, in-situ testing), drill bit selection (roller cone bit), wall protection method (mud, casing), and suitable formation type.

[0054] Matching multiple drilling scheme features from a pre-established drilling scheme database can be understood as a logical process of comparing the applicable conditions of the input drilling environment features with those of the drilling scheme features in the database. Scheme construction is the process of combining multiple independent and feasible platform features, equipment features, and method features into a complete and executable drilling scheme according to engineering logic after matching them.

[0055] In one exemplary embodiment, such as Figure 3 As shown, before matching multiple drilling scheme features from a pre-established drilling scheme database based on multi-dimensional drilling environment characteristics, and constructing schemes based on these features to obtain multiple first candidate drilling schemes, the process also includes: Step S310: Obtain the set of historical successful drilling schemes, and deconstruct each historical successful drilling scheme in the set to obtain atomized drilling feature elements.

[0056] Step S320: Establish a weighted mapping relationship between each atomized drilling feature element and the drilling environment feature to obtain a pre-established drilling scheme database. The weighted mapping relationship includes the correspondence and matching weight between the atomized drilling feature elements and the drilling environment feature.

[0057] The historical successful drilling scheme set refers to a collection of drilling scheme cases collected from past engineering projects that have been proven effective in practice, including but not limited to project completion reports, technical summaries, recommended operating conditions in equipment operation manuals, expert experience cases, and practical data obtained from simulations. Deconstruction processing refers to the process of breaking down a complete, comprehensive historical drilling scheme into several independent, indivisible (or no further subdivision required) basic technical units, i.e., deconstructing it into atomized drilling feature elements, which are characteristic data points describing a single dimension of the drilling scheme. For example, "platform type: jack-up" is one feature element, and "maximum operating water depth: 100 meters" is another. The weighted mapping relationship can be understood as a mathematical model used to quantify the correlation strength and applicability between each drilling feature element and different drilling environment characteristics. The matching degree weight is used to represent the importance and reliability of the correspondence between the drilling feature element and the drilling environment characteristics. For example, for the drilling environment characteristic of "hard rock formation (UCS (uniaxial compressive strength) > 80 MPa)," the weight of "drill bit type: diamond drill bit" is high (e.g., 0.95), while the weight of "drill bit type: tricone drill bit" is low (e.g., 0.6).

[0058] As an example, if a historically successful drilling program was described as follows: "In a certain sea area with an interbedded layer of hard clay and sandstone at a water depth of 50 meters, the 'Explorer' jack-up platform (operating water depth 10-80 m, wave resistance 3.5 m) was used, equipped with a 'xx-500' hydraulic top-drive drilling rig (maximum drilling depth 500 m), and the 'yy' drill bit and 'double-tube coring' technology were used to successfully complete a 120-meter core drilling operation," after deconstruction, the atomized drilling characteristic elements include: Platform type: jack-up, Platform model: 'Explorer', Applicable water depth range: [10m, 80m], Wave resistance: 3.5m, Drilling rig type: hydraulic top drive, Drilling rig model: xx-500, Maximum drilling depth capability: 500m, Drill bit type: yy drill bit, Drilling technology: double-tube coring, Target strata: hard clay, sandstone. Furthermore, if the drilling environment characteristics are: water depth = 50m, formation strength = hard, wave height = 2.0m, then for the characteristic element platform type: jack-up, the matching weight with the environmental characteristic water depth = 50m is very high, and can be set to 0.98 (this is because 50m perfectly falls within its applicable range of 10-80m), but the weight with the environmental characteristic formation strength = hard is 0.1 (this is because the relationship between platform type and formation hardness is not very significant). The weighted mapping relationships between other atomized drilling characteristic elements and drilling environment characteristics will not be explained one by one, and can be flexibly adjusted according to the actual implementation scenario. By repeating the above process, a large number of historical successful schemes are deconstructed and mapped, and statistical methods (such as frequency analysis and machine learning model training) are used to determine the corresponding matching weights, thereby obtaining a pre-established drilling scheme database.

[0059] It should be noted that when constructing the pre-established drilling scheme database, the weighted mapping relationship between each atomized drilling feature element and the drilling environment feature can be obtained by processing the historical successful drilling scheme set using statistical methods, or it can be generated based on a pre-trained machine learning model. The pre-trained machine learning model can, for example, use a pre-trained relation building model to establish the weighted mapping relationship between the atomized drilling feature elements and the drilling environment feature. This relation building model can be a network structure such as CNN (Convolutional Neural Networks) or RNN (Recurrent Neural Network), and there are no restrictions on this. Of course, a large model can also be used to process the historical successful drilling scheme set to obtain the weighted mapping relationship; the exemplary embodiments of this disclosure do not impose any special limitations on this.

[0060] The exemplary embodiments of this disclosure, by constructing a drilling scheme database containing weighted mapping relationships, can transform fuzzy experiences and reports from historical successful drilling into structured, computable data. This avoids the loss of successful case data and provides data support for subsequent drilling scheme recommendations. Furthermore, based on this drilling scheme data, the subsequent recommendation process can be more inclined towards safe and reliable choices that have been verified in practice, thereby avoiding subjective bias and increasing the objectivity and scientific nature of decision-making.

[0061] Based on the foregoing exemplary embodiments, such as Figure 4 As shown, based on the multidimensional drilling environment characteristics, multiple drilling scheme features are matched from a pre-established drilling scheme database, and schemes are constructed based on these multiple drilling scheme features to obtain multiple first candidate drilling schemes, which may include: Step S410: Based on the weighted mapping relationship and multidimensional drilling environment characteristics, calculate the environment fit score of each atomized drilling feature element in the pre-established drilling scheme database.

[0062] The environmental adaptability score measures the suitability of a given atomized drilling feature element within a specific multidimensional drilling environment. A higher score indicates that the feature element is more suitable for the current environment. The score is calculated by iterating through each atomized drilling feature element in a pre-established drilling scheme database and utilizing a weighted mapping relationship based on its current environmental characteristics.

[0063] For example, for the drilling feature element "Platform Type: Jack-up", the weights for water depth = 55m are 0.95, wave height = 2.5m are 0.90, and hard bedrock are 0.10. Therefore, its environmental fit score can be calculated as 0.85 using a weighted aggregation function (such as weighted average). Similarly, the environmental fit score is calculated for each atomized drilling feature element in the drilling scheme data; details will not be provided individually.

[0064] Step S420: Based on the environmental adaptability score, select multiple drilling scheme features from the atomized drilling feature elements.

[0065] A score threshold, such as 0.7, can be preset and adjusted according to actual needs. Drilling feature elements with scores higher than this threshold can then be filtered out to obtain multiple drilling scheme features.

[0066] Step S430: Based on the engineering constraint rule base, perform compatibility and mutual exclusion judgment on the features of multiple drilling schemes to filter out drilling scheme features that are contradictory.

[0067] An engineering constraint rule base is a set of rules that stores prior knowledge and physical limitations in the drilling engineering field. It defines the basic logic for whether different equipment, processes, and methods can work together. This engineering constraint rule base can be stored in the form of "IF…THEN…". Compatibility rules refer to rules that allow two or more characteristic elements to work effectively together, such as IF drilling rig type = hydraulic jack drive, THEN requiring deck crane capacity >= 50 tons. Mutually exclusive rules refer to rules that allow two or more characteristic elements to not exist simultaneously in a single scheme, such as drilling process = impact drilling and drilling process = rotary coring being mutually exclusive (this is because generally only one primary process is used).

[0068] This involves judging the compatibility and mutual exclusion of features of multiple drilling schemes to filter out drilling scheme features that contradict each other. In other words, before the scheme is constructed, the logical consistency of the selected high-scoring drilling scheme features is checked to ensure that the final constructed scheme is technically self-consistent and feasible.

[0069] Step S440: Based on the characteristics of the remaining drilling schemes, construct multiple first candidate drilling schemes.

[0070] After obtaining the remaining drilling scheme features through filtering, multiple first candidate drilling schemes are constructed based on these features. Furthermore, these drilling scheme features can be combined in different ways to obtain multiple first candidate drilling schemes.

[0071] The exemplary embodiments of this disclosure, by matching and acquiring features of multiple drilling schemes and constructing schemes, and by calculating environmental adaptability scores, can perform fine-grained priority ranking of a large number of drilling scheme features, thereby prioritizing the option most suitable for the environment and improving the accuracy of quantitative screening. Furthermore, the introduction of an engineering constraint rule base for compatibility / mutual exclusion judgment enhances the practicality and reliability of the recommended schemes, avoids invalid combinations, and thus improves the accuracy and effectiveness of the first candidate drilling scheme.

[0072] In step S230, multiple first candidate drilling schemes are encoded to obtain multiple first encoded features, and multidimensional drilling environment features are encoded to obtain second encoded features.

[0073] In the exemplary embodiments of this disclosure, to standardize data and digitize features so that computers can better understand and process patterns and relationships in the data, each first candidate drilling scheme is encoded, and multidimensional drilling environment features are encoded. The first encoded feature is a numerical vector or matrix obtained by encoding the first candidate drilling scheme, used to characterize the essential attributes of each drilling scheme, including all technical details (platform, equipment, process) of the scheme, which are fused into a dense numerical representation containing rich semantic information. The second encoded feature is a numerical vector or matrix obtained by encoding the input multidimensional drilling environment features, used to capture the comprehensive state of the current operating environment, where all environmental factors (water depth, geology, meteorology, etc.) are fused into a unified numerical representation. Optionally, the feature encoding method can be one-hot encoding, embedding, a Transformer-based encoding network, etc. The exemplary embodiments of this disclosure do not specifically limit the encoding method.

[0074] In step S240, the second coding feature is interactively calculated with each of the first coding features to obtain the similarity score corresponding to each first candidate drilling scheme, and based on the similarity score, multiple second candidate drilling schemes are determined from multiple first candidate drilling schemes.

[0075] In an exemplary embodiment of this disclosure, the similarity score is a quantifiable scalar value output after interactive calculation, used to accurately measure the applicability of a drilling scheme in the current specific environment. The higher the score, the better the scheme matches the current environment.

[0076] like Figure 5 As shown, the second coding feature is interactively calculated with each of the first coding features to obtain the similarity score corresponding to each first candidate drilling scheme. Based on the similarity score, multiple second candidate drilling schemes can be determined from multiple first candidate drilling schemes, including: Step S510: For each first coding feature, the first coding feature and the second coding feature are interactively calculated based on the cross-attention mechanism to obtain the target coding feature, and the target coding feature is processed into a similarity score using a fully connected network.

[0077] The cross-attention mechanism allows one feature to focus on the most relevant part of another feature. The target encoded feature is a new feature representation obtained after weighted fusion through the cross-attention mechanism. It is not the original scheme or environment encoding, but a reinforced feature containing deep interaction information between the two. During the interactive computation process, the second encoded feature can be used as the Query (Q), and the first encoded feature of a candidate drilling scheme can be used as the Key (K) and Value (V). By calculating the similarity (e.g., dot product) between Q and K, a set of attention weights is obtained. The level of the weight indicates the relevance between a certain requirement (Q) of the environment and a certain capability (K) of the scheme. Furthermore, the attention weights obtained in the previous step can be weighted and summed on the encoding (V) of the scheme to obtain the target encoded feature. This attention mechanism-based approach is a conventional approach, and the exemplary embodiments of this disclosure apply it to the interactive computation process of the second encoded feature and the first encoded feature respectively.

[0078] Furthermore, after obtaining the target encoded features, a pre-trained fully connected network can be used to process the target encoded features into similarity scores.

[0079] Step S520 determines the mean and standard deviation of each similarity score, and determines the target threshold based on the mean and standard deviation.

[0080] Step S530: Based on the target threshold and each similarity score, determine multiple second candidate drilling schemes from multiple first candidate drilling schemes.

[0081] The mean and standard deviation of each similarity score are calculated, and then the target threshold is dynamically determined based on the mean and standard deviation. This target threshold is not fixed in advance, but is dynamically calculated based on the statistical distribution characteristics of the scores of the current batch of candidate solutions. For example, the target threshold can be determined according to Equation 1: T = μ + nσ Equation 1 Where T is the target threshold and n is an adjustable parameter, for example, set to 0.5. Schemes that score above the average level (μ) by more than half a standard deviation (σ) based on Equation 1 are the second candidate drilling schemes.

[0082] The exemplary embodiments disclosed herein can focus more precisely on the specific characteristic dimensions most relevant to the environment and the proposed solution, thereby yielding a more accurate second candidate drilling solution. Furthermore, by determining a dynamic threshold, the problem of low-quality selected solutions that may result from a fixed threshold can be avoided.

[0083] In step S250, the drilling demand information is quantified to obtain multiple demand indicators, and multiple second candidate drilling schemes are evaluated based on the multiple demand indicators to obtain evaluation scores, so as to determine the reference drilling scheme from the multiple second candidate drilling schemes according to the evaluation scores.

[0084] In the exemplary embodiments of this disclosure, quantification is the process of transforming subjective and vague drilling demand information from users into a series of measurable and calculable numerical indicators. These demand indicators, obtained after quantification, represent specific values ​​for a particular dimension of drilling demand and may include economic, time-related, and technical indicators, such as estimated total cost, equipment rental rate, daily operating cost, estimated total duration, operating efficiency (meters / day), expected core recovery rate, and environmental compliance score. When evaluating a second candidate drilling scheme, demand indicators with different dimensions can be mapped to a unified scale to achieve data standardization.

[0085] In an exemplary embodiment, the second candidate drilling scheme includes at least equipment, platform, duration, and process. Wherein, such as Figure 6 As shown, drilling demand information is quantified to obtain multiple demand indicators. Multiple second-candidate drilling schemes are then evaluated based on these indicators to obtain evaluation scores. The selection of a reference drilling scheme from these second-candidate schemes based on these evaluation scores may include: Step S610: For each second candidate drilling scheme, evaluate the cost-effectiveness of the second candidate drilling scheme based on multiple demand indicators and in combination with equipment, platform, schedule and process.

[0086] Cost-benefit ratio refers to the ratio between the total benefits generated by a drilling plan and the total cost incurred. The benefits mentioned here include, but are not limited to, positive gains such as reduced time, improved quality, and reduced risk. Cost-benefit ratio = Total Benefits / Total Cost. It can be calculated based on multiple demand indicators, combined with equipment, platform, time, and process. The calculation method for the cost-benefit ratio in this disclosure is similar to conventional methods and will not be elaborated upon here.

[0087] Step S620: Based on the multidimensional drilling environment characteristics, a large model is used to predict the failure probability of the second candidate drilling scheme.

[0088] Large-scale models refer to models that utilize large-scale deep learning models (such as Transformer, LSTM (Long Short-Term Memory) networks), which are based on massive amounts of historical operational data, equipment maintenance data, and environmental data to perform high-precision predictions. Multidimensional drilling environment characteristics and second candidate drilling schemes are input into the large-scale model to obtain the failure probability.

[0089] Step S630: Determine the evaluation score of the second candidate drilling scheme based on the cost-benefit ratio and failure probability.

[0090] The evaluation score for the second candidate drilling scheme needs to consider both the cost-effectiveness ratio (the higher the better) and the probability of failure (the lower the better). This can be determined by defining an evaluation function: Evaluation score = cost-benefit ratio (1 - Fault Prediction Probability) Equation 2 Step S640: Based on the evaluation scores of each second candidate drilling scheme, determine the reference drilling scheme from multiple second candidate drilling schemes.

[0091] After determining the evaluation scores of each second-candidate drilling scheme, a reference drilling scheme can be selected from the multiple second-candidate drilling schemes. For example, the second-candidate drilling schemes with the highest evaluation scores can be obtained.

[0092] The exemplary embodiments of this disclosure improve the objectivity and accuracy of the evaluation score by combining cost-effectiveness ratio and failure probability predicted by a large model, thereby improving the accuracy of the reference drilling scheme.

[0093] Step S260: Based on historical amendment example data, drilling demand information and drilling environment characteristics, the reference drilling plan is revised to obtain the target drilling plan, and the reliability of the target drilling plan is verified. The target drilling plan that passes the verification is determined as the target recommended drilling plan.

[0094] In an exemplary embodiment of this disclosure, historical amendment case data stores records of adjustments, optimizations, and modifications made to the initial plan before or during actual execution in past engineering projects, along with related data on their final effects. For example, each case includes the original plan, the problems and constraints faced, the corrective measures taken, the corrected plan, and the correction results. In an exemplary embodiment, each piece of historical amendment case data is a triple including drilling scenario information, original plan data, and corrected plan data. The drilling scenario information includes drilling environment data and drilling demand data.

[0095] A triple is a structured data representation that consists of three parts. For example, a historical amendment case is defined as a triple of (drilling scenario information, original scheme data, and amended scheme data). The drilling scenario information is a complete description of the background and conditions in which the historical case occurred, including drilling environment data and drilling demand data.

[0096] like Figure 7 As shown, based on historical amendment data, the drilling demand information, and the drilling environment characteristics, the reference drilling plan is modified to obtain the target drilling plan, which may include: Step S710: Based on the drilling demand information and drilling environment characteristics, match the drilling environment data and drilling demand data in the historical amendment case data to determine multiple target historical amendment case data based on the matching results.

[0097] Multiple target historical amendment case data can be obtained by searching the case library for historical amendment case data that matches the current drilling demand information and drilling environment characteristics. Matching can be performed using a similarity algorithm, or by encoding each drilling environment data and drilling demand data into vectors and then calculating cosine similarity to obtain multiple target historical amendment case data that match the drilling demand information and drilling environment characteristics.

[0098] Step S720: For each target historical amendment example data, determine the correction difference data based on the original scheme data and the revised scheme data. The correction difference data reflects the difference between the original scheme data and the revised scheme data.

[0099] Correction of discrepancy data can be understood as the specific set of change instructions extracted by comparing and analyzing the original scheme data and the corrected scheme data. The discrepancies may include equipment replacement, process adjustment, parameter optimization, etc.

[0100] Step S730: Based on the correction difference data corresponding to the historical amendment examples of each target, revise the reference drilling plan to obtain the target drilling plan.

[0101] Once the corrected discrepancy data is determined, it can be applied to the current reference drilling plan to refine it and obtain the target drilling plan. For example, replacing the standard drill bit with an ultrahard composite material drill bit.

[0102] In the exemplary embodiments disclosed herein, the correction action is no longer a black-box operation, but rather based on evidence. Because the current scenario is similar to a historical situation where a certain modification was successful, it is recommended to perform the same modification this time, further improving the accuracy and reliability of the target drilling plan. Optionally, a prompt message may be sent to the user before correction, so that the correction operation is performed only after obtaining the user's confirmation.

[0103] In an exemplary embodiment, the reliability of the target drilling plan is reviewed, and the target drilling plan that passes the review is determined as the target recommended drilling plan, including: First, a pre-trained risk detection model is obtained, which is trained based on historical abnormal drilling data and corresponding drilling environment characteristics.

[0104] Secondly, a pre-trained risk detection model is used to assess the risk of the target drilling plan and obtain the risk probability. If the risk probability is lower than a preset risk threshold, the target drilling plan is determined as the recommended drilling plan.

[0105] The risk detection model is used to assess the risk level of the drilling plan and can be a network structure such as CNN or RNN, without limitation. Of course, a large language model can also be used, and the exemplary embodiments of this disclosure do not impose special limitations on it. The model can be trained or fine-tuned using recorded data of negative events such as failures, accidents, major delays, or cost overruns that have occurred in historical drilling operations. Risk probability is a quantitative indicator output by the risk detection model, representing the likelihood of a major abnormal event occurring under a given plan and environment. The preset risk threshold can be an acceptable risk threshold value pre-set by domain experts based on the project's risk tolerance.

[0106] After determining the target drilling plan, further risk assessment is conducted, transforming the high and low risks that originally relied on expert subjective judgment into precise probability values. Based on preset thresholds, automated decision-making on whether to pass or fail is achieved, improving the efficiency and objectivity of the review process and reducing human uncertainty.

[0107] The drilling scheme recommendation method in the exemplary embodiments of this disclosure, on the one hand, achieves deep, non-linear feature matching by introducing interactive calculations of multi-dimensional drilling environment feature encoding (second encoding features) and drilling scheme encoding (first encoding features). This captures the inherent connection between the complexity of the offshore drilling environment and the drilling scheme, ensuring that the recommended second candidate drilling scheme has a higher degree of fit with the current environment, thereby improving the accuracy of the initial screening. On the other hand, through quantitative evaluation, drilling requirements are transformed into measurable indicators, enabling the selection of the reference drilling scheme with the highest comprehensive evaluation score and best suited to the client's actual interests from multiple technically feasible schemes. Furthermore, the method is revised based on historical amendment data and undergoes reliability verification, demonstrating high feasibility and safety in practice, greatly reducing the risk of project failure, and improving drilling efficiency while enhancing drilling results.

[0108] In an exemplary embodiment of this disclosure, a drilling scheme recommendation apparatus is also provided. (See reference...) Figure 8 As shown, the drilling scheme recommendation device 800 may include an information acquisition module 810, a first scheme determination module 820, a feature encoding module 830, a second scheme determination module 840, a third scheme determination module 850, and a fourth scheme determination module 860. Specifically: The information acquisition module 810 is used to acquire drilling demand information and multi-dimensional drilling environment characteristics; the first scheme determination module 820 is used to match multiple drilling scheme features from a pre-established drilling scheme database based on the multi-dimensional drilling environment characteristics, and construct schemes based on the multiple drilling scheme features to obtain multiple first candidate drilling schemes; the feature encoding module 830 is used to encode the multiple first candidate drilling schemes respectively to obtain multiple first encoded features, and to encode the multi-dimensional drilling environment characteristics to obtain second encoded features; the second scheme determination module 840 is used to perform interactive calculations between the second encoded features and each first encoded feature to obtain the similarity score corresponding to each first candidate drilling scheme, and to determine the second scheme based on the first encoded features. The similarity score determines multiple second-candidate drilling schemes from multiple first-candidate drilling schemes; the third scheme determination module 850 is used to quantify the drilling demand information to obtain multiple demand indicators, and evaluate the multiple second-candidate drilling schemes based on the multiple demand indicators to obtain evaluation scores, so as to determine the reference drilling scheme from the multiple second-candidate drilling schemes according to the evaluation scores; the fourth scheme determination module 860 is used to modify the reference drilling scheme based on historical amendment example data, drilling demand information and drilling environment characteristics to obtain the target drilling scheme, and verify the reliability of the target drilling scheme based on historical abnormal drilling data, and determine the target drilling scheme that passes the verification as the target recommended drilling scheme.

[0109] In an exemplary embodiment of this disclosure, the first scheme determination module 820 is configured to perform the following: before matching multiple drilling scheme features from a pre-established drilling scheme database based on multi-dimensional drilling environment features, and constructing a scheme based on the multiple drilling scheme features to obtain multiple first candidate drilling schemes, the method further includes: obtaining a set of historical successful drilling schemes, deconstructing each historical successful drilling scheme in the set of historical successful drilling schemes to obtain atomic drilling feature elements; establishing a weighted mapping relationship between each atomic drilling feature element and drilling environment features to obtain a pre-established drilling scheme database; wherein the weighted mapping relationship includes the correspondence between atomic drilling feature elements and drilling environment features and the matching degree weight.

[0110] In one exemplary embodiment of this disclosure, the first scheme determination module 820 is configured to perform: calculating the environment adaptability score of each atomized drilling feature element in the pre-established drilling scheme database based on the weighted mapping relationship and multi-dimensional drilling environment characteristics; selecting multiple drilling scheme features from the atomized drilling feature elements based on the environment adaptability score; performing compatibility and mutual exclusion judgment on the multiple drilling scheme features based on the engineering constraint rule base to filter out drilling scheme features that contradict each other; and constructing multiple first candidate drilling schemes based on the remaining drilling scheme features.

[0111] In one exemplary embodiment of this disclosure, the second scheme determination module 840 is configured to perform: for each first encoded feature, interactively calculate the first encoded feature and the second encoded feature based on a cross-attention mechanism to obtain a target encoded feature, and process the target encoded feature into a similarity score using a fully connected network; determine the mean and standard deviation of each similarity score, and determine a target threshold based on the mean and standard deviation; and determine a plurality of second candidate drilling schemes from a plurality of first candidate drilling schemes based on the target threshold and each similarity score.

[0112] In one exemplary embodiment of this disclosure, the second candidate drilling scheme includes at least equipment, platform, schedule, and process; the third scheme determination module 850 is configured to perform: for each second candidate drilling scheme, evaluating the cost-effectiveness ratio of the second candidate drilling scheme based on multiple demand indicators and in combination with equipment, platform, schedule, and process; predicting the failure probability of the second candidate drilling scheme using a large model based on multidimensional drilling environment characteristics; determining the evaluation score of the second candidate drilling scheme based on the cost-effectiveness ratio and failure probability; and determining a reference drilling scheme from multiple second candidate drilling schemes based on the evaluation scores of each second candidate drilling scheme.

[0113] In one exemplary embodiment of this disclosure, each historical modification example data is a triple including drilling scenario information, original scheme data, and modified scheme data. The drilling scenario information includes drilling environment data and drilling demand data. The fourth scheme determination module 860 is configured to perform the following: matching the drilling demand information and drilling environment characteristics with the drilling environment data and drilling demand data in the historical modification example data to determine multiple target historical modification example data based on the matching results; for each target historical modification example data, determining modification difference data based on the original scheme data and modified scheme data, the modification difference data reflecting the difference between the original scheme data and the modified scheme data; and modifying the reference drilling scheme based on the modification difference data corresponding to each target historical modification example data to obtain the target drilling scheme.

[0114] In one exemplary embodiment of this disclosure, the fourth scheme determination module 860 is configured to perform: acquiring a pre-trained risk detection model, the pre-trained risk detection model being trained based on historical abnormal drilling data and corresponding drilling environment characteristics; using the pre-trained risk detection model to perform a risk assessment on the target drilling scheme to obtain a risk probability; if the risk probability is lower than a preset risk threshold, then determining the target drilling scheme as the target recommended drilling scheme.

[0115] Since the details of each functional module of the drilling scheme recommendation apparatus of the exemplary embodiments of this disclosure have been described in the exemplary embodiments of the drilling scheme recommendation method described above, they will not be repeated here.

[0116] It should be noted that although several modules or units of the recommended drilling scheme apparatus have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0117] Exemplary embodiments of this disclosure also provide a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the drilling scheme recommendation method described above.

[0118] In one implementation, the computer program product can be a tangible product containing a computer program, such as a computer-readable storage medium storing the computer program. The readable storage medium can be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory, hard disk drive (HDD), solid-state drive (SSD), etc. For example, the computer program product can be implemented as a non-volatile storage medium storing a computer program, such as read-only memory, NAND flash memory, etc.

[0119] In one implementation, the computer program product can be an intangible product containing a computer program. For example, the computer program product can be implemented as a virtual digital product, such as an executable file, installation package, or other digital file storing the computer program.

[0120] Computer program code can be written in one or more programming languages. The program code can execute entirely on the user's computing device, or partially on the user's computing device, or as a standalone software package, or partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device through any type of network, such as a local area network (LAN), a wide area network (WAN), etc., or it can be connected to an external computing device (e.g., through an internet connection provided by a mobile network operator).

[0121] Computer programs can be carried or transmitted via signals such as electrical, magnetic, optical, electromagnetic, and infrared rays. Electronic devices can convert the signals carrying computer programs into digital signals, thereby running the computer programs. When a computer program runs on an electronic device, its code is used to cause the electronic device to execute (more specifically, to execute) the method steps of various exemplary embodiments of this disclosure, such as the steps of the drilling scheme recommended method described above.

[0122] Furthermore, in exemplary embodiments of this disclosure, an electronic device capable of implementing the above-described methods is also provided. Those skilled in the art will understand that various aspects of this disclosure can be implemented as systems, methods, or program products. Therefore, various aspects of this disclosure can be specifically implemented as: entirely hardware embodiments, entirely software embodiments (including firmware, microcode, etc.), or embodiments combining hardware and software aspects, collectively referred to herein as "circuit," "module," or "system."

[0123] The following reference Figure 9 To describe an electronic device 900 according to such an embodiment of the present disclosure. Figure 9 The electronic device 900 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0124] like Figure 9 As shown, the electronic device 900 is presented in the form of a general-purpose computing device. The components of the electronic device 900 may include, but are not limited to: at least one processing unit 910, at least one storage unit 920, a bus 930 connecting different system components (including storage unit 920 and processing unit 910), and a display unit 940.

[0125] The storage unit stores program code that can be executed by the processing unit 910, causing the processing unit 910 to perform the steps described in the "Exemplary Methods" section above, according to various exemplary embodiments of this disclosure.

[0126] Storage unit 920 may include readable media in the form of volatile storage units, such as random access memory (RAM) 921 and / or cache memory 922, and may further include read-only memory (ROM) 923. Storage unit 920 may also include a program / utility 924 having a set (at least one) of program modules 925, such program modules 925 including but not limited to: operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0127] Bus 930 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0128] Electronic device 900 can also communicate with one or more external devices 1000 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 900, and / or with any device that enables electronic device 900 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 950. Furthermore, electronic device 900 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 960. As shown, network adapter 960 communicates with other modules of electronic device 900 via bus 930. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0129] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0130] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0131] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

Claims

1. A method for recommending drilling schemes, characterized in that, include: Obtain drilling demand information and multi-dimensional drilling environment characteristics; Based on the multidimensional drilling environment characteristics, multiple drilling scheme features are matched from a pre-established drilling scheme database, and schemes are constructed based on the multiple drilling scheme features to obtain multiple first candidate drilling schemes. The multiple first candidate drilling schemes are encoded to obtain multiple first encoding features, and the multidimensional drilling environment features are encoded to obtain second encoding features; The second coding feature is interactively calculated with each of the first coding features to obtain the similarity score corresponding to each of the first candidate drilling schemes, and based on the similarity score, a plurality of second candidate drilling schemes are determined from the plurality of first candidate drilling schemes. The drilling demand information is quantified to obtain multiple demand indicators, and the multiple second candidate drilling schemes are evaluated based on the multiple demand indicators to obtain evaluation scores, so as to determine a reference drilling scheme from the multiple second candidate drilling schemes according to the evaluation scores. Based on historical amendment data, drilling demand information, and drilling environment characteristics, the reference drilling plan is revised to obtain the target drilling plan. The reliability of the target drilling plan is then verified, and the target drilling plan that passes the verification is determined as the target recommended drilling plan.

2. The method according to claim 1, characterized in that, Before matching multiple drilling scheme features from a pre-established drilling scheme database based on the multidimensional drilling environment features, and constructing schemes based on the multiple drilling scheme features to obtain multiple first candidate drilling schemes, the method further includes: Obtain a set of historical successful drilling schemes, and deconstruct each historical successful drilling scheme in the set to obtain atomized drilling feature elements. Establish a weighted mapping relationship between each of the atomized drilling feature elements and the drilling environment features to obtain the pre-established drilling scheme database; The weighted mapping relationship includes the correspondence and matching weight between atomized drilling feature elements and drilling environment features.

3. The method according to claim 2, characterized in that, The process involves matching multiple drilling scheme features from a pre-established drilling scheme database based on the multi-dimensional drilling environment characteristics, and constructing a scheme based on these features to obtain multiple first candidate drilling schemes, including: Based on the weighted mapping relationship and the multidimensional drilling environment characteristics, calculate the environment adaptability score of each atomized drilling feature element in the pre-established drilling scheme database; Based on the environmental adaptability score, the features of the multiple drilling schemes are selected from the atomized drilling feature elements. Based on the engineering constraint rule base, the compatibility and mutual exclusion of the features of the multiple drilling schemes are judged to filter out the drilling scheme features that are contradictory. Based on the characteristics of the remaining drilling schemes, the plurality of first candidate drilling schemes are constructed.

4. The method according to claim 1, characterized in that, The step of interactively calculating the second encoded feature with each of the first encoded features to obtain a similarity score corresponding to each of the first candidate drilling schemes, and determining a plurality of second candidate drilling schemes from the plurality of first candidate drilling schemes based on the similarity scores, includes: For each of the first encoded features, the first encoded features and the second encoded features are interactively calculated based on the cross-attention mechanism to obtain the target encoded features, and the target encoded features are processed into the similarity score using a fully connected network; Determine the mean and standard deviation of each similarity score, and determine the target threshold based on the mean and standard deviation; Based on the target threshold and the similarity scores, a plurality of second candidate drilling schemes are determined from the plurality of first candidate drilling schemes.

5. The method according to claim 1, characterized in that, The second candidate drilling scheme includes at least equipment, platform, schedule, and process; The process of quantifying the drilling demand information to obtain multiple demand indicators, evaluating the multiple second candidate drilling schemes based on the multiple demand indicators to obtain evaluation scores, and determining a reference drilling scheme from the multiple second candidate drilling schemes according to the evaluation scores includes: For each of the second candidate drilling schemes, the cost-effectiveness ratio of the second candidate drilling scheme is evaluated based on the multiple requirement indicators and in combination with the equipment, platform, schedule and process. Based on the multidimensional drilling environment characteristics, a large model is used to predict the failure probability of the second candidate drilling scheme. The evaluation score of the second candidate drilling scheme is determined based on the cost-benefit ratio and the failure probability. The reference drilling scheme is determined from the plurality of second candidate drilling schemes based on the evaluation scores of each of the second candidate drilling schemes.

6. The method according to claim 1, characterized in that, Each of the aforementioned historical amendment examples is a triplet comprising drilling scenario information, original scheme data, and revised scheme data, wherein the drilling scenario information includes drilling environment data and drilling demand data; The process of revising the reference drilling plan based on historical amendment data, drilling demand information, and drilling environment characteristics to obtain the target drilling plan includes: Based on the drilling demand information and the drilling environment characteristics, the data is matched with the drilling environment data and drilling demand data in the historical amendment example data to determine multiple target historical amendment example data based on the matching results. For each of the target historical amendment example data, correction difference data is determined based on the original scheme data and the revised scheme data, and the correction difference data reflects the difference between the original scheme data and the revised scheme data; Based on the correction difference data corresponding to the historical amendment examples of each target, the reference drilling scheme is modified to obtain the target drilling scheme.

7. The method according to claim 1, characterized in that, The process of verifying the reliability of the target drilling plan and determining the target drilling plan that passes the verification as the recommended target drilling plan includes: A pre-trained risk detection model is obtained, which is trained based on historical abnormal drilling data and corresponding drilling environment characteristics; The pre-trained risk detection model is used to assess the risk of the target drilling scheme and obtain the risk probability. If the risk probability is lower than a preset risk threshold, then the target drilling scheme is determined to be the target recommended drilling scheme.

8. A drilling scheme recommendation device, characterized in that, include: The information acquisition module is used to acquire drilling demand information and multi-dimensional drilling environment characteristics; The first scheme determination module is used to match multiple drilling scheme features from a pre-established drilling scheme database based on the multi-dimensional drilling environment features, and to construct a scheme based on the multiple drilling scheme features to obtain multiple first candidate drilling schemes. The feature encoding module is used to encode the multiple first candidate drilling schemes respectively to obtain multiple first encoded features, and to encode the multidimensional drilling environment features to obtain second encoded features; The second scheme determination module is used to perform interactive calculations between the second coding feature and each of the first coding features to obtain the similarity score corresponding to each of the first candidate drilling schemes, and to determine a plurality of second candidate drilling schemes from the plurality of first candidate drilling schemes based on the similarity score. The third scheme determination module is used to quantify the drilling demand information to obtain multiple demand indicators, and to evaluate the multiple second candidate drilling schemes based on the multiple demand indicators to obtain an evaluation score, so as to determine a reference drilling scheme from the multiple second candidate drilling schemes according to the evaluation score. The fourth scheme determination module is used to modify the reference drilling scheme based on historical amendment example data, the drilling demand information and the drilling environment characteristics to obtain the target drilling scheme, and to verify the reliability of the target drilling scheme based on historical abnormal drilling data, and to determine the target drilling scheme that passes the verification as the target recommended drilling scheme.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

10. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 7 by executing the executable instructions.

Images