Intelligent stacking method and device

Abstract

The application provides a kind of intelligent stacking method and device, it is related to the technical field of logistics field, method includes: obtaining real-time warehousing data in warehouse management system, constructs structured warehousing state matrix;Extract the material storage data of the military material to be warehoused, construct the adaptive vector set of the military material to be warehoused;Adaptive vector set and structured warehousing state matrix are matched, determine the stacking adaptive candidate position set;Based on the constructed stacking feasibility score matrix, the stacking adaptive candidate position set is evaluated;Based on the stacking feasibility score matrix, search the global optimal stacking configuration in the stacking candidate atlas, determine the mapping relationship between military material and target position, to generate stacking scheme.The application can generate stacking scheme in combination with the characteristic requirements of military material.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of logistics, in particular to an intelligent stacking method and device. BACKGROUND

[0002] The traditional way of stacking military materials in the warehouse mainly includes manual operation and mechanical assistance, such as using a forklift or crane to place according to certain rules. With the development of IT and OT technology, artificial intelligence, Internet of Things technology and automation technology are gradually applied in the traditional warehouse stacking process of military materials. Enterprises use automated guided vehicles (AGV) instead of manual handling, use robot arms for precise stacking, use warehouse management systems (WMS) to optimize the storage and real-time monitoring of military materials in the warehouse, use RFID or two-dimensional code technology for automatic identification and tracking of military material information, and use SCADA data acquisition systems to collect real-time temperature and humidity data to improve safety, etc.

[0003] The main difference between military material stacking and ordinary material stacking lies in the purpose, priority and specific requirements of stacking. Military material stacking usually involves specific safety, mobility and protection requirements. The storage and retrieval of materials must be fast and have emergency response capabilities, so the stacking scheme needs to consider efficient mobilization and transportation in emergency situations. In addition, military material stacking also needs to consider the compatibility of different types of materials, such as the isolation of flammable and explosive materials, the safe storage of ammunition, etc., while ordinary material stacking focuses more on the optimization of warehouse space, cost-effectiveness and regular management of material types.

[0004] In summary, conventional algorithms usually focus on the optimization of warehouse space and cost-effectiveness, while ignoring the special needs of military materials in terms of safety, emergency response and protection. Military material stacking requires considering more complex factors such as efficient material access, flexible emergency scheduling and safety isolation between different materials, which are beyond the design scope of conventional stacking algorithms. Therefore, a method is needed to generate a stacking scheme that combines the characteristics of military materials. SUMMARY

[0005] The present application provides an intelligent stacking method and device that can generate a stacking scheme that combines the characteristics of military materials.

[0006] In a first aspect of the present application, an intelligent stacking method is provided, the method comprising:

[0007] Obtaining real-time warehouse data in a warehouse management system, and constructing a structured warehouse state matrix;

[0008] extracting the material storage data of the military material to be stored, and constructing an adaptive vector set of the military material to be stored;

[0009] matching the adaptive vector set with the structured storage state matrix, and determining a stack adaptive candidate position set;

[0010] evaluating the stack adaptive candidate position set based on the constructed stack feasibility scoring matrix;

[0011] searching for a globally optimal stack configuration in a stack candidate graph based on the stack feasibility scoring matrix, determining a mapping relationship between the military material and a target position, and thereby generating a stack scheme.

[0012] On the basis of the above technical solutions, preferably, the real-time storage data in the storage management system is obtained, and a structured storage state matrix is constructed, specifically including:

[0013] Based on the real-time storage data, static structure data and dynamic state data of the current storage space are extracted

[0014] On the basis of the above technical solutions, preferably, the material storage data of the military material to be stored is extracted, and the adaptive vector set of the military material to be stored is constructed, specifically including:

[0015] The material storage data is extracted, including structure parameter data, danger level data, compatibility label data and historical storage record data of the military material to be stored;

[0016] For the structure parameter data, the spatial size parameter and the quality parameter of each military material are extracted, and a four-dimensional size and quality vector is constructed;

[0017] For the danger level data, the heat sensitivity level, vibration response level, explosion risk level and electrostatic response level of each military material are extracted as discrete level variables, and are mapped into a quantitative risk index vector;

[0018] For the compatibility label data, a Boolean vector with the same length as the known set of military material categories is constructed;

[0019] For the historical storage record data, the historical stack structure stability label, the historical environmental response curve and the abnormal response record frequency are extracted, the environmental sensitivity score quantization value is constructed based on the rules, and the heat accumulation response index, stack stability residual mean and abnormal frequency factor are added to form a historical response vector;

[0020] splicing the four-dimensional size quality vector, the quantitative risk index vector, the Boolean vector and the historical response vector in sequence to form a complete adaptation feature vector of the military material;

[0021] organizing all the adaptation feature vectors into the adaptation vector set.

[0022] On the basis of the above technical solutions, preferably, the matching of the adaptation vector set with the structured warehouse state matrix to determine a stack adaptation candidate warehouse set specifically includes:

[0023] performing one-to-one correspondence comparison of each of the adaptation feature vectors in the adaptation vector set with each warehouse position attribute vector in the structured warehouse state matrix, performing feature alignment operation in attribute dimension, ensuring that the four-dimensional size quality vector corresponds to the spatial size attribute vector and the bearing quality attribute vector of the structured warehouse state matrix, the quantitative risk index vector corresponds to the warehouse safety level label, the Boolean vector performs set intersection judgment with the current common stack material label of the warehouse, and the historical response vector performs corresponding regression comparison with the historical accident response factor distribution of the warehouse;

[0024] After completing the feature alignment, for each of the stack adaptation feature vectors and each of the warehouse attribute vectors, the matching rule calculation is sequentially performed.

[0025] According to the results of the multiple matching rule calculations, a stack adaptation scoring function is constructed according to a preset weighting coefficient, and an adaptation score value is comprehensively generated;

[0026] determining a target adaptation score value higher than a dynamic safety threshold value in the multiple adaptation score values;

[0027] marking the warehouse corresponding to the target adaptation score value as a stack position, and forming the stack adaptation candidate warehouse set with multiple stack positions.

[0028] On the basis of the above technical solutions, preferably, after completing the feature alignment, for each of the stack adaptation feature vectors and each of the warehouse attribute vectors, the matching rule calculation is sequentially performed, specifically including:

[0029] calculating a spatial containment degree score, calculating a spatial containment degree score based on the spatial size attribute vector and the four-dimensional size quality vector, and measuring the quality bearing margin score of the material quality data relative to the bearing quality attribute vector according to a proportional function;

[0030] calculating a risk response compatibility score by the quantitative risk index vector and the warehouse safety level label, and obtaining a safety matching degree by comparison;

[0031] According to the compatibility label matching score calculated based on the Boolean vector and the current shared stock label of the position, it is determined whether there is an unshareable conflict;

[0032] The residual sum of squares of the historical response vector and the historical accident response factor distribution of the position is used as a fitting index score to evaluate the fitting degree of the historical environment response.

[0033] On the basis of the above technical solutions, preferably, the constructed stacking feasibility score matrix is used to evaluate the stacking adaptation candidate position set, specifically including:

[0034] The stacking feasibility score matrix is used as input to evaluate each position in the stacking adaptation candidate position set one by one, each element in the stacking feasibility score matrix corresponds to a position and a military material matching score in multiple dimensions, and the stacking feasibility score matrix includes the space accommodation degree score, the mass bearing margin score, the risk response compatibility score, the compatibility label matching score, and the fitting index score.

[0035] The space accommodation degree score, the mass bearing margin score, the risk response compatibility score, the compatibility label matching score, and the fitting index score are weighted and fused based on a weighting coefficient to obtain a total stacking feasibility score of the position.

[0036] On the basis of the above technical solutions, preferably, the stacking feasibility score matrix is used to search for a globally optimal stacking configuration in a stacking candidate graph to determine the mapping relationship between the military material and the target position, thereby generating a stacking scheme, specifically including:

[0037] Each element in the stacking feasibility score matrix is used as the weight of an edge to construct a stacking candidate graph, where each node represents a position or a military material, the edges between nodes represent the adaptability between positions and materials, and the weight of the edge is the total stacking feasibility score.

[0038] A globally optimal algorithm is used to search the stacking candidate graph to seek a stacking configuration scheme.

[0039] An adaptability value is calculated for each stacking configuration scheme, and the adaptability value is the weighted sum of the total stacking feasibility score in the stacking feasibility score matrix.

[0040] After multiple iterations, the optimal stacking configuration is selected from the multiple stacking configuration schemes according to the adaptability value, the optimal stacking configuration includes the mapping relationship between each military material and the target position, and a stacking scheme is generated.

[0041] In a second aspect of the present application, an intelligent stacking device is provided, which is used to perform any one of the intelligent stacking methods described above, and the device comprises an acquisition module, a processing module and an output module, wherein:

[0042] The acquisition module is configured to acquire real-time warehouse data in a warehouse management system, and construct a structured warehouse state matrix.

[0043] The processing module is configured to extract the material storage data of the military material to be stored in the warehouse, and construct an adaptive vector set of the military material to be stored in the warehouse.

[0044] The processing module is configured to match the adaptive vector set with the structured warehouse state matrix, and determine a stacking adaptive candidate warehouse position set.

[0045] The processing module is configured to evaluate the stacking adaptive candidate warehouse position set based on the constructed stacking feasibility scoring matrix.

[0046] The output module is configured to search for a globally optimal stacking configuration in a stacking candidate graph based on the stacking feasibility scoring matrix, determine the mapping relationship between the military material and the target warehouse position, and generate a stacking scheme.

[0047] In a third aspect of the present application, an electronic device is provided, which comprises a processor, a memory, a user interface and a network interface, the memory is configured to store instructions, the user interface and the network interface are both configured to communicate with other devices, and the processor is configured to execute the instructions stored in the memory to enable the electronic device to perform the method described in any one of the above aspects.

[0048] In a fourth aspect of the present application, a computer readable storage medium is provided, which stores instructions, and when the instructions are executed, the method described in any one of the above aspects is performed.

[0049] In summary, the one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0050] 1. By introducing the structured warehouse state matrix and the military material adaptive vector set, the present application realizes accurate modeling of the physical properties, safety level, environmental state of the warehouse space and the multi-dimensional characteristics such as size, quality, danger level and compatibility of the military material, and through the stacking feasibility scoring matrix and candidate graph construction mechanism, combined with the multi-objective optimization algorithm to search for the optimal matching relationship in the global solution space, the strict requirements of safety isolation, emergency scheduling and historical response stability of the military material are met while ensuring the space utilization, and a safe, efficient and controllable stacking scheme based on the characteristics of the military material is generated.

[0051] 2. By extracting static structure data and dynamic state data in the warehouse space, and generating a structured warehouse state matrix, the physical properties, safety capacity and real-time occupancy of the storage space are finely modeled, enabling the stacking scheme to accurately select the optimal stacking area based on the storage space dimension, significantly improving the structural representation capability and task matching accuracy of the warehouse resources.

[0052] 3. By multi-dimensionally extracting and uniformly encoding the structure parameters, danger level, compatibility label and historical storage record of the military materials to be stored, a set of adaptive feature vectors is constructed, enabling the quantifiable expression of material characteristics in the space, safety, collaboration and response dimensions, providing a stable, uniform and high-dimensional calculation input basis for subsequent stacking strategies, and improving the intelligent decision-making capability of the stacking system.

[0053] 4. By multi-dimensionally aligning the adaptive feature vectors with the structured warehouse state matrix and performing matching rule evaluation, combined with a scoring function and a dynamic safety threshold mechanism, a set of stacking adaptive candidate storage spaces that meet complex safety constraints is screened out, enabling high-precision pairing between stacking input data and actual feasible stacking areas, and enhancing the safety and pertinence of the material storage strategy.

[0054] 5. The matching rules of space tolerance, quality bearing margin, risk response compatibility, co-stacking label matching and historical response fitting degree are introduced, and each rule is quantitatively scored, enabling the stacking evaluation to expand from the traditional spatial dimension to multi-dimensional collaborative attributes, enabling precise modeling of the complex adaptive characteristics of military materials and stacking feasibility evaluation, significantly improving the discrimination ability and safety evaluation ability of the stacking algorithm.

[0055] 6. The multi-dimensional scoring results are calculated by weighted fusion to obtain the total stacking feasibility score, enabling the quantitative sorting of the comprehensive performance of each candidate storage space, improving the global consistency and comparability of the stacking optimization process, providing a standardized evaluation basis for the optimal stacking configuration, and enhancing the reliability and evaluation transparency of the overall stacking scheme.

[0056] 7. Based on the stacking feasibility score matrix, a stacking candidate graph is constructed, and a global optimization algorithm is used to search for the optimal mapping configuration, effectively solving the combinatorial optimization problem of the matching relationship between storage spaces and materials under multi-objective stacking tasks, avoiding local optimal traps, and ensuring that the generated stacking scheme reaches the global optimal level in terms of space utilization, safety guarantee and scheduling efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 is a flowchart of an intelligent stacking method disclosed by an embodiment of the present application;

[0058] Figure 2 is a module schematic diagram of an intelligent stacking device disclosed by an embodiment of the present application;

[0059] Figure 3 Figure 1 is a structural schematic diagram of an electronic device according to an embodiment of the present application.

[0060] Figure 1 is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0061] In order for those skilled in the art to better understand the technical solutions in the specification, the technical solutions in the specification will be clearly and completely described below in combination with the drawings in the embodiments of the specification. Obviously, the described embodiments are only some of the embodiments of the present application, not all.

[0062] In the description of the embodiments of the present application, the words such as "for example" or "for instance" are used to represent an example, illustration or description. Any embodiment or design scheme described as "for example" or "for instance" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words such as "for example" or "for instance" are intended to present the relevant concept in a specific manner.

[0063] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are used for description purposes only and should not be interpreted or implied to indicate or imply relative importance or implicitly indicate the indicated technical features. Therefore, the features defined with "first" and "second" can explicitly or implicitly include one or more features. The terms "include", "contain", "have" and their variants mean "include but are not limited to", unless otherwise specifically emphasized.

[0064] The traditional military material stacking method usually relies on manual operation combined with mechanical assistance, but with the development of IT and OT technologies, artificial intelligence, Internet of Things technology and automation technology are gradually applied to this process, such as using automatic guided vehicles (AGV), robotic arms, warehouse management systems (WMS), RFID and two-dimensional code technology to optimize the stacking process. However, the main difference between military material stacking and ordinary material stacking is the special requirements for safety, mobility, protection and emergency response, especially considering the efficiency of material access, flexibility of emergency scheduling and safety isolation between different materials, which are beyond the design scope of conventional stacking algorithms, so it is necessary to generate more complex stacking schemes combined with the characteristics of military materials.

[0065] The embodiment discloses an intelligent stacking method, referring to Figure 1 , comprising the following steps S110-S150:

[0066] S110, obtaining real-time warehouse data in a warehouse management system, and constructing a structured warehouse state matrix.

[0067] The intelligent stacking method disclosed by the embodiment of the application is applied to a server. The server includes but is not limited to electronic devices such as mobile phones, tablet computers, wearable devices, PC (Personal Computer), and the like, and can also be a background server running an intelligent stacking method. The server can be implemented by an independent server or a server cluster composed of multiple servers.

[0068] In a possible implementation, the real-time warehouse data in the warehouse management system is obtained, and a structured warehouse state matrix is constructed, specifically including: based on the real-time warehouse data, extracting static structure data and dynamic state data of the current warehouse space; based on the static structure data and the dynamic state data, establishing a unique number for all storage spaces and generating a multi-field data table; logically grouping the multi-field data table according to a space area, constructing a region index mapping table, and then generating a structured warehouse state matrix, wherein each row of the structured warehouse state matrix corresponds to a storage space attribute vector, and each column corresponds to a specific attribute dimension.

[0069] Specifically, first, based on the real-time warehouse data, static structure data and dynamic state data of the current warehouse space are extracted. The static structure data includes information such as the physical layout of the warehouse, the size of each storage space, the maximum carrying capacity, etc. The dynamic state data contains the occupancy state of each storage space, the storage type of the material, the warehouse environment data (such as temperature and humidity), and the compatibility information with other materials. These data sources are usually collected from sensor data of automatic devices such as warehouse management systems (WMS) and automatic guided vehicles (AGV). The static structure data reflects the fixed characteristics of the warehouse facility, and the dynamic state data reflects the current operation condition and real-time changes of the warehouse.

[0070] Secondly, based on the static structure data and the dynamic state data, a unique number is established for all storage spaces and a multi-field data table is generated. Each storage space is assigned a unique number according to its position, size, carrying capacity, and current state in the warehouse space, which will serve as the identifier of the storage space. The multi-field data table is a detailed record of each attribute of the storage space, usually including: storage space number, space size (length, width, height), maximum carrying capacity, current occupancy state, material type, compatibility label, environment data (such as temperature and humidity), etc. The definition and recording method of these fields determine the completeness and effectiveness of the warehouse data.

[0071] Then, the multi-field data table is logically grouped by spatial regions to construct a region index mapping table. The spatial regions are divided based on the physical layout of the warehouse, for example, the warehouse is partitioned by shelves, regions, floors, etc. dimensions, and each spatial region contains a number of storage positions. The region index mapping table corresponds each storage position to the spatial region it belongs to, facilitating subsequent management and query of the entire warehouse space. Through such spatial grouping, the location of the storage position can be quickly located, improving the efficiency of warehouse operations.

[0072] Finally, a structured warehouse state matrix is generated, with each row of the matrix corresponding to a storage position attribute vector and each column corresponding to a specific attribute dimension. The rows of the matrix represent each storage position in the warehouse, and the columns represent the specific attributes of each storage position (such as size, carrying capacity, current occupancy status, etc.). The attribute vector of each storage position is composed of multiple attribute values, which are filled according to the static and dynamic data of the storage position. This structured warehouse state matrix can provide complete warehouse space information for the stacking algorithm, ensuring that subsequent stacking decisions can fully consider the characteristics of each storage position.

[0073] S120, extracting the material storage data of the military material to be stored, and constructing an adaptive vector set of the military material to be stored.

[0074] In one possible implementation, the material storage data of the military material to be stored is extracted, and an adaptive vector set of the military material to be stored is constructed, specifically including: extracting the material storage data, the material storage data including the structure parameter data, the hazard level data, the compatibility label data, and the historical storage record data of the military material to be stored; for the structure parameter data, extracting the spatial size parameter and the quality parameter of each military material to construct a four-dimensional size-quality vector; for the hazard level data, extracting the heat sensitivity level, the vibration response level, the explosion risk level, and the electrostatic response level of each military material as discrete level variables, and mapping them into a quantitative risk index vector; for the compatibility label data, constructing a Boolean vector with the same length as the complete set of known military material categories; for the historical storage record data, extracting the historical stacking structure stability label, the historical environmental response curve, and the abnormal response record frequency, constructing an environmental sensitivity score quantization value based on rules, and adding a heat accumulation response index, a stacking stability residual mean value, and an abnormal frequency factor to form a historical response vector; concatenating the four-dimensional size-quality vector, the quantitative risk index vector, the Boolean vector, and the historical response vector in order to form a complete adaptive feature vector of the military material; and organizing all adaptive feature vectors into an adaptive vector set.

[0075] Specifically, first, the storage data of the military materials to be warehoused is extracted from the warehouse management system. The material storage data includes structural parameter data, hazard level data, compatibility label data, and historical storage record data of the military materials. The structural parameter data provides the physical characteristics of the materials, such as spatial dimensions, weight, etc., the hazard level data reflects the safety requirements of the materials, the compatibility label data is used to indicate whether the materials are compatible with other materials, and the historical storage record data records the historical stacking behavior, environmental response, etc. of the materials. The collection of these data is updated in real time through devices such as warehouse management system (WMS), RFID system, and environmental monitoring system.

[0076] For the structural parameters of each item of military materials to be warehoused, the spatial dimension parameters (such as length, width, height) and mass parameters of the materials are extracted. A four-dimensional size-mass vector is constructed, specifically in the form of

[0077]

[0078] where L represents the length of the material, W represents the width, H represents the height, and M represents the mass of the material. This vector provides the basic size and load-bearing information of the material for subsequent stacking decision-making, which helps to determine the spatial requirements and warehouse position selection of the material. For example, if the material is a large-sized and heavy ammunition box, this vector will provide the specific spatial and load-bearing requirements of the material, thereby providing basic data for warehouse position allocation.

[0079] For the hazard level data, the heat sensitivity level, vibration response level, explosion risk level, and electrostatic response level of each item of military materials are extracted. Each level can be divided into multiple discrete levels (such as low, medium, high) by pre-defined standards, and these levels are mapped to quantitative risk indices. The mapped quantitative risk index vector can be represented as

[0080]

[0081] where represent the quantitative risk indices of heat sensitivity, vibration response, explosion risk, and electrostatic response, respectively. This risk index vector provides the basis for safety evaluation for stacking decision-making, ensuring that the needs of safety isolation and emergency response are considered during the stacking process of the materials. For example, the heat sensitivity and explosion risk of flammable materials will result in a higher risk index, and isolation from other materials will be prioritized during stacking.

[0082] For the compatibility label data, a Boolean vector of the same length as the full set of known military material categories is constructed. Each bit of this vector indicates whether the current material is compatible with a certain category of material, with 1 indicating compatibility and 0 indicating incompatibility. The specific Boolean vector form is

[0083]

[0084] wherein, indicates whether the material is compatible with the category of materials. The role of the compatibility label data is to ensure that the isolation and co-stacking rules of materials are followed during stacking, avoiding the mutual contact of dangerous materials. For example, explosive materials and flammable materials usually have an incompatible relationship and need to be separated during stacking, so they are marked as incompatible (0) in this vector.

[0085] For historical storage record data, the historical stacking structure stability label, the historical environmental response curve, and the abnormal response record frequency of each item of material are extracted. Through these data, it is evaluated whether the material has appeared stacking instability, environmental change too large or other abnormal events in the past storage process. Based on this information, the environmental sensitivity score quantitative value is constructed, and the heat accumulation response index, the stacking stability residual mean and the abnormal frequency factor are calculated to generate the historical response vector. The vector can be represented as

[0086]

[0087] wherein, indicates the historical stacking stability, indicates the heat accumulation response index, indicates the abnormal response record frequency. The historical response vector provides historical data support for stacking decision, ensuring the stability during stacking and the long-term storage safety of materials.

[0088] The four vectors extracted above, the four-dimensional size and mass vector, the quantitative risk index vector, the Boolean vector and the historical response vector, are spliced into a complete military material adaptation feature vector in order. This adaptation feature vector will become the core input of the stacking decision, representing the comprehensive characteristics of each item of military material, including the spatial demand, safety, compatibility and historical stacking performance of the material. The specific splicing form is

[0089]

[0090] The feature vector can help the subsequent stacking algorithm to effectively evaluate the matching degree between the material and the storage position.

[0091] Finally, the adaptation feature vectors of all the military materials to be warehoused are organized into an adaptation vector set. The adaptation feature vector of each item of material represents the detailed information of the material. Through the adaptation vector set, the stacking algorithm can quickly obtain the complete characteristic data of each item of material and make stacking decisions, storage position selection and safety evaluation based on these data. For example, during stacking, the system can automatically determine the optimal storage location of the material by analyzing the data in the adaptation vector set.

[0092] S130, match the set of adaptation vectors with the structured warehouse state matrix to determine a set of stack adaptation candidate positions.

[0093] In a possible implementation, matching the set of adaptation vectors with the structured warehouse state matrix to determine a set of stack adaptation candidate positions specifically includes:

[0094] Each adaptation feature vector in the set of adaptation vectors is respectively matched with each position attribute vector in the structured warehouse state matrix, a feature alignment operation in the attribute dimension is performed, based on a pre-defined attribute mapping index table, it is ensured that the four-dimensional size quality vector corresponds to the spatial size attribute vector and the bearing quality attribute vector of the structured warehouse state matrix, the quantitative risk index vector corresponds to the position safety level label, the Boolean vector and the position current common stock label perform set intersection judgment, and the historical response vector and the position historical accident response factor distribution are correspondingly regressed and compared; after the feature alignment is completed, the matching rule calculation is sequentially performed for each stack adaptation feature vector and each position attribute vector; the stack adaptation score function is constructed according to the results of the multiple matching rule calculations according to the preset weighting coefficients, and the adaptation score value is comprehensively generated; the target adaptation score value higher than the dynamic safety threshold value in the multiple adaptation score values is determined; the position corresponding to the target adaptation score value is marked as a stack position, and the multiple stack positions constitute the set of stack adaptation candidate positions.

[0095] Specifically, when each adaptation feature vector in the set of adaptation vectors is respectively matched with each position attribute vector in the structured warehouse state matrix, first, the field level alignment is performed through the index of the attribute dimension. In order to realize the automatic matching, the attribute mapping index table needs to be constructed in advance, which is used to specify the attributes in the adaptation feature vector and the corresponding fields in the position attribute vector. For example, the four-dimensional size quality vector in the adaptation feature vector corresponds to the spatial size attribute and the maximum bearing quality field in the position attribute vector; the quantitative risk index vector and the position safety level label are matched by level coding; the Boolean vector and the type set of the stacked materials in the position are calculated by intersection to judge the compatibility; the historical response vector is fitted with the historical accident response factor data of the position to establish a regression model, and a residual vector is extracted for subsequent stability judgment. This process ensures the dimensional consistency and accurate semantic correspondence of various data, which constitutes the basis for subsequent score function calculation.

[0096] After completing the feature alignment, for each item of the adapted feature vector and each item of the position attribute vector, the matching rule calculation is sequentially executed. The matching rule is based on the value of the aligned vector dimension to determine, including: the spatial containment rule, that is, to determine whether the material is completely contained in the space size, if any direction exceeds, it is determined as not stackable; the quality bearing rule, that is, to determine whether the material quality is within the maximum bearing weight allowed range of the position; the risk compatibility rule, that is, to compare the quantitative risk index with the position environmental risk tolerance threshold, if it exceeds, it is marked as incompatible; the co-stacking rule, that is, to perform intersection judgment on the material Boolean vector and the type set of the current stacked materials of the position, if there is a conflict label, it is determined as not co-stacking; the environmental response matching rule, that is, to perform residual analysis on the historical response vector and the position historical accident response curve, if the residual sum of squares is within the allowable range, it is determined as stable matching.

[0097] For all matching rule calculation results, a stacking adaptation score function is constructed according to a preset weighting coefficient. The score function takes each type of score index as a sub-item, respectively assigns a weight, and constructs a weighted linear combination model: for example, the spatial containment score accounts for 30%, the quality bearing score accounts for 25%, the risk response score accounts for 20%, the compatibility score accounts for 15%, and the historical response matching score accounts for 10%. After normalization of each score value, the weighted sum is generated to generate the adaptation score value, and the higher the score, the more suitable the position is for the corresponding material stacking. The weight setting of the score function can be dynamically adjusted according to the actual material stacking safety strategy to strengthen the evaluation focus of specific scenarios.

[0098] After obtaining all the adaptation score values, the target adaptation score values higher than the threshold value are selected according to the dynamic safety threshold value. The dynamic safety threshold value can be dynamically set according to the current environmental risk level, safety control level and task urgency of the warehouse, for example, in high temperature season, important material storage or war readiness state, the threshold value will be increased accordingly, to strengthen the stacking safety screening standard. The system compares the adaptation score value with the threshold value item by item, and only keeps the positions that meet the threshold condition as the candidate stacking target.

[0099] Finally, all positions with a score higher than the dynamic safety threshold value are marked as stacking positions, and the position set constitutes the stacking adaptation candidate position set. This set is used for the construction of the subsequent stacking feasibility score matrix and the search for the optimal stacking configuration, and is the key data source to ensure the safety, efficiency and stability of the stacking path.

[0100] In a possible implementation, after completing feature alignment, for each item stacking adaptation feature vector and each item position attribute vector, matching rule calculation is sequentially performed, specifically including: calculating spatial containment degree score, calculating spatial containment degree score based on three-dimensional geometric projection according to spatial size attribute vector and four-dimensional size quality vector, calculating quality bearing margin score of material quality data relative to bearing quality attribute vector according to a proportional function; calculating risk response compatibility score through quantitative risk index vector and position safety level label, and obtaining safety matching degree by comparison; calculating compatibility label matching score according to Boolean vector and position current co-stacking material label, and judging whether there is an unco-stacking conflict; using residual sum of squares of historical response vector and position historical accident response factor distribution as fitting index score to evaluate historical environment response fitting degree.

[0101] Specifically, when calculating the spatial containment degree score, first, the spatial size attribute vector in the structured warehouse state matrix is extracted and the spatial size parameter in the adaptation feature vector is wherein the subscript represents the position, represents the military material. Based on three-dimensional geometric volume relationship, if the material is less than or equal to the position in each dimension, the spatial containment degree score is calculated, and the formula is as follows:

[0102]

[0103] If the value is less than 1, it means that the material can be completely contained, and the score is , if greater than or equal to 1, the score is recorded as 0, indicating that it cannot be stacked. In order to avoid misjudgment of the volume critical value, a safety tolerance coefficient can be set, and the containment determination condition is changed to:

[0104]

[0105] Under the premise that the space is satisfied, the quality bearing margin score is continued to be calculated , wherein is the mass of the material, is the maximum bearing capacity of the position, which is defined as:

[0106]

[0107] If , it means overloading, and the score is 0, if it is in the interval , the value is directly used. The two scores comprehensively reflect the physical containment and support capacity of the position to the material.

[0108] When calculating the risk response compatibility score, the quantitative risk index vector with the position safety level label vector According to the dimension comparison, the risk compatibility margin of each dimension is calculated respectively:

[0109]

[0110] Among them , respectively represent heat sensitive, vibration, explosion, static dimension, To prevent the positive decimal of the denominator from being zero. The four scores are equally averaged to obtain the risk response compatibility score :

[0111]

[0112] If any dimension score is 0, the overall risk response compatibility is considered unqualified, and is directly assigned 0 to exclude the position.

[0113] When calculating the compatibility label matching score, the Boolean vector in the adaptation feature vector and the current position has been stacked with the label set of the material Do bit-by-bit logical operation, define conflict judgment as:

[0114]

[0115] Add all If the total is 0, it means complete compatibility, and the score is ; If there is a conflict, the score will decrease in proportion:

[0116]

[0117] Where the denominator represents the number of types of materials already stacked in the position, ensuring that the conflict degree is accurately measured.

[0118] Finally, evaluate the historical environmental response fitting degree, extract the historical response vector and the historical accident response factor distribution vector of the position , calculate the residual sum of squares as the fitting error:

[0119]

[0120] If the error is smaller, the score is closer to 1, indicating high matching degree of historical response behavior. If the residual exceeds the threshold , set to exclude unstable stacking history positions.

[0121] S140, based on the constructed stacking feasibility score matrix, evaluate the stacking adaptation candidate position set.

[0122] In a possible implementation, the set of stack-adaptive candidate positions is evaluated based on the constructed stack feasibility scoring matrix, specifically including: taking the stack feasibility scoring matrix as input, evaluating each position in the set of stack-adaptive candidate positions one by one, each element in the stack feasibility scoring matrix corresponding to a matching score of a position and military materials in multiple dimensions, the stack feasibility scoring matrix including a space accommodation degree score, a quality load margin score, a risk response compatibility score, a compatibility label matching score, and a fitting index score; and performing weighted fusion on the space accommodation degree score, the quality load margin score, the risk response compatibility score, the compatibility label matching score, and the fitting index score based on a weighting coefficient to obtain a total stack feasibility score of the position.

[0123] Specifically, when the stack feasibility scoring matrix is taken as input to evaluate each position in the set of stack-adaptive candidate positions one by one, first, the structure of the stack feasibility scoring matrix is determined, the matrix taking rows to correspond to candidate positions and columns to correspond to matching dimension scores, and each element representing a score value of a certain position on a certain item of military materials in a specific matching dimension. The matching dimensions include the space accommodation degree score, the quality load margin score, the risk response compatibility score, the compatibility label matching score, and the fitting index score, and each score value is a floating-point number in the interval [0, 1] and is used to measure the degree of adaptation in this dimension. The system sequentially traverses each row of the matrix to extract a score sub-vector of the current position from the five dimensions as the basic input for subsequent fusion calculation. This process ensures that each candidate position is quantified in all key dimensions and has uniform structured evaluation data.

[0124] After obtaining the score values of each position in the five dimensions, the system performs weighted fusion on the scores according to a preset weighting coefficient to generate a total stack feasibility score of the position. The weighting coefficient represents the relative importance of each dimension score in the comprehensive evaluation, and is usually configured according to the military material stacking strategy, for example, in a safety-oriented scenario, the weights of the risk response compatibility score and the fitting index score can be increased; and in a scenario where space utilization efficiency is prioritized, the proportions of the space accommodation degree score and the quality load margin score can be increased. Let the weighting coefficients be , which satisfy

[0125]

[0126] The five scores are respectively , and the total stack feasibility score is calculated according to the following formula:

[0127]

[0128] The fusion score reflects the multi-dimensional matching degree and the priority of the stacking strategy through weight adjustment, and realizes flexible control of the evaluation standard.

[0129] In a possible implementation, the global optimal stacking configuration is searched in the stacking candidate graph based on the stacking feasibility score matrix, the mapping relationship between the military materials and the target storage positions is determined, and a stacking scheme is generated.

[0130] In a possible implementation, the global optimal stacking configuration is searched in the stacking candidate graph based on the stacking feasibility score matrix, the mapping relationship between the military materials and the target storage positions is determined, and a stacking scheme is generated.

[0131] Specifically, when the stacking candidate graph is constructed by taking each element in the stacking feasibility score matrix as the weight of an edge, first, two sets in the graph structure are defined: a material node set and a storage position node set. Each material node represents a military material to be stored in the warehouse, and each storage position node represents a stacking candidate storage position. In the bipartite graph structure, each edge between a material node and a storage position node represents a set of optional stacking allocation relationships, and the weight value of the edge is the total stacking feasibility score obtained in the previous evaluation. The data structure of the stacking candidate graph is stored in the form of a sparse matrix, which saves memory space and improves calculation efficiency. The graph reflects the advantages and disadvantages of all material-storage position pairs in multi-dimensional matching, and is the basis for searching the stacking configuration solution space.

[0132] When the stacking candidate graph is searched using a global optimization algorithm, an algorithm suitable for combinatorial optimization problems is selected for solution, such as a multi-objective genetic algorithm or a simulated annealing algorithm. Taking the multi-objective genetic algorithm as an example, a number of random stacking configuration individuals are generated in the initial stage, each individual being a mapping scheme representing a one-to-one allocation relationship of all military materials in the feasible storage positions. In each iteration, selection, crossover, and mutation genetic operations are performed to constantly generate new individuals. The selection operation retains high-quality individuals according to the individual fitness values, the crossover operation exchanges part of the material-storage position mappings between individuals, and the mutation operation randomly changes the storage position assignment of individual materials. The process gradually approaches the global optimal solution through population evolution.

[0133] When calculating the fitness value of each stacking configuration scheme, the total stacking feasibility scores corresponding to each material and its assigned position in the scheme are added up. Let the current stacking configuration scheme be , which contains materials, each material corresponds to an assigned position , then the fitness value of the scheme is The calculation formula is:

[0134]

[0135] wherein represents the total stacking feasibility score of material and position . The higher the fitness value, the better the overall material adaptability of the stacking scheme, which is an important indicator for judging the individual.

[0136] After multiple iterations are completed, the individual with the highest fitness value is selected from all stacking configuration schemes as the optimal stacking configuration, and the mapping relationship between the corresponding military materials and target positions is recorded. This mapping relationship constitutes the final stacking scheme output, ensuring that the most optimal and most coordinated stacking layout is selected from all candidate matches. This stacking scheme will be used to generate specific stacking scheduling instructions, drive automatic guided vehicle path planning and robot action control, and complete physical stacking operations.

[0137] The embodiment also discloses an intelligent stacking device, referring to Figure 2 , comprising an acquisition module 201, a processing module 202 and an output module 203, and the device is used for executing any one of the intelligent stacking methods described above, wherein:

[0138] The acquisition module 201 is used for acquiring real-time warehouse data in a warehouse management system and constructing a structured warehouse state matrix.

[0139] The processing module 202 is used for extracting material storage data of the military materials to be stored in the warehouse and constructing an adaptive vector set of the military materials to be stored in the warehouse.

[0140] The processing module 202 is used for matching the adaptive vector set with the structured warehouse state matrix and determining a stacking adaptive candidate position set.

[0141] The processing module 202 is used for evaluating the stacking adaptive candidate position set based on the constructed stacking feasibility score matrix.

[0142] The output module 203 is configured to search for a globally optimal stacking configuration in the stacking candidate graph based on the stacking feasibility scoring matrix, determine the mapping relationship between the military materials and the target storage positions, and generate a stacking scheme.

[0143] In a possible implementation, v is based on real-time warehouse data, and static structure data and dynamic state data of the current warehouse space are extracted

[0144] In a possible implementation, the acquisition module 201 is configured to extract material storage data, and the material storage data includes structure parameter data, danger level data, compatibility label data, and historical storage record data of the military materials to be stored.

[0145] The acquisition module 201 is configured to extract the spatial size parameter and the quality parameter of each military material according to the structure parameter data, and construct a four-dimensional size-quality vector.

[0146] The acquisition module 201 is configured to extract the heat sensitivity level, the vibration response level, the explosion risk level, and the electrostatic response level of each military material as discrete level variables according to the danger level data, and map them into a quantitative risk index vector.

[0147] The acquisition module 201 is configured to construct a Boolean vector with the same length as the set of known military material categories according to the compatibility label data.

[0148] The acquisition module 201 is configured to extract the historical stacking structure stability label, the historical environmental response curve, and the abnormal response record frequency according to the historical storage record data, construct an environmental sensitivity scoring quantization value based on rules, and add a heat accumulation response index, a stacking stability residual mean value, and an abnormal frequency factor to form a historical response vector.

[0149] The processing module 202 is configured to sequentially splice the four-dimensional size-quality vector, the quantitative risk index vector, the Boolean vector, and the historical response vector to form a complete adaptive feature vector of the military material.

[0150] The output module 203 is configured to organize all the adaptive feature vectors into an adaptive vector set.

[0151] In a possible implementation, the processing module 202 is configured to perform feature alignment in the attribute dimension by one-to-one comparison between each item of the set of adapted feature vectors and each item of the attribute vectors of the structured warehouse state matrix, ensure that the spatial size attribute vector of the structured warehouse state matrix and the bearing mass attribute vector in the four-dimensional size quality vector correspond based on the predefined attribute mapping index table, the quantitative risk index vector corresponds to the warehouse safety level label, the Boolean vector and the current shared stock label of the warehouse perform set intersection judgment, and the historical response vector and the historical accident response factor distribution of the warehouse are correspondingly compared and compared.

[0152] The processing module 202 is configured to sequentially perform matching rule calculation for each item of the stack adapted feature vector and each item of the warehouse attribute vector after completing the feature alignment.

[0153] The processing module 202 is configured to construct a stack adaptation score function according to the results of the plurality of matching rule calculations according to a preset weighting coefficient, and comprehensively generate an adaptation score value.

[0154] The processing module 202 is configured to determine a target adaptation score value higher than the dynamic safety threshold from the plurality of adaptation score values.

[0155] The processing module 202 is configured to mark the warehouse corresponding to the target adaptation score value as a stack position, and form a stack adaptation candidate warehouse set with a plurality of stack positions.

[0156] In a possible implementation, the processing module 202 is configured to calculate a spatial containment score, calculate a spatial containment score based on the three-dimensional geometric projection according to the spatial size attribute vector and the four-dimensional size quality vector, and measure the quality bearing margin score of the material quality data relative to the bearing mass attribute vector according to a proportional function.

[0157] The processing module 202 is configured to calculate a risk response compatibility score by the quantitative risk index vector and the warehouse safety level label, and obtain a safety matching degree by comparison.

[0158] The processing module 202 is configured to calculate a compatibility label matching score according to the Boolean vector and the current shared stock label of the warehouse, and judge whether there is an unshareable conflict.

[0159] The processing module 202 is configured to use the residual sum of squares of the historical response vector and the historical accident response factor distribution of the warehouse as a fitting index score to evaluate the fitting degree of the historical environment response.

[0160] In a possible implementation, the processing module 202 is configured to take the stacking feasibility scoring matrix as input, and evaluate each bin in the stacking adaptation candidate bin set one by one, where each element in the stacking feasibility scoring matrix corresponds to a matching score of a bin and the military supplies in multiple dimensions, and the stacking feasibility scoring matrix includes the space accommodation degree score, the mass load margin score, the risk response compatibility score, the compatibility label matching score, and the fitting index score.

[0161] The processing module 202 is configured to perform weighted fusion on the space accommodation degree score, the mass load margin score, the risk response compatibility score, the compatibility label matching score, and the fitting index score based on the weighting coefficient, to obtain a total stacking feasibility score of the bin.

[0162] In a possible implementation, the processing module 202 is configured to take each element in the stacking feasibility scoring matrix as a weight of an edge, and construct a stacking candidate graph, where each node represents a bin or an item of military supplies, and an edge between nodes represents the adaptability between a bin and a supply, and the weight of the edge is the total stacking feasibility score.

[0163] The processing module 202 is configured to search the stacking candidate graph using a global optimization algorithm to seek a stacking configuration scheme.

[0164] The processing module 202 is configured to calculate a fitness value for each stacking configuration scheme, where the fitness value is a weighted sum of the total stacking feasibility scores in the stacking feasibility scoring matrix.

[0165] The processing module 202 is configured to filter out an optimal stacking configuration from the plurality of stacking configurations according to the fitness values after a plurality of iterations, where the optimal stacking configuration includes a mapping relationship between each item of military supplies and a target bin, and generate a stacking scheme.

[0166] It should be noted that the apparatus provided in the above embodiments is used to implement its functions, and the above division of functional modules is used as an example for illustration. In actual applications, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the apparatus is divided into different functional modules to complete all or part of the above described functions. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is described in the method embodiments, which will not be repeated here.

[0167] The embodiment further discloses an electronic device, which refers to Figure 3 The electronic device can include at least one processor 301, at least one communication bus 302, a user interface 303, a network interface 304, and at least one memory 305.

[0168] The communication bus 302 is configured to realize the connection communication between the components.

[0169] The user interface 303 can include a display and a camera. Optionally, the user interface 303 can further include a standard wired interface and a wireless interface.

[0170] The network interface 304 can optionally include a standard wired interface and a wireless interface (e.g., a WI-FI interface).

[0171] The processor 301 can include one or more processing cores. The processor 301 is connected to various parts of the server through various interfaces and lines, and performs various functions and processes data of the server by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 301 can be integrated with a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU is mainly used to process an operating system, a user interface, and an application program. The GPU is used to render and draw the content to be displayed on the display. The modem is used to process wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 301, but can be implemented by a separate chip.

[0172] The memory 305 can include a random access memory (RAM) and can also include a read-only memory (ROM). Optionally, the memory includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 305 can include a program storage area and a data storage area, where the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described above, and the like. The data storage area can store data involved in the various method embodiments described above, and the like. The memory 305 can also optionally be at least one storage device located away from the aforementioned processor 301. The memory 305, as a computer storage medium, can include an operating system, a network communication module, a user interface 303 module, and an application program of an intelligent stacking method.

[0173] In Figure 3 In the electronic device shown, the user interface 303 is mainly used to provide an interface for user input and obtain data input by the user. The processor 301 can be used to call an application program of an intelligent stacking method stored in the memory 305, and when executed by one or more processors 301, cause the electronic device to perform the method of one or more of the above embodiments.

[0174] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the action sequence described, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0175] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0176] In several embodiments provided by the present application, it should be understood that the disclosed apparatus can be implemented in other manners. For example, the division of the apparatus embodiments is merely illustrative, and the division of units can be changed according to actual needs. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0177] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0178] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can be physically present separately, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0179] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part of the prior art that contributes to the technical solutions or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium 305 and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method of each embodiment of the present application. The aforementioned storage medium 305 includes: a U disk, a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0180] The present application also discloses a computer readable storage medium, which stores instructions. When executed by one or more processors 301, the electronic device executes one or more methods as described in the above embodiments.

[0181] The above merely show example embodiments of the present disclosure, and cannot limit the scope of the present disclosure. That is, equivalent changes and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon considering the specification and practice of the present disclosure. The present disclosure is intended to cover any variations, uses, or adaptive changes of the present disclosure following the general principles thereof and including those art-recognized equivalents and adaptations that are within the scope of the present disclosure. The specification and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are to be limited only by the claims.

Claims

1. A smart stacking method, characterized in that, The method includes: Obtain real-time warehouse data from the warehouse management system and construct a structured warehouse status matrix; Extract the material storage data of the military materials to be put into storage, and construct the adaptation vector set of the military materials to be put into storage; The set of adaptation vectors is matched with the structured warehouse state matrix to determine the set of candidate stacking adaptation locations; The stacking feasibility scoring matrix is ​​used to evaluate the set of candidate storage locations for stacking adaptation. Based on the stacking feasibility scoring matrix, the globally optimal stacking configuration is searched in the stacking candidate map to determine the mapping relationship between the military materials and the target storage location, thereby generating a stacking scheme; The step of extracting the storage data of the military supplies to be stored and constructing the adaptation vector set of the military supplies to be stored specifically includes: Extract the material storage data, which includes the structural parameter data, hazard level data, compatibility label data, and historical storage record data of the military materials to be stored. Based on the structural parameter data, the spatial dimension parameters and mass parameters of each military material are extracted, and a four-dimensional dimension-mass vector is constructed. For the aforementioned hazard level data, the thermal sensitivity level, vibration response level, explosion risk level, and electrostatic response level of each military material are extracted as discrete level variables and mapped to a quantitative risk index vector. For the aforementioned compatibility tag data, construct a Boolean vector with the same length as the complete set of known military material categories; For the historical stored record data, historical stacking structure stability labels, historical environmental response curves and abnormal response record frequencies are extracted. Based on rules, an environmental sensitivity score quantification value is constructed, and a thermal accumulation response index, the average stacking stability residual, and an abnormal frequency factor are added to form a historical response vector. The four-dimensional size mass vector, the quantitative risk index vector, the Boolean vector, and the historical response vector are sequentially concatenated to form a complete adaptation feature vector for military materials. All the aforementioned adaptation feature vectors are organized into the adaptation vector set.

2. The intelligent stacking method according to claim 1, characterized in that, The process of acquiring real-time warehouse data from the warehouse management system and constructing a structured warehouse status matrix specifically includes: Based on the real-time warehouse data, extract the static structure data and dynamic status data of the current warehouse space; Based on the static structure data and the dynamic status data, a unique number is established for each position and a multi-field data table is generated. The multi-field data table is logically grouped according to spatial regions to construct a regional index mapping table, thereby generating the structured warehouse status matrix. In the structured warehouse status matrix, each row corresponds to a warehouse location attribute vector, and each column corresponds to a specific attribute dimension.

3. The intelligent stacking method according to claim 1, characterized in that, The step of matching the set of adaptation vectors with the structured warehouse state matrix to determine the set of candidate stacking locations specifically includes: Each of the adaptation feature vectors in the adaptation vector set is compared one-to-one with each warehouse attribute vector in the structured warehouse state matrix. Feature alignment operation is performed on the attribute dimension. Based on the predefined attribute mapping index table, it is ensured that the four-dimensional size quality vector corresponds to the spatial size attribute vector and the bearing capacity attribute vector of the structured warehouse state matrix. The quantitative risk index vector corresponds to the warehouse safety level label. The Boolean vector is used to determine the set intersection with the current co-stacked material label of the warehouse. The historical response vector is used to perform a corresponding regression comparison with the historical accident response factor distribution of the warehouse. After feature alignment is completed, matching rules are calculated sequentially for each stacking adaptation feature vector and each warehouse location attribute vector. Based on the results calculated by multiple matching rules, a stacking adaptation scoring function is constructed according to a preset weighting coefficient, and an adaptation score value is generated comprehensively. Determine the target adaptation score that is higher than the dynamic safety threshold from among multiple adaptation score values; The warehouse corresponding to the target adaptation score is marked as a stacking position, and multiple stacking positions constitute the stacking adaptation candidate warehouse set.

4. The intelligent stacking method according to claim 3, characterized in that, After feature alignment is completed, matching rule calculations are performed sequentially for each stacking adaptation feature vector and each warehouse location attribute vector, specifically including: Calculate the spatial containment score based on the spatial size attribute vector and the four-dimensional size mass vector according to the three-dimensional geometric projection. Calculate and measure the mass bearing margin score of the material quality data relative to the bearing mass attribute vector according to the proportional function. The risk response compatibility score is calculated by comparing the quantitative risk index vector with the position safety level label to obtain the safety matching degree. Calculate the compatibility tag matching score based on the Boolean vector and the current co-pile material tag of the warehouse to determine whether there is a non-co-pile conflict. The sum of squared residuals between the historical response vector and the distribution of historical accident response factors of the warehouse is used as a fitting index to evaluate the fit of historical environmental response.

5. The intelligent stacking method according to claim 4, characterized in that, The evaluation of the stacking feasibility scoring matrix based on the stacking suitability candidate storage location set specifically includes: Using the stacking feasibility scoring matrix as input, each storage location in the stacking adaptation candidate storage location set is evaluated one by one. Each element in the stacking feasibility scoring matrix corresponds to the matching score of a storage location and military materials in multiple dimensions. The stacking feasibility scoring matrix includes the space capacity score, the quality carrying capacity margin score, the risk response compatibility score, the compatibility label matching score, and the fitting index score. The space capacity score, the mass carrying capacity margin score, the risk response compatibility score, the compatibility label matching score, and the fitting index score are weighted and fused based on weighted coefficients to obtain the total stacking feasibility score of the warehouse.

6. The intelligent stacking method according to claim 1, characterized in that, The process of searching for the globally optimal stacking configuration in the candidate stacking map based on the stacking feasibility scoring matrix, determining the mapping relationship between the military supplies and the target storage location, and thus generating a stacking scheme specifically includes: Each element in the stacking feasibility score matrix is ​​used as the weight of an edge to construct a stacking candidate graph, where each node represents a storage location or a military supply item, the edges between nodes represent the compatibility between the storage location and the supply item, and the weight of the edge is the total stacking feasibility score. The global optimization algorithm is used to search the candidate stacking map to find a stacking configuration scheme; For each of the stacking configuration schemes, a fitness value is calculated, which is the result of a weighted sum of the total stacking feasibility scores in the stacking feasibility scoring matrix; After multiple iterations, the optimal stacking configuration among the multiple stacking configuration schemes is selected based on the fitness value. The optimal stacking configuration includes the mapping relationship between each military material and the target storage location, and a stacking scheme is generated.

7. An intelligent stacking device, characterized in that, The apparatus is used to execute an intelligent stacking method as described in any one of claims 1-6, the apparatus comprising an acquisition module, a processing module, and an output module, wherein: The acquisition module is used to acquire real-time warehouse data from the warehouse management system and construct a structured warehouse status matrix. The processing module is used to extract the material storage data of the military materials to be put into storage and construct the adaptation vector set of the military materials to be put into storage. The processing module is used to match the set of adaptation vectors with the structured warehouse state matrix to determine the set of candidate stacking adaptation locations. The processing module is used to evaluate the stacking suitability candidate warehouse set based on the constructed stacking feasibility scoring matrix; The output module is used to search for the globally optimal stacking configuration in the stacking candidate map based on the stacking feasibility scoring matrix, determine the mapping relationship between the military materials and the target storage location, and thus generate a stacking scheme.

8. An electronic device, characterized in that, The device includes a processor, a communication bus, a user interface, a network interface, and a memory. The memory is used to store instructions. The user interface and the network interface are both used to communicate with other devices. The communication bus is used to enable communication between the components within the electronic device. The processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the method as described in any one of claims 1-6.

Images