Oil and gas field project development site selection method, system and equipment based on multi-factor algorithm

Abstract

The invention discloses an oil and gas field project development site selection method, system and device based on a multi-factor algorithm, and belongs to the technical field of planning and development, and the method comprises the steps: S1, determining key influence factors influencing oil and gas field project development site selection; s2, quantifying key influence factors influencing oil and gas field project development site selection; s3, on the basis of the quantified key factors influencing the oil and gas field project development site selection, calculating a pre-site selection comprehensive evaluation index, and according to the comprehensive evaluation index, judging whether the pre-site selection is implemented or not; according to the method, influence factors in multiple aspects such as land types, geological conditions, energy reserve, land space planning, environmental influence and development and production supporting are comprehensively considered, artificial intelligence is utilized for data analysis and model optimization, land meeting the conditions can be accurately screened out, weight analysis and decision making are carried out according to different factors, and the method is suitable for large-scale popularization and application. And finally determining an optimal oil and gas field project development site selection scheme.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of oil and gas field planning and development, and specifically relates to an oil and gas field project development site selection method, system and device based on a multi-factor algorithm. BACKGROUND

[0002] With the continuous growth of global energy demand, the importance of oil and gas field project development site selection is increasingly prominent. However, oil and gas field project development site selection is a complex process that needs to consider multiple factors such as geological conditions, energy reserves, land space planning, environmental impact, development production supporting facilities, etc. Traditional site selection methods have obvious shortcomings in systematization, graphical representation, and visualization. There is no quantitative scientific support means, mainly relying on field reconnaissance and graphical experience judgment, which is difficult to meet the diversified site selection needs of current oil and gas field project development scheme design and field implementation, affecting the scheme implementation rate and oil and gas field construction rate. Therefore, it is of great significance to develop an oil and gas field project development site selection method based on a multi-factor algorithm.

[0003] The current research status of oil and gas field project development site selection mainly focuses on how to improve the accuracy of site selection, optimize land use management, and improve the scientific nature of decision-making:

[0004] Domestic oil and gas field project development site selection usually uses field reconnaissance combined with Geographic Information System (GIS) layer superposition and other technologies to assist in visualizing land location.

[0005] At present, the research methods and technologies still have certain drawbacks and limitations in some aspects, which are as follows:

[0006] 1) High cost: During field reconnaissance, a large amount of manpower, material resources, and financial resources need to be invested, which makes the cost of the entire process relatively high. This situation to some extent restricts the deepening reform and innovation of oil and gas field project development site selection;

[0007] 2) Difficult to quickly respond to development deployment adjustments: The current methods and technologies still need to be improved in terms of adaptability and flexibility, and cannot be adjusted in time when external environment, internal development deployment, etc. change;

[0008] 3) Accuracy needs to be improved: Existing means such as GIS layer superposition, information system visualization assistance, etc. still mainly rely on manual decision-making, lack of quantitative basis, which to some extent affects the accuracy of the results;

[0009] 4) Not fully considering the national land resource utilization prospect planning and the new requirements of digital ecological development of national space governance by the state.

[0010] In summary, in order to improve the timeliness and scientificity of oil and gas field project development site selection, it is still necessary to continue to research and develop new methods that are more efficient, adaptable and can provide accurate decision support. SUMMARY

[0011] The purpose of the present application is to provide an oil and gas field project development site selection method, system and device based on a multi-factor algorithm, which comprehensively considers the influence factors of land type, geological conditions, energy reserves, land space planning, environmental impact, development production supporting and other aspects, uses artificial intelligence for data analysis and model optimization, can accurately screen the land that meets the conditions, and according to different factors, carries out weight analysis and decision, and finally determines the optimal oil and gas field project development site selection scheme.

[0012] In order to achieve the above purpose, the present application adopts the following technical scheme:

[0013] In a first aspect, the present application provides an oil and gas field project development site selection method based on a multi-factor algorithm, comprising:

[0014] S1, determining the key influence factors affecting the oil and gas field project development site selection, comprising the following steps:

[0015] Step S1.1, constructing a structured graph data model, the data model is used to express the relationship between entities, the entities include land, geological information, engineering information and new energy information;

[0016] Step S1.2, constructing a knowledge graph, the knowledge graph includes entities, attributes, relationships and events;

[0017] Step S1.3, based on the structured graph data model and the knowledge graph, the association rules are summarized, and the key influence factors are determined according to the association rules;

[0018] S2, quantifying the key influence factors affecting the oil and gas field project development site selection;

[0019] S3, based on the quantified key influence factors affecting the oil and gas field project development site selection, calculating the pre-site comprehensive evaluation index, and judging whether the pre-site is implemented according to the pre-site comprehensive evaluation index.

[0020] Further, the knowledge graph fusion technology is used to determine the key influence factors affecting the oil and gas field project development site selection.

[0021] Further, step S1.3 comprises:

[0022] Based on the structured graph data model, the data items in the knowledge graph are sliced from three categories of time, space and business scenarios to form data sets, and the frequent sets are mined from the data sets by using the classic algorithm of the frequent set, the support and the confidence are calculated, and then the association rules are summarized according to the frequent set, the support and the confidence, and the key influence factors are determined according to the association rules.

[0023] Further, the Eclat algorithm is used to mine the frequent sets from the data sets.

[0024] Further, the analytic hierarchy process is used to quantify the key influence factors affecting the development site selection of the oil and gas field project.

[0025] Further, the analytic hierarchy process is used to quantify the key influence factors affecting the development site selection of the oil and gas field project, including the following steps:

[0026] Step S2.1, constructing a hierarchical structure;

[0027] Step S2.2, creating a pair-wise comparison matrix in the hierarchical structure, and the elements in the pair-wise comparison matrix are the relative importance of the same type of influence factors;

[0028] Step S2.3, checking the consistency of the comparison matrix, if the comparison matrix has an acceptable consistency level, executing step S2.4, otherwise adjusting the comparison matrix until the comparison matrix has an acceptable consistency level;

[0029] Step S2.4, filling in the score and calculating the weight vector of the pair-wise comparison matrix;

[0030] Step S2.5, calculating the consistency ratio CR of the pair-wise comparison matrix and evaluating the consistency according to the consistency ratio CR of the pair-wise comparison matrix; if CR is less than a threshold value, executing step S2.6; otherwise, re-evaluating the relative importance of each influence factor;

[0031] Step S2.6, calculating the overall weight of the top-level target based on the weight vector of the pair-wise comparison matrix;

[0032] Step S2.7, based on the overall weight result of the top-level target obtained, evaluating the comprehensive development difficulty of the land;

[0033] Step S2.8, calculating the area proportion of the oil and gas field land.

[0034] Further, a multi-factor quantification algorithm based on the oil and gas field project development site selection is constructed by using the vector machine method of machine learning, and a pre-site comprehensive evaluation index is calculated based on the multi-factor quantification algorithm.

[0035] Further, the calculation formula of the comprehensive evaluation index is:

[0036] determining whether A_i>0 is true, i=6, i=7, i=8, i=12, i=13, i=15;

[0037] if true, EDC=100;

[0038] otherwise, EDC=(Σ(A_i*W_i*D_i)+Σ(B_j*W_j*D_j)+Σ(C_k*W_k*D_k)) / Σ(W_i+W_j+W_k);

[0039] wherein: EDC is a comprehensive evaluation index, A_i represents the i-th land use type; B_j represents the reserve condition classification; C_k represents the classification of ground development difficulty; W_i, W_j, and W_k are the area weights of the corresponding classifications; D_i is the influence factor weight of the i-th land use type; D_j is the influence factor weight of the j-th ground development difficulty; and D_k is the influence factor weight of the k-th reserve condition.

[0040] In a second aspect, the present application provides an oil and gas field project development site selection system based on a multi-factor algorithm, comprising:

[0041] a key influence factor acquisition module configured to determine key influence factors affecting the oil and gas field project development site selection;

[0042] a quantification module configured to quantify the key influence factors affecting the oil and gas field project development site selection;

[0043] a calculation module configured to determine whether to implement the pre-selected site based on the pre-selected site comprehensive evaluation index and the quantified key influence factors affecting the oil and gas field project development site selection.

[0044] In a third aspect, the present application provides an electronic device, comprising:

[0045] at least one processor; and

[0046] a memory communicatively connected to the at least one processor; wherein

[0047] the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of the first aspect of the present application.

[0048] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the method of any one of the first aspect of the present application.

[0049] Compared with the prior art, the present application has at least the following beneficial technical effects:

[0050] 1) Increase the oil and gas well production rate: Through in-depth analysis of oil and gas field land use and production process, the key influencing factors affecting land site selection are found out, the development project site selection area can be better understood, and areas such as ecological red line, basic farmland, railway and road facilities are avoided, and the land layout is scientific. Compared with the traditional method, geology researchers and ground scheme designers can work on a dataset that has been preliminarily screened and analyzed, avoiding a lot of unnecessary preliminary investigation and data processing work. Using data analysis and model optimization reduces human intervention and errors, improves the speed and accuracy of scheme design; reduces repeated reconnaissance and adjustment due to poor location or non-compliance with planning requirements, saving time and resources; with more scientific and accurate site selection, the development team can quickly start construction in the confirmed location, reducing preparation and waiting time; in terms of increasing production and building production, oil and gas production work can be started faster, and the operation time of each oil well is relatively extended, thereby producing more oil and gas in the same total time. More scientific site selection also means that areas with more superior geological conditions are selected, which will naturally result in higher single-well production. Overall, it is expected that the geological scheme and engineering scheme preparation time will be shortened by 1-2 days, the field reconnaissance and site selection time will be shortened by at least 2 days, the oil and gas well production time will be advanced by 2-4 days, and the estimated increase in production is 5480-10960 tons per year for a new well with an annual output of 100 million tons. According to the calculation of 3100 yuan per ton of crude oil, it is expected to generate 1698-3396 million economic benefits.

[0051] 2) Reduce land acquisition cost: Preferentially select low-value land areas such as oil and gas field ownership land and unused land, and reduce the use of high-value land areas such as forest land, farmland, and grassland, to improve land use efficiency and land management level.

[0052] 3) Reduce field reconnaissance cost: Through the quantitative oil and gas field land project development site selection method, online analysis of various quantitative site selection factors is realized, the quality of field reconnaissance work is improved, the number of field reconnaissance is reduced, and the cost is reduced.

[0053] Through the implementation of the present application, scientific site selection of oil and gas field project development is realized, and the executable rate of oil and gas field geological scheme and engineering scheme, the economic and social benefits of oil and gas field enterprises are further improved. BRIEF DESCRIPTION OF DRAWINGS

[0054] Figure 1 is the overall technical roadmap of the present application;

[0055] Figure 2 is a structural block diagram of an oil and gas field project development site selection system based on a multi-factor algorithm provided by an embodiment of the present application;

[0056] Figure 3 Block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to better understand the technical scheme of the present application, the technical scheme in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the protection scope of the present application.

[0058] It should be noted that the terms "comprising" and "having" and any variations thereof are intended to cover not exclusively containing, for example, a process, method, system, product or device comprising a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0059] Embodiment 1

[0060] Reference Figure 1 The embodiment provides a multi-factor algorithm-based oil and gas field project development site selection method, which comprises the following steps:

[0061] Step S1, all associated factors in the process of oil and gas field land development and operation are analyzed in depth through knowledge graph fusion technology, three key influence factors of land class, reserve condition and ground development difficulty related to land value are calculated, and specific representation indexes of each key influence factor are given, comprising the following steps:

[0062] Step S1.1, constructing a structured graph data model

[0063] Research on the establishment method and rules of the graph data model, the data structure representing the relationship between business entities, in the land full-factor correlation application model, the relationship between entities such as land, geological information, engineering information and new energy information is expressed by using the graph data model.

[0064] In the step of constructing the structured graph data model, the expression of the graph data model can be defined and enriched in the following ways:

[0065] 1) Entity definition:

[0066] Land plot: represented as a node in the graph, the attributes include land plot size, location, land class (such as farmland, forest land), current utilization state, etc.

[0067] Geological Information: As a node, attributes include geological structure, mineral composition, historical mining information, etc.

[0068] Engineering Information: As a node, attributes include engineering type (e.g., drilling, surface construction), budget, duration, etc.

[0069] New Energy Information: Related to new energy projects (wind, solar, etc.), node attributes include equipment type, energy efficiency, installation date, etc.

[0070] 2) Relationship Definition:

[0071] Parcel and Geological Information: Through boundary connections, it represents the specific geological attribute correspondence of the parcel.

[0072] Parcel and Engineering Information: Edges represent the implementation of specific engineering projects in specific parcels.

[0073] Geological Information and Engineering Information: Edges represent the adaptability or engineering limitations under specific geological conditions.

[0074] 3) Graph Model Attributes:

[0075] Edge Weight: Can represent the strength or importance of the relationship, for example, the severity of the impact of geological conditions on engineering.

[0076] Directionality: Some relationships may have directionality, for example, engineering affects the state change of the parcel.

[0077] 4) Query and Analysis:

[0078] Use the graph query language Cypher to query specific patterns, such as finding all parcels that cannot be developed on a large scale due to geological condition restrictions.

[0079] Graph algorithm application, shortest path analysis determines the optimal route for engineering resource allocation.

[0080] Step S1.2, Unstructured Data Analysis Algorithm Research

[0081] Research a kind of for unstructured data, such as text, picture, professional model, based on entity recognition and relationship extraction, the result helps experts to build knowledge graph. Through the research of unstructured data analysis algorithm to build knowledge graph. The following is the process of building a knowledge graph and an overview of the types of data that may be included in the knowledge graph:

[0082] 1) Data Collection:

[0083] Collect relevant unstructured data, including text (research reports, news articles, regulatory documents, etc.), pictures (satellite images, field photos, etc.), and professional models (such as geological model data).

[0084] 2) Data Preprocessing:

[0085] Text is segmented, stop words are removed, and standardized processing is performed.

[0086] Image data is formatted, denoised, and feature extracted for preprocessing.

[0087] Professional model data is converted and standardized.

[0088] 3) Entity Recognition:

[0089] Use natural language processing techniques to identify key entities in text, such as place names, device types, and project names.

[0090] Apply image recognition techniques to identify specific signs and geographical features in images.

[0091] Extract key parameters and features from professional models as entities.

[0092] 4) Relationship Extraction:

[0093] Use pattern matching or machine learning algorithms to extract relationships between entities from text (such as "located in", "use", "belong to", etc.).

[0094] Identify spatial and functional relationships between entities from image and model data.

[0095] 5) Knowledge Fusion and Integration:

[0096] Integrate entities and relationships extracted from different data sources, resolving ambiguity and redundancy in entity recognition.

[0097] Construct a graph to store entities and relationships in graph form.

[0098] 6) Optimization and Updating of Knowledge Graph:

[0099] Regularly update and expand the knowledge graph to reflect new discoveries and changes.

[0100] Apply graph analysis techniques for knowledge discovery and verification, optimizing knowledge structure.

[0101] Data included in the knowledge graph:

[0102] Entities: Individuals involved, including land, reserve conditions, and ground supporting facilities.

[0103] Attributes: Descriptive data related to entities, such as land area, category, and reserve conditions.

[0104] Relationships: Connections between entities, representing a logical or physical connection, such as "located in", "use", "belong to".

[0105] Event: Important activities that occur at a specific time, such as the start and end dates of land development, contract signing, etc.

[0106] Step S1.3: Construct an oil and gas field project development site selection correlation analysis model based on business attributes in the spatial and temporal dimensions.

[0107] A correlation analysis model is constructed, which slices the data items in the knowledge graph into datasets according to three categories: time, space, and business scenario. Then, the support (support(A) = count(A) / count(dataset) = P(A)) and the confidence score are calculated.

[0108] Confidence = P(A&B) / P(A). Frequent sets are mined from the dataset using classic frequent set mining algorithms, and association rules are then summarized based on these frequent sets. Classic frequent set mining algorithms include Apriori, FP-growth, and Eclat. This invention uses the Eclat algorithm for frequent set mining.

[0109] The process of constructing a spatial-temporal correlation analysis model for oil and gas field project development site selection involves three main parts: data preparation, frequent set mining, and association rule generation. These steps can help reveal implicit relationships and patterns in the knowledge graph, providing data support for decision-making. The following is a detailed description of the construction process and the expression of the correlation analysis model:

[0110] The process of building an association analysis model:

[0111] 1) Dataset slicing:

[0112] The data in the knowledge graph is categorized and sliced ​​based on time, space, and business scenario dimensions. For example, the data can be divided into specific time periods (by quarter), specific regions (drilling blocks), and specific business scenarios (mining types). By conducting more detailed correlation analysis on the data, behavioral patterns or regularities under specific conditions can be identified.

[0113] 2) Frequent set mining:

[0114] The Eclat algorithm is used to process the dataset and identify frequently occurring itemsets, i.e., frequent sets.

[0115] Frequent sets are itemsets that appear in a dataset with a probability higher than a set threshold (minimum support threshold).

[0116] 3) Calculate support and confidence:

[0117] Support: The frequency of an itemset appearing in all transactions. The formula is \(\text{Support}(A)=\frac{\text{count}(A)}{\text{count}(\text{dataset})}=P(A)\).

[0118] Confidence: The conditional probability that itemset B will also occur if itemset A occurs. The formula is \(\text{Confidence}(A\Rightarrow B)=\frac{P(A\cap B)}{P(A)}\).

[0119] 4) Association rule generation:

[0120] Based on the mined frequent sets and the calculated support and confidence scores, potential association rules are generated. These rules help to understand how specific data items are associated with other items.

[0121] 5) Model validation and optimization:

[0122] Use techniques such as cross-validation to validate association rules to ensure their effectiveness and accuracy.

[0123] Adjust the support and confidence thresholds according to business needs to optimize model performance.

[0124] Expressions or descriptions of the site selection correlation analysis model for oil and gas field project development:

[0125] Model Description: The site selection association analysis model for oil and gas field development is a statistical model that derives strong association rules between itemsets by identifying frequent co-occurrence patterns among data items. The model utilizes algorithms such as Apriori, FP-growth, and Eclat to mine meaningful relationships from large-scale datasets.

[0126] Example of an expression: If there is a rule \(\text{Geological Type A}\Rightarrow\text{Engineering Type B}\), with a support of 0.5% and a confidence of 70%, this means that in all data, the probability of geological type A and engineering type B occurring simultaneously is 0.5%, and if geological type A occurs, there is a 70% probability that the engineering type is B.

[0127] The following is an analysis and comparison based on the three existing algorithms:

[0128] ① Mining based on the Apriori algorithm

[0129] Apriori is a classic algorithm used to discover frequent itemsets and learn association rules. It is based on a principle called the Apriori property, which states that all non-empty subsets of a frequent itemset are also frequent. Its operation steps are:

[0130] 1) Set a minimum support threshold: an itemset is considered frequent only if its support is not lower than this value.

[0131] 2) Generate candidate set: First, calculate the frequency of site selection for a single oil and gas field project to form a single candidate set (C1).

[0132] 3) Calculate support: Remove items from the candidate set whose support is less than the minimum support threshold.

[0133] 4) Generate frequent itemsets: Create frequent 1-itemsets (L1) based on the retained candidate itemsets.

[0134] 5) Generate a new candidate options set: Generate a 2-option candidate options set (C2) through the join operation of L1 itself.

[0135] 6) Repeat steps 3 to 5 until no more frequent itemsets can be found.

[0136] Code:

[0137]

[0138] ② Mining based on FP-growth algorithm

[0139] The FP-growth algorithm is a more efficient algorithm than Apriori for finding frequent itemsets in a dataset. It uses a tree structure called an FP-tree (Frequent Pattern Tree) to compress the dataset.

[0140] Specific operations:

[0141] 1) Constructing the initial FP-tree: First, the FP-tree is constructed by scanning the dataset to record the frequency of occurrence of each oil and gas field project site selection factor (such as land type, whether it is a favorable area for reserves, etc.). Infrequent terms are removed, and frequent terms are sorted in descending order of frequency.

[0142] 2) Create the tree header: record the linked list pointer of each item in the FP tree.

[0143] 3) Construct an FP-tree using each location influence factor in the dataset: For each location influence factor, sort them in descending order of global frequency and insert them into the tree. If a part of the path that shares a prefix (a set of the same factors) already exists, increment the count; otherwise, create a new node.

[0144] 4) Mining frequent sets using FP-trees: Starting with each factor (in the order of the table header), construct a conditional pattern base, then construct a conditional FP-tree, and recursively mine frequent sets.

[0145] Code:

[0146] FP-growth(T,min_support)

[0147] Create the root of an FP-tree,T

[0148] for each transaction trans in database do

[0149] Select and sort the frequent items in trans into pattern P

[0150] insert_pattern(T,P)

[0151] end for

[0152] If T is not empty, then

[0153] for each item aiin the header of T do

[0154] generate_pattern_from_tree(ai,T,min_support)

[0155] end for

[0156] end if

[0157] ③ Mining based on the Eclat (Equivalence Clustering & Bottom-up Traversal) algorithm

[0158] The Eclat algorithm is a depth-first search algorithm used for equivalence class transformation and base association rule mining.

[0159] Specific operations:

[0160] 1) Vertical data format: The Eclat algorithm uses a vertical data format, which can associate a list of factor IDs (TID list) with each candidate factor.

[0161] 2) Recursive search: The algorithm recursively searches all frequent sets in terms of influence factors.

[0162] 3) Intersection: To generate frequent sets, perform an intersection operation on the TID list.

[0163] 4) Generate candidate sets using depth-first search: Start with a single frequent set and recursively combine other items to perform intersection operations on the TID lists.

[0164] Code:

[0165] ECLAT(prefix P,items I,min_support)

[0166] for each item i∈I do

[0167] Q = P∪{i}

[0168] T(Q) = T(P) ∩ T(i) / / T(X) represents the list of TIDs of the factor set X.

[0169] if|T(Q)|≥min_support then

[0170] Output the frequent factor set Q and |T(Q)|

[0171] I = I - {i}

[0172] ECLAT(Q,I,min_support)

[0173] end if

[0174] end for

[0175] In these algorithms, the _support_ of a factor set refers to the frequency of that factor set appearing in the entire database, while

[0176] The _fp_growth_ and _eclat_ algorithms are considered more efficient than the _apriori_ algorithm. _fp_growth_ avoids generating a large number of candidate sets, while _eclat_ reduces the number of scans required to access the entire database.

[0177] Based on the above-mentioned construction of structured graph data models, research on unstructured data analysis algorithms, and correlation analysis of business attributes from spatial and temporal dimensions, an oil and gas field site selection analysis model is constructed. The research uses a data / model dual-drive hybrid simulation technology to extract data and establish an oil and gas field site selection evaluation model for factors such as transportation location, land ownership, land type, planning conditions, environmental quality, reserve conditions, geological conditions, and development difficulty. This provides support for the site selection of geology, engineering plans, oil and gas pipelines, stations, photovoltaic facilities, and substations. Combined with machine learning, it enables the site selection for oil and gas field project development.

[0178] By comprehensively analyzing and calculating the support levels of factors such as transportation location, land ownership, land type, planning conditions, environmental quality, reserve conditions, geological conditions, and development difficulty, three factors—land type, reserve conditions, and surface development difficulty—were selected as key influencing factors.

[0179] These three types of factors have a direct and significant impact on the development and operation of oil and gas fields. The following is an analysis of the reasons for selecting these three types of factors and the potential reasons for not selecting other factors:

[0180] 1) Land Category

[0181] Land use type was chosen as a key influencing factor because it directly determines the potential location, development cost, and feasibility of oil and gas field projects. Different land types have different use restrictions, acquisition difficulties, and cost levels. For example, the conversion costs and environmental impact considerations between agricultural land and nature reserves are completely different. Furthermore, land use type is closely related to national land spatial planning and environmental protection regulations. Information such as land location, topography, and land features are also directly related to decisions regarding engineering design, road layout, and infrastructure. Therefore, these factors were extracted as core influencing factors, enabling the construction of closely correlated analysis models with multiple business attributes, providing fundamental data for oil and gas field project site selection.

[0182] 2) Reserve conditions

[0183] Reserve conditions are one of the core parameters for assessing the value and development potential of oil and gas fields. The quantity and distribution of oil and gas reserves determine the scale, extraction difficulty, and economic returns of an oil and gas field project. Exploration and appraisal well engineering provides detailed data on reserve size and geological characteristics. Furthermore, reserve conditions are closely related to development strategies, production planning, and return on investment. This factor must be carefully considered during site selection to ensure the economic viability of the project and the efficient development of resources.

[0184] 3) Difficulty of ground development

[0185] The difficulty of surface development encompasses natural factors such as topography, soil quality, and climate, as well as social factors such as infrastructure support, transportation connectivity, and the complexity of engineering construction and development. These factors directly impact the cost and project cycle of oil and gas field development projects. The level of surface development difficulty is closely linked to energy reserves, land use, and environmental protection. For example, complex terrain or environmentally sensitive areas will lead to higher development costs and more stringent environmental protection requirements. Furthermore, development difficulty also affects subsequent development plan design and the management of major development trials.

[0186] These three key influencing factors not only play a decisive role in selecting the site for oil and gas field development projects, but they also interact and intertwine with other factors such as transportation, land ownership, planning conditions, and environmental quality. By using knowledge graph technology to construct a correlation analysis model, the relationships between these factors and the degree of their mutual influence can be analyzed, thereby providing a scientific basis for the site selection of oil and gas field development projects.

[0187] 4) Potential reasons for not selecting other factors

[0188] While other factors such as location, land ownership, planning conditions, and environmental quality are also important, their contribution to achieving the purpose of the analysis is relatively small, mainly for the following reasons:

[0189] ① Information redundancy: If the selected factors have already reflected the information of the unselected factors to a certain extent (for example, the difficulty of ground development has already partially reflected the actual impact of transportation location), then these factors can be excluded to avoid information redundancy.

[0190] ② Data processing complexity: Some factors may be difficult to quantify or their support may be complex to calculate, such as planning conditions and land ownership, which may involve a wide range of legal and administrative provisions.

[0191] ③ Differences in Influence: Not all factors have equal influence on project decisions. Decision-makers, based on professional experience or historical data analysis, may believe that certain factors have a more direct and significant impact on project success than others.

[0192] ④ Optimize the analysis process: In order to simplify the analysis process and reduce the time and resources required for calculation, the most core factors are selected for in-depth analysis.

[0193] Step S2: Use the analytic hierarchy process (AHP) to quantify the key influencing factors affecting the site selection of oil and gas field development projects. The specific steps are as follows:

[0194] Step S2.1: Construction of the hierarchical structure

[0195] Constructing a hierarchical model: First, decompose the decision problem into different elements and arrange them into a hierarchical structure based on the relationships between them. In this case, the top layer represents the overall difficulty of project site selection, the middle layer represents the major categories of influencing factors, and the bottom layer represents the specific subcategories of influencing factors, thus constructing a hierarchical structure:

[0196] 1) Top-level objective: Selecting the optimal site for oil and gas field project development.

[0197] 2) Criterion Layer (Three Categories): Land Type, Reserve Conditions, and Surface Development Difficulty

[0198] 3) Sub-criteria layer (24 sub-categories): Mining land, unused land, grassland, forest land, ordinary cultivated land, basic farmland, special land (cemetery land, etc.), areas outside mining rights, land within ordinary urban planning areas, land within the Xinjiang Production and Construction Corps boundary, land within the capital city planning area, railway and highway facilities, core areas of nature reserves, non-core areas of nature reserves, land for water conservancy facilities such as rivers and reservoirs, land for municipal facilities (pipelines, power lines, etc.), areas with supporting facilities for oil and gas field development and production, and the supporting facilities are ≤50 km away; areas far from supporting facilities for oil and gas field development and production, and the supporting facilities are greater than 50 km but less than 100 km away; areas far from supporting facilities for oil and gas field development and production, and the supporting facilities are greater than 100 km but less than 200 km away; areas far from supporting facilities for oil and gas field development and production, and the supporting facilities are greater than 200 km away; favorable areas for reserves; marginal areas for rolling development; unexplored areas.

[0199] Table 1. Land Site Selection Evaluation Index System

[0200]

[0201] Step S2.2: Create a pairwise comparison matrix

[0202] For each of the listed major categories, create a comparison matrix for each subcategory. For example, for the major category "Out-of-City Land," compare each subcategory (mining land, unused land, grassland, etc.) pairwise and determine their relative importance based on their influence factor weights. Importance can be represented on a scale of 1 to 5, where 1 indicates that both are equally important, and 5 indicates that one is extremely important to the other. The intermediate values ​​represent different levels of priority.

[0203] For the three main categories and 24 subcategories, create four pairwise comparison matrices:

[0204] 1) For the comparison matrix between the three major categories, the size will be 3×3.

[0205] Table 2. Comparison Matrix of Three Major Categories of Land Site Selection (Land Type, Reserve Conditions, and Difficulty of Surface Development)

[0206] Indicator S1 S2 S3 Weight S1 1 0.2 4 0.2635 S2 5 1 3 0.6091 S3 0.25 1 / 3 1 0.1275

[0207] 2) For each subclass within a major category, the size will depend on the number of subclasses contained in that major category (ground development difficulty has 4 subclasses, so the matrix size is 4×4).

[0208] Table 3. Comparison Matrix of Ground Development Difficulty

[0209] Indicator S3_1 S3_2 S3_3 S3_4 Weight S3_1 1 3 4 5 0.517 S3_2 1 / 3 1 3 4 0.272 S3_3 1 / 4 1 / 3 1 1 0.101 S3_4 1 / 5 1 / 4 1 1 0.090

[0210] (There are 3 subcategories of reserve conditions, and the matrix size is 3×3).

[0211] Table 4. Comparison Matrix of Reserve Conditions

[0212] Indicator S3_1 S3_2 S3_3 Weight S2_1 1 1 / 3 1 / 4 0.174 S2_2 3 1 1 / 5 0.206 S2_3 4 5 1 0.620

[0213] (There are 17 subcategories of land use, and the matrix size is 17×17).

[0214] Table 5. Land Category Comparison Matrix

[0215]

[0216]

[0217] Step S2.3: Calculate the CI, RI, and CR of the comparison matrix to evaluate consistency.

[0218] Comparison Matrix and Consistency Test: Elements are compared pairwise at each level (excluding the top level) and scored. For example, in the category of "Land Outside the City," each subcategory is compared pairwise by importance. Then, the consistency of the comparison matrix is ​​tested using the AHP consistency index (CI) and the random consistency ratio (CR), ensuring that the comparisons provided are consistent (CR is typically less than 0.1).

[0219] If the matrix consistency comparison fails, meaning the calculated CR value exceeds the usual acceptance criterion (0.1), it indicates insufficient matrix consistency, and the pairwise comparison criteria need to be re-examined and re-evaluated.

[0220] Reassess the judgment: Check all pairwise comparisons for logical errors or evaluation biases, especially those with high weighting ratios.

[0221] Consulting experts: Invite more experts to conduct the evaluation to increase the diversity and accuracy of the assessment.

[0222] Use the median or mean: Using the median or mean as determined by experts can improve the consistency of the matrix.

[0223] Weight Calculation and Ranking: By normalizing the comparison matrix and calculating its eigenvectors, the relative weights of each influencing factor (such as criteria and sub-criteria) can be obtained. These weights are normalized to ensure a sum of 1, thus reflecting the relative importance of each factor in the decision-making process. This method helps decision-makers clarify the contribution of different factors to the overall objective (such as location decisions), making the entire decision-making process both scientific and systematic. These weights are then ranked to determine the degree of contribution of each influencing factor to the overall decision. Consistency Index (CI)

[0224] [CI={λ_{text{max}}-n} / {n-1}]

[0225] (λ_{text{max}}) is the largest eigenvalue of the pairwise comparison matrix.

[0226] (n) is the number of criteria or sub-criteria.

[0227] Random Consistency Index (RI)

[0228] RI is an average random consistency index given by the matrix order. It can be found in Table 6:

[0229] Table 6

[0230] Matrix order (n) RI 1 0.00 2 0.00 3 0.58 4 0.90 5 1.12 6 1.24 7 1.32 8 1.41 9 1.45 10 1.49 11 1.51 12 1.48 13 1.56 14 1.57 15 1.59 16 1.60 17 1.61

[0231] The consistency ratio (CR) is calculated based on the consistency index CI and the random consistency index RI.

[0232] [CR={CI} / {RI}]

[0233] If (CR < 0.10), the matrix is ​​considered to have an acceptable level of consistency.

[0234] Calculate the CR for each pairwise comparison matrix. If the CR is less than 0.10, it is acceptable; otherwise, re-evaluate the relative importance of the criteria or sub-criteria.

[0235] ① According to the index matrix S1 in step S2.2, where λ_S1{max}=19.194, n=4, RI=1.61,

[0236] Calculate CI = (19.194 - 17) / (17 - 1) = 0.137125

[0237] Calculate CR = 0.137125 / 1.61 ≈ 0.0852

[0238] Therefore, a CR of less than 0.1 is acceptable.

[0239] ② According to the index matrix S2 in step S2.2, where λ_S2{max}=3.133, n=3, RI=0.58,

[0240] Calculate CI = (3.113 - 3) / (3 - 1) = 0.05

[0241] Calculate CR = 0.05 / 0.58 ≈ 0.097

[0242] Therefore, a CR of less than 0.1 is acceptable.

[0243] ③ According to the index matrix S3 in step S2.2, where λ_S3{max}=4.098, n=4, RI=0.90,

[0244] Calculate CI = (4.098 - 4) / (4 - 1) ≈ 0.033

[0245] Calculate CR = 0.033 / 0.90 ≈ 0.037

[0246] Therefore, a CR of less than 0.1 is acceptable.

[0247] Step S2.4: Fill in the score and calculate the weight vector

[0248] Complete the AHP tables based on expert judgment (see Tables 2, 3, 4, and 5 in step S2.2), where each table is scored as S2_n in Table 2, S3_n in Table 3, S4_n in Table 4, and S5_n in Table 5, with scores typically ranging from 1 to 5. This range is chosen based on human intuition regarding the relative importance of things. When two factors are almost equally important, the score may be close to 1; while when one factor is extremely important relative to the other, the score may be close to 5. For each pairwise comparison matrix, normalize it using the same method, calculate the largest eigenvalue of the pairwise comparison matrix, and determine the weight vector and CI value.

[0249] Step S2.5: Calculate the CR of the pairwise comparison matrix and evaluate its consistency.

[0250] Calculate the CR for each pairwise comparison matrix. If the CR is less than 0.10, it is acceptable; otherwise, re-evaluate the relative importance of the criteria or sub-criteria.

[0251] Step S2.6: Calculate the overall weight of the top-level objective.

[0252] The weights of the lower-level units are multiplied by the weights of their corresponding upper-level units, and then summed to obtain the overall weight for the top-level objective, as detailed in Table 7-1. Overall Weight = Σ(Category Weight × Lower-Level Weight)

[0253] Table 7-1

[0254]

[0255]

[0256] Step S2.7: Assess the overall development difficulty

[0257] Based on the overall weight results of the obtained top-level objectives, the difficulty of comprehensive land development is assessed.

[0258] Step S2.8: Calculate the land area ratio of oil and gas fields

[0259] Due to the complex surface environment of oil and gas fields, a single land parcel often contains multiple land types such as grassland and woodland, and the reserve conditions and surface development difficulties also vary. Therefore, it is necessary to consider the area proportion of various influencing factors and to calculate them comprehensively in conjunction with the weight of land development difficulty. The quantitative indicators of land type influencing factors are shown in Table 7-2, the quantitative indicators of reserve condition influencing factors are shown in Table 7-3, and the quantitative indicators of surface development difficulty influencing factors are shown in Table 7-4.

[0260] Table 7-2 Quantitative Indicators of Land Category Type Influencing Factors

[0261]

[0262] Table 7-3 Quantitative Indicators of Factors Affecting Reserve Conditions

[0263]

[0264] Table 7-4 Quantitative Indicators of Factors Affecting Ground Development Difficulty

[0265]

[0266] Step S2.9: Make a decision

[0267] Thus, we have obtained the weight matrix reflecting the importance of each indicator. Using this indicator system, we derive the comprehensive evaluation index for oil and gas field site selection: EDC = Σ(W_i*D_i).

[0268] The Overall Evaluation Criterion (EDC) is calculated as follows:

[0269] Determine whether A_i (i=6, i=7, i=8, i=12, i=13, i=15) > 0 is true: if true, EDC = 100;

[0270] otherwise

[0271] EDC=(Σ(A_i*W_i*D_i)+Σ(B_j*W_j*D_j)+Σ(C_k*W_k*D_k)) / Σ(W_i+W_j+

[0272] W_k)

[0273] in:

[0274] A_i represents various land use types;

[0275] B_j represents the classification of reserve conditions;

[0276] C_k represents the classification of ground development difficulty;

[0277] W_i, W_j, and W_k are the area weights of the corresponding categories, respectively.

[0278] D_i is the influence factor weight of the i-th land use type;

[0279] D_j is the weight of the influencing factor on the difficulty of ground development of the j-th type;

[0280] D_k is the weight of the influencing factor for the kth type of reserve condition;

[0281] Σ represents the summation symbol, which performs a weighted summation over all categories.

[0282] At this point, a preliminary assessment of the comprehensive evaluation indicators for oil and gas field site selection can be conducted.

[0283] The definition of the EDC (Electronic Data Center) comprehensive evaluation index for oil and gas field site selection is as follows:

[0284] If EDC = 100, it indicates that the selected site is an undevelopable area;

[0285] If 80 < EDC < 100, then the selected site is an extremely difficult area to develop.

[0286] If 60 < EDC ≤ 80, the selected site is a relatively difficult area to develop.

[0287] If 40 < EDC ≤ 60, then the selected site area is a suitable development area;

[0288] If EDC≤40, the selected area is an area that is very easy to develop.

[0289] Step S3: Construct a multi-factor quantitative algorithm for oil and gas field project development site selection using Support Vector Machine (SVM) for machine learning; mine the information behind the scoring data to find the logic behind the expert scores, and then derive a new weight matrix. This new weight matrix is ​​an improved version that optimizes the evaluation process while fully respecting the expert evaluation results.

[0290] Using Support Vector Machines (SVMs) in machine learning to construct a multi-factor quantification algorithm for oil and gas field development site selection requires data. This data reflects the actual measured values ​​of the aforementioned influencing factors, as well as the historical site selection results corresponding to these factors. SVMs can be used to find the complex relationships between different factors and predict whether new land is suitable for oil and gas field development. The following is a basic framework of the algorithm:

[0291] Based on a multi-factor quantification algorithm built using Support Vector Machines (SVM), after training and testing, a comprehensive evaluation of land resources in different regions can be conducted, thereby optimizing the site selection for oil and gas field projects. The following is the algorithmic framework for training and testing using SVM:

[0292] 1) Data import and preprocessing:

[0293] ① Import data; The imported data includes the land type and area, reserve conditions and area, and surface development difficulty type and area of ​​a certain oil and gas field project development site. The types of land type, reserve conditions, and surface development difficulty are determined by the regional location of the project development site.

[0294] ②Segment the feature set and label set;

[0295] ③ Divide the dataset into training and testing sets;

[0296] ④ Standardized eigenvalues;

[0297] 2) Model training:

[0298] ① Create an SVM classifier;

[0299] ② Train the model using the training set;

[0300] 3) Model testing:

[0301] ① Use the test set for prediction;

[0302] ②Evaluate the model's performance.

[0303] Experiments have verified that by constructing a site selection model using Support Vector Machine (SVM) technology and comprehensively considering various influencing factors, the method has successfully achieved the prediction and optimization of site selection for oil and gas field development. Experimental results show that this method demonstrates excellent application performance in terms of accurate prediction, factor importance analysis, site selection optimization, and dynamic adjustment, providing a solid guarantee for the smooth progress of oil and gas field project development.

[0304] Future research could explore the application of other machine learning algorithms in oil and gas field development site selection to improve prediction accuracy and model stability. Simultaneously, a deeper analysis of influencing factors would be conducted to identify practically significant factors for optimizing the site selection model. Furthermore, using specific project case studies, the practical application strategies of multi-factor quantification algorithms in oil and gas field development site selection would be investigated, providing valuable insights for oil and gas field development in my country.

[0305] This is a system embodiment of the present invention, which can be used to execute the method embodiments of the present invention. For details not disclosed in the device embodiments, please refer to the method embodiments of the present invention.

[0306] Example 2

[0307] Please see Figure 2 This embodiment describes an oil and gas field project development site selection system based on a multi-factor algorithm, comprising:

[0308] The key impact factor acquisition module is used to identify the key impact factors affecting the site selection for oil and gas field project development.

[0309] The quantification module is used to quantify the key influencing factors affecting the site selection of oil and gas field development projects;

[0310] The calculation module is used to determine whether to implement the pre-site selection based on the quantified key influencing factors affecting the development and site selection of oil and gas field projects, and according to the comprehensive evaluation index of the pre-site selection, as described in the technical comprehensive evaluation index.

[0311] All relevant content of each step involved in the aforementioned embodiment of an oil and gas field project development site selection method based on a multi-factor algorithm can be referenced to the functional description of the corresponding functional module of an oil and gas field project development site selection system based on a multi-factor algorithm in this embodiment of the invention, and will not be repeated here.

[0312] Example 3

[0313] Reference Figure 3This embodiment provides an electronic device, which includes a processor and a memory, connected via a bus. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to achieve corresponding method flows or corresponding functions. The processor described in this embodiment can be used in the operation of an oil and gas field project development site selection method based on a multi-factor algorithm. The bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 3 The symbol is represented by only one line, but this does not mean that there is only one bus or one type of bus.

[0314] Example 4

[0315] This embodiment provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in an electronic device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the electronic device and extended storage media supported by the electronic device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the oil and gas field project development site selection method based on a multi-factor algorithm in the above embodiment.

[0316] Application Examples

[0317] Example 1:

[0318] Using the site selection sample data of the "JHW1302 well" well project of Xinjiang Oil and Gas Field Company as an example (Table 7-4), the specific parameters are as follows:

[0319] Unused land: accounting for 16.44% of the area, with an impact factor weight of 5.8%;

[0320] Grassland: accounting for 62.06% of the area, with an impact factor weight of 3.8%;

[0321] Forest land: accounting for 12.6% of the area, with an impact factor weight of 3.2%;

[0322] Ordinary arable land: accounting for 5.13% of the area, with an impact factor weight of 2.8%;

[0323] Favorable areas for reserves: accounting for 2.87% of the area, with an influencing factor weight of 10.6%;

[0324] Regions with supporting oil and gas field development and production: accounting for 0.9% of the total area, with an impact factor weight of 6.6%;

[0325] As shown in Table 7-4, the influencing factor parameters of the JHW1302 well site are calculated according to the comprehensive evaluation index of oil and gas field site selection as follows:

[0326] The weights (W_i, W_j, W_k) and area weights (D_i, D_j, D_k) are as follows:

[0327] Unused land: (W_2 = 0.046), (D_2 = 16.44%)

[0328] Grassland: (W_3=0.038), (D_3=62.06%)

[0329] Woodland: (W_4=0.032), (D_4=12.6%)

[0330] Ordinary arable land: (W_5=0.028), (D_5=5.13%)

[0331] Favorable area for reserves: (W18 = 0.106), (D18 = 2.87%)

[0332] Areas with supporting oil and gas field development and production: (W21 = 0.066), (D21 = 0.9%)

[0333] Total weight=W_2+W_3+W_4+W_5+W_{18}+W_{21}=0.046+0.038+0.032+0.028+0.106+0.066=0.316

[0334] Total product = (0.1644 × 0.046) + (0.6206 × 0.038) + (0.126 × 0.032) + (0.0513 × 0.028) + (0.0287 × 0.106) + (0.009 × 0.066) = 0.00756 + 0.02357 + 0.00403 + 0.00144 + 0.00305 + 0.000594 = 0.04025

[0335] EDC = Total Product / Total Weight

[0336] EDC = 0.04025 / 0.316

[0337] EDC = 12.74

[0338] Conclusion: Therefore, the comprehensive evaluation index for this land site selection is 12.74. According to the EDC index range definition in step S2.8, it belongs to the "extremely easy development area" category and can be implemented. The subsequent implementation of this land parcel was smooth and the output was good, which is consistent with this conclusion.

[0339] Table 7-5. Sample parameters of parcel 1 - "JHW1302 well"

[0340]

[0341]

[0342] Example 2:

[0343] Using the Xinjiang Oilfield Company's oil and gas field development project, "Kedou Oil Pipeline Enhancement and Renovation Project - Kedou Third Pipeline Renovation Project Land Parcel" as the site selection sample data (Table 7-5), the specific parameters are as follows:

[0344] Mining land: accounting for 12.3% of the area, with an impact factor weight of 5.8%;

[0345] Unused land: accounting for 25.78% of the total area, with an impact factor weight of 4.6%;

[0346] Forest land: accounting for 33.87% of the area, with an impact factor weight of 3.2%;

[0347] Land use within ordinary urban planning areas: accounting for 13.22% of the area, with an influencing factor weight of 2%;

[0348] The marginal area of ​​rolling development: accounting for 11.76% of the area, with an impact factor weight of 12.5%;

[0349] Regions with supporting oil and gas field development and production: accounting for 3.07% of the total area, with an influencing factor weight of 6.6%;

[0350] As shown in Table 7-4, the influencing factor parameters for the "Kedu Oil Pipeline Enhancement and Renovation Project - Kedu Third Pipeline Renovation Project Land Parcel" are calculated according to the following steps based on the comprehensive evaluation index for oil and gas field land selection:

[0351] The weights (W_i, W_j, W_k) and area weights (D_i, D_j, D_k) are as follows:

[0352] Mining land: (W_1 = 0.058), (D_2 = 12.3%)

[0353] Unused land: (W_2 = 0.046), (D_2 = 25.78%)

[0354] Woodland: (W_4 = 0.032), (D_4 = 3.2%)

[0355] Land use within ordinary urban planning areas: (W_9 = 0.020), (D_5 = 13.22%)

[0356] Edge region of rolling development: (W_{19} = 0.125), (D_{19} = 11.76%)

[0357] Areas with supporting oil and gas field development and production: (W21 = 0.066), (D21 = 3.07%)

[0358] Total weight=W_1+W_2+W_4+W_9+W_{19}+W_{21}=0.058+0.046+0.032+0.020+0.125+0.066=0.347

[0359] Total product = (0.1230 × 0.058) + (0.2578 × 0.046) + (0.0032 × 0.032) + (0.1322 × 0.020) + (0.1176 × 0.125) + (0.00307 × 0.066) = 0.007134 + 0.0118588 + 0.0108384 + 0.002644 + 0.0147 +

[0360] 0.0020262 = 0.0492014

[0361] EDC = Total Product / Total Weight

[0362] EDC = 0.0492014 / 0.347

[0363] EDC = 14.179

[0364] Conclusion: Therefore, the comprehensive evaluation index for this land site selection is 14.179. According to the EDC index range definition in step S2.8, it belongs to the "extremely easy development area" category and can be implemented. The pipeline was subsequently laid smoothly, which is consistent with this conclusion.

[0365] Table 7-6. Sample parameters for land parcel 2 - "Kedou Oil Pipeline Expansion and Renovation Project - Kedou Third Pipeline Renovation Project Land Parcel"

[0366]

[0367]

[0368] Example 3:

[0369] Using the proposed "North 419 Well" from the Xinjiang Oilfield Company's oil and gas field development project as a site selection sample (Table 7-6), the specific parameters are as follows:

[0370] Basic farmland: accounting for 45% of the area, with an impact factor weight of 5.8%;

[0371] Areas with favorable reserves: accounting for 25% of the total area, with an influencing factor weight of 10.6%;

[0372] Areas with supporting facilities for oil and gas field development and production, and where the supporting facilities are ≤50 km away: accounting for 30% of the area, with an impact factor weight of 6.6%;

[0373] According to the impact factor parameters of the proposed "North 419 Well" as shown in Table 7-6, since it involves basic farmland, although it is a favorable area for reserves and has supporting oil and gas field development and production, and the supporting facilities are ≤50 km away, the evaluation index (EDC) calculation formula is as follows:

[0374] Determine whether A_i (i=6, i=7, i=8, i=12, i=13, i=15)>0 is true:

[0375] If A_6 > 0, then EDC = 100;

[0376] Therefore, the comprehensive evaluation index for this land site was 100, classifying it as an unsuitable area for implementation. Following a well location adjustment, the land was moved out of the basic farmland area for implementation.

[0377] Table 7-7. Sample parameters of the proposed "North 419 Well" in Parcel 3.

[0378]

[0379] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0380] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0381] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The function specified in one or more boxes.

[0382] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0383] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0384] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A site selection method for oil and gas field project development based on a multi-factor algorithm, characterized in that, include: S1. Identify the key influencing factors affecting the site selection for oil and gas field development, including the following steps: Step S1.1: Construct a structured graph data model, which is used to express the relationships between entities, including land parcels, geological information, engineering information, and new energy information; Step S1.2: Construct a knowledge graph, which includes entities, attributes, relationships, and events; Step S1.3: Based on the structured graph data model and knowledge graph, summarize the association rules and determine the key influencing factors according to the association rules; S2. Quantify the key influencing factors affecting the site selection of oil and gas field projects; S3. Based on the quantified key influencing factors affecting the development and site selection of oil and gas field projects, calculate the comprehensive evaluation index for pre-site selection, and determine whether the pre-site selection should be implemented based on the comprehensive evaluation index for pre-site selection.

2. The method for site selection of oil and gas field projects based on a multi-factor algorithm according to claim 1, characterized in that, Knowledge graph fusion technology was used to identify key influencing factors affecting the site selection of oil and gas field projects.

3. The method for site selection of oil and gas field projects based on a multi-factor algorithm according to claim 2, characterized in that, Step S1.3 includes: Based on the structured graph data model, data items in the knowledge graph are sliced ​​into three categories: time, space, and business scenario to form a dataset. Frequent sets are mined from the dataset using the classic frequent set algorithm, and support and confidence are calculated. Then, association rules are summarized based on the frequent sets, support, and confidence, and key influencing factors are determined based on the association rules.

4. The method for site selection of oil and gas field projects based on a multi-factor algorithm according to claim 3, characterized in that, The Eclat algorithm is used to extract frequent sets from the dataset.

5. The method for site selection of oil and gas field projects based on a multi-factor algorithm according to claim 1, characterized in that, The analytic hierarchy process (AHP) was used to quantify the key influencing factors affecting the site selection of oil and gas field development projects.

6. The method for site selection of oil and gas field projects based on a multi-factor algorithm according to claim 5, characterized in that, The analytic hierarchy process (AHP) is used to quantify the key influencing factors affecting the site selection of oil and gas field development projects, including the following steps: Step S2.1: Construct a hierarchical structure; Step S2.2: Create pairwise comparison matrices for each layer in the hierarchical structure, where the elements in the pairwise comparison matrices represent the relative importance of the same type of influencing factors; Step S2.3: Check the consistency of the comparison matrix. If the comparison matrix has an acceptable level of consistency, proceed to step S2.4; otherwise, adjust the comparison matrix until it has an acceptable level of consistency. Step S2.4: Fill in the score and calculate the weight vector of the pairwise comparison matrix; Step S2.5: Calculate the consistency ratio CR of the pairwise comparison matrix and evaluate consistency based on the consistency ratio CR of the pairwise comparison matrix; if CR is less than the threshold, proceed to step S2.6; otherwise, re-evaluate the relative importance of each influencing factor. Step S2.6: Calculate the overall weight of the top-level target based on the weight vector of the pairwise comparison matrix; Step S2.7: Based on the overall weight results of the obtained top-level objectives, assess the difficulty of comprehensive land development; Step S2.8: Calculate the land area ratio of oil and gas fields.

7. The method for site selection of oil and gas field projects based on a multi-factor algorithm according to claim 1, characterized in that, A multi-factor quantification algorithm for oil and gas field project development and site selection is constructed using the vector machine method of machine learning, and a comprehensive evaluation index for pre-site selection is calculated based on the multi-factor quantification algorithm.

8. The method for site selection of oil and gas field projects based on a multi-factor algorithm according to claim 1, characterized in that, The formula for calculating the comprehensive evaluation index is as follows: Determine whether A_i>0 is true, i=6, i=7, i=8, i=12, i=13, i=15; If true, EDC = 100; Otherwise, EDC=(Σ(A_i*W_i*D_i)+Σ(B_j*W_j*D_j)+Σ(C_k*W_k*D_k)) / Σ(W_i+W_j+W_k); Wherein: EDC is the comprehensive evaluation index, A_i represents the i-th land use type; B_j represents the reserve condition classification; C_k represents the surface development difficulty classification; W_i, W_j, and W_k are the area weights of the corresponding classifications; D_i is the influence factor weight of the i-th land use type; D_j is the influence factor weight of the j-th surface development difficulty; and D_k is the influence factor weight of the k-th reserve condition.

9. A site selection system for oil and gas field project development based on a multi-factor algorithm, characterized in that, include: The key impact factor acquisition module is used to identify the key impact factors affecting the site selection for oil and gas field project development. The quantification module is used to quantify the key influencing factors affecting the site selection of oil and gas field development projects; The calculation module is used to determine whether to implement the pre-site selection based on the quantified key influencing factors affecting the development and site selection of oil and gas field projects, and according to the comprehensive evaluation index of the pre-site selection, as described in the technical comprehensive evaluation index.

10. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform a site selection method for oil and gas field project development based on a multi-factor algorithm as described in any one of claims 1 to 8.

Images