Sampling determination method and apparatus for offshore wind power, program product and device

Abstract

This disclosure relates to the field of sampling control technology, and specifically to a sampling determination method, apparatus, program product, and equipment for offshore wind power. The method includes: acquiring an information matching library, including recommendation level information for candidate sampling schemes under different sea state categories and recommendation level information for candidate sampling schemes under different soil types under different sampling indicators; determining the target sea state category and the target soil type; matching the sampling requirement indicators and target sea state category of the sea area to be sampled with the information matching library to determine first target recommendation level information, and determining a first recommendation score based on the first target recommendation level information; matching the sampling requirement indicators and target soil type with the information matching library to determine second target recommendation level information, and determining a second recommendation score based on the second target recommendation level information; and fusing the first recommendation score and the second recommendation score to obtain a target recommendation score, thereby determining the target sampling scheme from the candidate sampling schemes.

Description

Technical Field

[0001] This disclosure relates to the field of sampling control technology, and more specifically, to a sampling determination method, a sampling determination device, a program product, and equipment for offshore wind power. Background Technology

[0002] Sampling for offshore wind power refers to the process of obtaining soil and rock samples (such as soil and rock samples), water samples, or sediment samples from the seabed strata through drilling, in-situ testing, and other methods during the offshore wind farm exploration phase. Sampling for offshore wind power is a crucial link connecting "field exploration" and "indoor analysis." The accurate data obtained through sample testing directly determines the rationality of the wind farm's foundation design, the feasibility of the construction plan, and the safety during the operational period. It is the core support for offshore wind power projects from "geological understanding" to "project implementation."

[0003] However, the inability to efficiently select a suitable sampling scheme currently leads to low sampling efficiency to some extent.

[0004] It should be noted that the information in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this disclosure is to provide a sampling determination method, a sampling determination device, a computer program product, and an electronic device for offshore wind power, thereby enabling efficient determination of a suitable sampling scheme for offshore wind power and improving sampling efficiency and quality.

[0006] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0007] According to one aspect of this disclosure, a sampling determination method for offshore wind power is provided, comprising: acquiring a pre-established information matching library, the pre-established information matching library including recommendation level information of multiple candidate sampling schemes under different sea state categories under different sampling indicators, and recommendation level information of multiple candidate sampling schemes under different soil categories; determining a target sea state category based on the sea state characteristics of the sea area to be sampled, and determining a target soil category based on the soil characteristics of the sea area to be sampled; matching the sampling requirement indicators and target sea state category of the sea area to be sampled with the pre-established information matching library to determine a first target of multiple candidate sampling schemes. The system generates recommendation level information and determines the first recommendation score for multiple candidate sampling schemes based on the first target recommendation level information. It then matches the sampling requirement indicators and target soil type of the sea area to be sampled with a pre-established information matching database to determine the second target recommendation level information for multiple candidate sampling schemes, and determines the second recommendation score for each candidate sampling scheme based on the second target recommendation level information. For each candidate sampling scheme, the corresponding first recommendation score and second recommendation score are fused to calculate the target recommendation score, and the target sampling scheme is determined from among the candidate sampling schemes based on the target recommendation scores of each candidate sampling scheme.

[0008] In one exemplary embodiment of this disclosure, obtaining a pre-established information matching library includes: collecting sampling task sample data from multiple channels, the sampling task sample data including at least sea state sample data, soil sample data, sampling scheme sample data, and sampling index sample data; using the sampling index sample data, sea state sample data, and soil sample data as inputs, and the corresponding sampling scheme sample data as outputs, and training a recommendation model based on historical sampling data and expert rule base data, the recommendation model is used to determine the recommendation level for the sampling scheme samples; based on the recommendation model, outputting recommendation level information for multiple candidate sampling schemes under different sea state categories under different sampling indices, and outputting recommendation level information for multiple candidate sampling schemes under different soil categories.

[0009] In one exemplary embodiment of this disclosure, the sampling requirement indicators and target sea state categories of the sea area to be sampled are matched with a pre-established information matching database to determine the first target recommendation level information of multiple candidate sampling schemes, and the first recommendation score of multiple candidate sampling schemes is determined according to the first target recommendation level information. This includes: establishing multiple processing threads corresponding to the number of sampling requirement indicators; using multiple processing threads to match multiple sampling requirement indicators and target sea state categories with the pre-established information matching database in parallel, and determining the first target recommendation level information and corresponding first recommendation score of multiple candidate sampling schemes according to the matching results.

[0010] In one exemplary embodiment of this disclosure, determining a first recommendation score for a candidate sampling scheme for each processing thread includes: determining a corresponding recommendation score processing strategy based on the category of the sampling requirement index corresponding to the processing thread; and processing and converting the first target recommendation level information corresponding to the processing thread into a first recommendation score based on the recommendation score processing strategy.

[0011] In one exemplary embodiment of this disclosure, for each candidate sampling scheme, a target recommendation score is obtained by fusing the corresponding first recommendation score and second recommendation score. A target sampling scheme is then determined from the candidate sampling schemes based on the target recommendation scores of each candidate sampling scheme. This includes: acquiring environmental characteristic information of the sea area to be sampled, and determining sea state weight values ​​and soil quality weight values ​​based on the environmental characteristic information; weighting and fusing the first recommendation score and second recommendation score based on the sea state weight values ​​and soil quality weight values ​​to obtain a target recommendation score; filtering out candidate sampling schemes with first recommendation scores lower than the sea state score threshold from each candidate sampling scheme according to the sea state score threshold to obtain a first reference sampling scheme; filtering out candidate sampling schemes with second recommendation scores lower than the soil quality score threshold from each candidate sampling scheme according to the soil quality score threshold to obtain a second reference sampling scheme; and determining the target sampling scheme from the first reference sampling scheme and the second reference sampling scheme based on the target recommendation score.

[0012] In one exemplary embodiment of this disclosure, the method further includes: establishing a multidimensional feature vector for each of the first and second reference sampling schemes based on the scheme metadata of the reference sampling scheme, wherein the scheme metadata is obtained by deconstructing the reference sampling scheme; performing clustering processing on each reference sampling scheme based on the multidimensional feature vector corresponding to each reference sampling scheme to obtain multiple clusters; and obtaining the reference sampling scheme with the highest target recommendation score from the clusters that do not contain the target sampling scheme as candidate sampling schemes.

[0013] In one exemplary embodiment of this disclosure, the method further includes: generating a decision report based on the target sampling scheme and the corresponding target recommendation score, and the alternative sampling scheme and the corresponding target recommendation score.

[0014] According to one aspect of this disclosure, a sampling determination device for offshore wind power is provided, comprising: an information acquisition module for acquiring a pre-established information matching library, the pre-established information matching library including recommendation level information of multiple candidate sampling schemes under different sea state categories under different sampling indicators, and recommendation level information of multiple candidate sampling schemes under different soil categories; a category determination module for determining a target sea state category based on the sea state characteristics of the sea area to be sampled, and determining a target soil category based on the soil characteristics of the sea area to be sampled; and a first matching module for matching the sampling requirement indicators and target sea state category of the sea area to be sampled with the pre-established information matching library to determine multiple candidate sampling schemes. The system comprises: a first target recommendation level information, and a second matching module, which matches the sampling requirement indicators and target soil type of the sea area to be sampled with a pre-established information matching database to determine the second target recommendation level information of multiple candidate sampling schemes, and determines the second recommendation score of multiple candidate sampling schemes based on the second target recommendation level information; and a scheme determination module, which calculates the target recommendation score by fusing the corresponding first recommendation score and second recommendation score for each candidate sampling scheme, and determines the target sampling scheme from the candidate sampling schemes based on the target recommendation score of each candidate sampling scheme.

[0015] According to one aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements any of the above methods.

[0016] According to one aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any of the above methods by executing the executable instructions.

[0017] The sampling determination method for offshore wind power in an exemplary embodiment of this disclosure includes: acquiring a pre-established information matching library, which includes recommendation level information for multiple candidate sampling schemes under different sea state categories under different sampling indicators, and recommendation level information for multiple candidate sampling schemes under different soil types; determining a target sea state category based on the sea state characteristics of the sea area to be sampled, and determining a target soil type based on the soil characteristics of the sea area to be sampled; matching the sampling requirement indicators and target sea state category of the sea area to be sampled with the pre-established information matching library to determine a first target recommendation for multiple candidate sampling schemes, etc. The system firstly obtains first-level information and determines the first recommendation score for multiple candidate sampling schemes based on the first target recommendation level information. It then matches the sampling requirement indicators and target soil type of the sea area to be sampled with a pre-established information matching database to determine the second target recommendation level information for multiple candidate sampling schemes, and determines the second recommendation score for each candidate sampling scheme based on the second target recommendation level information. For each candidate sampling scheme, the corresponding first recommendation score and second recommendation score are fused to calculate the target recommendation score, and the target sampling scheme is determined from among the candidate sampling schemes based on the target recommendation scores of each candidate sampling scheme.

[0018] On the one hand, by introducing a pre-established information matching database based on multi-source data, traditional qualitative decision-making relying on personal experience is transformed into quantitative and standardized decision-making based on data and models. This allows for precise coupling of the two key environmental constraints—sea state and soil quality—ensuring a high degree of matching between the recommended sampling plan and the specific conditions of the sampling area, thereby improving the success rate and sample quality of sampling operations from the outset. On the other hand, by fusing the recommendation scores from both parts to obtain the target recommendation score, a comprehensive evaluation of the sampling plan is achieved. This helps in selecting the plan with the highest overall stability, improving the accuracy and efficiency of determining sampling plans for offshore wind power, thus enhancing sampling efficiency and quality.

[0019] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0020] The above and other objects, features, and advantages of this disclosure will become readily apparent from the following detailed description of exemplary embodiments, taken in conjunction with the accompanying drawings. Several embodiments of this disclosure are illustrated in the drawings by way of example and not limitation.

[0021] Figure 1 An application environment diagram is shown for a sampling determination method for offshore wind power, which is an exemplary embodiment of this disclosure.

[0022] Figure 2A flowchart of a sampling determination method for offshore wind power according to an exemplary embodiment of the present disclosure is shown.

[0023] Figure 3 A flowchart illustrating an embodiment of the present disclosure for obtaining a pre-established information matching library is shown.

[0024] Figure 4 A schematic diagram illustrating the determination of a processing thread and its corresponding processing task according to an exemplary embodiment of the present disclosure is shown.

[0025] Figure 5 A flowchart illustrating a target sampling scheme according to an exemplary embodiment of the present disclosure is shown.

[0026] Figure 6 A flowchart illustrating an example of obtaining an alternative sampling scheme according to an exemplary embodiment of the present disclosure is shown.

[0027] Figure 7 A schematic diagram of the composition of a sampling and determination apparatus for offshore wind power according to an exemplary embodiment of the present disclosure is shown.

[0028] Figure 8 A block diagram of an electronic device according to an exemplary embodiment of the present disclosure is shown.

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

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

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

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

[0033] Sampling for offshore wind power refers to the process of obtaining soil and rock samples, water samples, or sediment samples from the seabed strata through drilling, in-situ testing, and other methods during the offshore wind farm exploration phase. Offshore wind power sampling is a crucial link connecting "field exploration" and "indoor analysis." Accurate data obtained through sample testing directly determines the rationality of the wind farm's foundation design, the feasibility of the construction plan, and the safety during the operational period. It is the core support for offshore wind power projects from "geological understanding" to "project implementation." However, current methods lack approaches for selecting appropriate sampling schemes under different sea conditions and geological conditions, leading to sampling efficiency and, to some extent, affecting sampling quality.

[0034] Based on this, an exemplary embodiment of this disclosure provides a sampling determination method for offshore wind power. By establishing an information matching database, the traditional qualitative decision-making based on personal experience is transformed into quantitative and standardized decision-making based on data and models. This method can simultaneously and accurately couple the two key environmental constraints of sea state and soil quality, ensuring that the recommended sampling plan is highly matched with the specific conditions of the sea area to be sampled. Thus, the target sampling plan is determined by comprehensively considering the recommended scores of the two key environmental constraints. This method can improve the efficiency and quality of sampling work while meeting sampling requirements.

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

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

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

[0038] Furthermore, in another exemplary embodiment, terminal 101 may also have similar functions to server 102, thereby performing the sampling determination method for offshore wind power provided by the exemplary embodiments of this disclosure.

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

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

[0041] like Figure 2 The diagram shown is a flowchart of a sampling determination method for offshore wind power, an exemplary embodiment of this disclosure, with reference to... Figure 2 As shown, the method includes steps S210 to S250:

[0042] Step S210: Obtain the pre-established information matching library, which includes the recommendation level information of multiple candidate sampling schemes under different sea state categories under different sampling indicators, and the recommendation level information of multiple candidate sampling schemes under different soil categories.

[0043] Step S220: Determine the target sea state category based on the sea state characteristics of the sea area to be sampled, and determine the target soil category based on the soil characteristics of the sea area to be sampled.

[0044] Step S230: Match the sampling requirement indicators and target sea state category of the sea area to be sampled with the pre-established information matching database to determine the first target recommendation level information of multiple candidate sampling schemes, and determine the first recommendation score of multiple candidate sampling schemes according to the first target recommendation level information.

[0045] Step S240: Match the sampling requirement indicators and target soil type of the sea area to be sampled with the pre-established information matching database to determine the second target recommendation level information of multiple candidate sampling schemes, and determine the second recommendation score of multiple candidate sampling schemes according to the second target recommendation level information.

[0046] Step S250: For each candidate sampling scheme, the corresponding first recommendation score and second recommendation score are fused to calculate the target recommendation score, and the target sampling scheme is determined from each candidate sampling scheme based on the target recommendation score of each candidate sampling scheme.

[0047] The sampling determination method for offshore wind power in the exemplary embodiments of this disclosure, on the one hand, transforms traditional qualitative decision-making based on personal experience into quantitative and standardized decision-making based on data and models by introducing a pre-established information matching library based on multi-source data. This enables precise coupling of the two key environmental constraints—sea state and soil quality—ensuring a high degree of matching between the recommended sampling scheme and the specific conditions of the sea area to be sampled, thereby improving the success rate and sample quality of sampling operations from the source. On the other hand, by fusing the recommendation scores from both parts to obtain a target recommendation score, a comprehensive evaluation of the sampling scheme is achieved, which helps to select the scheme with the highest overall stability, improving the accuracy and efficiency of determining the sampling scheme for offshore wind power, thereby improving sampling efficiency and quality.

[0048] Steps S210 to S250 will be described in more detail below.

[0049] In step S210, a pre-established information matching library is obtained. The pre-established information matching library includes recommendation level information of multiple candidate sampling schemes under different sea state categories under different sampling indicators, and recommendation level information of multiple candidate sampling schemes under different soil categories.

[0050] In the exemplary embodiments of this disclosure, the pre-established information matching library is a structured, processed expert knowledge model obtained by processing sample data from sampling tasks across multiple channels. Sampling indicators are the specific requirements of the user for the sampling operation, representing quantitative inputs from the demand side, including sampling efficiency, sampling cost, target sample material, and sampling depth. Candidate sampling schemes refer to all available marine sampling technologies and equipment and their operational procedures. For example, a gravity piston sampler utilizes gravity and a piston to generate negative pressure, suitable for soft seabed surface soil; a box sampler is used to obtain large areas of undisturbed seabed surface sediments. The exemplary embodiments of this disclosure can set candidate sampling schemes according to actual scenario requirements, without special limitations.

[0051] The sea state and soil categories can be classification labels generated through analysis. For example, sea state categories can be generated based on parameters such as wave height, current velocity, and wind speed, including Category 1 (e.g., wave height <1m, current velocity <0.5 knots, wind speed <4), where the operating window is generally wide and equipment operation is stable. Category 2 (e.g., wave height <1m, current velocity <0.5 knots, wind speed <4), where equipment with strong resistance to current and waves must be selected, and so on. Soil categories can be generated based on parameters such as cone tip resistance and shear strength. For example, Category A is soft clay (extremely low strength, easily disturbed), where specialized equipment such as fixed piston samplers is required. Category B is dense sand (high permeability, difficult to obtain undisturbed samples), where frozen sampling or special liner tubes can be used, and so on.

[0052] Recommendation rating information is an applicability evaluation level or score assigned to each candidate sampling scheme for a specific combination of (sampling indicators, sea state category, soil type), such as a recommendation score.

[0053] In one exemplary embodiment, such as Figure 3 As shown, obtaining a pre-established information matching database may include:

[0054] Step S310: Collect sampling task sample data from multiple channels. The sampling task sample data shall include at least sea state sample data, soil sample data, sampling plan sample data, and sampling index sample data.

[0055] Multi-channel sampling task sample data is a structured data set obtained from different sources, recording complete sampling task information. It can be understood that a sample is a complete data record of a historical sampling operation. Sea state sample data includes marine weather forecasts and ship sensor records, including specific values ​​such as wave height, wave period, current velocity, and wind speed. Soil sample data comes from borehole logs, static cone penetration tests, and laboratory geotechnical tests, including soil type, undrained shear strength, and grain size distribution. Sampling plan sample data records information on the actual equipment type and operational parameters, while sampling index sample data records the objectives of the task, such as the target sampling depth, required sample quality level, and sampling cost. The exemplary embodiments of this disclosure can obtain sampling task sample data from multiple channels, improving the comprehensiveness of the basic data.

[0056] Step S320: Using sampling index sample data, sea state sample number and soil sample data as input, and the corresponding sampling scheme sample data as output, a recommendation model is trained based on historical sampling data and expert rule base data. The recommendation model is used to determine the recommendation level for the sampling scheme samples.

[0057] The recommendation model is a trained machine learning model, such as a decision tree model, a CNN (Convolutional Neural Network), or an RNN (Recurrent Neural Network). Of course, the recommendation model can also be other heavyweight models or large language models; the exemplary embodiments disclosed herein do not limit this.

[0058] During training, the model takes sampling index sample data, sea state sample data, and soil sample data as inputs and corresponding sampling scheme sample data as outputs. Historical sampling data and expert rule base data are used to guide and constrain the training process of the model, so as to adjust the parameters in the model until the number of training iterations is reached to obtain the recommendation model.

[0059] Step S330: Based on the recommendation model, output the recommendation level information of multiple candidate sampling schemes under different sea state categories for different sampling indicators, and output the recommendation level information of multiple candidate sampling schemes under different soil categories.

[0060] After training the recommendation model, it can be used to output recommendation level information for multiple candidate sampling schemes under different sea state categories and under different soil types for different sampling indicators.

[0061] The exemplary embodiments disclosed herein, by integrating a large amount of historical data (objective laws) and rules (prior knowledge), the recommendation level derived by the model compensates for the logical loopholes that may exist in purely human experience, and provides an accurate information basis for subsequently determining the sampling scheme.

[0062] In step S220, the target sea state category is determined based on the sea state characteristics of the sea area to be sampled, and the target soil category is determined based on the soil characteristics of the sea area to be sampled.

[0063] In the exemplary embodiments of this disclosure, the sea state characteristics and soil characteristics of the sea area to be sampled can be obtained through on-site measurements, sensors, preliminary surveys, etc., and are original, multi-dimensional, and continuous specific parameters describing the environmental conditions of the sea area to be sampled. The sea state characteristics include, but are not limited to, significant wave height (meters), average wave period (seconds), surface current velocity (meters / second), and wind speed (meters / second). The soil characteristics include, but are not limited to, soil and rock type (such as sand, silt, clay, etc.), particle size, water content, and density.

[0064] Among them, the target sea state category and the target soil category are discrete, standardized category labels obtained by mapping the above continuous feature parameters, which are consistent with the classification system used when constructing the information matching library.

[0065] In step S230, the sampling requirement indicators and target sea state category of the sea area to be sampled are matched with the pre-established information matching database to determine the first target recommendation level information of multiple candidate sampling schemes, and the first recommendation score of multiple candidate sampling schemes is determined according to the first target recommendation level information.

[0066] In an exemplary embodiment of this disclosure, the matching here refers to quickly locating a subset of data consistent with the current task conditions from an information matching database to determine the first target recommendation level information of candidate sampling schemes. The first target recommendation level information refers to the recommendation level obtained by each candidate sampling scheme, ignoring soil conditions and considering only the current sampling requirement indicators and target sea state category. It reflects the ability and applicability of each scheme to complete specific sampling requirements under specific sea conditions. The first recommendation score is a numerical value converted from the qualitative first target recommendation level information through a quantization mapping function; the larger the value, the greater the likelihood that the candidate sampling scheme will be recommended. Correspondingly, the second target recommendation level information refers to the recommendation level obtained by each candidate sampling scheme, ignoring sea state conditions and considering only the current sampling requirement indicators and target soil category. It reflects the ability and applicability of each scheme to complete specific sampling requirements under specific soil conditions. The second recommendation score is a numerical value converted from the qualitative second target recommendation level information through a quantization mapping function; the larger the value, the greater the likelihood that the candidate sampling scheme will be recommended.

[0067] In an exemplary embodiment, the sampling requirement indicators and target sea state category of the sea area to be sampled are matched with a pre-established information matching database to determine the first target recommendation level information of multiple candidate sampling schemes, and the first recommendation score of each candidate sampling scheme is determined based on the first target recommendation level information, including:

[0068] First, based on the number of sampling requirement indicators, establish a corresponding number of processing threads.

[0069] Then, multiple processing threads are used to match multiple sampling requirement indicators and target sea state categories with a pre-established information matching database in parallel, and the first target recommendation level information and corresponding first recommendation score of multiple candidate sampling schemes are determined based on the matching results.

[0070] In this context, a processing thread is the smallest unit capable of computational scheduling. In an exemplary embodiment of this disclosure, a processing thread is an independent, concurrently executable task execution flow responsible for the matching process corresponding to the sampling requirement indicators. Multiple processing threads are used for parallel matching, with multiple threads started simultaneously, each thread independently responsible for matching one or more sampling requirement indicators with the information matching database.

[0071] As an example, such as Figure 4 As shown, if the sampling requirement indicators include sampling efficiency and sampling cost, and the target sea state category is determined to be Category 1, and if two sampling requirement indicators need to be processed, the main thread can dynamically create two independent worker threads and assign "sampling requirement indicator + target sea state category" to each thread. This allows each thread to independently handle the matching of one sampling requirement indicator with the information matching database. Within each thread, based on the sampling requirement indicator and the target sea state category, the first target recommendation level information of multiple candidate sampling schemes is determined in the information matching database, and then the first recommendation score is determined based on the first target recommendation level information.

[0072] The exemplary embodiments disclosed herein achieve parallel matching and scoring calculation of different indicators by creating multiple processing threads corresponding to the number of sampling requirement indicators, thereby improving matching processing efficiency and reducing processing time complexity. Furthermore, the evaluation process for each requirement indicator is independent and does not block each other, thus clearly demonstrating the advantages and disadvantages of each candidate sampling scheme across different indicator dimensions.

[0073] Based on the foregoing exemplary embodiments, determining a first recommendation score for a candidate sampling scheme for each processing thread may include:

[0074] First, determine the corresponding recommendation score processing strategy based on the category of the sampling requirement metric corresponding to the processing thread.

[0075] Then, based on the recommendation score processing strategy, the first target recommendation level information corresponding to the processing thread is processed and converted into the first recommendation score.

[0076] The category of sampling requirement indicators corresponding to a processing thread can be understood as the category of sampling requirement indicators processed by that processing thread, that is, the category of sampling requirement indicators assigned to that processing thread. Examples include sampling efficiency and sampling cost. Since different categories of sampling requirement indicators are converted into recommendation scores using different methods, different correspondences between the categories of sampling requirement indicators and recommendation score processing strategies can be pre-defined. The recommendation score processing strategy defines how to convert qualitative recommendation levels into recommendation scores with specific mathematical meaning. For example, for sampling efficiency, one recommendation score processing strategy is binary judgment: if the information matching library gives a recommendation level of A (e.g., high level), then its score is mapped to a high score (e.g., 100 points); otherwise, if the recommendation level is B (e.g., low level), then its score is mapped to an extremely low score or zero. For sampling cost, if the information matching library gives a recommendation level of 1, then its score is mapped to a low score; otherwise, if the recommendation level is 2, then its score is mapped to a high score.

[0077] An exemplary embodiment of this disclosure, by distinguishing indicator categories and applying a differentiation strategy, can differentiately convert grade processing information into recommendation scores in different threads, thereby making the recommendation score related to whether it is prioritized for recommendation during the conversion process, thus improving the accuracy of recommendation processing.

[0078] In step S240, the sampling requirement indicators and target soil type of the sea area to be sampled are matched with a pre-established information matching database to determine the second target recommendation level information of multiple candidate sampling schemes, and the second recommendation score of each candidate sampling scheme is determined based on the second target recommendation level information. This process is similar to the process of determining the first recommendation score based on the target sea state type, and will not be described in detail here.

[0079] In step S250, for each candidate sampling scheme, the corresponding first recommendation score and second recommendation score are fused to obtain the target recommendation score, and the target sampling scheme is determined from each candidate sampling scheme based on the target recommendation score of each candidate sampling scheme.

[0080] In an exemplary embodiment of this disclosure, fusion computation is the process of merging scores from two dimensions into a single comprehensive score. The target recommendation score can be used to quantify the overall performance of a scheme and to determine a scheme.

[0081] In one exemplary embodiment, such as Figure 5As shown, for each candidate sampling scheme, the corresponding first recommendation score and second recommendation score are fused to calculate the target recommendation score. Based on the target recommendation scores of each candidate sampling scheme, the target sampling scheme is determined from the candidate sampling schemes, which may include:

[0082] Step S510: Obtain environmental characteristic information of the sea area to be sampled, and determine the sea state weight value and soil weight value based on the environmental characteristic information.

[0083] Environmental characteristic information refers to objective parameters used to determine factors such as sea state or soil quality in the current environment. In addition to sea state and soil quality characteristics, it may also include other environmental characteristics to reflect the actual situation of the current environment in the sea area to be sampled. The sea state weight value and soil quality weight value represent the proportions of the first recommended score (sea state score) and the second recommended score (soil quality score) in the fusion calculation, respectively.

[0084] The correspondence between environmental feature information and weights can be pre-set, and the sea state weight value and soil quality weight value can be determined according to the correspondence between environmental feature information and weights. Optionally, a pre-trained weight discrimination model can also be used to output the sea state weight value and soil quality weight value. This weight discrimination model is trained based on environmental feature information samples and weight information. The network structure of this model can be a lightweight model such as CCN or RNN, or a large language model. The exemplary embodiments of this disclosure do not limit this.

[0085] Step S520: Based on the sea state weight value and soil quality weight value, the first recommendation score and the second recommendation score are weighted and fused to obtain the target recommendation score.

[0086] After determining the sea state weight value and soil quality weight value, the first recommendation score and the second recommendation score are weighted and fused to obtain the target recommendation score.

[0087] Step S530: Based on the sea state score threshold, filter out the candidate sampling schemes whose first recommended score is lower than the sea state score threshold from each candidate sampling scheme to obtain the first reference sampling scheme, and based on the soil quality score threshold, filter out the candidate sampling schemes whose second recommended score is lower than the soil quality score threshold from each candidate sampling scheme to obtain the second reference sampling scheme.

[0088] The sea state score threshold and soil quality score threshold are preset score lines representing the minimum acceptable standard, which can be understood as the bottom line for engineering safety and feasibility. If a scheme's score in a certain dimension is lower than the threshold, regardless of its total score, it means that there is an unacceptable risk or performance defect in that dimension. Therefore, the candidate sampling scheme must be filtered out to avoid any risks or defects in the scheme that could lead to subsequent sampling failures.

[0089] Step S540: Based on the target recommendation score, determine the target sampling scheme from the first reference sampling scheme and the second reference sampling scheme.

[0090] The higher the target recommendation score, the larger the selected generalization. After obtaining the first reference sampling scheme and the second reference sampling scheme, the target sampling scheme can be determined from the first reference sampling scheme and the second reference sampling scheme based on the target recommendation score.

[0091] The exemplary embodiments disclosed herein provide dual protection by establishing two independent judgment methods for sea conditions and soil quality. This ensures that an effective target sampling plan is obtained while avoiding the recommendation of risky plans, thereby improving sampling efficiency and quality.

[0092] In an exemplary embodiment, in addition to providing a sampling scheme, alternative sampling schemes may also be provided. Specifically, such as Figure 6 As shown, it includes:

[0093] Step S610: For each reference sampling scheme in the first reference sampling scheme and the second reference sampling scheme, establish a multi-dimensional feature vector based on the scheme metadata of the reference sampling scheme. The scheme metadata is obtained by deconstructing the reference sampling scheme.

[0094] Metadata for a sampling scheme consists of parameters describing its essential characteristics, obtained by deconstructing a complete candidate sampling scheme. These parameters include, for example, the sampling drive method, the minimum tonnage of the required mother ship, whether it relies on a drilling platform, the maximum operating water depth, the theoretical sampling length, the sampling tube diameter, and the typical operating cycle. A multidimensional feature vector is formed by combining these numerically represented metadata.

[0095] Step S620: Based on the multidimensional feature vectors corresponding to each reference sampling scheme, perform clustering processing on each reference sampling scheme to obtain multiple clusters.

[0096] Clustering algorithms can automatically group schemes whose feature vectors are spatially similar. Schemes within the same cluster share similar technical paths and resource requirements. Clustering algorithms such as K-means can be used, and there are no restrictions on which one to use.

[0097] Step S630: From the clusters that do not contain the target sampling scheme, obtain the reference sampling scheme with the highest target recommendation score as the alternative sampling scheme.

[0098] After obtaining multiple clusters, the cluster containing the target sampling scheme, such as cluster A, can be identified. All other schemes in cluster A can then be completely excluded because they are homogeneous alternatives to the target scheme A. If scheme A is infeasible, other schemes within cluster A are likely to face the same implementation obstacles. Therefore, alternative sampling schemes can be selected from all other clusters, each with the highest target recommendation score.

[0099] The exemplary embodiments of this disclosure, which determine alternative sampling schemes in a manner that provides a certified, high-quality alternative unaffected by the same causes, offer decision-makers more options and avoid the same obstacles affecting the implementation of sampling efforts.

[0100] Based on the aforementioned exemplary embodiments, a decision report can also be generated according to the target sampling scheme and the corresponding target recommendation score, and the alternative sampling scheme and the corresponding target recommendation score.

[0101] The decision report is a structured, highly readable document or visual interface. In addition to presenting the target sampling plan and its corresponding recommended score, the report also provides alternative sampling plans and their target recommended scores, clearly demonstrating the recommendation logic and providing a basis for selecting a plan.

[0102] The sampling determination method for offshore wind power in the exemplary embodiments of this disclosure, on the one hand, transforms traditional qualitative decision-making based on personal experience into quantitative and standardized decision-making based on data and models by introducing a pre-established information matching library based on multi-source data. This enables precise coupling of the two key environmental constraints—sea state and soil quality—ensuring a high degree of matching between the recommended sampling scheme and the specific conditions of the sea area to be sampled, thereby improving the success rate and sample quality of sampling operations from the source. On the other hand, by fusing the recommendation scores from both parts to obtain a target recommendation score, a comprehensive evaluation of the sampling scheme is achieved, which helps to select the scheme with the highest overall stability, improving the accuracy and efficiency of determining the sampling scheme for offshore wind power, thereby improving sampling efficiency and quality.

[0103] In an exemplary embodiment of this disclosure, a sampling and determination apparatus for offshore wind power is also provided. (See reference...) Figure 7 As shown, the sampling and determination device 700 for offshore wind power may include an information acquisition module 710, a category determination module 720, a first matching module 730, a second matching module 740, and a scheme determination module 750. Specifically:

[0104] The information acquisition module 710 is used to acquire a pre-established information matching library, which includes recommendation level information of multiple candidate sampling schemes under different sea state categories under different sampling indicators, and recommendation level information of the multiple candidate sampling schemes under different soil types.

[0105] The category determination module 720 is used to determine the target sea state category based on the sea state characteristics of the sea area to be sampled, and to determine the target soil category based on the soil characteristics of the sea area to be sampled; the first matching module 730 is used to match the sampling requirement indicators and target sea state category of the sea area to be sampled with a pre-established information matching database to determine the first target recommendation level information of multiple candidate sampling schemes, and to determine the first recommendation score of multiple candidate sampling schemes based on the first target recommendation level information; the second matching module 740 is used to match the sampling requirement indicators and target soil category of the sea area to be sampled with a pre-established information matching database to determine the second target recommendation level information of multiple candidate sampling schemes, and to determine the second recommendation score of multiple candidate sampling schemes based on the second target recommendation level information; the scheme determination module 750 is used to calculate the target recommendation score by fusing the corresponding first recommendation score and second recommendation score for each candidate sampling scheme, and to determine the target sampling scheme from the candidate sampling schemes based on the target recommendation scores of each candidate sampling scheme.

[0106] In one exemplary embodiment of this disclosure, the information acquisition module 710 is configured to perform the following: collect sampling task sample data from multiple channels, the sampling task sample data including at least sea state sample data, soil sample data, sampling scheme sample data, and sampling index sample data; take the sampling index sample data, sea state sample data, and soil sample data as inputs, take the corresponding sampling scheme sample data as outputs, and train a recommendation model based on historical sampling data and expert rule base data, the recommendation model being used to determine the recommendation level for the sampling scheme samples; based on the recommendation model, output recommendation level information for multiple candidate sampling schemes under different sea state categories under different sampling indices, and output recommendation level information for multiple candidate sampling schemes under different soil categories.

[0107] In one exemplary embodiment of this disclosure, the first matching module 730 is configured to perform: establishing a corresponding number of multiple processing threads based on the number of sampling requirement indicators; using the multiple processing threads to match the multiple sampling requirement indicators and target sea state categories with a pre-established information matching library in parallel, and determining the first target recommendation level information and the corresponding first recommendation score of multiple candidate sampling schemes based on the matching results.

[0108] In one exemplary embodiment of this disclosure, the first matching module 730 is configured to perform: determining the corresponding recommendation score processing strategy according to the category of the sampling requirement index corresponding to the processing thread; and processing and converting the first target recommendation level information corresponding to the processing thread into a first recommendation score based on the recommendation score processing strategy.

[0109] In one exemplary embodiment of this disclosure, the scheme determination module 750 is configured to perform: acquiring environmental characteristic information of the sea area to be sampled, and determining sea state weight value and soil quality weight value based on the environmental characteristic information; weighting and fusing the first recommendation score and the second recommendation score based on the sea state weight value and the soil quality weight value to obtain a target recommendation score; filtering out candidate sampling schemes whose first recommendation score is lower than the sea state score threshold from each candidate sampling scheme according to the sea state score threshold to obtain a first reference sampling scheme, and filtering out candidate sampling schemes whose second recommendation score is lower than the soil quality score threshold from each candidate sampling scheme according to the soil quality score threshold to obtain a second reference sampling scheme; and determining a target sampling scheme from the first reference sampling scheme and the second reference sampling scheme according to the target recommendation score.

[0110] In one exemplary embodiment of this disclosure, the scheme determination module 750 is configured to perform the following: for each of the first and second reference sampling schemes, establish a multi-dimensional feature vector based on the scheme metadata of the reference sampling scheme, wherein the scheme metadata is obtained by deconstructing the reference sampling scheme; based on the multi-dimensional feature vectors corresponding to each reference sampling scheme, perform clustering processing on each reference sampling scheme to obtain multiple clusters; and from the clusters that do not contain the target sampling scheme, obtain the reference sampling scheme with the highest target recommendation score as the candidate sampling scheme.

[0111] In one exemplary embodiment of this disclosure, the scheme determination module 750 is configured to perform: generating a decision report based on the target sampling scheme and the corresponding target recommendation score and the alternative sampling scheme and the corresponding target recommendation score.

[0112] Since the details of the various functional modules of the sampling and determination apparatus for offshore wind power in the exemplary embodiments of this disclosure have been described in the exemplary embodiments of the sampling and determination method for offshore wind power described above, they will not be repeated here.

[0113] It should be noted that although several modules or units for sampling and determination devices for offshore wind power have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0114] An exemplary embodiment of this disclosure also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the above-described sampling determination method for offshore wind power.

[0115] In one implementation, the computer program product can be a tangible product containing a computer program, such as a computer-readable storage medium storing the computer program. The readable storage medium can be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory, hard disk drive (HDD), solid-state drive (SSD), etc. For example, the computer program product can be implemented as a non-volatile storage medium storing a computer program, such as read-only memory, NAND flash memory, etc.

[0116] In one implementation, the computer program product can be an intangible product containing a computer program. For example, the computer program product can be implemented as a virtual digital product, such as an executable file, installation package, or other digital file storing the computer program.

[0117] Computer program code can be written in one or more programming languages. The program code can execute entirely on the user's computing device, or partially on the user's computing device, or as a standalone software package, or partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device through any type of network, such as a local area network (LAN), a wide area network (WAN), etc., or it can be connected to an external computing device (e.g., through an internet connection provided by a mobile network operator).

[0118] Computer programs can be carried or transmitted via signals such as electricity, magnetism, light, electromagnetic radiation, and infrared radiation. Electronic devices can convert signals carrying computer programs into digital signals, thereby running the computer programs. When a computer program runs on an electronic device, its code is used to cause the electronic device to execute (more specifically, the processor of the electronic device to execute) the method steps of various exemplary embodiments of this disclosure, such as the steps of the sampling and determination method for offshore wind power described above.

[0119] Furthermore, in exemplary embodiments of this disclosure, an electronic device capable of implementing the above-described methods is also provided. Those skilled in the art will understand that various aspects of this disclosure can be implemented as systems, methods, or program products. Therefore, various aspects of this disclosure can be specifically implemented as: entirely hardware embodiments, entirely software embodiments (including firmware, microcode, etc.), or embodiments combining hardware and software aspects, collectively referred to herein as "circuit," "module," or "system."

[0120] The following reference Figure 8To describe an electronic device 800 according to such an embodiment of the present disclosure. Figure 8 The electronic device 800 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0121] like Figure 8 As shown, the electronic device 800 is presented in the form of a general-purpose computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one storage unit 820, a bus 830 connecting different system components (including storage unit 820 and processing unit 810), and a display unit 840.

[0122] The storage unit stores program code that can be executed by the processing unit 810, causing the processing unit 810 to perform the steps described in the "Exemplary Methods" section above, according to various exemplary embodiments of this disclosure.

[0123] Storage unit 820 may include readable media in the form of volatile storage units, such as random access memory (RAM) 821 and / or cache memory 822, and may further include read-only memory (ROM) 823.

[0124] The storage unit 820 may also include a program / utility 824 having a set (at least one) of program modules 825, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0125] Bus 830 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0126] Electronic device 800 can also communicate with one or more external devices 900 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 800, and / or with any device that enables electronic device 800 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 850. Furthermore, electronic device 800 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 860. As shown, network adapter 860 communicates with other modules of electronic device 800 via bus 830. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0127] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0128] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0129] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

Claims

1. A sampling determination method for offshore wind power, characterized in that, The method comprises the following steps: obtaining a pre-established information matching library, wherein the pre-established information matching library comprises recommended level information of a plurality of candidate sampling schemes under different sea state categories under different sampling indexes, and comprises recommended level information of the plurality of candidate sampling schemes under different soil categories; determining a target sea state category according to a sea state feature of a to-be-sampled sea area, and determining a target soil category according to a soil feature of the to-be-sampled sea area; matching the sampling demand index of the to-be-sampled sea area and the target sea state category with the pre-established information matching library to determine first target recommended level information of the plurality of candidate sampling schemes, and determining a first recommended score of each of the plurality of candidate sampling schemes according to the first target recommended level information; matching the sampling demand index of the to-be-sampled sea area and the target soil category with the pre-established information matching library to determine second target recommended level information of the plurality of candidate sampling schemes, and determining a second recommended score of each of the plurality of candidate sampling schemes according to the second target recommended level information; for each of the candidate sampling schemes, fusing the corresponding first recommended score and the second recommended score to obtain a target recommended score, and determining a target sampling scheme from each of the candidate sampling schemes according to the target recommended score of each of the candidate sampling schemes; wherein the obtaining of the pre-established information matching library comprises: collecting multi-channel sampling task sample data, wherein the sampling task sample data at least comprises sea state sample data, soil sample data, sampling scheme sample data and sampling index sample data; training a recommendation model based on historical sampling data and expert rule library data, wherein the recommendation model is used to determine a recommended level for the sampling scheme sample, and the recommendation model takes the sampling index sample data, the sea state sample data and the soil sample data as input, and takes the corresponding sampling scheme sample data as output; outputting recommended level information of a plurality of candidate sampling schemes under different sea state categories under different sampling indexes based on the recommendation model, and outputting recommended level information of the plurality of candidate sampling schemes under different soil categories based on the recommendation model; the matching of the sampling demand index of the to-be-sampled sea area and the target sea state category with the pre-established information matching library to determine the first target recommended level information of the plurality of candidate sampling schemes, and the determination of the first recommended score of each of the plurality of candidate sampling schemes according to the first target recommended level information comprises: establishing a plurality of processing threads corresponding to the number of sampling demand indexes; parallel matching of a plurality of sampling demand indexes and the target sea state category with the pre-established information matching library by using the plurality of processing threads, and determining the first target recommended level information of the plurality of candidate sampling schemes and the corresponding first recommended scores according to the matching results; the fusing of the corresponding first recommended score and the second recommended score to obtain the target recommended score for each of the candidate sampling schemes, and the determination of the target sampling scheme from each of the candidate sampling schemes according to the target recommended score of each of the candidate sampling schemes comprises: obtain environmental characteristic information of the sea area to be sampled, and determine a sea state weight value and a soil weight value according to the environmental characteristic information; perform weighted fusion calculation on the first recommended score and the second recommended score based on the sea state weight value and the soil weight value to obtain the target recommended score; filter out, according to a sea state score threshold, candidate sampling schemes with a first recommended score lower than the sea state score threshold from the candidate sampling schemes to obtain a first reference sampling scheme, and filter out, according to a soil score threshold, candidate sampling schemes with a second recommended score lower than the soil score threshold from the candidate sampling schemes to obtain a second reference sampling scheme; determine the target sampling scheme from the first reference sampling scheme and the second reference sampling scheme according to the target recommended score.

2. The method of claim 1, wherein, For each processing thread, the first recommended score of a candidate sampling scheme is determined, including: determining a corresponding recommended score processing strategy according to the category of the sampling demand index corresponding to the processing thread; processing and converting the first target recommended level information corresponding to the processing thread into the first recommended score based on the recommended score processing strategy.

3. The method of claim 1, wherein, The method further includes: establishing a multi-dimensional feature vector for each reference sampling scheme in the first reference sampling scheme and the second reference sampling scheme according to scheme metadata of the reference sampling scheme, the scheme metadata being obtained by deconstructing the reference sampling scheme; performing clustering processing on each reference sampling scheme based on the multi-dimensional feature vector corresponding to the reference sampling scheme to obtain a plurality of clustering clusters; respectively obtaining, from the clustering clusters not containing the target sampling scheme, a reference sampling scheme with the highest target recommended score as an alternative sampling scheme.

4. The method of claim 3, wherein, The method further includes: generating a decision report according to the target sampling scheme and the corresponding target recommended score and the alternative sampling scheme and the corresponding target recommended score.

5. A sampling determination device for offshore wind power, characterized in that, including: an information acquisition module configured to acquire a pre-established information matching library, the pre-established information matching library including recommended level information of a plurality of candidate sampling schemes under different sea state categories under different sampling indexes, and including recommended level information of the plurality of candidate sampling schemes under different soil categories; a category determination module configured to determine a target sea state category according to a sea state characteristic of a sea area to be sampled, and determine a target soil category according to a soil characteristic of the sea area to be sampled; a first matching module configured to match sampling demand indexes of the sea area to be sampled and the target sea state category with the pre-established information matching library, determine first target recommended level information of the plurality of candidate sampling schemes, and determine first recommended scores of the plurality of candidate sampling schemes according to the first target recommended level information, respectively; a second matching module configured to match sampling demand indexes of the sea area to be sampled and the target soil category with the pre-established information matching library, determine second target recommended level information of the plurality of candidate sampling schemes, and determine second recommended scores of the plurality of candidate sampling schemes according to the second target recommended level information, respectively; a scheme determination module configured to, for each of the candidate sampling schemes, fuse the corresponding first recommendation score and the second recommendation score to obtain a target recommendation score, and determine a target sampling scheme from the candidate sampling schemes according to the target recommendation scores of the candidate sampling schemes; wherein the information acquisition module is configured to perform: collecting multi-channel sampling task sample data, the sampling task sample data at least including sea state sample data, soil sample data, sampling scheme sample data, and sampling index sample data; training a recommendation model based on historical sampling data and expert rule base data, taking the sampling index sample data, the sea state sample data, and the soil sample data as inputs, and taking corresponding sampling scheme sample data as outputs, the recommendation model being configured to determine a recommendation level for the sampling scheme sample; based on the recommendation model, outputting recommendation level information of a plurality of candidate sampling schemes under different sea state categories under different sampling indexes, and outputting recommendation level information of the plurality of candidate sampling schemes under different soil categories; the first matching module is configured to perform: establishing a corresponding number of multiple processing threads according to the number of the sampling requirement indexes; using the multiple processing threads, matching the multiple sampling requirement indexes and the target sea state category with the pre-established information matching library in parallel, and determining first target recommendation level information and corresponding first recommendation scores of the multiple candidate sampling schemes according to the matching results; the scheme determination module is configured to perform: obtaining environmental characteristic information of the sea area to be sampled, and determining sea state weight values and soil weight values according to the environmental characteristic information; based on the sea state weight values and the soil weight values, performing weighted fusion calculation on the first recommendation scores and the second recommendation scores to obtain the target recommendation scores; according to a sea state score threshold, filtering out candidate sampling schemes with first recommendation scores lower than the sea state score threshold from the candidate sampling schemes to obtain first reference sampling schemes, and according to a soil score threshold, filtering out candidate sampling schemes with second recommendation scores lower than the soil score threshold from the candidate sampling schemes to obtain second reference sampling schemes; determining the target sampling scheme from the first reference sampling schemes and the second reference sampling schemes according to the target recommendation scores.

6. A program product comprising a computer program, characterized in that The computer program, when executed by a processor, implements the method of any one of claims 1 to 4.

7. An apparatus, comprising: comprise: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the method of any one of claims 1 to 4 by executing the executable instructions.

Images