Data acquisition and analysis AI intelligent edge integrated data acquisition method

Abstract

The invention discloses a data acquisition and analysis AI intelligent edge integrated data acquisition method, and relates to the technical field of oil field data acquisition, and the method comprises the following steps: S1, constructing an oil field edge side multi-object original data expression unit; s2, performing AI-participated data validity judgment by using an oil field edge side original data expression unit; s3, performing structure recombination on the original data expression unit by using the edge side effective data constraint set; s4, performing unified packaging by using an oil field edge integrated analysis data unit; and S5, performing oil field analysis adaptive reconstruction by using the edge side standardized analysis data object. According to the method, the effective data constraint set on the edge side is set, whether the original data expression units on the edge side of the oil field meet subsequent analysis conditions or not is marked one by one, meanwhile, a clear use basis is provided for data structure recombination and AI analysis, pre-validity judgment of data on the edge side is achieved, and the accuracy and traceability of an analysis result are improved.

Description

Technical Field

[0001] This invention relates to the field of oilfield data acquisition technology, specifically to an AI-powered intelligent edge data acquisition method for data acquisition and analysis. Background Technology

[0002] With the expansion of oilfield development and the improvement of production automation, oilfield data collection is becoming increasingly large and complex, including information such as wellhead pressure, production volume, fluid temperature, and equipment operating status. Currently, oilfield data is typically uploaded to a central system from various acquisition nodes for unified processing and analysis. This approach suffers from high data transmission latency, insufficient real-time analysis capabilities at the edge, and weak correlation between analysis results and the original data objects. To improve the real-time performance and traceability of data acquisition and analysis, intelligent analysis methods are being gradually introduced at the edge, enabling preliminary judgment and structured processing of data at the acquisition end, thereby achieving intelligent edge management of data.

[0003] In existing technologies, the validity determination of raw data from the edge of oilfields usually relies on fixed rules or threshold methods. The determination results are implicit in the data processing results and are mostly completed on the central system side, which cannot fully guarantee the availability and consistency of edge data before analysis. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides an integrated AI-powered edge data acquisition method for data acquisition and analysis, thereby resolving the problems mentioned in the background section.

[0005] To achieve the above objectives, the present invention provides the following technical solution: In a first aspect, embodiments of the present invention provide a data acquisition and analysis AI-powered intelligent edge computing integrated data acquisition method, comprising the following steps: S1. Construct a multi-object raw data representation unit on the edge of the oilfield; S2. Use the original data representation unit of the oilfield edge side to determine the validity of AI-assisted data and obtain the set of valid data constraints on the edge side. S3. Use the effective data constraint set on the edge side to restructure the original data expression unit to obtain the integrated analysis data unit of the oilfield edge. S4. Use the integrated analysis data unit of the oilfield edge to encapsulate the data and obtain the standardized analysis data object of the edge side. S5. Use the standardized analysis data objects on the edge side to perform oilfield analysis adaptation and reconstruction, and obtain the integrated AI intelligent edge data results for oilfield data acquisition and analysis.

[0006] To further optimize this technical solution, step S1 uses oilfield data acquisition and engineering processing technology to organize field data scattered across different acquisition objects and time scales into raw data expression units with clear structure, single semantics, and definite engineering meaning.

[0007] To further optimize this technical solution, the set of original data representation units for multiple objects on the oilfield edge side output in step S1 is expressed as follows: ; in: Indicates the first A unit of original data representation. , The number of original data representation units formed at the same edge node or within the same acquisition range; Each raw data representation unit for: ; Each element has a clear meaning and fixed boundaries: : Identifier of the data collection object; Location identifier for data collection; : Data collection time identifier; Physical quantity type identifier; : The numerical value of a physical quantity.

[0008] To further optimize this technical solution, step S2, based on the set of original data expression units for multiple objects on the oilfield edge side already formed in step S1, introduces AI-involved analysis logic to determine whether each original data expression unit meets the basic prerequisites required for subsequent analysis, and expresses the determination result independently in the form of constraints. Step S2, in determining the validity of AI-involved data, includes the following steps: Determination of temporal continuity; Physical consistency determination; Determining the correlation between operating conditions; The results of the validity determination were collected.

[0009] To further optimize this technical solution, in step S2, when determining the continuity of time, for multiple original data expression units formed during continuous acquisition of the same acquisition object, the AI ​​analysis unit analyzes the distribution of time intervals between adjacent data units based on time series consistency analysis technology to determine whether the data unit is in a continuous acquisition state.

[0010] To further optimize this technical solution, in step S2, when determining physical consistency, for the original data expression units formed by the same collection object or the same type of physical quantity, the AI ​​analysis unit analyzes whether the changes in data values ​​conform to the physical laws of oilfield engineering based on physical consistency detection technology.

[0011] To further optimize this technical solution, in step S2, when determining the correlation between working conditions, the AI ​​analysis unit uses multivariate correlation analysis technology to analyze the correlation between the original data expression unit and other collected data within the same time period, in order to determine whether the data maintains a reasonable correlation with the current production status.

[0012] To further optimize this technical solution, in step S2, when collecting the validity determination results, for each original data expression unit, the time continuity determination results, physical consistency determination results, and working condition correlation determination results are comprehensively collected to form a validity determination result of whether the data unit meets the conditions for subsequent analysis and use.

[0013] To further optimize this technical solution, step S2, through the above process, ultimately outputs the following: The effective data constraint set on the edge side is expressed as follows: ; in, For the effective data constraint set on the edge side; Represents any original data representation unit The corresponding validity constraint results; ; In the formula, For each , ; express Satisfying constraints ; express Constraints not satisfied ; exist middle: :express Does it satisfy the time continuity constraint? ; :express Does it satisfy the physical consistency constraint? ; :express Does it satisfy the working condition correlation constraint? .

[0014] To further optimize this technical solution, in step S3, on the edge side of the oilfield, based on the effective data constraint set formed in step S2, the original data expression units constructed in step S1 are reorganized by constraint-driven structure, and the scattered and independent original data expression units are organized into integrated oilfield edge analysis data units with unified analytical semantics and structural integrity. The integrated oilfield edge analysis data unit formed in step S3 is subjected to unified expression and format standardization processing at the object level, and is transformed into a standardized edge-side analysis data object with consistent structure and interface. Step S5 converts the standardized analysis data objects on the edge side into an AI-usable result expression form that directly matches the oilfield data acquisition and analysis task, thereby forming the final integrated AI intelligent edge data result for oilfield data acquisition and analysis.

[0015] In a second aspect, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the computer program instructions, when executed by the processor, implement the steps of a data acquisition and analysis AI intelligent edge integrated data acquisition method as described in the first aspect of the present invention.

[0016] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, they implement the steps of a data acquisition and analysis AI intelligent edge integrated data acquisition method as described in the first aspect of the present invention.

[0017] Compared with existing technologies, this invention provides an integrated AI-powered edge data acquisition method for data acquisition and analysis, which has the following beneficial effects: This AI-powered edge data acquisition and analysis method sets up a set of valid data constraints on the edge side. It identifies each original data expression unit on the oilfield edge side to determine whether it meets the conditions for subsequent analysis, thus achieving a preliminary validity determination of the data on the edge side. This constraint set exists independently of the original data, ensuring the integrity of the original data. At the same time, it provides a clear basis for data structure reorganization and AI analysis, improving the accuracy and traceability of the analysis results. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating an AI-powered intelligent edge data acquisition method for data acquisition and analysis proposed in this invention. Figure 2 This is a schematic diagram of the AI-involved data validity determination process in the AI-integrated data acquisition and analysis method for intelligent edge computing proposed in this invention. Figure 3 This is a schematic diagram of the structural reorganization process of an AI-powered intelligent edge data acquisition method for data acquisition and analysis proposed in this invention. Figure 4 This is a schematic diagram of the oilfield analysis adaptation and reconstruction process of an AI-powered intelligent edge integrated data acquisition method proposed in this invention. Detailed Implementation

[0020] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0021] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0023] Example 1:

[0024] Reference Figures 1-4 This is the first embodiment of the present invention, which provides a data acquisition and analysis AI intelligent edge integrated data acquisition method, including the following steps: S1. Construct a multi-object raw data representation unit on the edge of the oilfield; Step S1 uses mature oilfield data acquisition and engineering processing technologies to organize field data scattered across different acquisition objects and time scales into raw data expression units with clear structure, single semantics, and definite engineering meaning.

[0025] Oilfield object identification and edge node binding: Based on the existing production system of the oilfield, the data acquisition objects are identified at the engineering level. The acquisition objects include downhole measuring points, wellhead devices, and surface production equipment nodes. By using mature oilfield field monitoring and control and edge acquisition deployment technologies, each acquisition object is fixedly bound to the corresponding edge acquisition node, so that each piece of acquisition data has a clear acquisition object identifier and location identifier when it is generated.

[0026] Engineering processing and physical quantity conversion of raw acquired signals: For continuous or discrete signals collected in the oilfield, the raw signals are processed using mature industrial signal conditioning and acquisition technologies. This includes signal stabilization and conversion of the processed signals into physical quantity expressions commonly used in oilfield engineering. This conversion process involves necessary factual calculations and unit conversions in engineering, with the aim of enabling the collected results to participate in subsequent processing in a unified physical quantity form.

[0027] Time stamping and time sequence organization of collected data: After signal conversion is completed, a data acquisition time identifier is added to the data of each acquisition channel using mature industrial time synchronization and data alignment technology. For data generated by the same data collection object within a continuous collection period, it is organized in chronological order, and status is marked for collection interruptions or missing data. The status labels are only used to reflect the objective situation during the data collection process, and are not used to determine whether the data is valid, nor to filter or remove the data.

[0028] Structured encapsulation of raw data: After data collection, processing, and time organization are completed, the data is encapsulated according to a fixed field structure using mature industrial data encapsulation technology. Each raw data representation unit includes at least the object identifier, the location identifier, the time identifier, the physical quantity type identifier, and the corresponding physical quantity value; The data representation unit formed by this encapsulation process uses a single data acquisition object as the smallest encapsulation unit, and does not merge data from different data acquisition objects into the same unit.

[0029] Following the above process, the final output of step S1 is: The set of original data representation units for multiple objects on the edge of the oilfield is expressed as follows: ; in: Indicates the first A unit of original data representation. , The number of original data representation units formed at the same edge node or within the same acquisition range; Each raw data representation unit for: ; Each element has a clear meaning and fixed boundaries: : The data collection object identifier indicates a unique oilfield data collection object, corresponding to one of the downhole measuring points, wellhead devices, or surface production equipment; Location identifier: Indicates the physical location of the data acquisition object within the oilfield production system, used to distinguish between different wells, different stations, or different equipment nodes; : Collection time identifier, indicating the time point or time period when the data was generated, generated by the edge-side time synchronization mechanism; Physical quantity type identifier: This indicates the category of the engineering physical quantity corresponding to the data. It is only used to explain the dimensions and engineering meaning and does not contain any judgment information. The physical quantity value represents the actual collected results after engineering processing. It is a factual value and does not include analytical conclusions.

[0030] S2. Use the original data representation unit of the oilfield edge side to determine the validity of AI-assisted data and obtain the set of valid data constraints on the edge side. Step S2, based on the set of original data expression units for multiple objects on the oilfield edge side already formed in Step S1, introduces AI-involved analysis logic to determine whether each original data expression unit meets the basic prerequisites required for subsequent analysis, and expresses the determination results independently in the form of constraints.

[0031] Step S2, in determining the validity of AI-involved data, includes the following steps: Determine the organization of the target: Step S2 takes the set of raw data expression units on the oilfield edge side output in step S1 as input; each raw data expression unit participates in the validity analysis as an independent judgment object. During the judgment process, the raw data expression units are not merged, split, or modified, but only their existing collection object identifier, time identifier, and physical quantity information are referenced. When time continuity analysis is involved, the analysis is performed by referencing the temporal relationships between multiple original data representation units corresponding to the same data collection object, without changing the encapsulation structure of individual data representation units.

[0032] Determination of temporal continuity; For multiple raw data representation units formed during continuous acquisition of the same data object, the AI ​​analysis unit analyzes the time interval distribution between adjacent data units based on mature time series consistency analysis technology to determine whether the data unit is in a continuous acquisition state.

[0033] Physical consistency determination: For raw data representation units formed from the same collected object or the same type of physical quantity, the AI ​​analysis unit analyzes whether the changes in data values ​​conform to the physical laws of oilfield engineering based on mature physical consistency detection technology.

[0034] Working condition correlation determination: The AI ​​analysis unit, based on mature multivariate association analysis technology, analyzes the correlation between the original data expression unit and other collected data within the same time period to determine whether the data is reasonably correlated with the current production status.

[0035] Summary of validity determination results: For each original data unit, the results of time continuity determination, physical consistency determination, and working condition correlation determination are comprehensively collected to form a validity determination result of whether the data unit meets the conditions for subsequent analysis.

[0036] Following the above process, the final output of step S2 is: The effective data constraint set on the edge side is expressed as follows: ; in, For the effective data constraint set on the edge side; Represents any original data representation unit The corresponding validity constraint results; ; In the formula, For each , ; express Satisfying constraints ; express Constraints not satisfied ; exist middle: :express Does it satisfy the time continuity constraint? ; :express Does it satisfy the physical consistency constraint? ; :express Does it satisfy the working condition correlation constraint? .

[0037] The difference between step S2 and existing oilfield data processing methods is that existing technologies typically filter or remove data directly on the central system side using fixed rules or thresholds, and the data validity judgment results are often implicit in the processed data. In contrast, this method moves the data validity judgment to the edge of the oilfield and explicitly outputs the judgment results in the form of an independent "edge-side valid data constraint set". The original data expression unit itself remains unchanged, and its scope of use in subsequent analysis steps is limited only by constraint relationships. This creates an essential difference from existing mature technologies in terms of the organization of analysis logic and the construction of data usage boundaries.

[0038] S3. Use the effective data constraint set on the edge side to restructure the original data expression unit to obtain the integrated analysis data unit of the oilfield edge. In step S3, on the edge of the oilfield, based on the effective data constraint set formed in step S2, the original data expression units constructed in step S1 are reorganized by constraint-driven structure, and the scattered and independent original data expression units are organized into integrated analysis data units of the oilfield edge with unified analytical semantics and structural integrity.

[0039] Step S3, during structural reorganization, includes the following steps: Participation determination based on constraint results: Step S3 uses the edge-side valid data constraint set output in step S2 to make a participation determination for each of the original data expression units in step S1. This determination does not involve deleting or eliminating the original data, but rather determining whether each original data representation unit has the conditions to participate in subsequent structural reorganization. Specifically, an original data expression unit is marked as a structural reorganization object only if the constraint result corresponding to it meets the preset validity combination requirements; original data expression units that do not meet the conditions remain in the edge side original data set, but are not included in the target structure formed in this step.

[0040] Constraint-driven structure mapping and merging: After completing the participation determination, step S3 performs a structure mapping operation on the original data representation units that meet the participation conditions; This structural mapping, based on the object identifier, time identifier, and engineering semantic fields defined in step S1, performs the following on multiple original data representation units within the association scope defined by the constraint results in step S2: Field alignment; Semantic merging; Structural encapsulation; In this process, multiple raw data expression units are organized into an integrated data structure with clear oilfield production objects, time periods, and operating conditions, and each raw data expression unit maintains traceability within this structure.

[0041] Integrated analytical data unit formation: Through the above structure mapping and merging operations, step S3 forms multiple integrated data objects with consistent structures on the edge side; Each object corresponds to a specific analysis entity, which directly supports subsequent edge-side analysis steps without requiring cross-object association or structural reconstruction.

[0042] The expression for the integrated analysis data unit of the oilfield edge obtained in step S3 is: ; in, : The original data carrier item represents the set of original data expression units inherited from the edge side of step S1, which is used as the source of basic content for analysis data after being referenced in step S3; : Data availability constraint, representing the set of edge-side valid data constraints formed in step S2 and explicitly applied in step S3; this constraint is used to limit The scope of data that can be included in integrated analysis should be clearly defined, including the usable boundaries and applicable conditions of the data. The integrated analysis structure description item represents the unified structure description information formed in step S3 to enable constrained data to directly participate in the edge-side integrated analysis.

[0043] The difference in step S3 compared to existing oilfield data processing technologies is as follows: Existing technologies typically perform structural integration and correlation analysis on the central system side through database aggregation or offline processing. In contrast, this method introduces a structural reorganization mechanism driven by effective data constraints at the oilfield edge, directly transforming the data availability judgment results into the basis for structural organization. This ensures that the analytical semantics are solidified before entering the analysis stage, thus distinguishing it from existing mature technologies in terms of data organization timing and structural formation logic.

[0044] S4. Use the integrated analysis data unit of the oilfield edge to encapsulate the data and obtain the standardized analysis data object of the edge side. Step S4 involves performing object-level unified expression and format standardization processing on the integrated oilfield edge analysis data unit formed in step S3, transforming it into a standardized edge-side analysis data object with consistent structure and interface.

[0045] Step S4, during the unified packaging process, includes the following steps: Object-level structural integrity verification: Perform object-level structural integrity verification on each integrated oilfield edge analysis data unit output in step S3; This verification is based on a pre-defined analytical data object structure template. Through mature data structure verification technology, it compares whether the object fully contains the necessary identification fields, analytical fields, and descriptive fields to ensure that it meets the basic conditions for standardized encapsulation.

[0046] Unified field representation rules: After completing the structural integrity verification, the field expression rules in the integrated analysis data unit are uniformly processed; This process uses mature data normalization technology to uniformly map field naming conventions, field order, and field type representations, ensuring that integrated analytical data units from different sources maintain consistency at the external representation level.

[0047] Standardized packaging format generation: After the field expression rules are unified, a standardized encapsulation operation is performed on the processed data units; This encapsulation uses mature data object encapsulation technology to encapsulate the integrated analysis data unit as a predefined standardized analysis data object format, and adds unified data object identification and structural description information.

[0048] Step S4 ultimately yields the edge-side standardized analysis data object, whose expression is: ; in, This is an object-level identifier field used to uniquely identify standardized analysis data objects on the edge side. This identifier is generated or mapped during the standardization encapsulation process and is only used for object management and invocation, and does not participate in analysis semantic calculation. This is a set of structural descriptions of the object structure, representing the structure descriptions of standardized analysis data objects on the edge side. It is used to explain the hierarchical relationships, field organization methods, and parsing rules of the objects. This information comes from the unified encapsulation format generation sub-process in step S4, and is used to ensure the resolvable consistency of output objects at the structural level for different edge nodes.

[0049] For integrated analysis data content, it represents the portion of the integrated analysis data unit of the oilfield edge output in step S3 that carries the data in the object; Encapsulation rules and state description information represent the rule-based information used in step S4 to complete the uniformity of field expression, structural integrity verification, and encapsulation of state description.

[0050] S5. Use the standardized analysis data objects on the edge side to perform oilfield analysis adaptation and reconstruction, and obtain the integrated AI intelligent edge data results for oilfield data acquisition and analysis. Step S5 transforms the standardized analysis data object on the edge side into an AI-usable result expression form that directly matches the oilfield data acquisition and analysis task without changing the internal analysis semantics, thereby forming the final integrated AI intelligent edge data result for oilfield data acquisition and analysis.

[0051] Step S5, during oilfield analysis adaptation and reconstruction, includes the following steps: Oilfield analysis adaptation and reconstruction: After completing object parsing, based on the established requirements of the oilfield data acquisition and analysis task for the AI ​​input structure, the following steps are taken: Perform analysis, adaptation, and reconstruction processing; This restructuring process is manifested in the following ways: According to the definition of oilfield analysis tasks, The data dimensions in the data are rearranged; To unify the representation and transformation of data fields from different sources and at different scales; This transforms object-oriented data content into an input representation that edge AI analysis mechanisms can directly accept.

[0052] Edge AI analysis call: After the analysis adaptation is completed, the reconstructed analysis input data is sent to the AI ​​analysis model deployed on the edge for inference calculation.

[0053] In this subprocess: The AI ​​model used is an existing, mature oilfield data analysis model; The inference results directly reflect the current oilfield data at the levels of acquisition status, analysis and judgment, or operational characteristics.

[0054] Result object generation and association: Compare the AI ​​inference output with By correlating the data and combining it with necessary result description information, the final integrated AI intelligent edge data results for oilfield data acquisition and analysis are generated. This result, as the final output of step S5, is ready to be directly used for subsequent system calls, display, or decision-making.

[0055] The expression for the oilfield data acquisition and analysis AI intelligent edge integrated data result output in step S5 is: ; in: : Result association identifier item, which represents the object identifier information that corresponds one-to-one with the edge-side standardized analysis data object output in step S4; The AI ​​analysis result item indicates the result based on step S4. After analysis, adaptation, and reconstruction, the oilfield data acquisition and analysis results are output by the edge-side AI analysis model; : Result-level descriptive terms, indicating the... The result-level structure description and expression information are used to ensure that the analysis results can be directly parsed and used by the edge-side system or the upper-level system.

[0056] In the aforementioned integrated AI-powered edge data acquisition method for data acquisition and analysis, As the final output, the data collected from the edge side is transformed into usable oilfield analysis results after undergoing validity constraints, integrated analysis, standardized encapsulation, and AI analysis adaptation. This result enables the immediate expression of oilfield data acquisition status and analysis conclusions at the edge, while maintaining a clear correlation with the original data objects. This supports subsequent edge decision-making, status monitoring, or upper-level system calls, making the entire method a closed-loop process from data acquisition to analysis result output.

[0057] Compared to traditional oilfield data analysis methods that involve centralized uploading of data after acquisition and analysis at the central level, with a weak correlation between the analysis process and the data organization structure at the edge, this method conducts analysis based on standardized analytical data objects at the edge. Through analysis adaptation and reconstruction, it establishes a direct correspondence between data objects and the AI ​​analysis input structure. When generating analysis results, it maintains the correlation between the results and the object identifiers and structural information at the edge, thereby giving the analysis results clear data sources and traceability. Its core difference lies in the way the analysis results are generated and the correlation mechanism between the results and data objects, rather than a simple replacement of the algorithm or model itself.

[0058] Example 2: This embodiment provides a scenario for the practical application of an AI-powered intelligent edge data acquisition method for data acquisition and analysis: In the production area of ​​a large oilfield, multiple data acquisition nodes are deployed at the edge to collect real-time information such as well production, wellhead pressure, fluid temperature, and equipment operating status. To improve data analysis efficiency and achieve edge intelligence, this method is used for data acquisition and analysis.

[0059] Constructing multi-object raw data representation units at the oilfield edge: Each acquisition node constructs the raw oil well data, equipment operation data, and environmental data it collects into a multi-object raw data representation unit and stores it on the edge computing platform for subsequent analysis.

[0060] AI-assisted data validity assessment: The edge computing platform determines the validity of this raw data, such as removing abnormal or missing values, and forms a set of valid data constraints on the edge side to ensure the credibility of the data entering the analysis process.

[0061] Reorganization of the original data structure: The effective data constraint set obtained in step S2 is used to restructure the original data in step S1, and different types of oilfield data are uniformly organized into integrated oilfield edge analysis data units for unified processing.

[0062] Unified encapsulation of standardized analytical data objects: The analysis data units obtained in step S3 are encapsulated into edge-side standardized analysis data objects according to a predefined format, so that the data from different acquisition nodes are consistent in structure and field expression, which facilitates subsequent AI analysis calls.

[0063] Oilfield analysis, adaptation, reconstruction, and result generation: The edge AI model performs task-oriented adaptation on standardized analytical data objects, transforming them into an input format that AI can directly process, and generating integrated AI-powered edge data results for oilfield data acquisition and analysis.

[0064] Example 3:

[0065] This embodiment also provides a computer device applicable to a data acquisition and analysis AI intelligent edge integrated data acquisition method, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the data acquisition and analysis AI intelligent edge integrated data acquisition method proposed in the above embodiment.

[0066] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, it implements the data acquisition and analysis AI intelligent edge integrated data acquisition method proposed in the above embodiment.

[0067] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0068] If a function is implemented as 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 invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0069] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0070] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0071] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0072] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A data acquisition analysis AI intelligent edge integrated data acquisition method, characterized in that, Includes the following steps: S1. Construct a multi-object raw data representation unit on the edge of the oilfield; S2. Use the original data representation unit of the oilfield edge side to determine the validity of AI-assisted data and obtain the set of valid data constraints on the edge side. S3. Use the effective data constraint set on the edge side to restructure the original data expression unit to obtain the integrated analysis data unit of the oilfield edge. S4. Use the integrated analysis data unit of the oilfield edge to encapsulate the data and obtain the standardized analysis data object of the edge side. S5. Use the standardized analysis data objects on the edge side to perform oilfield analysis adaptation and reconstruction, and obtain the integrated AI intelligent edge data results for oilfield data acquisition and analysis.

2. The data acquisition and analysis AI intelligent edge integrated data acquisition method according to claim 1, characterized in that, Step S1 uses oilfield data acquisition and engineering processing technology to organize field data scattered across different acquisition objects and time scales into raw data expression units with clear structure, single semantics, and definite engineering meaning. 3.The data acquisition and analysis AI intelligent edge integrated data acquisition method of claim 2, wherein, The set of original data representation units for multiple objects on the oilfield edge side output in step S1 is expressed as follows: ； in: represents the number of the original data expression units, is the number of original data expression units formed in the same edge node or the same acquisition range.​​ each raw data representation unit is: ； Each element has a clear meaning and fixed boundaries: : Identifier of the data collection object; Location identifier for data collection; : Data collection time identifier; Physical quantity type identifier; : The numerical value of a physical quantity.

4. The data acquisition and analysis AI intelligent edge integrated data acquisition method according to claim 1, characterized in that, In step S2, based on the set of original data expression units for multiple objects on the edge of the oilfield already formed in step S1, AI-involved analysis logic is introduced to determine whether each original data expression unit meets the basic prerequisites required for subsequent analysis, and the determination results are expressed independently in the form of constraints. Step S2, in determining the validity of AI-involved data, includes the following steps: Determination of temporal continuity; Physical consistency determination; Determining the correlation between operating conditions; The results of the validity determination were collected.

5. The data acquisition and analysis AI intelligent edge integrated data acquisition method according to claim 4, characterized in that, In step S2, when determining time continuity, for multiple original data representation units formed during continuous acquisition of the same acquisition object, the AI ​​analysis unit analyzes the time interval distribution between adjacent data units based on time series consistency analysis technology to determine whether the data unit is in a continuous acquisition state.

6. The data acquisition and analysis AI intelligent edge integrated data acquisition method according to claim 4, characterized in that, In step S2, when determining physical consistency, the AI ​​analysis unit analyzes whether the changes in data values ​​conform to the physical laws of oilfield engineering for the original data expression units formed by the same collection object or the same type of physical quantity.

7. The data acquisition and analysis AI intelligent edge integrated data acquisition method according to claim 4, characterized in that, In step S2, when determining the correlation between operating conditions, the AI ​​analysis unit uses multivariate correlation analysis technology to analyze the correlation between the original data expression unit and other collected data within the same time period, in order to determine whether the data maintains a reasonable correlation with the current production status.

8. The data acquisition and analysis AI intelligent edge integrated data acquisition method according to claim 4, characterized in that, In step S2, when collecting the validity determination results, the time continuity determination results, physical consistency determination results, and working condition correlation determination results are comprehensively collected for each original data expression unit to form a validity determination result of whether the data unit meets the conditions for subsequent analysis and use.

9. The data acquisition and analysis AI intelligent edge integrated data acquisition method according to claim 4, characterized in that, The final output of step S2, following the above process, is as follows: The effective data constraint set on the edge side is expressed as follows: ； in, For the effective data constraint set on the edge side; Represents any original data representation unit The corresponding validity constraint results; ； In the formula, For each , ; express Satisfying constraints ; express Constraints not satisfied ; exist middle: :express Does it satisfy the time continuity constraint? ; :express Does it satisfy the physical consistency constraint? ; :express Does it satisfy the working condition correlation constraint? .

10. The data acquisition and analysis AI intelligent edge integrated data acquisition method according to claim 1, characterized in that, In step S3, on the edge side of the oilfield, based on the effective data constraint set formed in step S2, the original data expression units constructed in step S1 are reorganized by constraint-driven structure, and the scattered and independent original data expression units are organized into integrated analysis data units of the oilfield edge with unified analytical semantics and structural integrity. The integrated oilfield edge analysis data unit formed in step S3 is subjected to unified expression and format standardization processing at the object level, and is transformed into a standardized edge-side analysis data object with consistent structure and interface. Step S5 converts the standardized analysis data objects on the edge side into an AI-usable result expression form that directly matches the oilfield data acquisition and analysis task, thereby forming the final integrated AI intelligent edge data result for oilfield data acquisition and analysis.

Images