Production logistics state space-time modeling method

By constructing a spatio-temporal model of production logistics status, the problem of insufficient real-time and accuracy of production logistics management systems in the existing technology is solved, and a comprehensive and accurate reflection of production logistics status is achieved, and management efficiency and data processing accuracy are improved. .

CN119089133APending Publication Date: 2024-12-06CHONGQING SHOUHENG SOFTWARE CO LTD

Patent Information

Application Number
CN202411063267.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-05
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing production logistics management system has shortcomings in real-time and accuracy, and it is difficult to comprehensively and accurately reflect changes in production logistics status. Especially in complex environments, it is impossible to effectively capture dynamic changes in time and space.

Method used

By obtaining production logistics space and time description data, performing feature extraction, conducting space-time correlation analysis, and building a spatio-temporal model of production logistics states to comprehensively and accurately reflect the dynamic changes in production logistics states.

Benefits of technology

It improves the accuracy and completeness of data, reduces labor costs, enhances data processing efficiency and the accuracy of analysis results, provides stronger support for production logistics management, and avoids misjudgment and delays.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089133A_ABST
    Figure CN119089133A_ABST
Patent Text Reader

Abstract

According to the production logistics state space-time model construction method, production logistics space description data are acquired, and feature extraction is performed on the data, so that space features capable of reflecting production logistics space distribution and change features are obtained; the method comprises the following steps: obtaining production logistics time description data, and performing feature extraction on the data to obtain time features capable of reflecting a production logistics time change rule; according to the extracted spatial features and time features, carrying out production logistics spatial-temporal correlation analysis, revealing the internal relation and change rule of the production logistics state in time and space, and obtaining the representation of the production logistics spatial-temporal correlation; and on the basis of the spatial-temporal correlation representation, a production logistics state spatial-temporal model is constructed, so that the model can comprehensively and accurately reflect dynamic changes of the production logistics state in time and space, powerful support is provided for production logistics management, and misjudgment and delay of logistics state changes are avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the field of digital twins, and in particular to a method for spatiotemporal modeling of production logistics status. Background Art

[0002] In the current manufacturing and logistics industries, the management and monitoring of production logistics status is the key to improving production efficiency and reducing costs. However, the existing production logistics management system has deficiencies in real-time and accuracy, especially when dealing with complex production logistics environments, it is difficult to fully and accurately reflect the changes in production logistics status. This is mainly because the existing system lacks comprehensive consideration of production logistics space and time information, and cannot effectively capture the dynamic changes in production logistics status in time and space.

[0003] Specifically, when constructing a production logistics status model, existing technologies often only focus on the spatial distribution or temporal changes of logistics, while ignoring the intrinsic connection between the two. For example, some systems may only obtain the spatial layout and logistics flow of the production site through monitoring equipment, but cannot accurately analyze the temporal changes of these logistics activities; other systems may only focus on the time series data of logistics activities, but cannot accurately reflect the spatial distribution and changes of logistics activities. This single-dimensional analysis method is not only difficult to fully reflect the production logistics status, but may also lead to misjudgment and delays in changes in logistics status. Summary of the invention

[0004] The purpose of this application is to propose a method for spatiotemporal modeling of production logistics status to solve or overcome the above-mentioned technical problems existing in the prior art.

[0005] According to a first aspect of an embodiment of the present application, a method for constructing a spatiotemporal model of production logistics status is provided, which includes:

[0006] Acquiring production logistics space description data to perform feature extraction on the production logistics space description data to obtain production logistics space features;

[0007] Acquire production logistics time description data to perform feature extraction on the production logistics time description data to obtain production logistics time features;

[0008] According to the production logistics spatial characteristics and the production logistics temporal characteristics, a production logistics spatiotemporal correlation analysis is performed to obtain a production logistics spatiotemporal correlation representation;

[0009] Based on the spatiotemporal correlation characterization of the production logistics, the spatiotemporal model of the production logistics state is constructed.

[0010] In the method for constructing a spatiotemporal model of production logistics status of the present invention, spatial features that can reflect the spatial distribution and change characteristics of production logistics are obtained by acquiring production logistics spatial description data and extracting features from these data; temporal description data of production logistics are acquired and features are extracted from these data to obtain temporal features that can reflect the temporal change law of production logistics; spatiotemporal correlation analysis of production logistics is performed based on the extracted spatial features and temporal features to reveal the intrinsic connection and change law of production logistics status in time and space and obtain the spatiotemporal correlation representation of production logistics; based on the spatiotemporal correlation representation, a spatiotemporal model of production logistics status is constructed, so that the model can comprehensively and accurately reflect the dynamic changes of production logistics status in time and space, provide strong support for production logistics management, and avoid misjudgment and delay of logistics status changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Hereinafter, some specific embodiments of the present application will be described in detail in an exemplary and non-limiting manner with reference to the accompanying drawings. The same reference numerals in the accompanying drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the accompanying drawings:

[0012] Figure 1 A flow chart of a method for constructing a spatiotemporal model of production logistics status according to an embodiment of the present application. DETAILED DESCRIPTION

[0013] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the embodiments of the present application should fall within the scope of protection of the embodiments of the present application.

[0014] Figure 1 The following is a flow chart of a method for constructing a spatiotemporal model of production logistics status according to an embodiment of the present application. Figure 1 As shown, it includes:

[0015] Acquiring production logistics space description data to perform feature extraction on the production logistics space description data to obtain production logistics space features;

[0016] Acquire production logistics time description data to perform feature extraction on the production logistics time description data to obtain production logistics time features;

[0017] According to the production logistics spatial characteristics and the production logistics temporal characteristics, a production logistics spatiotemporal correlation analysis is performed to obtain a production logistics spatiotemporal correlation representation;

[0018] Based on the spatiotemporal correlation characterization of the production logistics, the spatiotemporal model of the production logistics state is constructed.

[0019] In the method for constructing a spatiotemporal model of production logistics status of the present invention, spatial features that can reflect the spatial distribution and change characteristics of production logistics are obtained by acquiring production logistics spatial description data and extracting features from these data; temporal description data of production logistics are acquired and features are extracted from these data to obtain temporal features that can reflect the temporal change law of production logistics; spatiotemporal correlation analysis of production logistics is performed based on the extracted spatial features and temporal features to reveal the intrinsic connection and change law of production logistics status in time and space and obtain the spatiotemporal correlation representation of production logistics; based on the spatiotemporal correlation representation, a spatiotemporal model of production logistics status is constructed, so that the model can comprehensively and accurately reflect the dynamic changes of production logistics status in time and space, provide strong support for production logistics management, and avoid misjudgment and delay of logistics status changes.

[0020] Optionally, the obtaining of production logistics space description data includes:

[0021] The workshop production data is acquired and parsed to acquire the workshop layout data and the workpiece processing path data therefrom, wherein the production logistics space description data at least includes the workshop layout data and the workpiece processing path data.

[0022] To this end, the above process of obtaining production logistics space description data has the following technical benefits:

[0023] (1) Improved data accuracy and completeness: By analyzing workshop production data, we can directly obtain workshop layout data and workpiece processing path data, which are the core content of the production logistics space description. Compared with manual input or indirect acquisition, this direct acquisition method reduces data errors and improves data accuracy. At the same time, the types of data obtained are comprehensive, including workshop layout and workpiece processing path, etc., ensuring data integrity.

[0024] (2) Improved data processing efficiency: The automated data analysis process can quickly extract the required workshop layout data and workpiece processing path data, greatly improving the speed and efficiency of data processing compared to manual processing. This efficient data processing can provide enterprises with more timely and accurate logistics space description information, helping enterprises to make more reasonable production plans and logistics arrangements.

[0025] (3) Reduced labor costs: Through the automated data analysis process, the degree of human involvement is reduced, reducing the reliance on human resources. This not only reduces the labor costs of enterprises, but also reduces the impact of human factors on data accuracy and improves data reliability.

[0026] (4) Easy to expand and maintain: The processing process is based on general data analysis technology and can be easily expanded to other similar data processing scenarios. At the same time, due to the modular design, the system can be easily maintained and upgraded to adapt to changing production needs.

[0027] To this end, the above process of obtaining production logistics space description data provides the following exemplary code (using Python language):

[0028]

[0029] In the above sample code, the parse_production_data function is used to read and parse the workshop production data, extract the workshop layout data and workpiece processing path data, and return the production logistics space description data.

[0030] Optionally, the extracting features of the production logistics space description data to obtain production logistics space features includes:

[0031] Based on the spatial heterogeneity constraints and spatial autocorrelation constraints of the workshop layout, feature extraction is performed on the production logistics space description data to obtain production logistics space features.

[0032] To this end, the above-mentioned process of extracting features from production logistics spatial description data based on the spatial heterogeneity constraints and spatial autocorrelation constraints of workshop layout has the following technical benefits:

[0033] (1) Improved pertinence of feature extraction: By considering the spatial heterogeneity constraints and spatial autocorrelation constraints of the workshop layout, key features related to production logistics can be extracted more accurately. These features can more accurately reflect the characteristics and laws of the production logistics space, providing more reliable support for subsequent analysis and decision-making.

[0034] (2) Enhanced representativeness of features: Spatial heterogeneity constraints ensure that the diversity and complexity of workshop layouts are taken into account during feature extraction, thereby improving the representativeness of the extracted production logistics space features. These features can more comprehensively reflect the actual conditions of the production logistics space and provide strong support for production optimization and decision-making.

[0035] (3) Improved accuracy of analysis results: Based on the extracted production logistics spatial features, further production logistics analysis, prediction and decision-making can be carried out. Since these features are more targeted and representative, the analysis results will be more accurate and reliable, helping enterprises to better respond to market changes and production challenges.

[0036] (4) Promoted the construction of intelligent production logistics system: By introducing spatial heterogeneity constraints and spatial autocorrelation constraints for feature extraction, it provides important technical support for the construction of intelligent production logistics system. These features can be used as system input to achieve automation, intelligent management and optimization of production logistics.

[0037] To this end, the above process of extracting spatial features of production logistics based on spatial heterogeneity constraints and spatial autocorrelation constraints provides the following exemplary code (using Python language and scikit-learn library):

[0038]

[0039] Optionally, the method further comprises:

[0040] Draw workshop layout maps with different layout methods based on product variety data and output data;

[0041] According to the workshop layout map, constructing spatial heterogeneity constraints of the workshop layout;

[0042] Among them, the layout methods include at least one of the following: product principle layout, process principle layout, fixed product layout, grouping principle layout, and roving layout. In the product principle layout, production units are divided according to processing objects. In the fixed product layout, production equipment is moved to the products to be processed for processing. In the grouping principle layout, production equipment is organized into production equipment clusters. In the roving layout, the products to be processed can be switched between production equipment in different product production rooms.

[0043] To this end, the above process of drawing workshop layout maps of different layout modes based on product variety data and output data, and constructing the spatial heterogeneity constraint of workshop layout based on these maps has the following technical benefits:

[0044] (1) Improved flexibility of production layout: By drawing workshop layout maps with different layout methods, enterprises can flexibly select or adjust production layout according to changes in product variety and output. This flexibility helps enterprises better adapt to changes in market demand and improve production efficiency and response speed.

[0045] (2) Optimized production resource allocation: Different layout methods correspond to different production resource allocation methods. By constructing spatial heterogeneity constraints on workshop layout, enterprises can ensure the rational allocation and efficient use of production resources, reducing resource waste and production costs.

[0046] (3) Improved production efficiency: According to the characteristics of product variety and output, choosing a suitable layout can reduce material handling time and distance, improve equipment utilization and personnel collaboration efficiency, and thus improve overall production efficiency.

[0047] (4) Supports decision analysis: By drawing workshop layout maps and constructing spatial heterogeneity constraints, enterprises can more intuitively understand the advantages, disadvantages and applicable scope of different layout methods, providing strong support for production layout decisions.

[0048] (5) Enhanced maintainability and scalability of the system: Due to the modular design concept, the process can be easily integrated into the existing production management system and expanded and upgraded as the enterprise develops and needs change.

[0049] To this end, the above-mentioned process of drawing workshop layout maps of different layout modes based on product variety data and output data and constructing the processing process of spatial heterogeneity constraints provides the following exemplary code (using Python language and matplotlib library for visualization):

[0050]

[0051]

[0052] The generate_layout function and layout_data variable in the above code generate and process layout data according to the specific layout algorithm and data structure. In addition, the specific implementation of the build_spatial_heterogeneity_constraints function also depends on the specific constraints and requirements.

[0053] Optionally, constructing the spatial heterogeneity constraint of the workshop layout according to the workshop layout map includes:

[0054] According to the workshop layout map, a heterogeneity measurement is performed on the corresponding layout mode to obtain a heterogeneity measurement evaluation;

[0055] According to the heterogeneity metric evaluation corresponding to different layout modes, the spatial heterogeneity constraint of the workshop layout is constructed;

[0056] Among them, the heterogeneity measurement evaluation includes at least one of the following: material handling volume measurement, work-in-process quantity measurement, equipment utilization measurement, production plan complexity measurement, multi-skilled worker demand difficulty measurement, customization degree measurement, flexibility degree measurement, unit product cost degree measurement.

[0057] To this end, the above process of evaluating the heterogeneity of different layout modes based on the workshop layout map and constructing the spatial heterogeneity constraint of the workshop layout has the following technical benefits:

[0058] (1) Improved layout rationality: By measuring the heterogeneity of different layout methods, we can clearly see the performance differences of each layout method in terms of production efficiency, cost control, etc. Based on these evaluation results, we can choose the layout method that best suits the actual situation of the enterprise and improve the rationality of the layout of the production workshop.

[0059] (2) Supports quantitative decision-making: Heterogeneous measurement evaluation provides specific quantitative indicators, such as material handling volume, number of work-in-progress, equipment utilization rate, etc. These indicators can intuitively reflect the advantages and disadvantages of different layout methods. Based on these quantitative data, enterprises can make more scientific and accurate decisions.

[0060] (3) Improved production efficiency: By choosing a layout with less heterogeneity, the amount of material handling can be reduced, the number of work-in-progress can be reduced, and equipment utilization can be improved, thereby reducing production costs and improving production efficiency.

[0061] (4) Enhanced production flexibility: By evaluating the flexibility of different layout methods, a more flexible layout method can be selected to cope with rapid changes in market demand. This flexible layout can adjust the production process more quickly to meet customers’ customized needs.

[0062] (5) Optimized resource allocation: Based on heterogeneity measurement evaluation, enterprises can more reasonably allocate production resources, such as equipment and personnel. This optimization can ensure the full utilization of production resources and avoid resource waste.

[0063] To this end, the above process of constructing spatial heterogeneity constraints based on the workshop layout map provides the following exemplary code:

[0064]

[0065] Optionally, the method further comprises:

[0066] The spatial autocorrelation constraint is constructed according to the distance between the workstations where the production equipment is arranged and the logistics, and the dependency relationship between different logistics states in the logistics network.

[0067] To this end, the above process of constructing spatial autocorrelation constraints based on the distance between the workstations where the production equipment is arranged and the logistics, as well as the dependency relationship between different logistics states in the logistics network, has the following technical benefits:

[0068] (1) Optimizing logistics efficiency: By considering the distance between production equipment stations and logistics, as well as the dependencies between logistics states, we can ensure that materials flow more smoothly and efficiently during the production process. This helps reduce material handling time, lower logistics costs, and improve the efficiency of the entire production process.

[0069] (2) Improving production flexibility: The construction of spatial autocorrelation constraints helps to identify bottlenecks and potential risks in the production process. By optimizing these bottlenecks and eliminating potential risks, the flexibility and responsiveness of the production system can be improved, enabling it to better adapt to changes in market demand.

[0070] (3) Supporting intelligent decision-making: Based on the information of spatial autocorrelation constraints, enterprises can formulate more accurate and scientific production plans and scheduling schemes. This helps to realize the intelligent management of the production process and improve the efficiency and accuracy of decision-making.

[0071] (4) Enhance the stability of the production system: By constructing spatial autocorrelation constraints, enterprises can more clearly understand the dependencies between various links in the production process. This helps prevent failures and interruptions in the production process and improve the stability and reliability of the production system.

[0072] To this end, the above process of constructing spatial autocorrelation constraints provides the following exemplary code:

[0073]

[0074]

[0075] Optionally, the step of constructing the spatial autocorrelation constraint based on the distance between the workstations where the production equipment is arranged and the logistics, and the dependency relationship between different logistics states in the logistics network, further includes:

[0076] Determine the degree of dispersion of logistics in the logistics network and the complexity of the processes on which the production equipment depends;

[0077] The degree of dispersion of logistics in the logistics network and the complexity of the processes on which the production equipment depends determine the logistics blocking characteristics;

[0078] According to the logistics blocking characteristics, material area buffer configuration data is set to optimize the constructed spatial autocorrelation constraints.

[0079] To this end, the above-mentioned distance between the workstations where the production equipment is arranged and the logistics, as well as the dependency between different logistics states in the logistics network, further determines the degree of dispersion of the logistics network and the complexity of the process on which the production equipment depends, thereby determining the logistics blocking characteristics, and setting the material area buffer configuration data according to the logistics blocking characteristics to optimize the processing process of spatial autocorrelation constraints, which has the following technical benefits:

[0080] (1) Improve logistics efficiency: By determining the degree of dispersion of the logistics network and the complexity of the processes on which the production equipment depends, potential logistics bottlenecks can be identified more accurately. The material area buffer configuration data set based on this information helps to establish a buffer zone before the bottleneck to reduce logistics bottlenecks and improve logistics efficiency.

[0081] (2) Optimizing resource allocation: The determination of logistics blocking characteristics and the setting of material area buffer configuration data help enterprises to reasonably allocate production resources according to actual needs, such as storage space, transportation tools, etc. This helps to avoid waste of resources while ensuring the smooth progress of the production process.

[0082] (3) Improving the stability of the production system: By optimizing spatial autocorrelation constraints, enterprises can more effectively prevent failures and interruptions in the production process. In particular, when facing unpredictable events such as market demand fluctuations or production equipment failures, the optimized constraints can ensure the stability and reliability of the production system.

[0083] (4) Supporting intelligent decision-making: Based on the analysis of logistics blocking characteristics and material area buffer configuration data, enterprises can formulate more accurate and scientific production plans and scheduling plans. This helps to achieve intelligent management of the production process and improve decision-making efficiency and accuracy.

[0084] To this end, the above processing process provides the following exemplary code:

[0085]

[0086]

[0087] Optionally, the spatial heterogeneity constraint and the spatial autocorrelation constraint based on the workshop layout are used to extract features from the production logistics space description data to obtain production logistics space features, including:

[0088] Based on the spatial heterogeneity constraint of the workshop layout, feature extraction is performed on the production logistics space description data to obtain the regional characteristics of the production equipment, including regional area, equipment density, and logistics flow frequency;

[0089] Based on the spatial autocorrelation constraint of the workshop layout, feature extraction is performed on the production logistics space description data to obtain the dependency relationship between the workstations where the production equipment is located and the logistics nodes;

[0090] The characteristics of the area where the production equipment is located and the dependency relationship between the workstation where the production equipment is located and the logistics node are integrated to obtain the production logistics space characteristics.

[0091] To this end, the above-mentioned spatial heterogeneity constraints and spatial autocorrelation constraints based on the workshop layout are used to extract features from the production logistics space description data to obtain the processing process of production logistics space features, which has the following technical benefits:

[0092] (1) Improving the level of refinement in production logistics management: By considering the spatial heterogeneity constraints and spatial autocorrelation constraints of the workshop layout, the key features of the production logistics space can be more accurately extracted, such as the regional characteristics of the production equipment (regional area, equipment density, logistics flow frequency) and the dependency relationship between production equipment and logistics nodes. These features help enterprises manage production logistics more finely and optimize resource allocation.

[0093] (2) Enhance the predictability and controllability of the production logistics system: Based on the extracted production logistics spatial characteristics, enterprises can establish a more accurate production logistics prediction model to achieve real-time monitoring and dynamic adjustment of the production logistics process. This helps to identify potential problems in advance, take corresponding measures, and enhance the predictability and controllability of the production logistics system.

[0094] (3) Supporting intelligent decision-making and optimization: The extraction of production logistics spatial features provides strong support for intelligent decision-making and optimization. Enterprises can use these features to formulate production plans, optimize equipment layout, plan logistics routes, etc., to achieve intelligent management of production logistics systems.

[0095] (4) Improve production efficiency and reduce logistics costs: By optimizing the spatial layout and resource allocation of production logistics, enterprises can shorten logistics routes, reduce material handling time, reduce logistics costs, and improve production efficiency. This is of great significance for enterprises to enhance their competitiveness and achieve sustainable development.

[0096] To this end, the above processing process provides the following exemplary code:

[0097]

[0098]

[0099] Optionally, the spatial heterogeneity constraint based on the workshop layout is used to extract features from the production logistics space description data to obtain features of the area where the production equipment is located, including:

[0100] Vectorizing the production logistics space description data to obtain a production logistics space description vector;

[0101] Based on the spatial heterogeneity constraint of the workshop layout, the production logistics space description vector is mapped to obtain the characteristics of the area where the production equipment is located, including the area, equipment density, and logistics flow frequency.

[0102] To this end, the above-mentioned process of extracting features from the production logistics spatial description data based on the spatial heterogeneity constraints of the workshop layout to obtain the characteristics of the area where the production equipment is located has the following technical benefits:

[0103] (1) Standardization and efficiency of data processing: By vectorizing the spatial description data of production logistics, it can be converted into structured data that is easy for computers to process, providing standardized input for subsequent feature extraction. At the same time, vectorization can significantly improve data processing efficiency and speed up feature extraction.

[0104] (2) Targetedness and accuracy of feature extraction: Based on the spatial heterogeneity constraints of the workshop layout, the spatial description vector of the production logistics is mapped and processed, which can specifically extract features closely related to the area where the production equipment is located, such as area, equipment density, and logistics flow frequency. These features are of great reference value for subsequent production logistics management and optimization.

[0105] (3) Optimizing production layout and resource allocation: By extracting the characteristics of the area where the production equipment is located, enterprises can have a clearer understanding of the layout of the production workshop, thereby optimizing the production layout and resource allocation. For example, according to information such as equipment density and logistics flow frequency, the layout of the equipment can be reasonably arranged to reduce the distance and time of material handling and improve production efficiency.

[0106] (4) Supporting intelligent decision-making and data analysis: The extracted regional features of production equipment can provide strong support for the intelligent decision-making and data analysis of enterprises. Enterprises can use these features to formulate production plans, predict equipment maintenance, optimize logistics routes, etc., to achieve intelligent and refined production logistics management.

[0107] For the above processing, the following exemplary code is provided:

[0108]

[0109]

[0110] Optionally, the spatial heterogeneity constraint based on the workshop layout is used to map the production logistics space description vector to obtain the regional characteristics of the production equipment, including the regional area, equipment density, and logistics flow frequency, including:

[0111] Based on the spatial heterogeneity constraint of the workshop layout, the production logistics space description vector is calibrated to a regional feature label to map the production logistics space description vector feature to a multi-scale representation feature;

[0112] Hierarchical clustering analysis and spatial statistical analysis are performed on the multi-scale characterization features to obtain the characteristics of the area where the production equipment is located, including the area, equipment density, and logistics flow frequency.

[0113] To this end, the above spatial heterogeneity constraints based on the workshop layout are used to map the production logistics space description vector to obtain the regional characteristics of the production equipment, including the regional area, equipment density, and logistics flow frequency. The processing has the following technical benefits:

[0114] (1) Introduction of multi-scale representation: By mapping the spatial description vector features of production logistics into multi-scale representation features, the spatial characteristics of the area where the production equipment is located can be more comprehensively described. This multi-scale representation method helps to capture spatial information at different granularities and improve the accuracy and completeness of feature extraction.

[0115] (2) Accuracy of hierarchical clustering analysis: Hierarchical clustering analysis of multi-scale characterization features can divide the areas where production equipment are located into different cluster groups based on the similarities and differences between the features. This clustering method can accurately reflect the spatial heterogeneity between regions and provide strong support for subsequent feature extraction and regional analysis.

[0116] (3) Practicality of spatial statistical analysis: Through spatial statistical analysis, we can further explore the spatial distribution patterns and characteristics of the area where the production equipment is located, such as regional area, equipment density, logistics flow frequency, etc. These characteristics have important reference value for optimizing production layout and improving production efficiency, and help enterprises realize intelligent and refined production logistics management.

[0117] (4) Data-driven decision support: The entire process is based on the spatial heterogeneity constraints of the workshop layout, and the characteristics of the area where the production equipment is located are extracted in a data-driven manner. This data-driven method can objectively reflect the actual situation of the production workshop and provide a scientific and reliable basis for the company's decision-making.

[0118] To this end, the following is an exemplary code to implement the above solution:

[0119]

[0120]

[0121] Optionally, the spatial autocorrelation constraint based on the workshop layout is used to extract features from the production logistics space description data to obtain the dependency relationship between the workstations where the production equipment is located and the logistics nodes, including:

[0122] Based on the spatial autocorrelation constraints of the workshop layout, the spatial autocorrelation measurement parameters are constructed;

[0123] According to the spatial autocorrelation measurement parameter, neighborhood correlation analysis is performed on the production logistics spatial description data to obtain spatial aggregation pattern statistics;

[0124] According to the statistics of the spatial aggregation pattern, the dependency relationship between the workstations where the production equipment is located and the logistics nodes is predicted.

[0125] To this end, the above-mentioned process of extracting features from the production logistics space description data based on the spatial autocorrelation constraint of the workshop layout to obtain the dependency relationship between the workstations where the production equipment is located and the logistics nodes has the following technical benefits:

[0126] (1) Improving the rationality of production layout: By considering the spatial autocorrelation of workshop layout, the dependency relationship between production equipment and logistics nodes can be accurately identified, thereby optimizing the production layout, reducing unnecessary logistics distances, and improving production efficiency.

[0127] (2) Realize intelligent logistics management: Based on the statistics of spatial aggregation patterns, the interaction patterns between production equipment and logistics nodes can be predicted, and intelligent logistics scheduling and management can be realized, thereby improving the speed and accuracy of logistics response.

[0128] (3) Support decision analysis: Through the extracted spatial features, enterprises can more clearly understand the bottlenecks and potential problems in the production process, and provide strong data support for the formulation of production plans, resource allocation and optimization.

[0129] (4) Enhance the interpretability of the system: The introduction of spatial autocorrelation makes the analysis process more intuitive and interpretable, making it easier for production managers to understand and apply the analysis results, thereby improving the scientificity and rationality of decision-making.

[0130] The following is an example code to implement the above solution:

[0131]

[0132]

[0133] Optionally, the spatial autocorrelation constraint based on the workshop layout is used to construct a spatial autocorrelation measurement parameter, including:

[0134] According to the location coordinates of production equipment, the location coordinates of logistics nodes and the layout information of production lines, neighborhood aggregation measurement parameters, kernel density function and logistics flow path measurement parameters are constructed based on the spatial autocorrelation constraints of workshop layout.

[0135] To this end, the above-mentioned process of constructing spatial autocorrelation measurement parameters based on the spatial autocorrelation constraints of the workshop layout includes constructing neighborhood aggregation measurement parameters, kernel density functions, and logistics flow path measurement parameters according to the location coordinates of production equipment, the location coordinates of logistics nodes, and the layout information of the production line, which has the following technical benefits:

[0136] (1) Accurately quantify spatial relationships: By constructing neighborhood aggregation measurement parameters, the degree of spatial aggregation between production equipment and logistics nodes can be accurately quantified, thereby more accurately reflecting the dependency relationship between them.

[0137] (2) Considering spatial distribution characteristics: The kernel density function can fully consider the spatial distribution characteristics of production equipment and logistics nodes in the workshop, differentiate between dense and sparse areas, and improve the accuracy of the analysis.

[0138] (3) Optimizing logistics flow paths: By constructing logistics flow path measurement parameters, we can analyze the flow of logistics within the workshop, identify potential bottlenecks and congestion points, and provide a basis for optimizing logistics flow paths.

[0139] (4) Support customized analysis: Combined with the layout information of the production line, the spatial autocorrelation measurement parameters can be customized according to different production line layouts to meet the needs of different production scenarios.

[0140] (5) Improve the scientific nature of decision-making: Based on these precisely quantified spatial autocorrelation measurement parameters, enterprises can make more scientific and reasonable decisions, optimize production layout, and improve production efficiency.

[0141] To this end, an exemplary code for implementing the above solution is provided as follows:

[0142]

[0143]

[0144] Optionally, performing neighborhood correlation analysis on the production logistics spatial description data according to the spatial autocorrelation measurement parameter to obtain spatial aggregation pattern statistics includes:

[0145] Constructing a spatial association matrix according to the neighborhood aggregation measurement parameters, the kernel density function, and the logistics flow path measurement parameters;

[0146] Based on the spatial association matrix, the production logistics spatial description data is subjected to neighborhood association analysis and mapping processing to obtain spatial aggregation pattern statistics.

[0147] To this end, the above process of performing neighborhood correlation analysis on the production logistics spatial description data based on the spatial autocorrelation measurement parameters to obtain the statistical processing of spatial aggregation patterns has the following technical benefits:

[0148] (1) Revealing spatial correlation patterns: By constructing a spatial correlation matrix, we can systematically reveal the spatial correlation patterns of production equipment, logistics nodes, and their relationships, thereby gaining a deeper understanding of the spatial relationships in the production logistics system.

[0149] (2) Quantifying the degree of spatial aggregation: The neighborhood aggregation metric parameters and kernel density function can be used to quantify the degree of spatial aggregation of production equipment and logistics nodes, which helps to identify high-density and low-density areas in the production logistics system.

[0150] (3) Optimizing logistics path planning: Combining the logistics flow path measurement parameters, the flow of logistics within the workshop can be analyzed, providing a scientific basis for optimizing logistics path planning and reducing logistics congestion and waste.

[0151] (4) Improve decision-making efficiency: Based on spatial aggregation pattern statistics, enterprises can identify bottlenecks and potential problems in production logistics systems more quickly and accurately, thereby formulating more effective improvement measures and improving decision-making efficiency.

[0152] (5) Support visual analysis: Spatial correlation matrix and spatial aggregation pattern statistics can be easily displayed and analyzed through visualization tools, helping decision makers to more intuitively understand the spatial layout and operation of the production logistics system.

[0153] To this end, an exemplary code for implementing the above solution is provided:

[0154]

[0155]

[0156] Optionally, the predicting the dependency relationship between the workstation where the production equipment is located and the logistics node according to the statistics of the spatial aggregation pattern includes:

[0157] According to the statistics of the spatial aggregation pattern, each workstation and logistics node is assigned a corresponding cluster label;

[0158] Based on the description of production synergy effects, the cluster labels assigned to each workstation and logistics node are used for functional association identification and logistics flow analysis to predict the dependency relationship between the workstation where the production equipment is located and the logistics node.

[0159] To this end, the above process of predicting the dependency relationship between the workstations where production equipment is located and the logistics nodes based on the statistics of spatial aggregation patterns has the following technical benefits:

[0160] (1) Improving prediction accuracy: By assigning a cluster label to each workstation and logistics node, more accurate functional association identification can be performed based on spatial cluster pattern statistics, thereby improving the prediction accuracy of the dependency relationship between production equipment and logistics nodes.

[0161] (2) Identify collaborative relationships: Based on the description of production synergy effects, it is possible to identify collaborative relationships between different workstations and logistics nodes, providing strong support for enterprises to optimize production processes and logistics planning.

[0162] (3) Optimize resource allocation: By predicting the dependency between production equipment and logistics nodes, enterprises can allocate resources more rationally, reduce unnecessary waste, and improve production efficiency.

[0163] (4) Support decision making: The forecast results can provide valuable reference information for enterprises and help decision makers formulate more scientific and reasonable production plans and logistics strategies.

[0164] (5) Strong adaptability: This method does not depend on the specific type of production equipment and logistics system. It has strong universality and scalability and can be applied to the production logistics systems of different industries and enterprises.

[0165] The following is an example code to implement the above solution:

[0166]

[0167]

[0168] Optionally, the functional association identification is as follows: within each cluster, the functional association identification analyzes the functions of the workstations and the service types of the logistics nodes, identifies which workstations are upstream and downstream in the production process, and which logistics nodes mainly serve specific types of workstations;

[0169] The logistics flow analysis is: using logistics nodes as bridges, analyzing the frequency and magnitude of material transfer from one cluster to another, and identifying the dependencies between workstations and nodes on key logistics paths.

[0170] Optionally, the fusion of the regional characteristics of the production equipment and the dependency relationship between the workstations of the production equipment and the logistics nodes to obtain the production logistics space characteristics includes:

[0171] Performing feature-to-feature attention analysis on the features of the area where the production equipment is located and the dependency relationship between the workstation where the production equipment is located and the logistics node to obtain an attention weight;

[0172] Performing principal component analysis on the characteristics of the area where the production equipment is located and the dependency relationship between the workstation where the production equipment is located and the logistics node to obtain the principal component characteristics of the area where the production equipment is located and the principal characteristics of the dependency relationship;

[0173] Based on the attention weight, a weighted average operation is performed on the principal component features of the area where the production equipment is located and the principal features of the dependency relationship to obtain the production logistics space features.

[0174] To this end, the above-mentioned functional association identification and logistics flow analysis, as well as the processing process of integrating the regional characteristics of the production equipment with the dependency relationship between the production station and the logistics node, have the following technical benefits:

[0175] (1) Accurately identify upstream and downstream relationships: Through functional association identification, the upstream and downstream relationships between workstations in the production process and the service conditions of logistics nodes for specific types of workstations can be accurately identified, which helps to optimize production layout and logistics routes.

[0176] (2) Identification of key logistics paths: Logistics flow analysis uses logistics nodes as a bridge to analyze the frequency and magnitude of material transfer. It can identify the dependency between workstations and nodes on key logistics paths, providing strong support for logistics optimization.

[0177] (3) Comprehensive spatial feature fusion: By integrating the characteristics of the area where the production equipment is located with the dependency relationship between the production stations and logistics nodes, the spatial layout and logistics relationship can be comprehensively considered to obtain more comprehensive and accurate production logistics spatial characteristics, providing a more scientific basis for production management and decision-making.

[0178] (4) Application of attention mechanism: By using inter-feature attention analysis, we can identify the degree of influence of different features on the spatial characteristics of production logistics, provide guidance for feature selection and fusion, and improve the accuracy and effectiveness of feature fusion.

[0179] (5) Principal component analysis to simplify features: Through principal component analysis, the main features of the production equipment area and dependencies can be extracted, the feature dimension can be reduced, the computational complexity can be reduced, and key information can be retained.

[0180] The following is an example code to implement the above solution:

[0181]

[0182] Optionally, the obtaining of production logistics time description data to extract features thereof to obtain production logistics time features includes:

[0183] Acquire workshop production data, and parse it to obtain production plan data and order-driven data therefrom, wherein the production logistics time description data includes the production plan data and order-driven data;

[0184] Feature extraction is performed on the production plan data and order-driven data to obtain production logistics time features.

[0185] To this end, the above process of obtaining production logistics time description data and extracting its features to obtain production logistics time features has the following technical benefits:

[0186] (1) Improve data accuracy: By directly acquiring workshop production data and parsing production plan data and order-driven data, the accuracy and real-time nature of the data can be ensured, providing a reliable data foundation for subsequent logistics time feature extraction.

[0187] (2) Optimizing production plans: Production plan data is an important part of the time characteristics of production logistics. By analyzing and extracting its features, we can understand the rationality and feasibility of the production plan and provide strong support for the optimization of the production plan.

[0188] (3) Responding to market demand: Order-driven data reflects the market demand for products. By extracting features from order-driven data, we can understand the changing trend of market demand and help companies better respond to market demand and adjust production strategies.

[0189] (4) Improving logistics efficiency: The time characteristics of production logistics can reflect the efficiency and bottlenecks of production logistics. By analyzing and optimizing these characteristics, we can improve logistics efficiency, reduce production costs, and enhance the competitiveness of enterprises.

[0190] (5) Support decision making: Based on the analysis results of the time characteristics of production logistics, enterprises can formulate more scientific and reasonable production plans and logistics strategies, and improve the decision-making level of production management.

[0191] To this end, the following example code is provided:

[0192]

[0193]

[0194] Optionally, the extracting features of the production plan data and the order-driven data to obtain production logistics time features includes:

[0195] Extracting features from the production plan data and the order-driven data to obtain production plan features and order-driven features;

[0196] The production plan characteristics and order-driven characteristics are serialized to generate production logistics time characteristics;

[0197] Among them, the production plan characteristics include: production plan start time, production plan end time, production plan duration, production plan type, and production plan priority; the order-driven characteristics include: order receipt time, order demand time, order urgency, order quantity, and order product type.

[0198] To this end, the above process of extracting features from production planning data and order-driven data and serializing these features to generate production logistics time features has the following technical benefits:

[0199] (1) Clear feature definition: By clearly extracting production plan features (such as production plan start time, end time, etc.) and order-driven features (such as order receipt time, demand time, etc.), we can clearly understand the impact of these features on production logistics time, providing a clear direction for subsequent analysis and optimization.

[0200] (2) Data serialization: Serializing the extracted features makes it easy to use these features in machine learning models or other data analysis tools, facilitating batch processing and automated analysis.

[0201] (3) Improve decision-making efficiency: Based on these characteristics, enterprises can more accurately predict production logistics time, optimize production planning and order processing processes, and improve decision-making efficiency and production efficiency.

[0202] (4) Flexibility: Since feature extraction is based on common data fields, this method has certain flexibility and can adapt to production logistics data of different industries and enterprises.

[0203] (5) Scalability: As enterprises’ demand for production logistics time analysis continues to increase, new features can be easily added or existing features can be adjusted to meet more complex analysis needs.

[0204] To this end, an exemplary code for implementing the above solution is provided:

[0205]

[0206]

[0207] Optionally, performing a spatiotemporal correlation analysis of production logistics according to the spatial characteristics of production logistics and the temporal characteristics of production logistics to obtain a spatiotemporal correlation representation of production logistics;

[0208] Mapping the production logistics spatial characteristics and the production logistics time characteristics to the production logistics graph network to obtain a production logistics spatial characteristic mapping vector and a production logistics time characteristic mapping vector;

[0209] The production logistics space feature mapping vector and the production logistics time feature mapping vector are fused to obtain the production logistics space-time correlation representation.

[0210] To this end, the above process of analyzing the spatiotemporal correlation of production logistics based on the spatial characteristics and temporal characteristics of production logistics and mapping them into the production logistics graph network to obtain the spatiotemporal correlation representation of production logistics has the following technical benefits:

[0211] (1) Comprehensive spatiotemporal analysis: Taking into account both the spatial and temporal characteristics of production logistics can more comprehensively analyze the spatiotemporal correlation of production logistics and provide more accurate guidance for the optimization of the production process.

[0212] (2) Efficient use of graph networks: By mapping features to graph networks, we can take advantage of the efficient computing power and structural information of graph networks to better capture the complex relationships in production logistics.

[0213] (3) Effectiveness of feature fusion: The fusion of spatial and temporal features can produce richer representations and help describe the spatiotemporal characteristics of production logistics more accurately.

[0214] (4) Visualization and interpretability: The graph network-based representation has strong visualization potential, which helps to intuitively understand the spatiotemporal relationships of production logistics and provide interpretable analysis results.

[0215] (5) Scalability and flexibility: This method can adapt to production logistics systems of different scales and complexities. By adjusting the structure and parameters of the graph network, it can flexibly handle spatiotemporal correlation problems in different situations.

[0216] To this end, an exemplary code for implementing the above solution is provided as follows:

[0217]

[0218]

[0219] Optionally, constructing the spatiotemporal model of the production logistics state based on the spatiotemporal correlation representation of the production logistics includes:

[0220] Based on the spatiotemporal correlation characterization of production logistics, feature engineering is constructed, and based on the feature engineering, the spatiotemporal pre-training model of production logistics status is trained until the output of the spatiotemporal pre-training model of production logistics status matches the spatiotemporal label classification of production logistics status.

[0221] To this end, the above process of constructing a spatiotemporal model of production logistics status based on the spatiotemporal correlation characterization of production logistics has the following technical benefits:

[0222] (1) High adaptability: The spatiotemporal correlation representation of production logistics is preprocessed through feature engineering, so that the model can better adapt to the characteristics and needs of different production logistics systems.

[0223] (2) Accurate prediction: Using pre-trained models to make spatiotemporal predictions of production logistics status can more accurately capture the dynamic changes of the production logistics system and improve prediction accuracy.

[0224] (3) Strong generalization ability: By training the spatiotemporal pre-training model of production logistics status, it is able to automatically learn and extract key information from the spatiotemporal correlation representation of production logistics, thereby enhancing the generalization ability of the model.

[0225] (4) Interpretability: Feature engineering makes model input more explicit and interpretable, which helps to understand and analyze the complex spatiotemporal relationships within the production logistics system.

[0226] (5) Flexibility: The processing can adjust feature engineering and model training parameters according to actual needs to adapt to production logistics status prediction tasks in different scenarios.

[0227] To this end, an exemplary code for implementing the above solution is provided as follows:

[0228]

[0229]

[0230] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A method for constructing a spatiotemporal model of production logistics status, It is characterized in that include: Acquiring production logistics space description data to perform feature extraction on the production logistics space description data to obtain production logistics space features; Acquire production logistics time description data to perform feature extraction on the production logistics time description data to obtain production logistics time features; According to the production logistics spatial characteristics and the production logistics temporal characteristics, a production logistics spatiotemporal correlation analysis is performed to obtain a production logistics spatiotemporal correlation representation; Based on the spatiotemporal correlation representation of the production logistics, constructing the spatiotemporal model of the production logistics state; Wherein, the obtaining of production logistics space description data includes: Acquire workshop production data, and parse it to obtain workshop layout data and workpiece processing path data therefrom, wherein the production logistics space description data at least includes the workshop layout data and workpiece processing path data; The feature extraction of the production logistics space description data to obtain the production logistics space features includes: Based on the spatial heterogeneity constraints and spatial autocorrelation constraints of the workshop layout, feature extraction is performed on the production logistics space description data to obtain production logistics space features.

2. A method for constructing a spatiotemporal model of production logistics status according to claim 1, It is characterized in that The method further comprises: Draw workshop layout maps with different layout methods based on product variety data and output data; According to the workshop layout map, constructing spatial heterogeneity constraints of the workshop layout; The layout method includes at least one of the following: product principle layout, process principle layout, fixed product layout, grouping principle layout, and itinerant layout. In the product principle layout, production units are divided according to processing objects. In the fixed product layout, production equipment is moved to the product to be processed for processing. In the grouping principle layout, production equipment is grouped into production equipment clusters. In the itinerant layout, the product to be processed can be switched between production equipment in different product production rooms. The step of constructing the spatial heterogeneity constraint of the workshop layout according to the workshop layout map includes: According to the workshop layout map, a heterogeneity measurement is performed on the corresponding layout mode to obtain a heterogeneity measurement evaluation; According to the heterogeneity metric evaluation corresponding to different layout modes, the spatial heterogeneity constraint of the workshop layout is constructed; Among them, the heterogeneity measurement evaluation includes at least one of the following: material handling volume measurement, work-in-process quantity measurement, equipment utilization measurement, production plan complexity measurement, multi-skilled worker demand difficulty measurement, customization degree measurement, flexibility degree measurement, unit product cost degree measurement.

3. A method for constructing a spatiotemporal model of production logistics status according to claim 2, It is characterized in that The method further comprises: The spatial autocorrelation constraint is constructed according to the distance between the workstations where the production equipment is arranged and the logistics, and the dependency relationship between different logistics states in the logistics network.

4. A method for constructing a spatiotemporal model of production logistics status according to claim 1, It is characterized in that The spatial heterogeneity constraint and the spatial autocorrelation constraint based on the workshop layout are used to extract features from the production logistics space description data to obtain production logistics space features, including: Based on the spatial heterogeneity constraint of the workshop layout, feature extraction is performed on the production logistics space description data to obtain the regional characteristics of the production equipment, including regional area, equipment density, and logistics flow frequency; Based on the spatial autocorrelation constraint of the workshop layout, feature extraction is performed on the production logistics space description data to obtain the dependency relationship between the workstations where the production equipment is located and the logistics nodes; The characteristics of the area where the production equipment is located and the dependency relationship between the workstation where the production equipment is located and the logistics node are integrated to obtain the production logistics space characteristics.

5. A method for constructing a spatiotemporal model of production logistics status according to claim 4, It is characterized in that The spatial heterogeneity constraint based on the workshop layout is used to extract features from the production logistics space description data to obtain the features of the area where the production equipment is located, including: Vectorizing the production logistics space description data to obtain a production logistics space description vector; Based on the spatial heterogeneity constraint of the workshop layout, the production logistics space description vector is mapped to obtain the characteristics of the area where the production equipment is located, including the area, equipment density, and logistics flow frequency.

6. A method for constructing a spatiotemporal model of production logistics status according to claim 5, It is characterized in that The spatial heterogeneity constraint based on the workshop layout is used to map the production logistics space description vector to obtain the regional characteristics of the production equipment, including the regional area, equipment density, and logistics flow frequency, including: Based on the spatial heterogeneity constraint of the workshop layout, the production logistics space description vector is calibrated to a regional feature label to map the production logistics space description vector feature to a multi-scale representation feature; Hierarchical clustering analysis and spatial statistical analysis are performed on the multi-scale characterization features to obtain the characteristics of the area where the production equipment is located, including the area, equipment density, and logistics flow frequency.

7. A method for constructing a spatiotemporal model of production logistics status according to claim 4, It is characterized in that The spatial autocorrelation constraint based on the workshop layout is used to extract features from the production logistics space description data to obtain the dependency relationship between the workstations where the production equipment is located and the logistics nodes, including: Based on the spatial autocorrelation constraints of the workshop layout, the spatial autocorrelation measurement parameters are constructed; According to the spatial autocorrelation measurement parameter, neighborhood correlation analysis is performed on the production logistics spatial description data to obtain spatial aggregation pattern statistics; According to the statistics of the spatial aggregation pattern, predict the dependency relationship between the workstations where the production equipment is located and the logistics nodes; The spatial autocorrelation constraint based on the workshop layout is used to construct the spatial autocorrelation measurement parameter, including: According to the location coordinates of production equipment, the location coordinates of logistics nodes and the layout information of production lines, based on the spatial autocorrelation constraints of workshop layout, neighborhood aggregation measurement parameters, kernel density functions and logistics flow path measurement parameters are constructed; Wherein, the neighborhood correlation analysis is performed on the production logistics spatial description data according to the spatial autocorrelation measurement parameter to obtain spatial aggregation pattern statistics, including: Constructing a spatial association matrix according to the neighborhood aggregation measurement parameters, the kernel density function, and the logistics flow path measurement parameters; Based on the spatial association matrix, the production logistics spatial description data is subjected to neighborhood association analysis and mapping processing to obtain spatial aggregation pattern statistics.

8. A method for constructing a spatiotemporal model of production logistics status according to claim 7, It is characterized in that The predicting the dependency relationship between the workstations where the production equipment is located and the logistics nodes according to the statistics of the spatial aggregation pattern includes: According to the statistics of the spatial aggregation pattern, each workstation and logistics node is assigned a corresponding cluster label; Based on the description of production synergy effects, the cluster labels assigned to each workstation and logistics node are used for functional association identification and logistics flow analysis to predict the dependency relationship between the workstation where the production equipment is located and the logistics node.

9. A method for constructing a spatiotemporal model of production logistics status according to claim 7, It is characterized in that The functional association identification is as follows: within each cluster, the functional association identification analyzes the functions of the workstations and the service types of the logistics nodes, identifies which workstations are upstream and downstream in the production process, and which logistics nodes mainly serve specific types of workstations; The logistics flow analysis is: using logistics nodes as bridges, analyzing the frequency and magnitude of material transfer from one cluster to another, and identifying the dependencies between workstations and nodes on key logistics paths.

Citation Information

Patent Citations

  • Spatial clustering feature extraction method for incoming logistics cluster

    CN112365217A

  • Time-space-based workshop dynamic bottleneck prediction method

    CN116739156A

  • Composite disaster knowledge platform construction method and system based on spatial-temporal characteristics

    CN118246539A

  • Controlling asynchronous fusion of spatio-temporal multimodal data

    WO2022212031A1

Cited By

  • Adaptive well tie-in system

    US20260203836A1