A method, device and equipment for predicting drilling difficulties and generating solutions to drilling difficulties

By constructing a knowledge map of well history and a knowledge map of difficult solutions, combined with a large model of drilling difficulty analysis, detailed analysis and solutions for drilling difficulties are generated, and the problem of low accuracy of drilling difficulty analysis in the existing technology is solved, and drilling prediction is improved and the accuracy and efficiency of the solution.

CN118885863BActive Publication Date: 2024-12-03RICHFIT INFORMATION TECH +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411388944.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-30
Publication Date
2024-12-03
Estimated Expiration
2044-09-30

AI Technical Summary

Technical Problem

The formulation of existing drilling difficulties and difficult solutions mainly relies on neighboring well data and expert experience. The lack of intelligent analysis technology leads to low model accuracy and the inability to integrate current well information and experience knowledge to generate targeted difficult solutions.

Method used

By obtaining the location information of the well points to be predicted, a well history knowledge map is constructed, the formation feature vectors of each adjacent well in the adjacent well list are calculated, and the formation feature vectors of each formation of the well points to be predicted are fused, and the pre-constructed difficulties are used The solution knowledge graph determines the geological condition label, drilling difficulty label and difficulty solution label, and enters it into the pre-trained drilling difficulty analysis large model to generate drilling difficulty prediction text and corresponding difficulty solution text.

Benefits of technology

It improves the accuracy and reliability of drilling difficulties prediction, and can automatically generate detailed drilling difficulties analysis text and corresponding difficult solutions, reduce drilling risks, shorten drilling cycles, and improve exploration and development efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118885863B_ABST
    Figure CN118885863B_ABST
Patent Text Reader

Abstract

The embodiments of this specification relate to the field of artificial intelligence technology, and provide a method, device and equipment for predicting drilling difficulties and generating solutions to the difficulties, including: determining a list of neighboring wells and a corresponding well history knowledge graph based on the location information of the well point to be predicted, calculating the formation feature vector of each neighboring well in each formation based on the well history knowledge graph, and obtaining the formation feature vector of the well point to be predicted in each formation, and then determining the geological condition label, drilling difficulty label and difficulty solution label of the well point to be predicted in each formation in combination with a pre-constructed difficulty solution knowledge graph, and inputting them into a pre-trained drilling difficulty analysis large model to obtain a drilling difficulty prediction text and a corresponding difficulty solution text for the well point to be predicted in each formation. Through the embodiments of this specification, a detailed drilling difficulty analysis text and a corresponding difficulty solution text can be automatically generated.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of this specification relate to the field of artificial intelligence technology, and in particular to a method, device and equipment for predicting drilling difficulties and generating solutions to the difficulties. Background Art

[0002] Oil drilling projects are an important means to achieve the goals of oil and gas exploration and development. Through drilling, we can go deep underground to explore and evaluate the existence and reserves of oil and gas resources. As drilling construction expands to deep wells and ultra-deep wells, the geological conditions are more complex. Problems such as ultra-high temperature and ultra-high pressure, multiple pressure systems, hard formations with poor drillability, and rich acidic fluids have greatly increased the difficulty of drilling construction. At the same time, some exploration areas have little drilling data and little drilling experience to draw on. Drilling accidents are complicated and occur from time to time, which seriously affects the progress of exploration and development.

[0003] At present, the analysis of drilling difficulties and the formulation of solutions to difficulties mainly rely on neighboring well data and expert experience, and lack intelligent analysis technology. The existing data-driven methods for drilling risk identification and prediction are still lacking in model accuracy due to the lack of professional knowledge and experience embedding. Difficulty solution recommendations can be achieved based on case reasoning and recommendation algorithms, but the recommendation results are only a copy of historical solutions, and it is impossible to integrate and summarize current well information with empirical knowledge to generate targeted difficulty solutions. Therefore, there is an urgent need for a drilling difficulty prediction and difficulty solution generation method that can accurately predict drilling difficulties and automatically generate corresponding difficulty solutions. Summary of the invention

[0004] In view of the above problems in the prior art, the purpose of the embodiments of this specification is to provide a method, device and equipment for predicting drilling difficulties and generating solutions to the difficulties, so as to accurately predict drilling difficulties and automatically generate corresponding solutions to the difficulties.

[0005] In order to solve the above technical problems, the specific technical solutions of the embodiments of this specification are as follows:

[0006] On the one hand, an embodiment of this specification provides a method for predicting drilling difficulties and generating a solution to the difficulties, the method comprising:

[0007] Obtaining location information of the well point to be predicted;

[0008] According to the location information of the well point to be predicted, a list of neighboring wells of the well point to be predicted and a corresponding well history knowledge graph are determined, wherein the well history knowledge graph is pre-constructed using historical drilling data, including stratigraphic characteristic data of different strata and the relationship between them;

[0009] Calculate the stratigraphic feature vector of each adjacent well in each stratigraphic layer in the adjacent well list according to the stratigraphic feature data in the well history knowledge graph;

[0010] The formation feature vector of the well point to be predicted in each stratum is calculated based on the formation feature vector of each adjacent well in the adjacent well list in each stratum;

[0011] Determine the geological condition label, drilling difficulty label and difficulty solution label of the well point to be predicted in each stratum according to the stratum feature vector of the well point to be predicted in each stratum and the pre-constructed difficulty solution knowledge graph, wherein the difficulty solution knowledge graph includes geological condition nodes, drilling difficulty nodes, difficulty solution nodes and the relationship between the three types of nodes;

[0012] According to the geological condition labels, drilling difficulty labels and difficulty solution labels, a prompt text is constructed and input into a pre-trained drilling difficulty analysis model to obtain the drilling difficulty prediction text and the corresponding difficulty solution text of the well point to be predicted in each stratum.

[0013] Furthermore, the step of determining a list of neighboring wells of the well point to be predicted based on the location information of the well point to be predicted includes:

[0014] Determine the block to which the well point to be predicted belongs according to the position information of the well point to be predicted;

[0015] Calculating the distance between the well point to be predicted and each well point in the block to which it belongs;

[0016] The well points whose well distance is less than a preset threshold are determined as neighboring wells of the well point to be predicted, and a list of neighboring wells of the well point to be predicted is obtained.

[0017] Further, the calculation of the stratigraphic feature vector of each adjacent well in each stratigraphic layer in the adjacent well list according to the stratigraphic feature data in the well history knowledge graph includes:

[0018] Performing characterization learning on the well history knowledge graph according to the formation feature data to obtain formation feature vector data;

[0019] Acquire a first formation characteristic vector and a second formation characteristic vector of a certain formation of a certain adjacent well according to the formation characteristic vector data;

[0020] The first formation feature vector and the second formation feature vector are merged to obtain a third formation feature vector of the certain adjacent well in a certain formation;

[0021] Calculating the formation characteristic vectors of the adjacent upper formation and the adjacent lower formation of the adjacent well in a certain formation;

[0022] Perform nonlinear calculation on the third formation characteristic vector, the formation characteristic vectors of the adjacent upper formation and the adjacent lower formation to obtain a fourth formation characteristic vector of the adjacent well in a certain formation;

[0023] Obtaining a list of neighboring wells of the certain neighboring well, and calculating a distance influence coefficient between each neighboring well in the list of neighboring wells and the certain neighboring well and a formation characteristic vector of each neighboring well in the certain formation;

[0024] The final formation characteristic vector of a certain neighboring well in a certain formation is calculated based on the fourth formation characteristic vector, the distance influence coefficient and the formation characteristic vector of each neighboring well in the neighboring well list of a certain neighboring well in the certain formation;

[0025] The above steps are repeated until the formation feature vector of each adjacent well in each formation in the adjacent well list is obtained.

[0026] Further, the step of calculating the final formation characteristic vector of a certain neighboring well in a certain formation according to the fourth formation characteristic vector, the distance influence coefficient and the formation characteristic vector of each neighboring well in the neighboring well list of a certain neighboring well in the certain formation comprises:

[0027] The final formation characteristic vector of a certain adjacent well in a certain formation is calculated using the following formula:

[0028] ;

[0029] Among them, E_W i S j represents the final formation feature vector of the i-th adjacent well in the j-th formation, E_W i S j _2 represents the fourth stratigraphic characteristic vector of the i-th adjacent well in the j-th stratigraphic layer, n1 represents the number of adjacent wells of the i-th adjacent well, β k represents the distance influence coefficient between the i-th neighbor well and the k-th neighbor well in its neighbor well list, E_W k S j _2 represents the stratigraphic characteristic vector of the jth stratigraphic layer of the kth adjacent well in the adjacent well list of the i-th adjacent well.

[0030] Furthermore, the formation feature vector of the well point to be predicted in each stratum is calculated based on the formation feature vector of each neighboring well in the neighboring well list, including:

[0031] The formation characteristic vector of the well point to be predicted in each formation is calculated using the following formula:

[0032] ;

[0033] Among them, E_W Loc S j represents the stratigraphic feature vector of the well point to be predicted in the jth stratum, n2 represents the number of neighboring wells of the well point to be predicted, and ρ irepresents the distance influence coefficient between the well point to be predicted and the i-th adjacent well, E_W i S j Represents the formation characteristic vector of the i-th adjacent well in the j-th formation.

[0034] Furthermore, the step of determining the geological condition label, drilling difficulty label and difficulty solution label of the well point to be predicted in each stratum according to the stratum feature vector of the well point to be predicted in each stratum and the pre-built difficulty solution knowledge graph includes:

[0035] Performing characterization learning on the difficult solution knowledge graph to obtain a geological condition feature vector corresponding to each geological condition class node in the difficult solution knowledge graph;

[0036] Calculate the similarity between the formation feature vector of the well point to be predicted in each formation and each geological condition feature vector in the knowledge graph of the difficulty solution;

[0037] The labels corresponding to the first preset number of geological condition feature vectors whose similarity is greater than a preset threshold are used as the geological condition labels of the well point to be predicted in each stratum;

[0038] According to the geological condition label of the well point to be predicted in each stratum, the drilling difficulty label and the difficulty solution label of the well point to be predicted in each stratum are determined from the difficulty solution knowledge graph.

[0039] Furthermore, the prompt text constructed according to the geological condition label, drilling difficulty label and difficulty solution label is input into the pre-trained drilling difficulty analysis model to obtain the drilling difficulty prediction text of the well point to be predicted in each stratum and the corresponding difficulty solution text, including:

[0040] Fill the geological condition label, drilling difficulty label and difficulty solution label into the placeholder corresponding to the pre-created prompt text template to obtain the prompt text;

[0041] The prompt text is input into a pre-trained large model for drilling difficulty analysis to generate drilling difficulty prediction text and corresponding difficulty solution text for the well point to be predicted in each stratum.

[0042] On the other hand, an embodiment of the present specification provides a drilling difficulty prediction and difficulty solution generation device, the device comprising:

[0043] An acquisition module is used to obtain the location information of the well point to be predicted;

[0044] A neighboring well list determination module is used to determine the neighboring well list of the well point to be predicted and the corresponding well history knowledge graph according to the location information of the well point to be predicted, wherein the well history knowledge graph is pre-built using historical drilling data, including stratigraphic characteristic data of different strata and the relationship between them;

[0045] An adjacent well formation feature vector calculation module is used to calculate the formation feature vector of each adjacent well in each formation in the adjacent well list according to the formation feature data in the well history knowledge graph;

[0046] A formation feature vector calculation module for the well point to be predicted, used to calculate the formation feature vector of the well point to be predicted in each formation according to the formation feature vector of each adjacent well in the adjacent well list;

[0047] A label determination module is used to determine the geological condition label, drilling difficulty label and difficulty solution label of the well point to be predicted in each stratum according to the stratum feature vector of the well point to be predicted in each stratum and the pre-built difficulty solution knowledge graph, wherein the difficulty solution knowledge graph includes geological condition nodes, drilling difficulty nodes, difficulty solution nodes and the relationship between the three types of nodes;

[0048] The drilling difficulty prediction and difficulty solution generation module is used to construct prompt text according to the geological condition label, drilling difficulty label and difficulty solution label and input it into the pre-trained drilling difficulty analysis model to obtain the drilling difficulty prediction text and corresponding difficulty solution text of the well point to be predicted in each stratum.

[0049] On the other hand, an embodiment of the present specification further provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein when the computer program is executed by the processor, the instructions of any one of the above methods are executed.

[0050] On the other hand, an embodiment of the present specification further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor of a computer device, the computer program executes instructions of any one of the above-described methods.

[0051] On the other hand, the embodiments of this specification further provide a computer program product, which, when executed by a processor of a computer device, executes instructions of any one of the above methods.

[0052] The method for predicting drilling difficulties and generating solutions to drilling difficulties provided in the embodiments of this specification can determine the list of neighboring wells and the corresponding well history knowledge graph based on the location information of the well point to be predicted, and then calculate the formation feature vector of each neighboring well in the neighboring well list in each formation based on the formation feature data in the well history knowledge graph, so as to obtain the formation feature vector of the well point to be predicted in each formation based on the formation feature vector of each neighboring well in each formation. Thus, the formation feature vector of the well point to be predicted is obtained based on the formation feature vector of the neighboring well, so that the formation feature vector of the well point to be predicted integrates the formation characteristics of the neighboring wells and its own characteristics, thereby improving the accuracy and reliability of the formation characteristics of the well point to be predicted. Afterwards, the geological condition label, drilling difficulty label and difficulty solution label of the well point to be predicted in each stratum are determined according to the stratigraphic feature vector of the well point to be predicted in each stratum and the pre-constructed knowledge graph of difficulty solution, and they are input into the pre-trained drilling difficulty analysis large model to obtain the drilling difficulty prediction text and the corresponding difficulty solution text of the well point to be predicted in each stratum. In this way, the characteristics of the well point to be predicted can be integrated with the historical drilling experience knowledge, and a detailed drilling difficulty analysis text and a corresponding difficulty solution text can be automatically generated, so as to provide drilling guidance plans for explorers, reduce the risk of drilling operations, shorten the drilling cycle, and improve the efficiency of exploration and development.

[0053] The above description is only an overview of the technical solutions of some embodiments of this specification. In order to more clearly understand the technical means of some embodiments of this specification, they can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiments of this specification more obvious and easy to understand, the following specifically cites the preferred embodiments and describes them in detail in conjunction with the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 A schematic flow chart of a method for predicting drilling difficulties and generating solutions to the difficulties in some embodiments of this specification is shown;

[0056] Figure 2 A schematic diagram of a process for determining a list of neighboring wells to be predicted for a well point in some embodiments of this specification is shown;

[0057] Figure 3A schematic diagram of a process for calculating the formation characteristic vector of each adjacent well in each formation in the adjacent well list of the well point to be predicted in some embodiments of this specification is shown;

[0058] Figure 4 A schematic diagram of a process for determining a geological condition label, a drilling difficulty label, and a difficulty solution label of a well point to be predicted in each stratum in some embodiments of this specification is shown;

[0059] Figure 5 A schematic diagram of a process for generating a drilling difficulty prediction text and a corresponding difficulty solution text in some embodiments of this specification is shown;

[0060] Figure 6 A schematic diagram of the module structure of a device for predicting drilling difficulties and generating solutions to difficulties in some embodiments of this specification is shown;

[0061] Figure 7 A schematic diagram of the structure of a computer device in this specification is shown.

[0062] Description of the accompanying symbols:

[0063] 601. Get module;

[0064] 602. Neighboring well list determination module;

[0065] 603. Neighboring well formation characteristic vector calculation module;

[0066] 604. Module for calculating formation characteristic vector of well point to be predicted;

[0067] 605. Tag determination module;

[0068] 606. Drilling difficulty prediction and difficulty solution generation module;

[0069] 702. Computer equipment;

[0070] 704, processor;

[0071] 706. Memory;

[0072] 708, driving mechanism;

[0073] 710, input / output module;

[0074] 712. Input devices;

[0075] 714. Output devices;

[0076] 716. Presentation equipment;

[0077] 718. Graphical user interface;

[0078] 720, network interface;

[0079] 722. Communication link;

[0080] 724. Communication bus. DETAILED DESCRIPTION

[0081] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0082] In order to solve the above problems, the embodiments of this specification provide a method for predicting drilling difficulties and generating a solution to the difficulties. Figure 1 This is a flowchart of a method for predicting drilling difficulties and generating solutions to difficulties provided by the embodiments of this specification. This specification provides method operation steps as described in the embodiments or flowcharts, but more or fewer operation steps may be included based on conventional or non-creative labor. The order of steps listed in the embodiments is only one way of executing the order of many steps and does not represent the only execution order. When the system or device product is executed in practice, it can be executed in the order of the methods shown in the embodiments or drawings or in parallel.

[0083] It should be noted that the terms "first", "second", etc. in this specification and claims and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of this specification described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0084] Reference Figure 1 As shown, the embodiment of this specification provides a method for predicting drilling difficulties and generating solutions to the difficulties, the method comprising:

[0085] S101: Acquire the location information of the well point to be predicted;

[0086] S102: Determine a list of neighboring wells of the well point to be predicted and a corresponding well history knowledge graph according to the location information of the well point to be predicted, wherein the well history knowledge graph is pre-built using historical drilling data and includes stratigraphic feature data of different strata and the relationship between them;

[0087] S103: Calculating the stratigraphic feature vector of each adjacent well in each stratigraphic layer in the adjacent well list according to the stratigraphic feature data in the well history knowledge graph;

[0088] S104: Calculating the formation feature vector of the well point to be predicted in each formation according to the formation feature vector of each neighboring well in the neighboring well list;

[0089] S105: Determine the geological condition label, drilling difficulty label and difficulty solution label of the well point to be predicted in each stratum according to the stratum feature vector of the well point to be predicted in each stratum and the pre-constructed difficulty solution knowledge graph, wherein the difficulty solution knowledge graph includes geological condition nodes, drilling difficulty nodes, difficulty solution nodes and the relationship between the above three types of nodes;

[0090] S106: Construct a prompt text according to the geological condition label, drilling difficulty label and difficulty solution label and input it into a pre-trained drilling difficulty analysis model to obtain the drilling difficulty prediction text of the well point to be predicted in each stratum and the corresponding difficulty solution text.

[0091] The method for predicting drilling difficulties and generating solutions to drilling difficulties provided in the embodiments of this specification can determine the list of neighboring wells and the corresponding well history knowledge graph based on the location information of the well point to be predicted, and then calculate the formation feature vector of each neighboring well in the neighboring well list in each formation based on the formation feature data in the well history knowledge graph, so as to obtain the formation feature vector of the well point to be predicted in each formation based on the formation feature vector of each neighboring well in each formation. Thus, the formation feature vector of the well point to be predicted is obtained based on the formation feature vector of the neighboring well, so that the formation feature vector of the well point to be predicted integrates the formation characteristics of the neighboring wells and its own characteristics, thereby improving the accuracy and reliability of the formation characteristics of the well point to be predicted. Afterwards, the geological condition label, drilling difficulty label and difficulty solution label of the well point to be predicted in each stratum are determined according to the stratigraphic feature vector of the well point to be predicted in each stratum and the pre-constructed knowledge graph of difficulty solution, and they are input into the pre-trained drilling difficulty analysis large model to obtain the drilling difficulty prediction text and the corresponding difficulty solution text of the well point to be predicted in each stratum. In this way, the characteristics of the well point to be predicted can be integrated with the historical drilling experience knowledge, and a detailed drilling difficulty analysis text and a corresponding difficulty solution text can be automatically generated, so as to provide drilling guidance plans for explorers, reduce the risk of drilling operations, shorten the drilling cycle, and improve the efficiency of exploration and development.

[0092] In the embodiment of this specification, the location information of the well point to be predicted includes the location coordinates of the well point to be predicted. Figure 2 , determining the neighboring well list of the well point to be predicted according to the location information of the well point to be predicted, comprises:

[0093] S201: Determine the block to which the well point to be predicted belongs according to the position information of the well point to be predicted;

[0094] S202: Calculating the distance between the well point to be predicted and each well point in the block to which it belongs;

[0095] S203: Determine the well points whose well distances are less than a preset threshold as neighboring wells of the well point to be predicted, and obtain a list of neighboring wells of the well point to be predicted.

[0096] It can be understood that in the process of oil exploration and development, the geological conditions of the neighboring wells of the wells to be predicted are closely related to their geological conditions. The geological data of the neighboring wells, such as lithology, structure, formation thickness, reservoir properties, etc., can provide important references for the exploration and development of the wells to be predicted. By comparing the geological conditions of the neighboring wells and the wells to be predicted, the similarities and differences of the geological characteristics can be identified, and the laws of geological evolution in the block to which they belong can be further analyzed to provide a basis for geological modeling and reservoir prediction. In addition, based on the drilling experience of the neighboring wells, the risks that the wells to be predicted may encounter during the drilling process can be evaluated, such as abnormal formation pressure, blowout, well collapse, etc., so as to formulate countermeasures. Under normal circumstances, since the geological conditions of the wells in the same block are relatively similar, in the embodiment of this specification, the block to which the wells to be predicted belong is first determined by the position coordinates of the wells to be predicted, and then the well spacing between the wells to be predicted and the remaining wells in the block is calculated and the preset threshold is determined to determine the neighboring wells, and finally a list of neighboring wells is formed. Preferably, in order to ensure the reliability of the formation characteristics of the subsequent wells to be predicted, the preset threshold in the embodiment of this specification is 5km.

[0097] In step S102, the well history knowledge graph corresponding to the neighboring well list is constructed based on historical drilling data. Specifically, the well history knowledge graph construction process includes the following steps:

[0098] Step a: Obtain historical drilling data. The data comes from the drilling engineering technical information, mainly including structured data and unstructured data. Structured data is mainly stored in relational databases, such as blocks, wellbores, formations, construction records, drill bit usage records, drilling fluid performance, drill tool assembly data, logging data, coring data, time-sensitive data, etc.; unstructured data is mainly stored in the file system in PDF, Word and other formats, such as geological design reports, drilling design reports, construction summary reports, case analysis reports, as well as drilling-related policies and regulations, standards and specifications, implementation details, technical manuals, etc.

[0099] Step b: Establish a single well knowledge ontology model (i.e., knowledge graph concept layer) based on historical drilling data, which mainly includes entities such as blocks, wells, characteristics of formations encountered, construction plans for different openings, and drilling time efficiency for different well sections, entity attributes, and relationships between entities.

[0100] Step c: Use ontology mapping, R2RML (RDB to RDF Mapping Language), D2RQ and other knowledge instance technologies to extract knowledge instances corresponding to the concept layer from the internal relational database to generate a well history knowledge graph. According to the single well knowledge ontology model, count the missing entity examples, attribute examples and relationship examples in the well history knowledge graph, use natural language processing and other technologies to extract knowledge instances from unstructured documents such as single well geological design and single well engineering design, and complete the well history knowledge graph.

[0101] Step d: Perform representation learning on the well history knowledge graph. Since most of the nodes and relationships in the well history knowledge graph are discrete and sparse data types, in order to facilitate calculation and reasoning, knowledge graph embedding technologies such as TransR, TransD, and DistMult are used to map the nodes and relationships in the well history knowledge graph to a low-dimensional, dense numerical vector space, and finally generate feature vector data of entities and relationships such as different blocks, different wells, different formations, and different construction plans.

[0102] In some embodiments of this specification, refer to Figure 3 , the calculation of the stratigraphic feature vector of each adjacent well in each stratigraphic layer in the adjacent well list according to the stratigraphic feature data in the well history knowledge graph includes:

[0103] S301: Perform characterization learning on the well history knowledge graph according to the formation feature data to obtain formation feature vector data.

[0104] S302: Obtain a first formation characteristic vector and a second formation characteristic vector of a certain adjacent well in a certain formation according to the formation characteristic vector data.

[0105] Specifically, the first formation characteristic vector is the global formation characteristic vector of a certain adjacent well in a certain formation, denoted as E_W i S j _0, the second formation characteristic vector is the local formation characteristic vector of a certain adjacent well in a certain formation, such as geological structure vector x1, sedimentation vector x2, lithology vector x3, temperature and pressure vector x4, etc., which are q vectors representing formation characteristics, denoted as X={x1, x2, x3,x4, ....., x q}.

[0106] S303: The first formation feature vector and the second formation feature vector are merged to obtain a third formation feature vector of the certain adjacent well in a certain formation.

[0107] It can be understood that by fusing the global stratigraphic feature vector and the local stratigraphic feature vector, the stratigraphic features of a certain adjacent well in a certain stratigraphic layer can be represented from multiple angles and levels, thereby capturing more comprehensive and richer information, thereby improving the accuracy and reliability of subsequent acquisition of corresponding geological labels based on the well points to be predicted. In some embodiments, the feature vector fusion can be performed using methods such as the average method, the weighted average method, and the KCNN method. For example, the average method is used to obtain a fused stratigraphic feature vector, that is, the third stratigraphic feature vector is shown as follows:

[0108] (1)

[0109] Among them, E_Wi S j _1 represents the third formation characteristic vector of the i-th adjacent well in the j-th formation, E_W i S j _0 represents the first formation characteristic vector of the i-th adjacent well in the j-th formation, q represents the number of local formation characteristic vectors, x q represents the qth local formation feature vector.

[0110] S304: Calculate the formation characteristic vectors of the adjacent upper formation and the adjacent lower formation of the certain adjacent well in a certain formation.

[0111] Specifically, the formation characteristic vectors of the adjacent upper formation and the adjacent lower formation of a certain adjacent well in a certain formation can be calculated using the calculation method of steps S302-S303.

[0112] S305: Perform nonlinear calculation on the third formation characteristic vector, the formation characteristic vectors of the adjacent upper formation and the adjacent lower formation to obtain a fourth formation characteristic vector of the certain adjacent well in a certain formation.

[0113] It can be understood that the geological conditions between adjacent strata have a high degree of similarity. By performing nonlinear calculations on the third stratum characteristic vector, the stratum characteristic vectors of the adjacent upper strata and the adjacent lower strata, the complex correlation between the characteristics of the local stratum and the adjacent stratum can be captured, and a new characteristic vector containing richer information can be generated, thereby obtaining a more comprehensive stratum characteristic vector that characterizes a certain adjacent well in a certain stratum. In some embodiments, nonlinear calculations can be performed using the following formula:

[0114] (2)

[0115] Among them, E_W i S j _2 represents the fourth formation feature vector of the i-th adjacent well in the j-th formation, ActFunc() represents the activation function, which can be RelU, LeaklyReLU, etc., w1, w2, w3 are trainable weights, E_W i S j _1 represents the third formation characteristic vector of the i-th adjacent well in the j-th formation, E_W i S j U_1 represents the characteristic vector of the adjacent upper formation of the i-th adjacent well in the j-th formation, E_W i S j D_1 represents the adjacent lower formation feature vector of the i-th adjacent well in the j-th formation.

[0116] S306: Obtain a list of neighboring wells of the certain neighboring well, and calculate a distance influence coefficient between each neighboring well in the list of neighboring wells and the certain neighboring well and a formation characteristic vector of each neighboring well in the certain formation.

[0117] Specifically, the list of neighboring wells of the i-th neighboring well is represented by W i List = {W1,W2,...W k ,......}, for W i Each well W in List k (k=1, 2, ...), calculate W k With W i Well spacing d k,i , and then calculate W by the following formula k With W i The distance influence coefficient β k :

[0118] β k =(d k,max -d k,i ) / (d k,max -d k,min ) (3)

[0119] Among them, β k represents the distance influence coefficient between the i-th neighbor well and the k-th neighbor well in its neighbor well list, d k,i W k With W i The well spacing, d k,max represents the maximum well spacing, d k,min Indicates the minimum well spacing. The distance influence coefficient represents the degree of influence of the adjacent well on the formation characteristics of the well. The larger the distance influence coefficient, the greater the influence of the adjacent well on the formation of the well.

[0120] The formation characteristic vector of each adjacent well of the i-th adjacent well to be predicted in each formation can be calculated using the calculation method of steps S302-S303.

[0121] S307: Calculate the final formation characteristic vector of a certain neighboring well in a certain formation according to the fourth formation characteristic vector, the distance influence coefficient and the formation characteristic vector of each neighboring well in the neighboring well list of a certain neighboring well in the certain formation.

[0122] Specifically, in the embodiment of this specification, the following formula is used to calculate the final formation characteristic vector of a certain adjacent well in a certain formation:

[0123] (4)

[0124] Among them, E_W i S jrepresents the final formation feature vector of the i-th adjacent well in the j-th formation, E_W i S j _2 represents the fourth stratigraphic characteristic vector of the i-th adjacent well in the j-th stratigraphic layer, n1 represents the number of adjacent wells of the i-th adjacent well, β k represents the distance influence coefficient between the i-th neighbor well and the k-th neighbor well in its neighbor well list, E_W k S j _2 represents the stratigraphic characteristic vector of the jth stratigraphic layer of the kth adjacent well in the adjacent well list of the i-th adjacent well.

[0125] S308: Repeat the above steps until the formation feature vector of each adjacent well in each formation in the adjacent well list is obtained.

[0126] In this way, by fusing the feature vectors of the adjacent upper strata, the adjacent lower strata and the adjacent well strata in the jth stratum of the ith adjacent well, the feature vectors of multiple strata can be integrated to avoid the omission of feature information caused by considering only a single stratum feature vector, thereby more comprehensively describing the stratum characteristics of the ith adjacent well in the jth stratum, and providing accurate and reliable support for the subsequent calculation of the stratum feature vectors of each stratum of the well point to be predicted.

[0127] In some embodiments of the present specification, in step S104, the formation feature vector of the well point to be predicted in each formation is calculated using the following formula:

[0128] (5)

[0129] Among them, E_W Loc S j represents the stratigraphic feature vector of the well point to be predicted in the jth stratum, n2 represents the number of neighboring wells of the well point to be predicted, and ρ i represents the distance influence coefficient between the well point to be predicted and the i-th adjacent well, E_W i S j Represents the stratigraphic characteristic vector of the i-th adjacent well in the j-th stratum. In this way, by weighting and summing the stratigraphic characteristic vectors of the adjacent wells of the predicted well point according to the distance influence coefficient of the adjacent wells, a more comprehensive stratigraphic characteristic vector of the predicted well point in each stratum can be obtained, which improves the accuracy of calculating each stratigraphic characteristic vector of the predicted well point, and provides accurate and reliable data support for the subsequent acquisition of corresponding geological condition labels based on the stratigraphic characteristic vectors.

[0130] In step S105, the knowledge graph of solutions to difficulties is formed by extracting geological conditions (such as piedmont structural belts, faults, salt-gypsum layers, etc.), drilling difficulties (such as coexistence of blowout and leakage, narrow safety density window, low mechanical drilling speed, etc.), solutions to difficulties (such as high-steep structure broken wellbore stabilization technology, tight sandstone fracture gas layer protection technology, etc.) from books, documents, drilling logs and other materials. The main construction process includes the following steps:

[0131] Step a: Establish a label system for drilling difficulties and solutions to difficulties. By establishing a label system, it is helpful for drilling engineers and other business experts to fully understand the complex geological conditions, drilling engineering difficulties and solutions to difficulties in each block. The label system mainly includes geological labels, drilling difficulty labels, and difficulty solution labels, as shown in Table 1.

[0132] Table 1

[0133]

[0134] Step b: Establish a corpus of drilling difficulties and solutions to the difficulties. Specifically, first take "drilling difficulties and solutions to the difficulties" as the theme, obtain relevant data from sources such as the Internet, books, documents, reports, etc., and perform operations such as cleaning, deduplication, and word segmentation on the data to form a text data set. For unstructured documents, technical tools such as image recognition, OCR, and GROBID can be used to identify the document structure, extract chapter content, and further extract semantic relationships and cross-relationships between texts. Then, keyword matching, text classification, large models and other technologies are used to filter out text content that represents drilling geological conditions, drilling difficulties or solutions to the difficulties from the above text data sets to form a corpus of drilling difficulties and solutions to the difficulties. Preferably, prompt words can be formulated to use large models to extract content related to the topic from the text data set.

[0135] Step c: Establish an entity relationship extraction model for drilling difficulties and technical countermeasures. First, divide the corpus in step b into three parts according to the ratio (e.g., 1:2:7, etc.): corpus1, corpus2, and corpus3. Manually annotate corpus1, annotate the labels corresponding to each text segment and the relationship between labels. The relationship between labels includes two categories: the relationship between geological conditions and drilling difficulties, and the relationship between drilling difficulties and solutions to difficulties. For corpus2, first use text classification technology to select matching instructions from the preset instruction set for each text, and then use knowledge extraction tools to automatically extract entity relationships such as geological conditions, drilling difficulties, and solutions to difficulties. After reviewing and verifying the extracted json results, generate a corpus2 annotated data set. Construct an entity relationship extraction data set based on the annotated data of corpus1 and corpus2, and use ETL-span, HBT, SpERT and other relationship extraction models to train on this data set to generate an entity relationship extraction model. Divide corpus3 into n batches, and perform the following operations on each batch: use the entity relationship extraction model to identify all text contents in the batch, extract entities such as geological conditions, drilling difficulties, solutions to difficulties, and the relationships between them; randomly select a part of the recognition results and calculate the accuracy of the model; if the accuracy does not meet the requirements, add the incorrectly recognized data to corpus1 for manual annotation, further expand the data set, optimize the entity relationship extraction, and apply the optimized entity relationship extraction model to the next batch; if the accuracy meets the requirements, execute the next batch.

[0136] Step d: Import the manual annotation results of corpus1, the extraction results of the large model of corpus2, and the extraction results of the entity relationship extraction model in corpus3 into the graph database to generate a knowledge graph of difficulty solutions. The node types in the knowledge graph of difficulty solutions are mainly divided into three categories, namely geological conditions, drilling difficulties, and difficulty solutions. Using the knowledge graph representation method, the nodes and relationships in the knowledge graph of difficulty solutions are mapped to a low-dimensional, dense numerical vector space to generate geological condition feature vectors, drilling difficulty feature vectors, and difficulty solution feature vectors.

[0137] In some embodiments of this specification, refer to Figure 4 , the step of determining the geological condition label, drilling difficulty label and difficulty solution label of the well point to be predicted in each stratum according to the stratum feature vector of the well point to be predicted in each stratum and the pre-built difficulty solution knowledge graph includes:

[0138] S401: Performing characterization learning on the difficult problem solution knowledge graph to obtain a geological condition feature vector corresponding to each geological condition class node in the difficult problem solution knowledge graph.

[0139] S402: Calculate the similarity between the formation feature vector of the well point to be predicted in each formation and each geological condition feature vector in the knowledge graph of the difficulty solution.

[0140] Specifically, similarity calculation methods such as cosine similarity, Euclidean distance or Pearson correlation coefficient can be used to calculate the similarity between the formation feature vector of the well point to be predicted in each formation and each geological condition feature vector in the knowledge graph of the difficulty solution.

[0141] S403: Using labels corresponding to the first preset number of geological condition feature vectors whose similarity is greater than a preset threshold as geological condition labels of the well point to be predicted in each stratum.

[0142] S404: Determine the drilling difficulty label and the difficulty solution label of the well point to be predicted in each stratum from the difficulty solution knowledge graph according to the geological condition label of the well point to be predicted in each stratum.

[0143] Specifically, after determining the geological condition labels of the well points to be measured in each stratum, the reasoning method based on the knowledge graph can be used, such as the recommendation algorithm based on the relationship path, the recommendation algorithm based on collaborative filtering, etc. to obtain the corresponding drilling difficulty labels and difficulty solution labels from the difficulty solution knowledge graph. Taking the recommendation algorithm based on the relationship path as an example, first search in the difficulty solution knowledge graph: all paths with the entity type of "drilling difficulty" as the starting point, the node of "difficulty solution" as the end point, and the number of hops less than the specified value, and take the difficulty solution entities in these paths as the candidate solution set, set weights according to factors such as blocks, strata and application effects, sort the candidate solutions, and take the first several candidate solutions after sorting as the recommendation results. In this way, since the difficulty solution knowledge graph contains the causal relationship between geological conditions, drilling difficulties and difficulty solutions, after determining the geological condition labels from the difficulty solution knowledge graph according to the stratum feature vector of the well points to be predicted in each stratum, the corresponding drilling difficulty labels and difficulty solution labels can be obtained according to the causal relationship between the three.

[0144] Since geological condition labels, drilling difficulty labels and difficulty solution labels are relatively general texts, in order to obtain more detailed drilling difficulty analysis texts and corresponding difficulty solution texts, it is necessary to construct prompt texts based on geological condition labels, drilling difficulty labels and difficulty solution labels and input them into the pre-trained drilling difficulty analysis model to obtain the drilling difficulty prediction texts and corresponding difficulty solution texts of the well points to be predicted in each stratum. Figure 5 , the prompt text constructed according to the geological condition label, drilling difficulty label and difficulty solution label is input into the pre-trained drilling difficulty analysis model to obtain the drilling difficulty prediction text of the well point to be predicted in each stratum and the corresponding difficulty solution text, including:

[0145] S501: Fill the geological condition label, drilling difficulty label and difficulty solution label into the placeholder corresponding to the pre-created prompt text template to obtain the prompt text.

[0146] Specifically, the embodiment of this specification designs a prompt text template based on the causal relationship between the three. Preferably, the prompt text template can be as follows:

[0147] You are a senior {role}, with {professional skills}, have worked in {oil field or drilling company} for many years, and are very familiar with the geological background and drilling plan of this block. Please help me generate a technical solution report based on the following geological condition tags, drilling difficulty tags, and difficulty solution tags and other control conditions:

[0148] Geological condition tag: {geological condition tag};

[0149] Drilling difficulty label: {drilling difficulty label};

[0150] Difficulty solution label: {difficulty solution label}.

[0151] The content in {} is the template placeholder, which is filled in according to the geological condition label, drilling difficulty label and difficulty solution label of the well point to be predicted.

[0152] S502: Input the prompt text into a pre-trained large model for drilling difficulty analysis to generate a drilling difficulty prediction text for the well point to be predicted in each stratum and a corresponding difficulty solution text.

[0153] Among them, the big model for drilling difficulty analysis is obtained by constructing a drilling knowledge system, collecting professional books, technical manuals, standards and specifications such as geology, drilling, mud logging, logging, cementing, and fracturing around the knowledge system, forming a drilling geological engineering corpus, and then training the general big model based on the drilling geological engineering corpus. Specifically, the construction of the big model for drilling difficulty analysis includes the stages of basic big model evaluation and optimization, pre-training, instruction fine-tuning and reinforcement learning. First, a big model evaluation system for the drilling industry is established to evaluate the understanding ability of different basic big models of drilling field knowledge from different dimensions, and obtain the optimal base big model. The basic big model can be any open source big model. In addition to general capabilities such as semantic understanding, generation, dialogue, encyclopedia, logical reasoning, computing power, and code, the evaluation dimensions mainly evaluate the basic big model's ability to understand professional knowledge, such as drilling professional terminology, drilling theoretical knowledge, drilling technical operations, safety operation specifications, emergency plans, etc. Representative test questions can be selected from the test question banks of driller training, mud logging training, and well control training to construct an evaluation data set. Secondly, based on the selected basic large model, self-supervised pre-training is performed on the corpus to learn geological engineering professional knowledge and language rules, and obtain the large model of the drilling industry. In the pre-training stage, the drilling field dictionary can be combined with the full-word masking strategy as a pre-training task to enhance the model's understanding of professional terms. Then, according to the distribution of entities and relationship types in the difficulty solution knowledge graph, the difficulty solution knowledge graph is stratified and sampled to construct a drilling difficulty and technical countermeasure instruction fine-tuning dataset, including instructions, input and output. The specific example is shown in Table 2. The dataset is used to fine-tune the drilling industry large model, learn drilling difficulties and technical countermeasures under complex geological conditions, and obtain a customized drilling difficulty analysis large model. Finally, based on the drilling difficulties and difficulty solution data of the drilled wells, a difficulty solution evaluation dataset is constructed. The reward model is trained based on the evaluation dataset. Through continuous iteration, the generation strategy of the drilling difficulty analysis large model is optimized, so that the generated difficulty solution has better guidance. In addition, in response to possible problems such as data leakage, sensitive words, false information, and prompt word attacks in the big model, security evaluation indicators for the drilling difficulty analysis big model are formulated, and the drilling difficulty analysis big model is optimized to ensure that the generated content is legal and compliant.

[0154] Table 2

[0155]

[0156] Taking the xx stratum as an example, based on the geological condition label, drilling difficulty label and difficulty solution label of the stratum, the prompt text is constructed as follows:

[0157] "Please help me write a drilling difficulty analysis and technical solution report based on the geological conditions, drilling difficulties and difficulty solution tags provided:

[0158] Geological condition label: gypsum mudstone, highly water sensitive;

[0159] Drilling difficulty tags: The filling material of the micro-fractures in the formation is basically montmorillonite, which is very easy to hydrate and disperse, and is easy to shrink and collapse; poor stability;

[0160] Difficulty Solution Tags: Oil-based drilling fluid. ”

[0161] Input the above prompt words into the drilling difficulty analysis model to automatically generate the drilling difficulty analysis text and difficulty solution text for the formation, as shown below:

[0162] 1. Overview of geological conditions

[0163] The main geological conditions faced by this drilling operation are gypsum-containing mudstone formations, which are characterized by strong water sensitivity. The mudstone in this formation contains a high content of gypsum salt, which gives the formation special physical and chemical properties and puts forward higher requirements for drilling operations.

[0164] 2. Analysis of drilling difficulties

[0165] (1) Influence of formation micro-fracture fillings

[0166] The microcracks in the formation are a major difficulty in the drilling process. The filling material of these microcracks is mainly montmorillonite, which is a mineral with strong water absorption and easy hydration and dispersion. Under the action of drilling fluid, montmorillonite is prone to hydration reaction, causing microcracks to expand, which in turn causes problems such as well wall instability, shrinkage and collapse.

[0167] (2) Poor wellbore stability

[0168] The water sensitivity of gypsum-bearing mudstone formations makes the well wall rocks easy to soften and peel off after contact with water, resulting in extremely poor well wall stability. This not only increases the safety risks during drilling, but may also lead to reduced drilling efficiency and increased drilling costs.

[0169] (3) Difficulty in selecting drilling fluid

[0170] Given the special properties of the micro-fracture fillings in the formation, choosing the right drilling fluid has become a major difficulty. Traditional water-based drilling fluids are prone to hydration dispersion and wellbore instability in gypsum-containing mudstone formations, so it is necessary to find a drilling fluid that can effectively inhibit montmorillonite hydration and improve wellbore stability.

[0171] 3. Solutions to Difficulties

[0172] In view of the above-mentioned drilling difficulties, it is recommended to use oil-based drilling fluid as the drilling fluid solution for this drilling operation. The following is the specific technical solution:

[0173] (1) Drilling fluid formula selection

[0174] Select oil-based drilling fluid with excellent inhibition and stability, and optimize the formula to effectively inhibit the hydration and dispersion of montmorillonite and improve the stability of the wellbore. At the same time, considering environmental protection requirements, environmentally friendly oil-based drilling fluid should be selected to reduce pollution to the environment.

[0175] (2) Drilling fluid performance control

[0176] During the drilling process, the density, viscosity and other performance parameters of the drilling fluid should be strictly controlled to ensure that the drilling fluid has good sand carrying capacity and wall protection performance. At the same time, according to the formation changes and drilling progress, the drilling fluid performance should be adjusted in time to meet the drilling needs at different stages.

[0177] 4. Summary

[0178] In summary, the strong water sensitivity of gypsum-bearing mudstone formations and the special properties of microfracture fillings have brought many difficulties to drilling operations. By using oil-based drilling fluid as a technical solution, the hydration and dispersion of montmorillonite can be effectively inhibited, the wellbore stability can be improved, and the drilling risk can be reduced. At the same time, strengthening the control of drilling fluid performance and the maintenance of wellbore stability, and formulating detailed emergency treatment measures can ensure the smooth progress of drilling operations. "

[0179] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. And the acquisition, storage, use, and processing of data in the technical solutions described in the embodiments of this application are in compliance with relevant regulations.

[0180] Based on the above-mentioned method for predicting drilling difficulties and generating solutions to difficulties, the embodiments of this specification also provide a device for predicting drilling difficulties and generating solutions to difficulties. The device may include a system (including a distributed system), software (application), module, component, server, client, etc. using the method described in the embodiments of this specification and a device combined with necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided in the embodiments of this specification is as described in the following embodiments. Since the implementation scheme and method of the device to solve the problem are similar, the implementation of the specific device in the embodiments of this specification can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0181] Specifically, Figure 6 This is a schematic diagram of the module structure of an embodiment of a drilling difficulty prediction and difficulty solution generation device provided in the embodiment of this specification, referring to Figure 6 As shown, a drilling difficulty prediction and difficulty solution generation device provided in an embodiment of this specification includes:

[0182] An acquisition module 601 is used to acquire the location information of the well point to be predicted;

[0183] A neighboring well list determination module 602 is used to determine the neighboring well list of the well point to be predicted and the corresponding well history knowledge graph according to the location information of the well point to be predicted, wherein the well history knowledge graph is pre-built using historical drilling data, including stratigraphic characteristic data of different strata and the relationship between them;

[0184] The adjacent well formation feature vector calculation module 603 is used to calculate the formation feature vector of each adjacent well in each formation in the adjacent well list according to the formation feature data in the well history knowledge graph;

[0185] The formation feature vector calculation module 604 of the well point to be predicted is used to calculate the formation feature vector of the well point to be predicted in each formation according to the formation feature vector of each adjacent well in the adjacent well list in each formation;

[0186] The label determination module 605 is used to determine the geological condition label, drilling difficulty label and difficulty solution label of the well point to be predicted in each stratum according to the stratum feature vector of the well point to be predicted in each stratum and the pre-built difficulty solution knowledge graph, wherein the difficulty solution knowledge graph includes geological condition nodes, drilling difficulty nodes, difficulty solution nodes and the relationship between the above three types of nodes;

[0187] The drilling difficulty prediction and difficulty solution generation module 606 is used to construct a prompt text based on the geological condition label, drilling difficulty label and difficulty solution label and input it into the pre-trained drilling difficulty analysis model to obtain the drilling difficulty prediction text and the corresponding difficulty solution text of the well point to be predicted in each stratum.

[0188] The beneficial effects obtained by the device provided in the embodiments of this specification are consistent with the beneficial effects obtained by the above method and will not be repeated here.

[0189] Reference Figure 7As shown, based on the above-mentioned method for predicting drilling difficulties and generating solutions to difficulties, a computer device 702 is also provided in an embodiment of this specification, wherein the above-mentioned method runs on the computer device 702. The computer device 702 may include one or more processors 704, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. The computer device 702 may also include any memory 706, which is used to store any kind of information such as code, settings, data, etc. Non-limitingly, for example, the memory 706 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any memory may use any technology to store information. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent a fixed or removable component of the computer device 702. In one case, when the processor 704 executes an associated instruction stored in any memory or combination of memories, the computer device 702 may perform any operation of the associated instruction. The computer device 702 also includes one or more drive mechanisms 708 for interacting with any storage, such as a hard disk drive mechanism, an optical disk drive mechanism, etc.

[0190] The computer device 702 may also include an input / output module 710 (I / O) for receiving various inputs (via input devices 712) and for providing various outputs (via output devices 714). A specific output mechanism may include a presentation device 716 and an associated graphical user interface (GUI) 718. In other embodiments, the input / output module 710 (I / O), the input device 712, and the output device 714 may not be included, and the computer device 702 may be used as a computer device in a network. The computer device 702 may also include one or more network interfaces 720 for exchanging data with other devices via one or more communication links 722. One or more communication buses 724 couple the components described above together.

[0191] The communication link 722 may be implemented in any manner, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 722 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc. governed by any protocol or combination of protocols.

[0192] Corresponding to Figures 1 to 5 In addition to the method shown, an embodiment of the specification also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are executed.

[0193] The embodiment of the present specification also provides a computer-readable instruction, wherein when the processor executes the instruction, the program therein causes the processor to execute the following Figures 1 to 5 The method shown.

[0194] The embodiments of the present specification also provide a computer program product, including at least one instruction or at least one program, wherein the at least one instruction or the at least one program is loaded and executed by a processor to implement the following Figures 1 to 5 The method shown.

[0195] It should be understood that in the various embodiments of this specification, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this specification.

[0196] It should also be understood that in the embodiments of this specification, the term "and / or" is only a description of the association relationship of the associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this specification generally indicates that the associated objects before and after are in an "or" relationship.

[0197] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this specification can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this specification.

[0198] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0199] In the several embodiments provided in this specification, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0200] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of this specification.

[0201] In addition, each functional unit in each embodiment of this specification may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0202] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this specification is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of this specification. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0203] Specific embodiments are used in this specification to illustrate the principles and implementation methods of this specification. The description of the above embodiments is only used to help understand the methods and core ideas of this specification. At the same time, for those skilled in the art, according to the ideas of this specification, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on this specification.

Claims

1. A method for predicting drilling difficulties and generating solutions to drilling difficulties, characterized in that: The method comprises: Obtaining location information of the well point to be predicted; According to the location information of the well point to be predicted, a list of neighboring wells of the well point to be predicted and a corresponding well history knowledge graph are determined, wherein the well history knowledge graph is pre-constructed using historical drilling data, including stratigraphic characteristic data of different strata and the relationship between them; Calculate the stratigraphic feature vector of each adjacent well in each stratigraphic layer in the adjacent well list according to the stratigraphic feature data in the well history knowledge graph; The formation feature vector of the well point to be predicted in each stratum is calculated based on the formation feature vector of each adjacent well in the adjacent well list in each stratum; Determine the geological condition label, drilling difficulty label and difficulty solution label of the well point to be predicted in each stratum according to the stratum feature vector of the well point to be predicted in each stratum and the pre-constructed difficulty solution knowledge graph, wherein the difficulty solution knowledge graph includes geological condition nodes, drilling difficulty nodes, difficulty solution nodes and the relationship between the three types of nodes; According to the geological condition labels, drilling difficulty labels and difficulty solution labels, a prompt text is constructed and input into a pre-trained drilling difficulty analysis model to obtain the drilling difficulty prediction text and the corresponding difficulty solution text of the well point to be predicted in each stratum.

2. The method according to claim 1, characterized in that Determining the neighboring well list of the well point to be predicted according to the location information of the well point to be predicted includes: Determine the block to which the well point to be predicted belongs according to the position information of the well point to be predicted; Calculating the distance between the well point to be predicted and each well point in the block to which it belongs; The well points whose well distance is less than a preset threshold are determined as neighboring wells of the well point to be predicted, and a list of neighboring wells of the well point to be predicted is obtained.

3. The method according to claim 1, characterized in that The step of calculating the stratigraphic feature vector of each adjacent well in each stratigraphic layer in the adjacent well list according to the stratigraphic feature data in the well history knowledge graph includes: Performing characterization learning on the well history knowledge graph according to the formation feature data to obtain formation feature vector data; Acquire a first formation characteristic vector and a second formation characteristic vector of a certain formation of a certain adjacent well according to the formation characteristic vector data; The first formation feature vector and the second formation feature vector are merged to obtain a third formation feature vector of the certain adjacent well in a certain formation; Calculating the formation characteristic vectors of the adjacent upper formation and the adjacent lower formation of the adjacent well in a certain formation; Perform nonlinear calculation on the third formation characteristic vector, the formation characteristic vectors of the adjacent upper formation and the adjacent lower formation to obtain a fourth formation characteristic vector of the adjacent well in a certain formation; Obtaining a list of neighboring wells of the certain neighboring well, and calculating a distance influence coefficient between each neighboring well in the list of neighboring wells and the certain neighboring well and a formation characteristic vector of each neighboring well in the certain formation; The final formation characteristic vector of a certain neighboring well in a certain formation is calculated based on the fourth formation characteristic vector, the distance influence coefficient and the formation characteristic vector of each neighboring well in the neighboring well list of a certain neighboring well in the certain formation; The above steps are repeated until the formation feature vector of each adjacent well in each formation in the adjacent well list is obtained.

4. The method according to claim 3, characterized in that The step of calculating the final formation characteristic vector of a certain neighboring well in a certain formation according to the fourth formation characteristic vector, the distance influence coefficient and the formation characteristic vector of each neighboring well in the neighboring well list of a certain neighboring well in the certain formation comprises: The final formation characteristic vector of a certain adjacent well in a certain formation is calculated using the following formula: ; Among them, E_W i S j represents the final formation feature vector of the i-th adjacent well in the j-th formation, E_W i S j _2 represents the fourth stratigraphic characteristic vector of the i-th adjacent well in the j-th stratigraphic layer, n1 represents the number of adjacent wells of the i-th adjacent well, β k represents the distance influence coefficient between the i-th neighbor well and the k-th neighbor well in its neighbor well list, E_W k S j _2 represents the stratigraphic characteristic vector of the jth stratigraphic layer of the kth adjacent well in the adjacent well list of the i-th adjacent well.

5. The method according to claim 1, characterized in that The step of calculating the formation feature vector of the well point to be predicted in each formation according to the formation feature vector of each neighboring well in the neighboring well list in each formation comprises: The formation characteristic vector of the well point to be predicted in each formation is calculated using the following formula: ; Among them, E_W Loc S j represents the stratigraphic feature vector of the well point to be predicted in the jth stratum, n2 represents the number of neighboring wells of the well point to be predicted, and ρ i represents the distance influence coefficient between the well point to be predicted and the i-th adjacent well, E_W i S j Represents the formation characteristic vector of the i-th adjacent well in the j-th formation.

6. The method according to claim 1, characterized in that The step of determining the geological condition label, drilling difficulty label and difficulty solution label of the well point to be predicted in each stratum according to the stratum feature vector of the well point to be predicted in each stratum and the pre-built difficulty solution knowledge graph includes: Performing characterization learning on the difficult solution knowledge graph to obtain a geological condition feature vector corresponding to each geological condition class node in the difficult solution knowledge graph; Calculate the similarity between the formation feature vector of the well point to be predicted in each formation and each geological condition feature vector in the knowledge graph of the difficulty solution; The labels corresponding to the first preset number of geological condition feature vectors whose similarity is greater than a preset threshold are used as the geological condition labels of the well point to be predicted in each stratum; The drilling difficulty label and the difficulty solution label of the well point to be predicted in each stratum are determined from the difficulty solution knowledge graph according to the geological condition label of the well point to be predicted in each stratum.

7. The method according to claim 1, characterized in that The prompt text constructed according to the geological condition label, drilling difficulty label and difficulty solution label is input into the pre-trained drilling difficulty analysis model to obtain the drilling difficulty prediction text of the well point to be predicted in each stratum and the corresponding difficulty solution text, including: Fill the geological condition label, drilling difficulty label and difficulty solution label into the placeholder corresponding to the pre-created prompt text template to obtain the prompt text; The prompt text is input into a pre-trained large model for drilling difficulty analysis to generate drilling difficulty prediction text and corresponding difficulty solution text for the well point to be predicted in each stratum.

8. A drilling difficulty prediction and difficulty solution generation device, characterized in that: The device comprises: An acquisition module is used to obtain the location information of the well point to be predicted; A neighboring well list determination module is used to determine the neighboring well list of the well point to be predicted and the corresponding well history knowledge graph according to the location information of the well point to be predicted, wherein the well history knowledge graph is pre-built using historical drilling data, including stratigraphic characteristic data of different strata and the relationship between them; An adjacent well formation feature vector calculation module is used to calculate the formation feature vector of each adjacent well in each formation in the adjacent well list according to the formation feature data in the well history knowledge graph; A formation feature vector calculation module for the well point to be predicted, used to calculate the formation feature vector of the well point to be predicted in each formation according to the formation feature vector of each adjacent well in the adjacent well list; A label determination module is used to determine the geological condition label, drilling difficulty label and difficulty solution label of the well point to be predicted in each stratum according to the stratum feature vector of the well point to be predicted in each stratum and the pre-built difficulty solution knowledge graph, wherein the difficulty solution knowledge graph includes geological condition nodes, drilling difficulty nodes, difficulty solution nodes and the relationship between the three types of nodes; The drilling difficulty prediction and difficulty solution generation module is used to construct prompt text according to the geological condition label, drilling difficulty label and difficulty solution label and input it into the pre-trained drilling difficulty analysis model to obtain the drilling difficulty prediction text and corresponding difficulty solution text of the well point to be predicted in each stratum.

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

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. A computer program product, characterized in that The method comprises at least one instruction or at least one program, wherein the at least one instruction or the at least one program is loaded and executed by a processor to implement the method according to any one of claims 1 to 7.