Land RIG move optimization through prediction of the release date with artificial intelligence

Abstract

The present disclosure relates to a computer-implemented method (100) for oil rig move operations, comprising: obtaining reservoir management data (110), obtaining real-time drilling data (120), estimating, using a trained artificial intelligence (Al) release date estimation engine, a release date of the oil rig based on the reservoir management data and the real-time drilling data (130), and allocating at least one resource for the oil rig move operation based on the estimated release data (140). In addition, the present disclosure relates to a corresponding system and computer program.

Description

[0001] December 20, 2024

[0002] MATRIX JVCO LTD trading as AIQ A1775O7WO CKA / HEP / Lef

[0003] LAND RIG MOVE OPTIMIZATION THROUGH PREDICTION OF THE RELEASE DATE WITH ARTIFICIAL INTELLIGENCE

[0004] 5 TECHNICAL FIELD

[0005] This disclosure generally relates to computer-implemented methods, computer programs, and systems for rig move operations, especially of an oil or gas drilling rig.

[0006] BACKGROUND

[0007] Efficient planning and execution of rig moves are critical for large-scale oil and gas0 operations. Oil rigs, which drill wells in reservoirs, must be relocated after completing operations at a well site. Precisely estimating the rig release date is essential for effective scheduling, resource allocation, and operational efficiency.

[0008] The challenges associated with rig moves are not new. However, the scale and complexity of modern drilling campaigns introduce significant new problems. 5 Operations now involve hundreds of well deliveries annually and the maintenance of thousands of existing wells across multiple fields. Concurrent rig moves— up to 20 per month— require careful coordination to optimize resource redeployment. This scale creates opportunities for cost -benefit trade-offs but also increases the potential for delays and inefficiencies. 0 Several factors exacerbate these challenges. Greener operations necessitate reducing carbon footprints and emissions, while shortages in heavy-duty equipment, unfulfilled maintenance and servicing schedules, and market supply constraints further complicate planning. Localized issues, such as jurisdiction-specific regulations or operator practices, add layers of complexity.

[0009] Traditionally, rig moves are planned based on well delivery schedules determined by the operator’s production profile. Rig contractors are notified once a well is completed. However, this communication often occurs too late to ensure optimal preparation and execution. This lack of timely information results in inefficiencies, including resource shortages, backlogs, increased costs, and extended move durations. Factors such as0 field congestion, terrain conditions, routing challenges, and long-distance moves further impede the process. Existing planning methods focus primarily on rig fleet sizing rather than the recurring and complex nature of large-scale rig moves. With fleets of loo or more onshore rigs performing 600-1000 moves annually across multiple oil fields, there is a pressing need for a more advanced scheduling system. Such a system must address challenges related to anticipation, preparation, and execution of rig moves while accounting for concurrent operations, resource optimization, and variability in field conditions.

[0010] The invention addresses critical challenges in large-scale land rig moves, such as ensuring dependable execution during concurrent operations, improving efficiency and cost management, and optimizing resource allocation across multiple oil fields. It reduces delays caused by field congestion, terrain conditions, and long-distance moves, while accounting for shortages in equipment and variability in move operations. By leveraging artificial intelligence (Al), automation, and cloud technology, the system predicts rig release dates and identifies disruptions early. This enables proactive planning, reduces costs, and ensures more efficient execution of rig moves at scale.

[0011] SUMMARY OF THE INVENTION

[0012] The objective of the present invention is to provide a computer-implemented method for oil rig move operations and the computer-implemented method according to the claims, which overcome one or more of the above-mentioned problems of the prior art.

[0013] A first aspect of the invention provides a computer-implemented method for oil rig move operations. The method comprising obtaining reservoir management data, obtaining real-time drilling data, estimating, using a trained artificial intelligence, Al, release date estimation engine, a release date of the oil rig based on the reservoir management data and the real-time drilling data, and allocating at least one resource for the oil rig move operation based on the estimated release data.

[0014] The method of the first aspect allows to allocate the resources for the oil rig move operation more efficiently as multiple data sources are considered.

[0015] In a first implementation of the method according to the first aspect, the method further comprises determining a pre-plan based on the reservoir management data, the pre-plan comprising a pre-plan release date, wherein estimating the release date of the oil rig is further based on the pre-plan.

[0016] The pre-plan allows for an early estimate of a release date of the oil rig. In a further implementation of the method according to the first aspect, the method further comprising updating the pre-plan based on the real-time drilling data, wherein the release date of the oil rig is estimated based on the updated pre-plan.

[0017] By updating the pre-plan based on the real-time drilling data, the estimated release date is more accurate.

[0018] In a further implementation of the method according to the first aspect, the method further comprising comparing a drilling process information included in the real-time drilling data with a planned drilling duration in the reservoir management data to determine a missed time information, the missed time information including invisible loss of time (ILT) non-productive times (NPT), and wherein updating the pre-plan is further based on the missed time information.

[0019] Updating the pre-plan based on the missed time information has proven to improve the accuracy of the estimation significantly.

[0020] In a further implementation of the method according to the first aspect, the method further comprising repeatedly comparing the drilling process at regular intervals or based on an instruction to obtain a cumulative missed time information, and wherein updating the pre-plan is further based on the cumulative missed time information determined based on multiple instances of the comparing step.

[0021] By considering the cumulative missed time information, the accuracy of the estimation can be further improved.

[0022] In a further implementation of the method according to the first aspect, the reservoir management data comprises data hub information (UDH) comprising one or more of a previous production data, preferably comprising one or more of oil, gas and / or water rate.

[0023] UDH is commonly used in oil rig applications. Using the data readily available allows for an easy implementation in current systems.

[0024] In a further implementation of the method according to the first aspect, the reservoir management data comprises one or more well intervention logs and / or other historical well data. In a further implementation of the method according to the first aspect, the reservoir management data comprises reservoir model information, comprising simulationbased model data of the reservoir.

[0025] In a further implementation of the method according to the first aspect, the reservoir management data comprises future well profiles, locations and / or trajectories.

[0026] The future well profiles, locations and / or trajectories information allows for a precise determination of effective rig movement.

[0027] In a further implementation of the method according to the first aspect, the reservoir management data comprises forecasted reservoir behavior information based on predefined scenarios.

[0028] Including forecasted reservoir behavior information improves the accuracy of the release date estimation.

[0029] In a further implementation of the method according to the first aspect, the reservoir management data comprises GPS coordinates associated with the oil rig and / or the reservoir.

[0030] In a further implementation of the method according to the first aspect, the real-time drilling data comprises live data, preferably comprising live drilling sensor data, live rig camera stream and / or daily drilling reports, DDR.

[0031] With the above, the current operation of the drill is also considered for estimating release date, improving the accuracy of the estimation.

[0032] In a further implementation of the method according to the first aspect, the real-time drilling data comprises well drilling plan information, comprising one or more of a trajectory, operations benchmarks and / or upcoming drilling information of the oil rig, the upcoming drilling information comprising a planned drilling activity information.

[0033] The above real-time drilling data allows for a precise determination of the drill performance.

[0034] In a further implementation of the method according to the first aspect, the method further comprising determining a buffer period based on the estimated release date.

[0035] The buffer period allows for an improved planning and resource management. In a further implementation of the method according to the first aspect, the at least one resource is further allocated based on proximity and / or availability of the oil rig.

[0036] With the above, the efficiency of rig movement can be improved.

[0037] In a further implementation of the method according to the first aspect, the method further comprises matching the obtained reservoir management data with well data system, WDS, data to obtained matched data, and determining the pre-plan based on the matched data.

[0038] In a further implementation of the method according to the first aspect, the method further comprising estimating, using the machine learning model, a move duration of the oil rig based on the reservoir management data and the real-time drilling data.

[0039] Incorporating the move data into the above allows to ensure that resources are allocated only in scenarios in which the is preferred to allocate the resources, even if the release date alone might indicate that the resource should be allocated but is not beneficial.

[0040] A second aspect of the invention refers to a system for oil rig move operations. The system comprising means for obtaining reservoir management data and real-time drilling data and means configured to perform the method according to any one of the preceding claims.

[0041] In an implementation of the system according to the second aspect, the system further comprising one or more sensors configured to obtain real-time drilling data and / or means for receiving real-time drilling data from one or more sensors.

[0042] A further aspect of the invention refers to a computer program comprising instructions, which, when executed by a computer, cause the computer to carry out the computer- implemented method according to the first aspect or one of the implementations of the first aspect.

[0043] A further aspect of the invention refers to a computer-readable storage medium storing program code, the program code comprising instructions that when executed by a processor carry out the method of the first aspect or one of the implementations of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] To illustrate the technical features of embodiments of the present invention more clearly, the accompanying drawings provided for describing the embodiments are introduced briefly in the following. The accompanying drawings in the following description are merely some embodiments of the present invention, modifications on these embodiments are possible without departing from the scope of the present invention as defined in the claims.

[0045] FIG. 1 is a block diagram illustrating a computer-implemented method in accordance with an embodiment of the present invention,

[0046] FIG. 2 is a block diagram illustrating a computer-implemented method in accordance with a further embodiment of the present invention,

[0047] FIG. 3 is a diagram of a system configured to perform a method in accordance with an embodiment of the present invention.

[0048] DETAILED DESCRIPTION OF EMBODIMENTS

[0049] The foregoing descriptions are only implementation manners of the present invention, the scope of the present invention is not limited to this. Any variations or replacements can be easily made through person skilled in the art. Therefore, the protection scope of the present invention should be subject to the protection scope of the attached claims.

[0050] Fig. 1 shows a block diagram of a computer-implemented method for oil rig move operations according to an aspect of the present invention.

[0051] In a first step no, reservoir management data is obtained. The reservoir management data may comprise information on previous, current and planned oil drilling operations. Generally speaking, the reservoir management data may provide data regarding the coordination of drilling operations, the trajectoiy of drilling operations and well allocation as well as expected production amounts of respective drill / well locations.

[0052] Additionally or alternatively, the reservoir management data may comprise data hub information, UDH. The UDH may comprise one or more of a previous production data, preferably comprising one or more of oil, gas and / or water extraction rate. The reservoir management data provided by the UDH may be indicative of a previous, current or future output / yield of the well / rig. Additionally or alternatively, the reservoir management data may comprise one or more of well intervention logs and / or historical well data. The well intervention logs and / or the historical well may indicate issues that have occurred during a previous or the present drilling operation at the rig / well.

[0053] Additionally or alternatively, the reservoir management data may comprise simulationbased model data of the reservoir / well. The simulation-based model data may indicate an expected output / yield of the drill at a specific geographic position. For example, the simulation-based model data may indicate an expected volume of the well and / or an expected pressure of the oil / water / gas pressure of the well. Additionally or alternatively, the reservoir management data comprises well profiles, locations and / or trajectories. The well profiles, locations and / or trajectories provide information on the location and size / shape of a well / oil reservoir that to be drilled by the oil rig. Additionally or alternatively, the reservoir management data may comprise GPS coordinates associated with the oil rig, the well and / or the reservoir.

[0054] Additionally or alternatively, the reservoir management data may comprise a forecasted reservoir behaviour information. The forecast reservoir behaviour information may indicate an expected behaviour of the reservoir / well. For example, the forecast reservoir behaviour information may comprise a material information indicating a material present in the reservoir / well and optionally the simulation-based model data. Based on this information, the forecast reservoir behaviour information may indicate the expected behaviour of the reservoir / well will regards to output and expected drilling performance (with regards to expected torque required for the drilling). The forecast reservoir behaviour information may indicate the expected output / performance based on predefined drilling / operation scenarios.

[0055] The reservoir management data may comprise information on a single rig / well or on a plurality of rigs / wells in the reservoir.

[0056] In a second step 120, real-time drilling data is obtained. The real-time drilling data is data associated with the drilling process of the oil rig. Preferably, the real-time drilling data indicates a current operation / mode of operation of the oil rig. Additionally or alternatively, the real-time drilling data may indicate a previous operation / mode of operation of the oil rig. For example, the real-time drilling data may be daily drilling report, DDR, data. The DDR may indicate a previous, a current and / or an upcoming drilling activity. Preferably, the real-time drilling data (live drilling sensor data) is generated by sensors, e.g., a drilling torque / rotation speed determination sensor. Additionally or alternatively, the real-time drilling data is obtained by means camera images, e.g., a live rig camera stream. For example, the camera images may indicate that drilling is currently being performed by the oil rig. The camera images may also indicate the rotational speed of the drilling process.

[0057] Additionally or alternatively, the real-time drilling data may comprise well drilling plan information. The well drilling plan information may comprise one or more of a (planned or current) trajectory of the oil rig, (planed or current) operations benchmarks and / or a planned drilling activity information. The planned drilling activity information may indicate the currently planned and executed or next drilling activity. The real-time drilling data may further include a drilling process information indicating the current process of drilling, The drilling process information may indicate an amount of obtained oil and or a distance travelled by the drill and / or the oil rig.

[0058] Preferably, a (rig-move) pre-plan is determined 121 based on the reservoir management data. The pre-plan may be determined using a trained artificial intelligence (Al) preplan engine. The pre-plan may correspond to a preliminary rig release plan indicating an expected date at which the rig is removed from the current well and moved to a different well or is to be serviced (a pre-plan release date).

[0059] Preferably, the pre-plan engine estimates 125 a move duration of the oil rig based on the reservoir management data and the real-time drilling data. The move duration may indicate an expected move duration of the rig to a different well in the reservoir, in addition to the corresponding well’s coordinates. The move duration may be included in the pre-plan.

[0060] Preferably, the obtained reservoir management data is matched 124 with well data system, WDS, data to obtained matched data, ensuring alignment between well locations and rig availabilities. In addition to the above input data, the pre-plan may further be determined based on the matched data.

[0061] Preferably, the determined pre-plan is updated 122 based on the real-time drilling data. Preferably, the updating of the pre-plan is performed using the pre-plan engine, or an additional trained artificial intelligence (Al) pre-plan updating engine. Preferably, the pre-plan is updated based on a comparison of the determined pre-plan and the realtime drilling data. For example, the determined pre-plan may indicate an expected yield / behavior of the well at a given time. If the real-time drilling data at that given time indicates that the yield / behavior of the well deviates (significantly) from the expected yield / behavior in the pre-plan, the pre-plan may be updated accordingly. In particular, the pre-plan maybe updated by considering the deviating real-time drilling data. Preferably, by assigning a large weighting factor the deviating real-time drilling data.

[0062] For example, the real-time drilling data may comprise a drilling process information. The drilling process information may indicate a drilling progress and an uninterrupted duration of the current drilling process. This information may be compared 123 with a planned drilling duration in the reservoir management data. The planned drilling duration may indicate an expected cumulative uninterrupted duration of the current drilling process. Based on the comparison, a missed time information maybe determined. The missed time information may include an invisible loss of time, ILT and non-productive times, NPT, indicating times of drilling interruptions.

[0063] The missed time information may be used to update the pre-plan.

[0064] Preferably, the drilling process is repeatedly compared with the planned drilling duration to obtain a cumulative missed time information. Preferably, the comparison is performed at regular intervals or based on an instruction by a program or an operator. For example, the pre-plan updating engine may determine an anomaly in the real-time drilling data and initiate the comparison. Subsequently, the pre-plan is updated based on the cumulative missed time information determined based on multiple instances of the comparison step. With this, the pre-plan can be updated iteratively, improving the accuracy of the pre-plan.

[0065] In a further step 130 a trained artificial intelligence (Al) release date estimation engine is used to estimate, the release date (information) of the oil rig based on the reservoir management data and the real-time drilling data. The release date (information) indicates the expected release date of the oil rig. Preferably, the release date estimation engine performs similar operations as described with respect to the pre-plan engine and the pre-plan updating engine above. For example, the release date estimation engine may determine the release date (information) based on a comparison of the reservoir management data (such as an expected yield information) and the real-time drilling data (a current yield information). The release date estimation engine may estimate the release date based on the pre-plan. Additionally or alternatively, the release date estimation engine may estimate the release date based on the updated preplan. IO

[0066] In some embodiments, the operations described with respect to the pre-plan estimation engine, the pre-plan updating engine and the release date estimation engine may be performed by a singular artificial intelligence engine. In other embodiments, operations described with respect to the pre-plan estimation engine, the pre-plan updating engine and the release date estimation engine may be performed by means of two or more artificial intelligence engines. In some embodiments, the pre-plan estimation engine, the pre-plan updating engine and the release date estimation engine each comprise of one or more trained artificial intelligence modules, each configured to infer release date information based on the provided input data and / or perform the above-described operations.

[0067] For example, in some examples, it may be beneficial that two or more trained artificial intelligence modules are tasked with the same determination based on the same input data and the outcome result is provided to an operator, to a third artificial intelligence module and / or as input to a predetermined algorithm.

[0068] In some examples, the release date estimation engine determines 131 a buffer period based on the estimated release date. The buffer period may correspond to an expected margin of error of the estimated release date. The expected margin of error may depend on the input data provided for the estimation process. For example, the release date estimation engine may determine a lack of input data for a precise estimation (e.g., only a small amount of real-time drilling data and / or of update iterations of the pre-plan). This might lead to a large margin of error. Consequently, the buffer period would be larger than in a scenario where the expected margin of error is small.

[0069] In step 140, at least one resource is allocated for the oil rig move operation based on the estimated release data. For example, equipment such as the drill may be moved into a mode that allows an oil rig move operation. For example, the drill may be removed from the well onto the storage area of the rig to allow the move operation of the rig. Additionally or alternatively, an output may be provided indicating the estimated release date of the oil rig. Additionally or alternatively, the allocation of at least one resource is the allocation of at least one oil rig (in one or more reservoirs) based on the estimated release data.

[0070] Preferably, the at least one resource is further allocated based on proximity and / or availability of the oil rig. For example, it maybe determined that a release date of the current rig is imminent, but the oil rig is dure for service. In this case, the oil rig will not be moved to the different well, but a subsequently released rig maybe allocated to the new well. Similarly, a first rig that may be significantly closer to the new well may be preferred over a second rig having a slightly earlier release date, in a scenario where the proximity of the first rig is beneficial compared to the earlies release data.

[0071] In some examples, the above method is executed on a local computing entity. Additionally or alternatively, the above method is executed on a cloud server infrastructure.

[0072] In some examples, for the movement of several oil rigs according to the above method, the steps may be executed on several local computing entities and coordinated by a central computing entity, e.g., using a cloud infrastructure. The coordination may include the allocation of several oil rig resources based on the respective estimated release dates. In other examples, for the movement of several oil rigs according to the above method, the input data (reservoir management data and real-time drilling data) may be provided by local entities and only a part of the coordination occurs on local computing entities, while at least a portion of the release date estimation and resource allocation, preferably the entire release date estimation and resource allocation is performed by the cloud infrastructure.

[0073] Preferably, the Al engines mentioned herein (in particular the above-described Al engines) are trained on labelled historical data comprising both raw input data (hardware based or operator based) and corresponding labelled relevant data (e.g., well / rig performance / yield data). Labelled historical data are a plurality of known data parameters / points which may be obtained by a plurality of hardware devices and corresponding relevant data. The labelling may, e.g., be performed by an oil rig operating professional. The training method may be understood as an iterative process starting with providing an Al engine to be trained using a supervised learning framework with input data. Input data may comprise labelled training datasets. A labelled training dataset may include one or more parameters associated with determining a relevant data (e.g., a sensor data / video data), while a label may indicate the corresponding relevant data or expected outcome derived when using the associated data in the labelled training dataset.

[0074] For the release date estimator, sensor data maybe provided with labels associated with the corresponding reservoir management data.

[0075] After completing a training cycle, the output data is compared against the label of the training dataset. The result of this comparison may be provided to the Al engine for further training. If the comparison indicates that the output data aligns with the label, modification of the Al engine may be omitted. However, if the comparison indicates that the output data deviates from the label, the model may be adjusted to better align the output data with the label during subsequent training cycles. The training data may be updated or extended by incorporating additional training datasets, for instance, by an operator during the training process, to enhance training effectiveness. The training data may originate from a pre-prepared dataset (e.g., based on data from simulated reservoir performance and / or data collected from real -wo rid incidents), while the labels for individual sets within the training data may be provided by the operator.

[0076] Fig. 2 is a block diagram illustrating a method in accordance with an embodiment of the present invention. Any aspects described above with respect to Fig. i apply also for Fig. 2.

[0077] In this example, after the reservoir management data and the real-time drilling data are obtained no, 120. Above-mentioned steps 124, 121, 122, 123 are performed before the release date estimation engine estimates the release date of the oil rig.

[0078] In this embodiment, the release date estimation engine estimates the release date based on the updated pre-plan. In particular, the obtained reservoir management data and real-time drilling data are merged 124, and the pre-plan is determined 121 based on the merged data. Subsequently, the determined pre-plan is updated based on the real-time drilling data 122 and based on the compared data of step 123. Preferably, this step is performed repeatedly at regular intervals.

[0079] Fig. 3 shows a flow diagram of a specific implementation of a system configured to execute computer-implemented invention described with respect to above Figs. 1 and 2. Accordingly, any aspects discussed with respect to Figs. 1 and 2 apply also for Fig. 3.

[0080] The system comprises of several modules configured to provide data and / or to process data.

[0081] Preferably, any of the modules of the system comprise a communication module configured to receive and / or transmit data via wire or wirelessly. For example, the communication module may receive or transmit data via LAN, WAN, WLAN, 3G-, 4G-, 5G-, 6G- wireless communication, data bus connection etc. However, the communication module is not limited to these examples, and any means for data transmission may be used as communication module. In this example, UDH 210 is a module for providing historical production data (oil, gas and / or water rates) of the current well / rig operation, as well as well intervention logs and other historical well data.

[0082] A reservoir model module 220 provides one or more of the simulation-based models of the reservoir, future well profiles, locations and / or trajectories or the forecasted reservoir behaviour based on scenarios.

[0083] The data provided by the UDH 210 and the reservoir model module 220 are obtained by an integrated reservoir management platform 230. The integrated management platform 230 is configured to collect the data form the UDH 210 and the reservoir model. Preferably, the integrated management platform is configured to obtain the (input) information discussed with respect to Figs. 1 and 2. In some examples the integrated management platform 230 may assign UDH data to corresponding reservoir model data. For example, information in the well intervention logs may correspond to information associated with forecasted reservoir behaviour. The integrated management platform 230 provides the reservoir management data.

[0084] The data from the integrated management platform 230 may be matched with data from WDS 240. A pre-plan engine 250 determines the pre-plan based on the information from the integrated management platform 230 and the WDS.

[0085] Alive data module 215 provides live drilling sensor data and preferably live rig camera data. For example, the live data module 215 may comprise a sensor, a camera.

[0086] Additionally or alternatively the live data module 215 may receive the sensor / camera data via the communication module.

[0087] A plan data module 225 provides the well’s drilling plan. Preferably, including trajectory, operations and benchmarks. Additionally or alternatively, the plan data module 225 receives the data via the communication module.

[0088] The data from the live data module 215 and the plan data module 225 is merged in realtime drilling activity monitoring platform 235. The real-time drilling activity monitoring platform 235 may store the input data in a data storage. Preferably, the real-time drilling activity monitoring platform 235 merges live data with corresponding drilling plan data. The real-time drilling activity monitoring platform 235 provides the real-time drilling data. In this example, a pre-plan engine 260 updates the pre-plan determined by the preplan engine based on real-time drilling data obtained from the real-time drilling activity monitoring platform 235.

[0089] Based on the obtained reservoir management data and the real-time drilling data, a resource allocation indication module 270 estimates a release date and allocates resources accordingly. The resource allocation indication module 270 comprises the release date estimation engine. Preferably, the resource allocation indication module 270 estimates the release date further based on the pre-plan from the pre-plan engine 250 and the real-time drilling data obtained from the real-time drilling activity monitoring platform 235. Preferably, the resource allocation indication module 270 estimates the release date further based on the updated pre-plan from the pre-plan update engine 260 and the real-time drilling data obtained from the real-time drilling activity monitoring platform 235.

[0090] The above system is described in detail with respect to the specific implementation shown in Fig. 3. It is apparent that only the means crucial for executing the corresponding computer-implemented method of the claims are necessary for the corresponding system according to the invention. The resource allocation indication module 270 may directly receive data from the UDH 210 and the live data module 215 and estimate the release date based on only the information from these two modules. In other examples, other sets of data from other modules may be used directly by the resource allocation indication module 270 or via other modules (e.g., the pre-plan engine 250 and / or the integrated reservoir management platform 230) shown inf Fig.

[0091] 3-

[0092] Any of the above aspects that are not crucial for executing the computer-implemented method of claim 1 may be omitted and replaced by other means without deviating from the scope and spirit of the present invention.

[0093] The methods according to the present invention may be implemented in terms of a computer program which may be executed on any suitable data processing device comprising means (e.g., a memory and one or more processors operatively coupled to the memory) being configured accordingly. The computer program may be stored as computer-executable instructions on a non-transitory computer-readable medium. Embodiments of the present disclosure may be realized in any of various forms. For example, in some embodiments, the present invention may be realized as a computer- implemented method, a computer-readable memory medium, or a computer system.

[0094] In some embodiments, a non-transitory computer-readable memory medium may be configured so that it stores program instructions and / or data, where the program instructions, if executed by a computer system, cause the computer system to perform a method, e.g., any of the method embodiments described herein, or, any combination of the method embodiments de-scribed herein, or, any subset of any of the method embodiments described herein, or, any com-bination of such subsets.

[0095] In some embodiments, a computing device may be configured to include a processor (or a set of processors) and a memory medium, where the memory medium stores program instructions, where the processor is configured to read and execute the program instructions from the memory medium, where the program instructions are executable to implement any of the various method embodiments described herein (or, any combination of the method embodiments described herein, or, any subset of any of the method embodiments described herein, or, any combination of such subsets). The device may be realized in any of various forms.

[0096] Although specific embodiments have been described above, these embodiments are not intended to limit the scope of the present disclosure, even where only a single embodiment is described with respect to a particular feature. Examples of features provided in the disclosure are intended to be illustrative rather than restrictive unless stated otherwise. The above description is intended to cover such alternatives, modifications, and equivalents as would be apparent to a person skilled in the art having the benefit of this disclosure.

[0097] The scope of the present disclosure includes any feature or combination of features disclosed herein (either explicitly or implicitly), or any generalization thereof, whether or not it mitigates any or all of the problems addressed herein. In particular, with reference to the appended claims, features from dependent claims may be combined with those of the independent claims and features from respective independent claims may be combined in any appropriate manner and not merely in the specific combinations enumerated in the appended claims.

Claims

December 20, 2024 MATRIX JVCO LTD trading as AIQ A1775O7WO CKA / HEP / LefCLAIMS1. A computer-implemented method (too) for oil rig move operations, comprising:5 obtaining (110) reservoir management data; obtaining (120) real-time drilling data; estimating (130), using a trained artificial intelligence, Al, release date estimation engine, a release date of the oil rig based on the reservoir management data and the real-time drilling data; and 0 allocating (140) at least one resource for the oil rig move operation based on the estimated release data.

2. The computer-implemented method according to the preceding claim, further comprising: determining (121) a pre-plan based on the reservoir management data, the pre-5 plan comprising a pre-plan release date, wherein estimating the release date of the oil rig is further based on the pre-plan.

3. The computer-implemented method according to the preceding claim, further comprising: updating (122) the pre-plan based on the real-time drilling data, wherein the0 release date of the oil rig is estimated based on the updated pre-plan.

4. The computer-implemented method according to the proceeding claim, further comprising: comparing (123) a drilling process information included in the real-time drilling data with a planned drilling duration in the reservoir management data to determine a5 missed time information, the missed time information including invisible loss of time,ILT, non-productive times, NPT; and wherein updating the pre-plan is further based on the missed time information.

5. The computer-implemented method according to the proceeding claim, further comprising: repeatedly comparing the drilling process with the planned drilling duration at regular intervals, or based on an instruction to obtain a cumulative missed time information; and wherein updating the pre-plan is further based on the cumulative missed time information determined based on multiple instances of the comparing step.

6. The computer-implemented method according to any one of the preceding claims, wherein the reservoir management data comprises: data hub information, UDH, comprising one or more of a previous production data, preferably comprising one or more of oil, gas and / or water rate.

7. The computer-implemented method according to any one of the preceding claims, wherein the reservoir management data comprises one or more well intervention logs and / or other historical well data.

8. The computer-implemented method according to any one of the preceding claims, wherein the reservoir management data comprises reservoir model information, comprising simulation-based model data of the reservoir.

9. The computer-implemented method according to any one of the preceding claims, wherein the reservoir management data comprises future well profiles, locations and / or trajectories.

10. The computer-implemented method according to any one of the preceding claims, wherein the reservoir management data comprises forecasted reservoir behavior information based on predefined scenarios.

11. The computer-implemented method according to any one of the preceding claims, wherein the reservoir management data comprises GPS coordinates associated with the oil rig and / or the reservoir.

12. The computer-implemented method according to any one of the preceding claims, wherein the real-time drilling data comprises live data, preferably comprising live drilling sensor data, live rig camera stream and / or daily drilling reports, DDR.13- The computer-implemented method according to any one of the preceding claims, wherein the real-time drilling data comprises well drilling plan information, comprising one or more of a trajectory, operations benchmarks and / or a planned drilling activity information.

14. The computer-implemented method according to any one of the proceeding claims, further comprising: determining (131) a buffer period based on the estimated release date.

15. The computer-implemented method according to any one of the proceeding claims, wherein the at least one resource is further allocated based on proximity and / or availability of the oil rig.

16. The computer-implemented method according to claim 2, further comprising: matching (124) the obtained reservoir management data with well data system, WDS, data to obtained matched data; and determining the pre-plan based on the matched data.

17. The computer-implemented method according to any one of the proceeding claims, further comprising: estimating (125), using the machine learning model, a move duration of the oil rig based on the reservoir management data and the real-time drilling data.

18. A system for oil rig move operations comprising: means configured to obtain reservoir management data and real-time drilling data; and means configured to perform the method according to any one of the preceding claims.

19. The system according to the proceeding claims, further comprising one or more sensors configured to obtain real-time drilling data and / or means for receiving realtime drilling data from one or more sensors.

20. A computer program comprising instructions, which, when executed by a computer, cause the computer to carry out the computer-implemented method according to any one of claims 1 to 17.

Images