Indoor warehouse material inventory and spatial positioning method based on improved cuckoo algorithm

Abstract

The present invention provides an indoor warehouse material inventory and spatial positioning method based on an improved cuckoo algorithm, which relates to the technical field of intelligent management of warehouse logistics. The method includes acquiring an indoor warehouse environment and constructing a three-dimensional model to determine candidate sensor points and a target material storage point set; introducing point constraint conditions, an error correction mechanism, a hybrid search optimization strategy, and an incremental node strategy to generate an improved cuckoo algorithm; establishing a single sensor error model to calculate the single sensor positioning error, and then calculating the multi-sensor joint positioning error and determining the positioning accuracy standard; based on the improved cuckoo algorithm, constructing an initialization solution vector through binary coding, iterating the solution vector through a fitness function and a dual point placement target to generate an optimal sensor point set, thereby optimizing the sensor point placement plan, improving the efficiency and accuracy of material inventory, meeting the industry's positioning accuracy requirements, reducing equipment deployment costs, and improving the automation level of warehouse material management.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent management of warehousing and logistics, and in particular to an indoor warehousing material inventory and spatial positioning method based on an improved cuckoo algorithm. Background Art

[0002] In modern warehousing systems, traditional manual inventory and space management methods are no longer able to meet the needs of efficient and accurate operations due to problems such as low efficiency, large data errors, and management loopholes.

[0003] In addition, existing technologies do not fully consider the physical constraints in the warehouse environment, such as shelf occlusion and obstacle distribution, which leads to large positioning errors; the standard cuckoo search algorithm often relies on idealized search space assumptions and is prone to falling into local optimality in complex warehouse topology structures, with slow convergence and poor stability; existing technologies lack systematic sensor deployment optimization strategies, making it difficult to minimize the number of devices while meeting accuracy requirements, which leads to high sensor deployment costs.

[0004] Therefore, it is necessary to provide an indoor warehouse material inventory and spatial positioning method based on the improved cuckoo algorithm to solve the above technical problems. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention provides an indoor warehouse material inventory and spatial positioning method based on an improved cuckoo algorithm, which is used to solve the problems of insufficient positioning accuracy, weak environmental adaptability and high sensor deployment cost of traditional indoor warehouse material inventory and spatial positioning methods.

[0006] The present invention provides an indoor warehouse material inventory and spatial positioning method based on an improved cuckoo algorithm, the method comprising:

[0007] Acquire an indoor storage environment, construct a three-dimensional storage environment model corresponding to the indoor storage environment using three-dimensional laser scanning technology, and determine a set of candidate sensor points and a set of target material storage points;

[0008] Based on the standard cuckoo algorithm, the improved cuckoo algorithm is generated by introducing the placement constraints, error correction mechanism, hybrid search optimization strategy and incremental node strategy.

[0009] Establishing a single sensor error model based on Euclidean distance and calculating the single sensor positioning error contribution, calculating the multi-sensor joint positioning error based on the single sensor error contribution using a weighted covariance formula, and determining a positioning accuracy standard based on the multi-sensor joint positioning error;

[0010] Based on the improved cuckoo algorithm, the three-dimensional warehouse environment model, the candidate sensor point set, the target material storage point set and the positioning accuracy standard are imported, an initialization solution vector is constructed through binary coding, and the initialization solution vector is iteratively updated through the fitness function and the corresponding dual point target to generate the optimal sensor point set.

[0011] Preferably, the acquiring of the indoor storage environment, constructing a three-dimensional storage environment model corresponding to the indoor storage environment using three-dimensional laser scanning technology, and determining a set of candidate sensor points and a set of target material storage points specifically include:

[0012] Acquire the indoor storage environment, determine the physical structure of the indoor storage environment using the three-dimensional laser scanning technology, and mark the shelf coordinates, aisle directions, and obstacle areas to generate the three-dimensional storage environment model;

[0013] Based on the three-dimensional warehouse environment model, multiple sensor installation locations are determined to form the candidate sensor point set, and the coordinates of the material storage area are marked to form the target material storage point set.

[0014] Preferably, the placement constraints include signal shielding rules, sensor installation height restrictions, and warehouse operation process constraints; the error correction mechanism obtains historical positioning data by establishing a real-time error feedback link, and calibrates the parameters of the single sensor error model; the hybrid search optimization strategy includes a global search strategy and a local optimization strategy, the global search strategy explores the sensor placement scheme through the Levy flight mechanism, and the local optimization strategy introduces a neighborhood search operator to refine the sensor placement scheme; the incremental node strategy dynamically adjusts the search granularity according to the scale of the indoor storage environment.

[0015] Preferably, establishing a single sensor error model based on Euclidean distance and calculating the single sensor positioning error contribution specifically includes:

[0016] Based on the single sensor error model, the candidate sensor points in the candidate sensor point set S are calculated. and the target material storage point in the target material storage point set T Euclidean distance :

[0017] Where, Represents candidate sensor locations Target material storage point The Euclidean distance of

[0018] Based on the Euclidean distance , calculate the single sensor positioning error contribution :

[0019] Where, represents the distance attenuation coefficient; represents the basic error term.

[0020] Preferably, the calculating of the multi-sensor joint positioning error based on the single sensor error contribution by using a weighted covariance formula, and determining the positioning accuracy standard based on the multi-sensor joint positioning error, specifically includes:

[0021] The target material storage point At the same time, k candidate sensors are deployed Based on the maximum likelihood estimation theory, the single sensor positioning error contribution of all the inventory sensors is calculated. The weighted harmonic mean of the multi-sensor joint positioning error is :

[0022] Based on the multi-sensor joint positioning error Constructing a set of candidate positioning accuracy , select the minimum value in the candidate positioning accuracy set A as the positioning accuracy standard .

[0023] Preferably, the improved cuckoo algorithm is based on importing the three-dimensional warehouse environment model, the candidate sensor point set, the target material storage point set, and the positioning accuracy standard, constructing an initialization solution vector through binary coding, and iteratively updating the initialization solution vector through a fitness function and a corresponding dual point target to generate an optimal sensor point set, specifically including:

[0024] The three-dimensional storage environment model, the candidate sensor point set S, the target material storage point set T and the positioning accuracy standard Importing the improved cuckoo algorithm;

[0025] Using the binary encoding Indicates the result of point selection. Indicates the candidate sensor locations The inventory sensors are deployed at Indicates the candidate sensor locations The inventory sensor is not deployed at the location, and the initialization solution vector is constructed , represents the candidate sensor points in the candidate sensor point set S The number of, and the solution space size of the initialization solution vector X is ;

[0026] The point selection result in the initialization solution vector X is iteratively updated through the fitness function and the corresponding dual point selection target , until the preset convergence condition of the improved cuckoo algorithm is met, the fitness function and the corresponding dual point distribution objective are expressed as follows:

[0027] Where, Indicates the result of point selection The fitness function value of represents the number of optimal sensor points in the optimal sensor point set A; represents the penalty coefficient; Indicates the result of point selection Corresponding multi-sensor joint positioning error ; max means taking the maximum value.

[0028] Preferably, the preset convergence condition of the improved cuckoo algorithm is that the fitness change degree of the fitness function value of consecutive v generations is less than a preset threshold , the corresponding expression is as follows:

[0029] Where, Represents the fitness function value of the uth generation; Represents the fitness function value of the uvth generation.

[0030] An indoor material inventory and spatial positioning system based on an improved cuckoo algorithm, the system comprising:

[0031] The sensor point placement and material storage point determination module is used to obtain the indoor storage environment, construct a 3D storage environment model corresponding to the indoor storage environment using 3D laser scanning technology, and determine the candidate sensor point set and target material storage point set;

[0032] Improved Cuckoo Algorithm Setting Module, which is used to generate an improved Cuckoo Algorithm based on the standard Cuckoo Algorithm by introducing placement constraints, error correction mechanism, hybrid search optimization strategy, and incremental node strategy;

[0033] a positioning error and accuracy standard calculation module, configured to establish a single sensor error model based on Euclidean distance and calculate the single sensor positioning error contribution, calculate the multi-sensor joint positioning error based on the single sensor error contribution using a weighted covariance formula, and determine the positioning accuracy standard based on the multi-sensor joint positioning error;

[0034] The optimal sensor point set generation module is used to import the three-dimensional warehouse environment model, the candidate sensor point set, the target material storage point set and the positioning accuracy standard based on the improved cuckoo algorithm, construct an initialization solution vector through binary coding, and iteratively update the initialization solution vector through the fitness function and the corresponding dual point target to generate the optimal sensor point set.

[0035] An electronic device includes a memory and a processor, wherein the memory stores a computer program. When the processor runs the computer program stored in the memory, the processor executes the steps of the indoor warehouse material inventory and spatial positioning method based on the improved cuckoo algorithm as described above.

[0036] A readable storage medium stores a computer program, which, when executed by a processor, is used to implement the steps of the indoor warehouse material inventory and spatial positioning method based on the improved cuckoo algorithm as described above.

[0037] Compared with related technologies, the indoor warehouse material inventory and spatial positioning method based on the improved cuckoo algorithm provided by the present invention has the following beneficial effects:

[0038] The present invention acquires the indoor storage environment, constructs a three-dimensional storage environment model corresponding to the indoor storage environment using three-dimensional laser scanning technology, and determines a candidate sensor point set and a target material storage point set; based on the standard cuckoo algorithm, introduces point constraint conditions, error correction mechanism, hybrid search optimization strategy and incremental node strategy to generate an improved cuckoo algorithm; establishes a single sensor error model based on Euclidean distance and calculates the single sensor positioning error contribution, adopts a weighted covariance formula to calculate the multi-sensor joint positioning error based on the single sensor error contribution, and determines the positioning accuracy standard based on the multi-sensor joint positioning error; based on the improved cuckoo algorithm, imports the three-dimensional storage environment model, the candidate sensor point set, the target material storage point set and the positioning accuracy standard, constructs an initialization solution vector through binary coding, and iteratively updates the initialization solution vector through the fitness function and the corresponding dual point target to generate the optimal sensor point set, thereby realizing intelligent optimization of the sensor point solution, improving the efficiency and accuracy of material inventory, significantly reducing equipment deployment costs while meeting the industry's positioning accuracy requirements, and improving the automation and precision of warehouse material management.

[0039] The present invention, by constructing a three-dimensional warehouse environment model, calculating the multi-sensor joint positioning error, and applying an improved cuckoo algorithm, combined with indoor positioning technology and intelligent recognition means, can optimize the number of sensors and the layout plan, reduce equipment deployment costs, and achieve real-time positioning and automatic inventory of goods, reduce manual intervention, improve long-term positioning stability, improve the intelligent level of warehouse management, and promote the development of smart logistics for enterprises. The method of the present invention can solve the problem that traditional manual inventory methods are time-consuming and error-prone. Through intelligent inventory technology, goods are accurately positioned, real-time data synchronization is achieved, the accuracy of material inventory and spatial positioning is improved, positioning errors are ensured to be less than industry standards, and the accuracy and update efficiency of inventory information are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A flowchart of an indoor warehouse material inventory and spatial positioning method based on an improved cuckoo algorithm provided in an embodiment of the present invention;

[0041] Figure 2 A system block diagram of an indoor material inventory and spatial positioning system based on an improved cuckoo algorithm provided by an embodiment of the present invention;

[0042] Figure 3 A schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0044] like Figure 1 FIG. 1 is a flow chart of an indoor storage material inventory and spatial positioning method based on an improved cuckoo algorithm provided by an embodiment of the present invention. Figure 1The execution subject of the method shown may be a software and / or hardware device. The execution subject of the present application may include but is not limited to at least one of the following: user equipment, network equipment, etc. Among them, user equipment may include but is not limited to computers, smart phones, personal digital assistants (PDAs) and the electronic devices mentioned above. Network equipment may include but is not limited to a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers, wherein cloud computing is a type of distributed computing, a super virtual computer composed of a group of loosely coupled computers. This embodiment does not limit this. It includes steps S1 to S4, as follows:

[0045] S1, obtaining an indoor storage environment, constructing a 3D storage environment model corresponding to the indoor storage environment using 3D laser scanning technology, and determining a set of candidate sensor points and a set of target material storage points;

[0046] An indoor warehouse environment refers to the physical space used for storing and managing materials, with clear functional divisions, spatial structures, and business processes. 3D laser scanning technology is a spatial data acquisition technique based on the principle of laser ranging. By emitting a laser beam and measuring the time or phase difference of the reflected signal, it obtains the three-dimensional coordinates and reflection intensity of an object's surface, generating high-density point cloud data. In warehousing scenarios, this technology is used to construct an accurate digital model of the indoor warehouse environment, including spatial features such as shelf outlines, aisle orientation, and obstacle distribution. This provides the geometric constraints of the physical space for subsequent sensor deployment and positioning algorithms. A 3D warehouse environment model is a parametric model constructed based on 3D laser scanning data. Through techniques such as point cloud processing and surface reconstruction, the warehouse environment can be abstracted into a digital entity consisting of spatial coordinates, object attributes, and topological relationships. Object attributes include shelf height and material, and topological relationships include aisle connectivity. This model serves as the spatial basis for the improved Cuckoo algorithm, supporting geometric operations such as distance calculation and collision detection, as well as signal propagation simulation, such as multipath analysis.

[0047] Furthermore, the candidate sensor point set is a finite set of all available sensor installation locations within the warehouse environment, typically selected based on building structure and signal coverage requirements, including building structure such as ceiling keels and column surfaces, and signal coverage requirements such as unobstructed field of view. The target material storage point set refers to the collection of fixed or dynamic material storage locations within the warehouse environment, with each target material storage point corresponding to the actual storage coordinates of the material.

[0048] In indoor warehouse environments, 3D laser scanning technology can be used to accurately measure the spatial structure and object distribution of the indoor warehouse environment. By processing and analyzing the scanned data, a corresponding 3D warehouse environment model can be constructed. This model can intuitively represent the layout of the warehouse space, including the location of shelves, the orientation of aisles, and the distribution of other obstacles. This can then be used to determine the set of candidate sensor locations and the set of target material storage points.

[0049] S2, based on the standard cuckoo algorithm, introduces point placement constraints, error correction mechanism, hybrid search optimization strategy and incremental node strategy to generate an improved cuckoo algorithm;

[0050] Understandably, the standard cuckoo algorithm is a metaheuristic optimization algorithm that simulates the parasitic behavior of cuckoos. It generates new solutions through the Levy flight mechanism and updates the population through the host bird expulsion mechanism, achieving global search. While the standard cuckoo algorithm assumes an unconstrained search space and is suitable for continuous optimization problems, it suffers from inadequate physical constraint modeling and weak local development capabilities when optimizing discrete warehouse locations.

[0051] Specifically, placement constraints refer to the constraints on sensor installation locations within a warehouse environment. These constraints are set based on the actual warehouse environment and engineering requirements. For example, sensors cannot be installed in certain areas, or their installation locations must meet preset height and angle restrictions. The error correction mechanism is a dynamic parameter calibration mechanism based on real-time positioning error data. By analyzing and processing the errors generated in actual measurements, this mechanism adjusts relevant parameters in the standard cuckoo algorithm, thereby improving positioning accuracy and reducing the impact of errors on the positioning results. The hybrid search optimization strategy is a composite optimization strategy that combines global search and local exploration. This strategy combines different search methods, integrating the advantages of global and local search, allowing the algorithm to both broadly explore the search space and perform fine-grained optimization in local areas when seeking the optimal solution. The incremental node strategy is an adaptive optimization strategy tailored to warehouse environments of varying sizes. It dynamically adjusts the number and method of search nodes based on the scale and characteristics of the warehouse environment, thereby improving the algorithm's efficiency and adaptability. By introducing these improved mechanisms into the standard cuckoo algorithm, an improved cuckoo algorithm can be generated.

[0052] S3, establishing a single sensor error model based on Euclidean distance and calculating the single sensor positioning error contribution, calculating the multi-sensor joint positioning error based on the single sensor error contribution using a weighted covariance formula, and determining a positioning accuracy standard based on the multi-sensor joint positioning error;

[0053] In practical applications, Euclidean distance refers to the straight-line distance between two points in three-dimensional space. It serves as a fundamental parameter for single-sensor error modeling, reflecting the physical separation between the sensor and the target point and positively correlated with signal propagation loss. A single-sensor error model is a model used to calculate the contribution of a single sensor to the positioning error of a target point. The weighted covariance formula is a joint evaluation formula for calculating the positioning errors of multiple sensors. It takes into account the correlation and weighting between the errors of different sensors, enabling a more accurate assessment of the positioning errors of multiple sensors. The positioning accuracy standard refers to the standard value of positioning accuracy.

[0054] S4, based on the improved cuckoo algorithm, import the three-dimensional warehouse environment model, the candidate sensor point set, the target material storage point set and the positioning accuracy standard, construct an initialization solution vector through binary coding, and iteratively update the initialization solution vector through the fitness function and the corresponding dual point target to generate the optimal sensor point set.

[0055] The initialization solution vector is the initial input to the improved Cuckoo algorithm. It can be generated randomly or through heuristic methods, such as prioritizing the deployment of high-coverage points. This solution vector serves as the starting point for subsequent algorithm optimization and must satisfy placement constraints to avoid invalid computations. The fitness function is a quantitative function used to evaluate the quality of sensor placement schemes. The dual placement objective is the combination of optimization goals of the improved Cuckoo algorithm: minimizing the number of sensors and maximizing the positioning accuracy rate.

[0056] Finally, the improved Cuckoo algorithm takes as input the 3D warehouse environment model, the candidate sensor placement set, the target material storage point set, and the positioning accuracy standard. An initial solution vector is constructed using binary encoding. Binary encoding is a method of representing the solution to a problem as a binary string, where each bit corresponds to a candidate placement location, with 0 indicating that the location is not selected and 1 indicating that it is selected. The initial solution vector is then iteratively updated using a fitness function and the corresponding dual placement objective, ultimately generating an optimal sensor placement set. This set minimizes the number of sensors used while meeting the positioning accuracy standard, achieving a balance between cost and performance.

[0057] In the specific implementation process, the indoor storage environment is acquired, a three-dimensional storage environment model corresponding to the indoor storage environment is constructed using three-dimensional laser scanning technology, and a candidate sensor point set and a target material storage point set are determined, specifically including:

[0058] Acquire the indoor storage environment, determine the physical structure of the indoor storage environment using the three-dimensional laser scanning technology, and mark the shelf coordinates, aisle directions, and obstacle areas to generate the three-dimensional storage environment model;

[0059] Based on the three-dimensional warehouse environment model, multiple sensor installation locations are determined to form the candidate sensor point set, and the coordinates of the material storage area are marked to form the target material storage point set.

[0060] In the digital construction and positioning system deployment of indoor warehouse environments, after acquiring the target environment, 3D laser scanning technology can be used to achieve precise modeling and data annotation of the physical space. First, 3D laser scanning technology can be used to conduct comprehensive data collection of the indoor warehouse environment. The 3D coordinate information of each object in the space can be obtained through the principle of laser ranging, and then the physical structure of the warehouse environment can be analyzed, including the spatial coordinates of the shelves, the distribution direction of the aisles, and the location and outline of the obstacle areas. Based on this data, a 3D warehouse environment model containing geometric features and topological relationships can be constructed. This model can intuitively reflect the three-dimensional layout of the warehouse space and provide basic spatial data for subsequent sensor deployment and positioning algorithms.

[0061] After completing the 3D model, it is necessary to further determine candidate locations for sensor deployment and target areas for material positioning. Based on the 3D warehouse environment model, combined with signal coverage requirements, equipment installation feasibility (such as load-bearing restrictions and wiring convenience), and warehouse operation processes, multiple qualified sensor installation locations are screened within the space to form a set of candidate sensor points. These locations need to effectively cover the material storage area while avoiding unfavorable factors such as obstruction. At the same time, by analyzing the material storage rules and historical data in the warehouse management system, the specific coordinates of the material storage area are marked to form a set of target material storage points, clarifying the key areas that require precise positioning.

[0062] 3D laser scanning technology enables digital mapping of the warehouse environment. Combining engineering constraints with business needs enables pre-planning of sensor locations and material storage points. This provides a structured spatial data foundation and optimization targets for subsequent positioning optimization based on the improved cuckoo algorithm, ensuring that the sensor deployment plan complies with both physical environmental constraints and the accuracy and coverage requirements for material positioning.

[0063] The placement constraints include signal blocking rules, sensor installation height restrictions, and warehouse operation process constraints; the error correction mechanism obtains historical positioning data by establishing a real-time error feedback link and calibrates the parameters of the single sensor error model; the hybrid search optimization strategy includes a global search strategy and a local optimization strategy. The global search strategy explores the sensor placement scheme through the Levy flight mechanism, and the local optimization strategy introduces a neighborhood search operator to refine the sensor placement scheme; the incremental node strategy dynamically adjusts the search granularity according to the scale of the indoor storage environment.

[0064] It should be noted that material location methods based on intelligent optimization algorithms can effectively overcome the limitations of traditional rule-based location methods and improve the utilization of spatial resources. However, the standard Cuckoo Search (CS) algorithm, also known as the existing Cuckoo Search algorithm, has the following main problems when applied in actual warehousing scenarios:

[0065] The search space assumptions of the standard cuckoo algorithm are too idealized and fail to fully consider the physical constraints of the warehouse environment, which leads to low feasibility of the search results; the positioning accuracy of the algorithm is difficult to meet the needs of warehouse scenarios, and it lacks an error correction mechanism, which may cause large positioning deviations in complex warehouse environments; the global search and local search capabilities of the algorithm are unbalanced, and it often relies on Levy flight for global search, but it is easy to fall into local optimality in high-dimensional optimization problems, affecting the convergence speed and solution stability; due to the significant differences in the topological structure of the warehouse environment, the single optimization strategy of the algorithm is difficult to meet the optimization needs of warehouses of different sizes.

[0066] To address the above issues, the present invention constructs an improved Cuckoo Search (ICS) algorithm. By setting placement constraints, introducing an error correction mechanism, combining local optimization with global optimization operators, and adopting an incremental node optimization strategy, it can perform adaptive optimization in warehouse environments of different sizes, ultimately forming an optimal sensor placement pattern and improving the accuracy and robustness of warehouse material positioning.

[0067] The step of establishing a single sensor error model based on Euclidean distance and calculating the single sensor positioning error contribution specifically includes:

[0068] Based on the single sensor error model, the candidate sensor points in the candidate sensor point set S are calculated. and the target material storage point in the target material storage point set T Euclidean distance :

[0069] Where, Represents candidate sensor locations Target material storage point The Euclidean distance of

[0070] Based on the Euclidean distance , calculate the single sensor positioning error contribution :

[0071] Where, represents the distance attenuation coefficient; represents the basic error term.

[0072] The method of calculating the multi-sensor joint positioning error based on the single sensor error contribution by using a weighted covariance formula, and determining the positioning accuracy standard based on the multi-sensor joint positioning error, specifically includes:

[0073] The target material storage point At the same time, k candidate sensors are deployed Based on the maximum likelihood estimation theory, the single sensor positioning error contribution of all the inventory sensors is calculated. The weighted harmonic mean of the multi-sensor joint positioning error is :

[0074] Based on the multi-sensor joint positioning error Constructing a set of candidate positioning accuracy , select the minimum value in the candidate positioning accuracy set A as the positioning accuracy standard .

[0075] It's important to note that for each candidate sensor point set and target material storage point set, the spatial distance between any candidate sensor point and the target material storage point must be calculated. Euclidean distance, representing the straight-line distance between two points in three-dimensional space, is used as the metric for measuring the spatial separation between them. This distance directly reflects the physical separation between the sensor and the target point and is a key parameter for evaluating signal propagation loss.

[0076] Then, a single-sensor error model can be established based on Euclidean distance. This model describes the linear relationship between distance and positioning error. The distance attenuation coefficient represents the error increment per unit distance, reflecting the rate at which signal strength decays with increasing distance. The basic error term incorporates inherent sensor device errors, multipath effects, and other environmental interference factors. This model can be used to convert spatial distance into the positioning error contribution of a single sensor to a target point, providing foundational data for multi-sensor error fusion.

[0077] Furthermore, when a target material storage point is observed simultaneously by multiple inventory sensors, a weighted covariance method can be used to calculate the joint positioning error. Based on maximum likelihood estimation theory, the errors are weighted by the inverse square of each individual sensor's error contribution. Sensors with smaller errors are given greater weight, indicating a higher confidence level in the positioning result; conversely, sensors with larger errors are given smaller weights. In this way, the multi-sensor joint positioning error comprehensively reflects the accuracy contributions of all observing sensors, optimizing the positioning results.

[0078] Finally, a candidate accuracy set can be constructed based on the multi-sensor joint positioning error. This set contains the joint error values ​​corresponding to all target material storage points. By selecting the minimum value in the candidate accuracy set as the positioning accuracy standard, it is ensured that the positioning error of all target points in the storage environment does not exceed this threshold, thus meeting the highest accuracy requirements.

[0079] A quantitative model of single-sensor error is established through Euclidean distance, and weighted covariance is used to achieve fusion optimization of multi-sensor errors. The minimum joint error is used as the benchmark for positioning accuracy, forming a complete technical chain of single-sensor modeling, multi-sensor collaboration, and accuracy standard establishment. The above method fully considers the spatial relationship between the sensor and the target point, improves the reliability of the positioning results through the weight distribution mechanism, and ultimately provides a scientific accuracy assessment basis for sensor layout optimization, ensuring that high-precision requirements are achieved while meeting engineering constraints.

[0080] The improved cuckoo algorithm, based on which the three-dimensional warehouse environment model, the candidate sensor point set, the target material storage point set, and the positioning accuracy standard are imported, an initialization solution vector is constructed through binary coding, and the initialization solution vector is iteratively updated through a fitness function and a corresponding dual point target to generate an optimal sensor point set, specifically includes:

[0081] The three-dimensional storage environment model, the candidate sensor point set S, the target material storage point set T and the positioning accuracy standard Importing the improved cuckoo algorithm;

[0082] Using the binary encoding Indicates the result of point selection. Indicates the candidate sensor locations The inventory sensors are deployed at Indicates the candidate sensor locations The inventory sensor is not deployed at the location, and the initialization solution vector is constructed , represents the candidate sensor points in the candidate sensor point set S The number of, and the solution space size of the initialization solution vector X is ;

[0083] The point selection result in the initialization solution vector X is iteratively updated through the fitness function and the corresponding dual point selection target , until the preset convergence condition of the improved cuckoo algorithm is met, the fitness function and the corresponding dual point distribution objective are expressed as follows:

[0084] Where, Indicates the result of point selection The fitness function value of represents the number of optimal sensor points in the optimal sensor point set A; represents the penalty coefficient; Indicates the result of point selection Corresponding multi-sensor joint positioning error ; max means taking the maximum value.

[0085] The preset convergence condition of the improved cuckoo algorithm is that the fitness change degree of the fitness function value of consecutive v generations is less than the preset threshold , the corresponding expression is as follows:

[0086] Where, Represents the fitness function value of the uth generation; Represents the fitness function value of the uvth generation.

[0087] The improved Cuckoo Algorithm can be fed with a pre-processed 3D warehouse environment model, a set of candidate sensor locations, a set of target material storage locations, and a positioning accuracy standard. The 3D warehouse environment model includes spatial features such as shelf layout, aisle orientation, and obstacle distribution; the candidate sensor location set is a set of locations that meet the installation requirements; the target material storage location set specifies the material area to be located; and the positioning accuracy standard specifies the maximum allowable positioning error threshold.

[0088] Secondly, a binary encoding strategy can be used to construct the initialization solution vector. This encoding method uses binary values ​​to represent the selection status of candidate locations, where the value 1 indicates that the inventory sensor is deployed at the corresponding location, and 0 indicates that it is not deployed. The dimension of the initialization solution vector is consistent with the number of candidate locations, forming a solution space that contains all possible location combinations, and its size grows exponentially with the number of candidate locations. For example, if the number of candidate locations is 100, the size of the solution space is , covering all possible sensor deployment scenarios.

[0089] During the iterative optimization phase, the initialized solution vector is evaluated and updated using the fitness function. The design of the fitness function needs to balance the dual deployment objectives, namely minimizing the number of sensor deployments to reduce costs while ensuring that the positioning errors of all target points meet the accuracy requirements. Specifically, the fitness function value consists of two parts: one is the number of sensors currently selected, which is used to measure the deployment cost; the other is the penalty term for exceeding the positioning error limit. This penalty term is calculated based on the difference between the joint positioning error of multiple sensors and the accuracy standard. If the error of a target point exceeds the threshold, the penalty term will increase linearly with the amount of excess. This design allows the improved cuckoo algorithm to prioritize solutions that both meet accuracy requirements and minimize the number of sensors.

[0090] It's important to note that the improved cuckoo algorithm updates the solution vector by simulating cuckoo egg-laying behavior and the host bird expulsion mechanism. This involves using the Lévy flight mechanism to generate new placement combinations, simulating a global search, and then fine-tuning the current optimal solution through a local neighborhood search to improve solution quality. This combination of two search strategies allows the improved cuckoo algorithm to explore a broader solution space while also performing deep optimization in local areas, avoiding being trapped in local optima.

[0091] The convergence condition for the improved cuckoo algorithm is based on the magnitude of the change in the fitness function value. Specifically, the algorithm is considered converged when the change in the fitness function value for v consecutive generations is less than a preset threshold. This condition determines whether the algorithm has reached an optimal solution or has stagnated by comparing the fitness function value for the current generation with that for v generations before. If the convergence condition is met, the algorithm terminates and outputs the optimal sensor point layout; otherwise, it continues iterating until the maximum number of iterations is reached.

[0092] By using digital model input, binary coding to represent the solution space, a fitness function to quantify the optimization objective, and a hybrid search strategy to improve optimization efficiency, a deployment plan with the minimum number of sensors can be generated while maintaining positioning accuracy. This allows the physical constraints of the warehouse environment, signal propagation characteristics, and optimization objectives to be integrated into a unified improved cuckoo algorithm framework. An adaptive iterative mechanism enables multi-objective optimization under complex constraints, providing a scientific solution for sensor deployment in intelligent warehousing systems. In practical applications, this can significantly reduce hardware costs, improve positioning accuracy, adapt to the dynamic adjustment needs of warehouse environments of varying sizes, and enhance the automation and intelligence of warehouse management.

[0093] like Figure 2 FIG. 1 is a system block diagram of an indoor material inventory and spatial positioning system based on an improved cuckoo algorithm provided by an embodiment of the present invention. The system includes:

[0094] The sensor point placement and material storage point determination module is used to obtain the indoor storage environment, construct a 3D storage environment model corresponding to the indoor storage environment using 3D laser scanning technology, and determine the candidate sensor point set and target material storage point set;

[0095] Improved Cuckoo Algorithm Setting Module, which is used to generate an improved Cuckoo Algorithm based on the standard Cuckoo Algorithm by introducing placement constraints, error correction mechanism, hybrid search optimization strategy, and incremental node strategy;

[0096] a positioning error and accuracy standard calculation module, configured to establish a single sensor error model based on Euclidean distance and calculate the single sensor positioning error contribution, calculate the multi-sensor joint positioning error based on the single sensor error contribution using a weighted covariance formula, and determine the positioning accuracy standard based on the multi-sensor joint positioning error;

[0097] The optimal sensor point set generation module is used to import the three-dimensional warehouse environment model, the candidate sensor point set, the target material storage point set and the positioning accuracy standard based on the improved cuckoo algorithm, construct an initialization solution vector through binary coding, and iteratively update the initialization solution vector through the fitness function and the corresponding dual point target to generate the optimal sensor point set.

[0098] Figure 2 The apparatus of the embodiment shown can be used to perform Figure 1 The implementation principles and technical effects of the steps in the method embodiment shown are similar and will not be repeated here.

[0099] An electronic device includes a memory and a processor, wherein the memory stores a computer program. When the processor runs the computer program stored in the memory, the processor executes the steps of the indoor warehouse material inventory and spatial positioning method based on the improved cuckoo algorithm as described above.

[0100] like Figure 3 FIG. 1 is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. The electronic device 30 includes: a processor 31, a memory 32 and a computer program;

[0101] The memory 32 is used to store the computer program, which may also be a flash memory. The computer program is, for example, an application program or a functional module for implementing the above method.

[0102] The processor 31 is configured to execute the computer program stored in the memory to implement the various steps performed by the device in the above method. For details, please refer to the relevant description in the above method embodiment.

[0103] Optionally, the memory 32 may be independent or integrated with the processor 31 .

[0104] When the memory 32 is a device independent of the processor 31, the device may further include:

[0105] The bus 33 is used to connect the memory 32 and the processor 31 .

[0106] A readable storage medium stores a computer program, which, when executed by a processor, is used to implement the steps of the indoor warehouse material inventory and spatial positioning method based on the improved cuckoo algorithm as described above.

[0107] The readable storage medium may be a computer storage medium or a communication medium. Communication media include any medium that facilitates the transfer of computer programs from one location to another. Computer storage media may be any available medium that can be accessed by a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may be located in an application-specific integrated circuit (ASIC). In addition, the ASIC may be located in a user device. Of course, the processor and the readable storage medium may also exist as discrete components in a communication device. The readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0108] The present invention also provides a program product, which includes execution instructions stored in a readable storage medium. At least one processor of a device can read the execution instructions from the readable storage medium, and at least one processor executes the execution instructions so that the device implements the methods provided in the various embodiments described above.

[0109] In the embodiments of the above-mentioned devices, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASICs), etc. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly executed by a hardware processor or by a combination of hardware and software modules within the processor.

[0110] Through the introduction of the above embodiments, the present invention adopts an indoor storage material inventory and spatial positioning method based on the improved cuckoo algorithm, obtains the indoor storage environment, adopts three-dimensional laser scanning technology to construct a three-dimensional storage environment model corresponding to the indoor storage environment, and determines the candidate sensor point set and the target material storage point set; based on the standard cuckoo algorithm, introduces point constraint conditions, error correction mechanism, hybrid search optimization strategy and incremental node strategy to generate an improved cuckoo algorithm; establishes a single sensor error model based on Euclidean distance and calculates the single sensor positioning error contribution, and adopts the weighted covariance formula to calculate the multi-sensor error contribution based on the single sensor error contribution The joint positioning error of multiple sensors is calculated, and the positioning accuracy standard is determined based on the joint positioning error of multiple sensors. Based on the improved cuckoo algorithm, the three-dimensional warehouse environment model, the candidate sensor point set, the target material storage point set and the positioning accuracy standard are imported, and the initialization solution vector is constructed through binary coding. The initialization solution vector is iteratively updated through the fitness function and the corresponding dual point target to generate the optimal sensor point set, thereby realizing the intelligent optimization of the sensor point scheme, improving the efficiency and accuracy of material inventory, and significantly reducing the equipment deployment cost while meeting the industry's positioning accuracy requirements, and improving the automation and precision level of warehouse material management.

[0111] The present invention, by constructing a three-dimensional warehouse environment model, calculating the multi-sensor joint positioning error, and applying an improved cuckoo algorithm, combined with indoor positioning technology and intelligent recognition means, can optimize the number of sensors and the layout plan, reduce equipment deployment costs, and achieve real-time positioning and automatic inventory of goods, reduce manual intervention, improve long-term positioning stability, improve the intelligent level of warehouse management, and promote the development of smart logistics for enterprises. The method of the present invention can solve the problem that traditional manual inventory methods are time-consuming and error-prone. Through intelligent inventory technology, goods are accurately positioned, real-time data synchronization is achieved, the accuracy of material inventory and spatial positioning is improved, positioning errors are ensured to be less than industry standards, and the accuracy and update efficiency of inventory information are improved.

[0112] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An indoor warehouse material inventory and spatial positioning method based on an improved cuckoo algorithm is characterized by: The method comprises: Acquire an indoor storage environment, construct a three-dimensional storage environment model corresponding to the indoor storage environment using three-dimensional laser scanning technology, and determine a set of candidate sensor points and a set of target material storage points; Based on the standard cuckoo algorithm, the improved cuckoo algorithm is generated by introducing the placement constraints, error correction mechanism, hybrid search optimization strategy and incremental node strategy. Establishing a single sensor error model based on Euclidean distance and calculating the single sensor positioning error contribution, calculating the multi-sensor joint positioning error based on the single sensor error contribution using a weighted covariance formula, and determining a positioning accuracy standard based on the multi-sensor joint positioning error; Based on the improved cuckoo algorithm, the three-dimensional warehouse environment model, the candidate sensor point set, the target material storage point set, and the positioning accuracy standard are imported, an initialization solution vector is constructed through binary coding, and the initialization solution vector is iteratively updated through the fitness function and the corresponding dual point target to generate the optimal sensor point set; The establishing of a single sensor error model based on Euclidean distance and calculating the single sensor positioning error contribution specifically includes: Based on the single sensor error model, calculate the candidate sensor point s in the candidate sensor point set S i (x i ,y i ,z i ) and the target material storage point t in the target material storage point set T j (x j ,y j ,z j ) of the Euclidean distance d ij : Where, dist(s i ,t j ) represents the candidate sensor point s i (x i ,y i ,z i ) and target material storage point t j (x j ,y j ,z j )’s Euclidean distance; Based on the Euclidean distance d ij , calculate the single sensor positioning error contribution σ ij : s ij =α*d ij +b Where α represents the distance attenuation coefficient; β represents the basic error term; The method of calculating the multi-sensor joint positioning error based on the single sensor error contribution by using a weighted covariance formula, and determining the positioning accuracy standard based on the multi-sensor joint positioning error, specifically includes: The target material storage point t j (x j ,y j ,z j ) is simultaneously distributed by k candidate sensors s i (x i ,y i ,z i ), calculate the single sensor positioning error contribution σ of all the inventory sensors based on the maximum likelihood estimation theory. ij The weighted harmonic mean of the multi-sensor joint positioning error is Based on the multi-sensor joint positioning error Constructing a set of candidate positioning accuracy Select the minimum value in the candidate positioning accuracy set A as the positioning accuracy standard ∈ 0; The improved cuckoo algorithm, based on which the three-dimensional warehouse environment model, the candidate sensor point set, the target material storage point set, and the positioning accuracy standard are imported, an initialization solution vector is constructed through binary coding, and the initialization solution vector is iteratively updated through a fitness function and a corresponding dual point target to generate an optimal sensor point set, specifically includes: The three-dimensional storage environment model, the candidate sensor point set S, the target material storage point set T and the positioning accuracy standard ∈ 0 are introduced into the improved cuckoo algorithm; Using the binary code x i ∈{0,1} represents the result of point selection, x i =1 indicates that at the candidate sensor point s i The inventory sensor is deployed at x i =0 means that at the candidate sensor point s i The inventory sensor is not deployed at the location, and the initialization solution vector X=[x1,x2,…,x |S| ], |S| represents the candidate sensor point s in the candidate sensor point set S i The number of, and the solution space size of the initialization solution vector X is 2 |S| ; The point selection result x in the initialization solution vector X is iteratively updated through the fitness function and the corresponding dual point selection target i , until the preset convergence condition of the improved cuckoo algorithm is met, the fitness function and the corresponding dual point distribution objective are expressed as follows: Where, fitness(x i ) represents the point selection result x i The fitness function value of |A| represents the number of optimal sensor points in the optimal sensor point set A; γ represents the penalty coefficient; Indicates the point selection result x i Corresponding multi-sensor joint positioning error max means taking the maximum value.

2. The indoor storage material inventory and spatial positioning method based on the improved cuckoo algorithm according to claim 1 is characterized in that: The method of acquiring an indoor storage environment, constructing a three-dimensional storage environment model corresponding to the indoor storage environment using three-dimensional laser scanning technology, and determining a set of candidate sensor points and a set of target material storage points specifically includes: Acquire the indoor storage environment, determine the physical structure of the indoor storage environment using the three-dimensional laser scanning technology, and mark the shelf coordinates, aisle directions, and obstacle areas to generate the three-dimensional storage environment model; Based on the three-dimensional warehouse environment model, multiple sensor installation locations are determined to form the candidate sensor point set, and the coordinates of the material storage area are marked to form the target material storage point set.

3. The indoor storage material inventory and spatial positioning method based on the improved cuckoo algorithm according to claim 1 is characterized in that: The placement constraints include signal blocking rules, sensor installation height restrictions, and warehouse operation process constraints; the error correction mechanism obtains historical positioning data by establishing a real-time error feedback link and calibrates the parameters of the single sensor error model; the hybrid search optimization strategy includes a global search strategy and a local optimization strategy. The global search strategy explores the sensor placement scheme through the Levy flight mechanism, and the local optimization strategy introduces a neighborhood search operator to refine the sensor placement scheme; the incremental node strategy dynamically adjusts the search granularity according to the scale of the indoor storage environment.

4. The indoor storage material inventory and spatial positioning method based on the improved cuckoo algorithm according to claim 1 is characterized in that: The preset convergence condition of the improved cuckoo algorithm is that the fitness change degree of the fitness function value of consecutive v generations is less than a preset threshold δ, and the corresponding expression is as follows: Where, fitness u Represents the fitness function value of the uth generation; fitness u-v Represents the fitness function value of the uvth generation.

5. An indoor material inventory and spatial positioning system based on an improved cuckoo algorithm, applied to an indoor warehouse material inventory and spatial positioning method based on an improved cuckoo algorithm as claimed in any one of claims 1 to 4, characterized in that: The system comprises: The sensor point placement and material storage point determination module is used to obtain the indoor storage environment, construct a 3D storage environment model corresponding to the indoor storage environment using 3D laser scanning technology, and determine the candidate sensor point set and target material storage point set; Improved Cuckoo Algorithm Setting Module, which is used to generate an improved Cuckoo Algorithm based on the standard Cuckoo Algorithm by introducing placement constraints, error correction mechanism, hybrid search optimization strategy, and incremental node strategy; a positioning error and accuracy standard calculation module, configured to establish a single sensor error model based on Euclidean distance and calculate the single sensor positioning error contribution, calculate the multi-sensor joint positioning error based on the single sensor error contribution using a weighted covariance formula, and determine the positioning accuracy standard based on the multi-sensor joint positioning error; The optimal sensor point set generation module is used to import the three-dimensional warehouse environment model, the candidate sensor point set, the target material storage point set and the positioning accuracy standard based on the improved cuckoo algorithm, construct an initialization solution vector through binary coding, and iteratively update the initialization solution vector through the fitness function and the corresponding dual point target to generate the optimal sensor point set.

6. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor runs the computer program stored in the memory, the processor executes the steps of the indoor warehouse material inventory and spatial positioning method based on the improved cuckoo algorithm as described in any one of claims 1 to 4.

7. A readable storage medium storing a computer program, wherein: When the computer program is executed by a processor, it is used to implement the steps of the indoor warehouse material inventory and spatial positioning method based on the improved cuckoo algorithm as described in any one of claims 1 to 4.

Images