A Warehouse Performance Diagnosis and Evaluation Method and System

Abstract

The present invention belongs to the field of warehouse diagnosis, and particularly relates to a warehouse performance diagnosis and evaluation method and system, including: obtaining a distributed three-dimensional virtual warehouse by using a three-dimensional modeling algorithm based on different warehouse attributes, then combining a reinforcement screening scheduling model with an evaluation correlation index library with a built-in hierarchical correlation index space to obtain a set of differential correlation evaluation indexes, then using this index set and the correlation evaluation model configured for each three-dimensional virtual warehouse to obtain a distributed evaluation result level cluster, and finally, according to the preset differential area evaluation result mapping, mapping the evaluation results to the corresponding three-dimensional virtual warehouse areas in real time visually, and generating an evaluation solution synchronization mapping through an integrated reasoning model, so as to realize the effective diagnosis and visual mapping of the performance of different warehouses and different areas within the warehouse, and realize the rapid evaluation of large warehouse groups and the recommendation of solutions.

Description

Technical Field

[0001] The present invention belongs to the field of warehouse diagnosis, and particularly relates to a warehouse performance diagnosis and evaluation method and system. Background Art

[0002] In the modern logistics system, as a key link, the operation efficiency, accuracy, and space utilization of warehouses have an increasingly significant impact on the competitiveness of enterprises. With the rapid development of industries such as e-commerce, the scale and business complexity of warehouses have been continuously increasing, and traditional performance evaluation methods are no longer able to meet the needs of enterprises. Existing methods often focus on single indicators, such as only paying attention to efficiency or accuracy, ignoring the correlations between various indicators, and unable to comprehensively reflect the operation status of warehouses. At the same time, the existing evaluation methods lack a clear and well-structured evaluation index system, unable to strictly evaluate the operating efficiency of each large warehouse cluster, resulting in the inability to detect specific defects and associated defect configurations corresponding to each warehouse, leading to a decline in efficiency. For example, a performance evaluation method for an intelligent warehouse of measuring instruments disclosed in a Chinese patent application with the publication number CN111915129A uses the principal component analysis method for dimensionality reduction. Although the indicators are simplified, due to over-reliance on the linear correlation hypothesis, information on non-linear correlation indicators is lost, and the implicit costs in the intelligent warehouse cannot be reflected; while a warehouse performance evaluation method based on the cloud model disclosed in a Chinese patent application with the publication number CN116644991A evaluates based on the cloud model. Since the weights are determined by expert experience, it is difficult to capture the dynamic coupling relationship between indicators, resulting in sorting bottlenecks during large promotions. Moreover, existing methods mostly focus on single-warehouse evaluation and cannot locate cross-warehouse associated defects in the warehouse cluster. Its essence is limited to static mapping, lacking a full-factor index network and dynamic causal reasoning capabilities. Therefore, the present invention provides a warehouse performance diagnosis and evaluation method and system. Summary of the Invention

[0003] Aiming at the deficiencies of the prior art, the present invention proposes a warehouse performance diagnosis and evaluation method and system, including: using a three-dimensional modeling algorithm based on different warehouse attributes to obtain a distributed three-dimensional virtual warehouse, then combining a reinforcement screening and scheduling model with an evaluation association index library with a built-in hierarchical association index space to obtain a set of differential association evaluation indicators, then using this set of indicators and the association evaluation models configured for each three-dimensional virtual warehouse to obtain a distributed evaluation result level cluster, and finally, according to the preset differential region evaluation result mapping, mapping the evaluation results to the corresponding three-dimensional virtual warehouse regions in real-time visualization, and generating an evaluation solution synchronization mapping through an integrated reasoning model, realizing effective diagnosis and visualization mapping of the performance of different warehouses and different regions within the warehouse, and achieving rapid evaluation and solution recommendation for large warehouse groups.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A warehouse performance diagnosis and evaluation method, comprising:

[0006] Based on different warehouse attributes and combined with a three-dimensional modeling algorithm, a distributed three-dimensional virtual warehouse is obtained;

[0007] Based on the distributed three-dimensional virtual warehouse, combined with a reinforcement screening scheduling model and an evaluation correlation index library, a set of differential correlation evaluation indexes is obtained;

[0008] The evaluation correlation index library has a hierarchical correlation index space built by a topological algorithm and a graph algorithm based on a three-level evaluation index set;

[0009] Based on the set of differential correlation evaluation indexes and combined with the correlation evaluation model configured for each three-dimensional virtual warehouse, a distributed evaluation result level cluster is obtained;

[0010] Based on the distributed evaluation result level cluster and combined with a preset differential area evaluation result mapping, the evaluation results are visually mapped to the corresponding three-dimensional virtual warehouse area in real time, and at the same time, through the configured integrated reasoning model, an evaluation solution is generated and synchronously mapped to the corresponding visual area of the three-dimensional virtual warehouse.

[0011] Specifically, the three-level evaluation index set includes a first evaluation index set, a second evaluation index set, and a third evaluation index;

[0012] Specifically, the rank order of the first evaluation index set, the second evaluation index set, and the third evaluation index is: the first evaluation index set > the second evaluation index set > the third evaluation index set; the first evaluation index set includes an efficiency index, an accuracy rate index, and a space utilization rate index;

[0013] Specifically, the second evaluation index set includes receiving timeliness, shelving timeliness, shelving delay rate, inbound throughput, picking timeliness, outbound throughput, order processing timeliness, per capita picking efficiency, equipment utilization rate, inventory accuracy rate, picking accuracy rate, shelving accuracy rate, storage capacity utilization rate, and shelf storage density;

[0014] The efficiency index includes receiving timeliness, shelving timeliness, shelving delay rate, inbound throughput, picking timeliness, outbound throughput, order processing timeliness, per capita picking efficiency, and equipment utilization rate;

[0015] The accuracy rate index includes inventory accuracy rate, picking accuracy rate, and shelving accuracy rate; the space utilization rate index includes storage capacity utilization rate and shelf storage density.

[0016] Specifically, the receiving timeliness includes the acceptance completion time, arrival time, and total inbound batch quantity in the third evaluation index set; the shelving timeliness includes the total number of items shelved per day and the total working hours of shelving personnel in the third evaluation index set; the shelving delay rate includes the number of orders not shelved on time and the total number of shelving orders in the third evaluation index set; the inbound throughput includes the total number of items received per day and the warehouse operation duration in the third evaluation index set; the picking timeliness includes the picking start time, order creation time, and total number of orders in the third evaluation index set; the outbound throughput includes the total number of items shipped per day and the warehouse operation duration in the third evaluation index set; the order processing timeliness includes the order completion time, order creation time, and total number of orders in the third evaluation index set; the per capita picking efficiency includes the total picking quantity and the working hours of picking personnel in the third evaluation index set; the equipment utilization rate includes the actual running time of the equipment and the planned available time in the third evaluation index set;

[0017] The inventory accuracy rate includes the number of correctly counted SKUs and the total number of SKUs counted in the third evaluation index set; the picking accuracy rate includes the number of error-free order lines and the total number of shipped order lines in the third evaluation index set; the shelving accuracy rate includes the number of correctly shelved storage locations and the total number of shelved storage locations in the third evaluation index set;

[0018] The storage space utilization rate includes the occupied storage volume and the total storage volume of the warehouse in the third evaluation index set; the shelf storage density includes the actual storage quantity of SKUs and the theoretical maximum storage quantity of the shelf in the third evaluation index set.

[0019] Specifically, the steps for constructing the hierarchical correlation index space include:

[0020] Construct the first index node layer in the evaluation correlation index library based on the index variables in the first evaluation index set, construct the second index node layer in the evaluation correlation index library based on the index variables in the second evaluation index set, and construct the third index node layer in the evaluation correlation index library based on the index variables in the third evaluation index set;

[0021] Based on the inclusion relationships of the index variables corresponding to the first evaluation index set, the second evaluation index set, and the third evaluation index, construct the corresponding first-layer inter-index connection and second-layer inter-index connection between the first index node layer and the second index node layer and between the second index node layer and the third index node layer;

[0022] Obtain the historical evaluation index combinations of different types of warehouses, the index frequency of each index variable, the combined index frequency between different index variables in the second evaluation index set and the third evaluation index set, and the maximum efficiency index, accuracy rate index, and space utilization rate index results in the first evaluation index set corresponding to the historical evaluation index combinations, and construct the index correlation data set;

[0023] Based on the index correlation data set, through the correlation algorithm, obtain the correlation degrees between the index variables in the second evaluation index set and the correlation degrees between the index variables in the third evaluation index set.

[0024] Specifically, the steps for constructing the hierarchical correlation index space further include:

[0025] Based on the correlation degrees between the index variables in the second evaluation index set, construct a second relationship connection set between the nodes in the second index node layer;

[0026] Based on the correlation degrees between the index variables in the third evaluation index set, construct a third relationship connection set between the nodes in the third index node layer;

[0027] Based on the inter-layer index connection, the second relationship connection set, the third relationship connection set, and the first index node layer, the second index node layer, and the third index node layer, construct a hierarchical correlation index space through the topological space algorithm;

[0028] Based on the correlation degrees on the hierarchical correlation index space and the corresponding connection relationships, through the graph algorithm combined with the density function in the density clustering algorithm, perform cyclic community clustering on the index variables in the second index node layer and the third index node layer respectively;

[0029] When the modularity corresponding to each clustering community after community clustering in the second index node layer and the third index node layer and the density of the neighboring nodes corresponding to each node in the corresponding community are a fixed value, then stop the cyclic community clustering, and obtain the second community clustering node group and the third community clustering node group corresponding to the second index node layer and the third index node layer respectively;

[0030] Take each community clustering node group in the second community clustering node group and the third community clustering node group as a super node, and construct a hierarchical super node correlation space through the hypergraph algorithm.

[0031] Specifically, the steps for constructing the hierarchical correlation index space further include:

[0032] Based on the index variables between the layers in the hierarchical correlation index space, set a visualization contribution mapping, specifically:

[0033] When at the current moment, through the enhanced screening scheduling model combined with the warehouse attribute configuration to be evaluated at the current moment, all the index variables are screened from the first evaluation index set, N variable indexes are screened from the second evaluation index set, and M index variables are screened from the third evaluation index set, construct a warehouse evaluation variable index set to be evaluated;

[0034] Input the set of evaluation variable indicators of the warehouse to be evaluated into the hierarchical evaluation model constructed by combining the comprehensive fuzzy evaluation algorithm with the autocorrelation function, obtain the evaluation scores corresponding to each evaluation indicator in the first evaluation indicator set, and screen the second and third evaluation indicator sets. Construct the second autocorrelation contribution degree space and the third autocorrelation contribution degree space corresponding to N and M variable indicators, and the inter-layer contribution degree space constructed by the inter-layer contribution degree of the third evaluation indicator to the second evaluation indicator and the inter-layer contribution degree of the second evaluation indicator to the first evaluation indicator.

[0035] Specifically, the construction steps of the hierarchical correlation index space further include:

[0036] Based on the magnitude and sign of the autocorrelation contribution between adjacent two index variables in the third autocorrelation contribution degree space, combined with the preset color type and color gradient, construct the intra-layer visualization contribution mapping between adjacent two index variables;

[0037] Embed the intra-layer visualization contribution mapping into the corresponding third relationship connection set of the third index node layer to obtain the visualized third index node layer. Similarly, use the second autocorrelation contribution degree space to obtain the visualized second index node layer;

[0038] Based on the preset color type and color gradient and the magnitude and sign of the inter-layer contribution degree of the third evaluation indicator to the second evaluation indicator in the inter-layer contribution degree space, obtain the second inter-layer visualization mapping between the second index node layer and the third index node layer. Similarly, obtain the first inter-layer visualization mapping through the inter-layer contribution degree of the second evaluation indicator to the first evaluation indicator;

[0039] Embed the first inter-layer visualization mapping and the second inter-layer visualization mapping into the corresponding first inter-layer index connection and second inter-layer index connection between the first index node layer and the second index node layer and between the second index node layer and the third index node layer to obtain the visualized hierarchical correlation index space corresponding to the warehouse to be evaluated;

[0040] When the evaluation and corresponding solution push for the warehouse to be evaluated are completed, automatically eliminate the visualization mapping on the corresponding intra-layer connections in the inter-layer index connection, the visualized second index node layer, and the visualized third index node layer, and mark the visualization mapping corresponding to the current warehouse to be evaluated and trace the historical evaluation;

[0041] Map the above visualization process of the evaluation of the current warehouse to be evaluated to all warehouses in the distributed control evaluation for the visualization evaluation mapping of the corresponding warehouses.

[0042] Specifically, the construction process of the mapping of the differential area evaluation result includes:

[0043] Use the spatial three-dimensional coordinates of the three-dimensional virtual warehouse corresponding to the currently described warehouse to be evaluated as the pixel projection coordinates;

[0044] Use the colors and color gradients corresponding to the connection relationships in the visual hierarchical association index space corresponding to the currently described warehouse to be evaluated, and combine the spatial index variables in the space utilization index with the dynamic LOD algorithm to construct a differential region evaluation result mapping;

[0045] Map the colors and color gradients corresponding to the connection relationships in the visual hierarchical association index space corresponding to the currently described warehouse to be evaluated through the differential region evaluation result mapping into the pixel projection coordinates corresponding to the currently warehouse to be evaluated, and obtain a three-dimensional virtual warehouse with regional visualization.

[0046] Specifically, the enhanced screening scheduling model is constructed by G enhanced screening scheduling sub-models; the G enhanced screening scheduling sub-models are integrated into the edge control nodes corresponding to Q warehouses;

[0047] Specifically, the screening process of the enhanced screening scheduling sub-model includes:

[0048] Establish a frequent index variable set through the set of warehouse evaluation variable indicators corresponding to each warehouse after each evaluation;

[0049] Establish a frequent index connection between the frequent index variable set and the corresponding enhanced screening scheduling sub-model, and embed the frequent index connection into the corresponding enhanced screening scheduling sub-model;

[0050] When evaluating the warehouse corresponding to the current enhanced screening scheduling sub-model, through the frequent index connection combined with the attribute configuration of the currently warehouse to be evaluated, index the set of warehouse evaluation variable indicators from the evaluation association index library, and feedback the index frequency and joint index frequency of the corresponding index variables to the hierarchical association index space to adjust the association degree marked by the corresponding connection relationships within and between layers in real time;

[0051] When the set of warehouse evaluation variable indicators to be evaluated by the current index does not belong to any community clustering node group in the hierarchical association index space, construct a new community clustering node group through the set of warehouse evaluation variable indicators to be evaluated by the current index and save the index variables as a new super-node in the hierarchical super-node association space and construct a frequent index connection.

[0052] A warehouse performance diagnosis and evaluation system includes: a three-dimensional simulation module, an index screening module, an evaluation module, and a mapping and recommendation module;

[0053] The three-dimensional simulation module obtains a distributed three-dimensional virtual warehouse based on different warehouse attributes and a three-dimensional modeling algorithm;

[0054] The index screening module obtains a set of differential correlation evaluation indexes based on a distributed three-dimensional virtual warehouse, combined with a reinforcement screening scheduling model and an evaluation correlation index library;

[0055] The evaluation module obtains a distributed evaluation result level cluster based on the set of differential correlation evaluation indexes combined with the correlation evaluation model configured for each three-dimensional virtual warehouse;

[0056] The mapping and recommendation module, based on the distributed evaluation result level cluster combined with the preset mapping of differential regional evaluation results, visually maps the evaluation results in real time to the corresponding three-dimensional virtual warehouse area. At the same time, through the configured integrated reasoning model, an evaluation solution is generated and synchronously mapped to the corresponding visual area of the three-dimensional virtual warehouse.

[0057] Compared with the prior art, the beneficial effects of the present invention are:

[0058] Aiming at the deficiencies of the prior art, the present invention obtains a set of differential correlation evaluation indexes by constructing a distributed three-dimensional virtual warehouse combined with a reinforcement screening scheduling model and an evaluation correlation index library, comprehensively considering various indexes in warehouse operation. Among them, the evaluation correlation index library is constructed through a hierarchical correlation index space, based on a three-level evaluation index set, considering the inclusion relationship and correlation degree among various indexes, making up for the deficiencies of the existing methods that focus on single indexes and ignore index correlations, and can comprehensively reflect the warehouse operation status. Secondly, through visual contribution mapping, complex index correlations and existing warehouse operation defects are presented in an intuitive manner, accurately finding specific warehouse defects and associated defect configurations, generating more accurate solutions, effectively avoiding benefit decline, and improving the level of warehouse operation management. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a flowchart of a warehouse performance diagnosis and evaluation method according to Embodiment 1 of the present invention;

[0060] Figure 2 It is an architecture diagram of the construction of a hierarchical correlation index space according to Embodiment 1 of the present invention;

[0061] Figure 3 It is a module diagram of a warehouse performance diagnosis and evaluation system according to Embodiment 2 of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0062] Embodiment 1

[0063] Please refer to Figure 1 , an embodiment provided by the present invention: a warehouse performance diagnosis and evaluation method, the steps include:

[0064] S1. Based on different warehouse attributes and combined with a three-dimensional modeling algorithm, obtain a distributed three-dimensional virtual warehouse;

[0065] Further, in this embodiment, a texture mapping algorithm is specifically combined with a 3D modeling algorithm and the actual attributes of different warehouses to configure and synchronously construct a virtual 3D model and simulate the operation process, and the overall evaluation process is cyclically corrected.

[0066] S2. Based on the distributed 3D virtual warehouse, combining the enhanced screening scheduling model and the evaluation correlation index library, obtain a set of differential correlation evaluation indexes;

[0067] Further, the set of differential correlation evaluation indexes in this embodiment is constructed from the evaluation variable index sets corresponding to each warehouse.

[0068] Further, the enhanced screening scheduling model in this embodiment is constructed by integrating G enhanced screening scheduling sub-models in a federated manner;

[0069] Further, in this embodiment, the G enhanced screening scheduling sub-models are integrated into the edge control nodes corresponding to the Q warehouses;

[0070] Further, in this embodiment, G and Q are numerically equal, and when the number of warehouses to be evaluated increases, the corresponding enhanced screening scheduling sub-models are synchronously increased.

[0071] Further, all the enhanced screening scheduling sub-models in this embodiment are constructed by the SAC algorithm and are simulated and trained in the above-mentioned distributed 3D virtual warehouse to obtain a trained enhanced screening scheduling model;

[0072] The evaluation correlation index library has a hierarchical correlation index space built according to a three-level evaluation index set through a topology algorithm and a graph algorithm;

[0073] Further, the three-level evaluation index set in this embodiment includes a first evaluation index set, a second evaluation index set, and a third evaluation index set;

[0074] The rank order of the first evaluation index set, the second evaluation index set, and the third evaluation index set is: first evaluation index set > second evaluation index set > third evaluation index set; the first evaluation index set includes efficiency indexes, accuracy indexes, and space utilization indexes;

[0075] The second evaluation index set includes receiving timeliness, shelving timeliness, shelving delay rate, inbound throughput, picking timeliness, outbound throughput, order processing timeliness, per capita picking efficiency, equipment utilization rate, inventory accuracy, picking accuracy, shelving accuracy, storage capacity utilization rate, and shelf storage density;

[0076] The efficiency indicators include receiving efficiency, shelving efficiency, shelving delay rate, inbound throughput, picking efficiency, outbound throughput, order processing efficiency, per capita picking efficiency, and equipment utilization rate;

[0077] The accuracy indicators include inventory accuracy, picking accuracy, and shelving accuracy; the space utilization indicators include storage capacity utilization rate and shelf storage density.

[0078] The receiving efficiency includes the acceptance completion time, arrival time, and total inbound batch quantity in the third set of evaluation indicators; the shelving efficiency includes the total number of items shelved per day and the total working hours of shelving personnel in the third set of evaluation indicators; the shelving delay rate includes the number of orders not shelved on time and the total number of shelving orders in the third set of evaluation indicators; the inbound throughput includes the total number of items received per day and the warehouse operation duration in the third set of evaluation indicators; the picking efficiency includes the picking start time, order creation time, and total number of orders in the third set of evaluation indicators; the outbound throughput includes the total number of items shipped per day and the warehouse operation duration in the third set of evaluation indicators; the order processing efficiency includes the order completion time, order creation time, and total number of orders in the third set of evaluation indicators; the per capita picking efficiency includes the total number of items picked and the working hours of picking personnel in the third set of evaluation indicators; the equipment utilization rate includes the actual running time of the equipment and the planned available time in the third set of evaluation indicators;

[0079] The inventory accuracy includes the number of correctly inventoried SKUs and the total number of SKUs inventoried in the third set of evaluation indicators; the picking accuracy includes the number of error-free order lines and the total number of shipped order lines in the third set of evaluation indicators; the shelving accuracy includes the number of correctly shelved positions and the total number of shelved positions in the third set of evaluation indicators;

[0080] The storage capacity utilization rate includes the occupied storage volume and the total storage volume of the warehouse in the third set of evaluation indicators; the shelf storage density includes the actual storage quantity of SKUs and the theoretical maximum storage quantity of the shelf in the third set of evaluation indicators.

[0081] Furthermore, in order to better illustrate the data sources corresponding to the indicator variables in the above-mentioned first set of evaluation indicators, second set of evaluation indicators, and third set of evaluation indicators, the relationship between the second set of evaluation indicators and the third set of evaluation indicators, and the actual business significance corresponding to the corresponding indicators in this embodiment, the relationships between the first set of evaluation indicators, the second set of evaluation indicators, and the third set of evaluation indicators are specifically shown in Table 1, Table 2, and Table 3 below;

[0082] Table 1: Efficiency Indicators

[0083]

[0084] Table 2: Accuracy Indicators

[0085]

[0086] Table 3: Space Utilization Index

[0087]

[0088] Furthermore, in this embodiment, the meanings corresponding to the English abbreviations in the above Table 1, Table 2, and Table 3 are as follows:

[0089] SKU: Stock Keeping Unit, which is the code used to uniquely identify a commodity or product in inventory management. In warehouse management, different SKUs represent different types, specifications, models, etc. of commodities. For example, shampoos of different brands and different capacities will correspond to different SKUs.

[0090] RFID: Radio Frequency Identification, which is a wireless communication technology that can identify specific targets and read and write relevant data through radio signals without establishing mechanical or optical contact between the identification system and the specific target. In a warehouse scenario, it is often used for the tracking and inventory of goods. For example, by attaching RFID tags to goods, the information of the goods can be quickly obtained through a reader.

[0091] PDA: Personal Digital Assistant, which generally refers to a handheld terminal device in warehouse management. Staff can use the PDA for operations such as scanning barcodes of goods, data entry, and task confirmation. For example, when goods are put on shelves, the PDA is used to scan the barcodes of the goods and the storage locations to record the shelving information.

[0092] IoT: Internet of Things, which is a network that, through various information sensors, radio frequency identification technologies, global positioning systems, infrared sensors, laser scanners, and other devices and technologies, can collect real-time data of any objects or processes that need to be monitored, connected, and interacted with. Through various possible network accesses, it realizes the ubiquitous connection between things and things, and between things and people, and realizes the intelligent perception, identification, and management of items and processes. IoT device sensors in a warehouse can be used to monitor the warehouse environment (such as temperature and humidity), equipment status, etc.

[0093] AGV: Automated Guided Vehicle, which is a transportation device that can automatically drive along a preset path. It is often used for the handling of goods inside a warehouse, which can improve the handling efficiency and accuracy and reduce labor costs.

[0094] WMS: Warehouse Management System, which is an information system for managing and controlling resources such as materials, personnel, and equipment in a warehouse. It can realize functions such as inbound management, outbound management, inventory management, and location management. For example, the WMS inventory module can be used to conduct inventory operations on warehouse goods.

[0095] Further, please refer to Figure 2 , and the steps for constructing the hierarchical association index space in this embodiment include:

[0096] Construct the first index node layer in the evaluation association index library based on the index variables in the first evaluation index set, construct the second index node layer in the evaluation association index library based on the index variables in the second evaluation index set, and construct the third index node layer in the evaluation association index library based on the index variables in the third evaluation index set;

[0097] Based on the inclusion relationships of the index variables corresponding to the first evaluation index set, the second evaluation index set, and the third evaluation index, construct the corresponding first inter-layer index connection between the first index node layer and the second index node layer and the second inter-layer index connection between the second index node layer and the third index node layer;

[0098] Obtain the historical evaluation index combinations of different types of warehouses, the index variable index frequency of each, the combined index frequency between different index variables in the second evaluation index set and the third evaluation index set, and the maximum efficiency index, accuracy index, and space utilization index results in the first evaluation index set corresponding to the historical evaluation index combinations, and construct an index association data set;

[0099] Based on the index association data set, through an association algorithm, obtain the association degrees between the index variables in the second evaluation index set and the association degrees between the index variables in the third evaluation index set.

[0100] Based on the association degrees between the index variables in the second evaluation index set, construct a second relationship connection set between the nodes in the second index node layer;

[0101] Based on the association degrees between the index variables in the third evaluation index set, construct a third relationship connection set between the nodes in the third index node layer;

[0102] Based on the inter-layer index connection, the second relationship connection set, the third relationship connection set, and the first index node layer, the second index node layer, and the third index node layer, construct a hierarchical association index space through a topological space algorithm;

[0103] Based on the association degree on the hierarchical association index space and the corresponding connection relationship, through the graph algorithm combined with the density function in the density clustering algorithm, circular community clustering is respectively performed on the index variables in the second index node layer and the third index node layer;

[0104] When the modularity corresponding to each clustering community after community clustering in the second index node layer and the third index node layer and the density of adjacent nodes corresponding to each node in the corresponding community are a fixed value, the circular community clustering is stopped, and the second community clustering node group and the third community clustering node group corresponding to the second index node layer and the third index node layer are obtained respectively;

[0105] Regarding each community clustering node group in the second community clustering node group and the third community clustering node group as a super node, a hierarchical super node association space is constructed through the hypergraph algorithm.

[0106] Based on the index variables between each layer in the hierarchical association index space, a visual contribution mapping is set, specifically:

[0107] When at the current moment, through the enhanced screening scheduling model combined with the warehouse attribute configuration to be evaluated at the current moment, all index variables are screened from the first evaluation index set, N variable indicators are screened from the second evaluation index set, and M index variables are screened from the third evaluation index set, a warehouse evaluation variable index set to be evaluated is constructed;

[0108] Input the warehouse evaluation variable index set to be evaluated into a hierarchical evaluation model constructed by combining the comprehensive fuzzy evaluation algorithm with the autocorrelation function, obtain the evaluation scores corresponding to each evaluation index in the first evaluation index set, and screen the second autocorrelation contribution degree space and the third autocorrelation contribution degree space corresponding to the N and M variable indicators in the second and third evaluation index sets, and the inter-layer contribution degree space constructed by the inter-layer contribution degree of the third evaluation index to the second evaluation index and the inter-layer contribution degree of the second evaluation index to the first evaluation index;

[0109] Based on the magnitude and positive / negative of the autocorrelation contribution degree between adjacent two index variables in the third autocorrelation contribution degree space and in combination with the preset color type and color gradient, construct an intra-layer visual contribution mapping between adjacent two index variables;

[0110] Embed the intra-layer visual contribution mapping into the corresponding third relationship connection set of the third index node layer to obtain a visual third index node layer. Similarly, use the second autocorrelation contribution degree space to obtain a visual second index node layer;

[0111] Based on the preset color type, color gradient, and the third evaluation index in the inter-layer contribution degree space, obtain the magnitude and positive / negative of the inter-layer contribution degree corresponding to the second evaluation index, and acquire the second-layer inter-layer visualization mapping between the second index node layer and the third index node layer. Similarly, obtain the first-layer inter-layer visualization mapping through the inter-layer contribution degree of the first evaluation index corresponding to the second evaluation index;

[0112] Integrate the first-layer inter-layer visualization mapping and the second-layer inter-layer visualization mapping into the corresponding first-layer inter-layer index connection between the first index node layer and the second index node layer and the second-layer inter-layer index connection between the second index node layer and the third index node layer, to obtain the visualization hierarchical association index space corresponding to the warehouse to be evaluated;

[0113] When the evaluation of the warehouse to be evaluated and the corresponding solution push are completed, automatically eliminate the visualization mapping on the corresponding intra-layer connections in the inter-layer index connection, the visualization second index node layer, and the visualization third index node layer, and perform a retention mark and historical evaluation traceability on the visualization mapping corresponding to the current warehouse to be evaluated;

[0114] Map the above visualization evaluation process of the current warehouse to be evaluated to all the warehouses in the distributed control evaluation for the visualization evaluation mapping of the corresponding warehouses.

[0115] This process comprehensively evaluates the warehouse operation from multiple dimensions by constructing a distributed three-dimensional virtual warehouse, combining a reinforcement screening scheduling model and an evaluation association index library, using the first evaluation index set including efficiency indicators, accuracy indicators, and space utilization indicators, as well as the second evaluation index set covering receiving timeliness, shelving timeliness, etc. and the more refined third evaluation index set. For example, in the efficiency indicators, it covers the timeliness and throughput indicators of each link from receiving to shipping, which can comprehensively reflect the warehouse operation efficiency; the accuracy indicator ensures the accuracy of inventory and operations; the space utilization indicator focuses on the utilization of warehouse space resources, avoiding the limitation of only focusing on a single indicator and comprehensively reflecting the warehouse operation status. Among them, first, through the established three-level evaluation index set, the hierarchical order and inclusion relationship between the index sets are clarified, and a hierarchical association index space is constructed; based on the index variables, each layer of nodes is constructed, and the inter-layer index connection is established according to the index inclusion relationship. At the same time, the intra-layer relationship connection set is constructed considering the correlation degree between the index variables, which makes the evaluation system structure clear and can strictly evaluate the operation efficiency of each large warehouse cluster, accurately find out the specific defects and associated defect configurations of each warehouse; for example, when analyzing the shelving delay rate, through the correlation analysis with indicators such as receiving timeliness and inbound throughput, various factors affecting the shelving delay can be found, such as slow receiving speed leading to goods backlog affecting the shelving timeliness, so as to solve the problem targeted and avoid the decline in efficiency.

[0116] Secondly, an index correlation dataset is constructed by obtaining historical evaluation index combinations of different types of warehouses, index variable index frequencies, etc. Based on this, the correlation degree between index variables is obtained through a correlation algorithm, which provides data support for warehouse operation decisions and enables the formulation of more reasonable operation strategies based on historical data and index correlation relationships. For example, it is found that there is a strong correlation between inbound throughput and equipment utilization rate. When planning to increase inbound throughput, the equipment utilization rate can be evaluated in advance and corresponding measures can be taken, such as reasonably arranging equipment maintenance time to increase the available time of equipment to meet the needs of business growth. The setting of visual contribution mapping presents the evaluation process and results in an intuitive way. A hierarchical evaluation model is constructed through a comprehensive fuzzy evaluation algorithm combined with an autocorrelation function to obtain the evaluation scores of each index and the contribution degree space between different indexes. Then, based on these, intra-layer and inter-layer visual mappings are constructed to obtain a visual hierarchical correlation index space, which helps warehouse managers quickly understand complex index relationships and evaluation results and make more accurate decisions. For example, through the visual interface, managers can intuitively see which indexes have a greater impact on the overall efficiency, as well as the positive and negative correlation relationships between different indexes and the positive and negative contribution relationships to the final index, so as to adjust the operation strategy in a timely manner. At the same time, the visual mapping after evaluation retains the marks and historical evaluation traceability, which is convenient for subsequent review and analysis to continuously optimize warehouse operation management. In addition, in this process, according to the attributes of the warehouse to be evaluated currently, index variables are screened from different evaluation index sets to construct an evaluation variable index set, realizing the dynamic evaluation of different warehouses. This flexibility enables the evaluation method to adapt to the characteristics and needs of various types of warehouses. Regardless of the size of the warehouse and the differences in business types, effective performance diagnosis and evaluation can be carried out, improving the generality and practicality of the method.

[0117] S3. Based on the differential correlation evaluation index set and the correlation evaluation model configured for each three-dimensional virtual warehouse, a distributed evaluation result level cluster is obtained;

[0118] Furthermore, in this embodiment, through the correlation evaluation model, each warehouse is evaluated according to the differential correlation evaluation index set to obtain the corresponding evaluation results. At the same time, the correlation algorithm is combined to conduct a correlation evaluation on different warehouses belonging to the same user, and the correlation impact between the corresponding results of different warehouses corresponding to the same user is obtained. Cross-scheme adjustment is performed on all warehouses through the correlation impact.

[0119] S4. Based on the distributed evaluation result level cluster and the preset differential area evaluation result mapping, the evaluation results are visually mapped to the corresponding three-dimensional virtual warehouse area in real time. At the same time, through the configured integrated reasoning model, an evaluation solution is generated and synchronously mapped to the visual warehouse area corresponding to the three-dimensional virtual.

[0120] Further, in this embodiment, based on the above evaluation results and the contribution degrees corresponding to individual index variables, an integrated inference model (such as a deep inference algorithm) is used to generate personalized and actionable optimization suggestions and decision-making solutions. For example, according to the inventory out-of-stock risk and order priority, an order scheduling and replenishment strategy is automatically generated; for the equipment failure risk, a preventive maintenance plan is formulated, etc.; further, the evaluation in this embodiment not only focuses on the final result, but also on the influence degree of intermediate index variables, and can generate solutions to problems existing in each corresponding process in more detail, so that each process of warehouse operation can be well diagnosed and improved.

[0121] Further, the construction process of the mapping of the differential area evaluation results in this embodiment includes:

[0122] Taking the spatial three-dimensional coordinates of the three-dimensional virtual warehouse corresponding to the warehouse to be evaluated currently as pixel projection coordinates;

[0123] Further, the spatial three-dimensional coordinates of the three-dimensional virtual warehouse in this embodiment accurately define the geometric information of each position in the warehouse. By taking them as pixel projection coordinates, the evaluation results can be accurately mapped to the specific positions in the warehouse;

[0124] For example, in a large-scale stereoscopic warehouse, the positions of different shelves, the directions of aisles, etc. can be accurately represented by three-dimensional coordinates, thus providing an accurate position basis for subsequent visual mapping.

[0125] Furthermore, in this embodiment, the colors and color gradients corresponding to the connection relationships in the visual hierarchical association index space corresponding to the currently to-be-evaluated warehouse are used to construct a differential region evaluation result mapping through the spatial index variables in the space utilization index in combination with the dynamic LOD (Level of Detail) algorithm. The connection relationship colors and color gradients in the visual hierarchical association index space represent information such as the association degree and contribution degree between different indexes; while the spatial index variables in the space utilization index, such as the storage capacity utilization rate and the shelf storage density, reflect the usage situation of the warehouse space. The dynamic LOD algorithm can dynamically adjust the detail level of the model according to different requirements and scenarios; when constructing the mapping, different regions will be represented differentially according to the value conditions of the spatial index variables, in combination with colors and color gradients. For example, for regions with a high storage capacity utilization rate, brighter colors can be used, while for regions with a low utilization rate, darker colors can be used; at the same time, according to the dynamic LOD algorithm, when observing from a long distance, the detail level of the model can be reduced to improve the rendering efficiency, and when observing from a short distance, the details can be increased to make the display clearer; at the same time, it can also more intuitively show which efficiency indexes have a negative impact on the operation of the warehouse at the current moment, so as to better improve the warehouse operation process corresponding to the corresponding efficiency indexes;

[0126] Map the colors and color gradients corresponding to the connection relationships in the visual hierarchical association index space corresponding to the currently to-be-evaluated warehouse into the pixel projection coordinates corresponding to the currently to-be-evaluated warehouse through the differential region evaluation result mapping to obtain a three-dimensional virtual warehouse with regional visualization;

[0127] In this embodiment, through this step, the abstract evaluation results and index association information are transformed into an intuitive three-dimensional visualization effect. Warehouse managers can quickly understand which areas in the warehouse are operating well and which areas have problems by observing the three-dimensional virtual warehouse with regional visualization.

[0128] Furthermore, the screening process of the enhanced screening and scheduling sub-model in this embodiment includes:

[0129] Establish a frequent index variable set through the to-be-evaluated warehouse evaluation variable index set corresponding to each warehouse after each evaluation;

[0130] In this embodiment, when evaluating a warehouse, a large amount of evaluation variable index data will be generated. The establishment of the frequent index variable set is achieved by statistically analyzing this data to find the index variables that appear frequently in multiple evaluations. For example, in multiple evaluations of multiple warehouses, it is found that index variables such as receiving timeliness and inventory accuracy often appear, and they can be included in the frequent index variable set. These frequent index variables are usually key indicators that have a greater impact on the warehouse operation status. Paying attention to and analyzing them helps to more accurately evaluate the performance of the warehouse;

[0131] Establish a frequent index connection between the frequent index variable set and the corresponding enhanced screening and scheduling sub-model, and embed the frequent index connection into the corresponding enhanced screening and scheduling sub-model;

[0132] In this embodiment, the establishment of the frequent index connection is to quickly locate and obtain information related to the frequent index variables. By embedding the frequent index connection into the enhanced screening and scheduling sub-model, the sub-model can more efficiently access and process the data of these key index variables during the screening and scheduling operations. For example, when evaluating a certain warehouse, the enhanced screening and scheduling sub-model can quickly find the frequent index variables and their data related to the warehouse through the frequent index connection, improving the efficiency and accuracy of the evaluation.

[0133] When evaluating the warehouse corresponding to the current enhanced screening and scheduling sub-model, through the frequent index connection combined with the attributes configuration of the warehouse to be evaluated currently, index the evaluation variable index set of the warehouse to be evaluated from the evaluation associated index library, and feedback the index frequency and joint index frequency of the corresponding index variables to the hierarchical associated index space, and adjust the association degree marked by the corresponding connection relationship within and between layers in real time;

[0134] In the evaluation process of this embodiment, according to the specific attributes configuration of the warehouse, such as the type of the warehouse (such as cold storage warehouse, general warehouse, etc.), business model (such as wholesale, retail, etc.), etc., obtain the corresponding evaluation variable index set from the evaluation associated index library through the frequent index connection. At the same time, record the index frequency and joint index frequency of the index variables. These frequency information reflects the degree of association tightness between the index variables. After feeding back this information to the hierarchical associated index space, the association degree marked by the corresponding connection relationship within and between layers will be adjusted in real time according to the set rules. For example, if it is found that a certain index variable has a high index frequency in the evaluation of the current warehouse and a high joint index frequency with other index variables, the association degree of the connection relationship between this index variable and other related index variables can be appropriately increased to more accurately reflect their actual relationship.

[0135] When the set of evaluation variable metrics for the warehouse to be evaluated by the current index does not belong to any community clustering node group in the hierarchical association metric space, a new community clustering node group is constructed through the set of evaluation variable metrics for the warehouse to be evaluated by the current index and saved as a new supernode in the hierarchical supernode association space, and frequent index connections are built.

[0136] In the evaluation process of this embodiment, some new combinations of metric variables or special situations may occur. The set of evaluation variable metrics for the warehouse to be evaluated corresponding to these situations may not belong to the existing community clustering node groups. At this time, in order to effectively manage and analyze these new situations, a new community clustering node group will be constructed based on these metric sets and used as a new supernode in the hierarchical supernode association space. In the new supernode, the relevant metric variables will be saved and corresponding frequent index connections will be established to ensure the smooth progress of subsequent evaluation and analysis work. This can ensure that the hierarchical association metric space can continuously adapt to new situations and requirements, and improve the flexibility and adaptability of the entire evaluation system.

[0137] This process combines the association evaluation model with the differential association evaluation metric set. It can not only accurately evaluate a single warehouse, but also use the association algorithm to evaluate the association impact between different warehouses of the same user and make cross - scheme adjustments, realizing the overall optimization of warehouse operations, avoiding isolated evaluation, and enhancing comprehensive benefits. Visualize the distributed evaluation result level clusters by combining with a preset mapping. Use three - dimensional coordinates as pixel projection coordinates, and construct a mapping by combining spatial metric variables and the dynamic LOD algorithm. This can transform the abstract evaluation into an intuitive three - dimensional effect, and the color difference can also show the impact of efficiency metrics, facilitating managers to quickly locate problem areas and optimize the warehouse operation process. The enhanced screening and scheduling sub - model can quickly obtain key metric data by establishing a frequent set of metric variables and index connections, improving the evaluation efficiency and accuracy. Adjusting the association degree in real - time makes the metric relationship more in line with the actual situation and enhances the scientific nature of the evaluation. Constructing a new community clustering node group can adapt to new situations and improve the flexibility and adaptability of the evaluation system.

[0138] Embodiment 2

[0139] Please refer to Figure 3 , another embodiment provided by the present invention: A warehouse performance diagnosis and evaluation system, including: a three - dimensional simulation module, a metric screening module, an evaluation module, and a mapping and recommendation module;

[0140] The three - dimensional simulation module, based on different warehouse attributes and combined with three - dimensional modeling algorithms, obtains a distributed three - dimensional virtual warehouse;

[0141] The metric screening module, based on the distributed three - dimensional virtual warehouse and combined with the enhanced screening and scheduling model and the evaluation association metric library, obtains a differential association evaluation metric set;

[0142] The evaluation module obtains distributed evaluation result level clusters based on the difference-related evaluation indicator set combined with the associated evaluation model of each three-dimensional virtual warehouse configuration;

[0143] The mapping and recommendation module maps the evaluation results to the corresponding three-dimensional virtual warehouse area in real time based on the distributed evaluation result level cluster combined with the preset difference area evaluation result mapping. At the same time, through the configured integrated reasoning model, it generates the evaluation solution and synchronously maps it to the corresponding visualization area of ​​the three-dimensional virtual warehouse.

[0144] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in the field may also change, modify, replace and modify the above-mentioned embodiments without departing from the scope of protection of the purpose of the present invention and the claims, and all of these are within the protection of the present invention.

[0145] If the disclosed technical solution involves personal information, the product using the disclosed technical solution has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing the personal information. If the disclosed technical solution involves sensitive personal information, the product using the disclosed technical solution has obtained the individual's separate consent before processing the sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, clear and prominent signs are set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that he or she agrees to the collection of his or her personal information; or on the device that processes personal information, when the personal information processing rules are notified by obvious signs / information, the individual's authorization is obtained through pop-up information or by asking the individual to upload his or her personal information; among them, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

Claims

1. A method for diagnosing and evaluating warehouse performance, characterized in that, Including: Based on different warehouse attributes and combined with 3D modeling algorithms, obtain a distributed 3D virtual warehouse; Based on the distributed 3D virtual warehouse, combined with the enhanced screening scheduling model and the evaluation correlation index library, obtain a set of differential correlation evaluation indicators; The evaluation correlation index library has a built-in hierarchical correlation index space, and the hierarchical correlation index space is constructed by a topology algorithm and a graph algorithm based on a three-level evaluation index set; Based on the set of differential correlation evaluation indicators and combined with the correlation evaluation model configured for each 3D virtual warehouse, obtain a distributed evaluation result level cluster; Based on the distributed evaluation result level cluster and combined with the preset differential area evaluation result mapping, map the evaluation results to the corresponding 3D virtual warehouse area in real-time visualization. At the same time, through the configured integrated reasoning model, generate an evaluation solution and synchronously map it to the corresponding visualization area of the 3D virtual warehouse; The three-level evaluation index set includes a first evaluation index set, a second evaluation index set, and a third evaluation index set; The rank order corresponding to the first evaluation index set, the second evaluation index set, and the third evaluation index set is: the first evaluation index set > the second evaluation index set > the third evaluation index set; The construction steps of the hierarchical correlation index space include: First, based on the first evaluation index set, the second evaluation index set, and the third evaluation index set, construct corresponding three-layer index node layers respectively, and establish inter-layer index connections through the inclusion relationship of index variables; Second, collect historical evaluation data to form an index correlation data set, use the correlation algorithm to calculate the correlation degree between index variables in the second and third layers, construct an intra-layer relationship connection set, combine the inter-layer connection and the intra-layer connection, and apply the topological space algorithm to generate a hierarchical correlation index space; Third, perform cyclic community clustering on the second and third layers through the graph algorithm and density clustering, stop when the modularity and node density reach a fixed value, and use the clustering result as a super node to construct a hierarchical super node correlation space; Finally, based on the selected evaluation variable index set, obtain the contribution degree space of each layer through a hierarchical evaluation model, and use color mapping to visualize the contribution degree on the intra-layer and inter-layer connections to form a visualized hierarchical correlation index space, and retain the historical mapping record after the evaluation is completed.

2. The warehouse performance diagnosis and evaluation method according to claim 1, characterized in that The first evaluation index set includes efficiency indicators, accuracy indicators, and space utilization indicators; The second evaluation index set includes receiving timeliness, shelving timeliness, shelving delay rate, inbound throughput, picking timeliness, outbound throughput, order processing timeliness, per capita picking efficiency, equipment utilization rate, inventory accuracy, picking accuracy, shelving accuracy, storage capacity utilization rate, and shelf storage density; The efficiency indicators include receiving timeliness, shelving timeliness, shelving delay rate, inbound throughput, picking timeliness, outbound throughput, order processing timeliness, per capita picking efficiency, and equipment utilization rate; The accuracy indicators include inventory accuracy, picking accuracy, and shelving accuracy; the space utilization indicators include storage capacity utilization rate and shelf storage density.

3. The warehouse performance diagnosis and evaluation method according to claim 2, wherein, The receiving timeliness includes the acceptance completion time, arrival time, and total inbound batch quantity in the third evaluation index set; the shelving timeliness includes the total number of items shelved per day and the total man-hours of shelving personnel in the third evaluation index set; the shelving delay rate includes the number of orders not shelved on time and the total number of shelving orders in the third evaluation index set; the inbound throughput includes the total number of items inbound per day and the warehouse operation duration in the third evaluation index set; the picking timeliness includes the picking start time, order creation time, and total number of orders in the third evaluation index set; the outbound throughput includes the total number of items outbound per day and the warehouse operation duration in the third evaluation index set; the order processing timeliness includes the order completion time, order creation time, and total number of orders in the third evaluation index set; the per capita picking efficiency includes the total picking quantity and the picking personnel man-hours in the third evaluation index set; the equipment utilization rate includes the actual operation time of the equipment and the planned available time in the third evaluation index set; The inventory accuracy rate includes the number of correctly inventoried SKUs and the total number of inventoried SKUs in the third evaluation index set; the picking accuracy rate includes the number of error-free order lines and the total number of shipped order lines in the third evaluation index set; the shelving accuracy rate includes the number of correctly shelved storage locations and the total number of shelved storage locations in the third evaluation index set; The storage space utilization rate includes the occupied storage volume and the total storage volume of the warehouse in the third evaluation index set; the shelf storage density includes the actual storage quantity of SKUs and the theoretical maximum storage quantity of the shelf in the third evaluation index set.

4. The warehouse performance diagnosis and evaluation method according to claim 3, characterized in that The steps for constructing the hierarchical associated index space include: Construct the first index node layer in the evaluation associated index library based on the index variables in the first evaluation index set, construct the second index node layer in the evaluation associated index library based on the index variables in the second evaluation index set, and construct the third index node layer in the evaluation associated index library based on the index variables in the third evaluation index set; Construct the corresponding first inter-layer index connection and second inter-layer index connection between the first index node layer and the second index node layer and between the second index node layer and the third index node layer based on the inclusion relationship of the index variables corresponding to the first evaluation index set, the second evaluation index set, and the third evaluation index; Obtain the historical evaluation index combinations of different types of warehouses, the index variable index frequency of each, the combined index frequency between different index variables in the second evaluation index set and the third evaluation index set, and the maximum efficiency index, accuracy rate index, and space utilization rate index results in the first evaluation index set corresponding to the historical evaluation index combinations, and construct an index association data set; Based on the index association data set, through an association algorithm, obtain the association degrees between the index variables in the second evaluation index set and the association degrees between the index variables in the third evaluation index set.

5. The warehouse performance diagnosis and evaluation method according to claim 4, wherein The steps for constructing the hierarchical associated index space further include: Construct a second relationship connection set between the nodes in the second index node layer based on the association degrees between the index variables in the second evaluation index set; Construct a third relationship connection set between the nodes in the third index node layer based on the association degrees between the index variables in the third evaluation index set; Based on the inter-layer index connection, the second relationship connection set, the third relationship connection set, and the first index node layer, the second index node layer, and the third index node layer, a hierarchical associated index space is constructed through a topological space algorithm; Based on the association degree on the hierarchical associated index space and the corresponding connection relationship, through the graph algorithm combined with the density function in the density clustering algorithm, circular community clustering is respectively performed on the index variables in the second index node layer and the third index node layer; When the modularity corresponding to each clustering community after community clustering in the second index node layer and the third index node layer and the density of the neighboring nodes corresponding to each node in the corresponding community are a fixed value, the circular community clustering is stopped, and the second community clustering node group and the third community clustering node group corresponding to the second index node layer and the third index node layer are obtained respectively; Taking each community clustering node group in the second community clustering node group and the third community clustering node group as a super node, a hierarchical super node association space is constructed through a hypergraph algorithm.

6. The warehouse performance diagnosis and evaluation method according to claim 5, wherein The construction steps of the hierarchical associated index space further include: Based on the index variables between layers in the hierarchical associated index space, a visual contribution mapping is set, specifically: When at the current moment, through the enhanced screening scheduling model combined with the warehouse attribute configuration to be evaluated at the current moment, all index variables are screened from the first evaluation index set, N variable indicators are screened from the second evaluation index set, and M index variables are screened from the third evaluation index set, an evaluation variable index set of the warehouse to be evaluated is constructed; The evaluation variable index set of the warehouse to be evaluated is input into a hierarchical evaluation model constructed by combining the comprehensive fuzzy evaluation algorithm with the autocorrelation function, and the evaluation score corresponding to each evaluation index in the first evaluation index set is obtained, and the second autocorrelation contribution space and the third autocorrelation contribution space corresponding to the N and M variable indicators in the second and third evaluation index sets, and the inter-layer contribution space constructed by the inter-layer contribution degree of the third evaluation index to the second evaluation index and the inter-layer contribution degree of the second evaluation index to the first evaluation index are screened.

7. The method for diagnosing and evaluating the performance of a warehouse according to claim 6, wherein The construction steps of the hierarchical associated index space further include: Based on the magnitude and positive / negative of the autocorrelation contribution between adjacent two index variables in the third autocorrelation contribution space, combined with the preset color type and color gradient, an intra-layer visual contribution mapping between adjacent two index variables is constructed; The intra-layer visual contribution mapping is built into the third relationship connection set corresponding to the third index node layer to obtain a visual third index node layer. Similarly, using the second autocorrelation contribution space, a visual second index node layer is obtained; Based on the preset color type and color gradient and the magnitude and positive / negative of the inter-layer contribution degree of the third evaluation index to the second evaluation index in the inter-layer contribution space, a second inter-layer visual mapping between the second index node layer and the third index node layer is obtained. Similarly, through the inter-layer contribution degree of the second evaluation index to the first evaluation index, a first inter-layer visual mapping is obtained; Build the first-layer visualization mapping and the second-layer visualization mapping into the corresponding first-layer index connection and second-layer index connection between the first index node layer and the second index node layer and between the second index node layer and the third index node layer, to obtain the visualization hierarchical association index space corresponding to the warehouse to be evaluated; When the evaluation and corresponding solution push for the warehouse to be evaluated are completed, automatically eliminate the visualization mapping on the corresponding intra-layer connection in the layer index connection, the visualization second index node layer, and the visualization third index node layer, and perform retention marking and historical evaluation tracing on the visualization mapping corresponding to the current warehouse to be evaluated; Map the above visualization process of the warehouse to be evaluated currently to all the warehouses for distributed control evaluation, and perform visualization evaluation mapping on the corresponding warehouses.

8. The method for diagnosing and evaluating warehouse performance according to claim 7, characterized in that, The construction process of the mapping of the differential area evaluation result includes: Use the spatial three-dimensional coordinates of the three-dimensional virtual warehouse corresponding to the current warehouse to be evaluated as the pixel projection coordinates; Construct the mapping of the differential area evaluation result by combining the color and color gradient corresponding to the connection relationship in the visualization hierarchical association index space corresponding to the current warehouse to be evaluated through the spatial index variable in the space utilization rate index and the dynamic LOD algorithm; Map the color and color gradient corresponding to the connection relationship in the visualization hierarchical association index space corresponding to the current warehouse to be evaluated into the pixel projection coordinates corresponding to the current warehouse to be evaluated through the mapping of the differential area evaluation result, to obtain the three-dimensional virtual warehouse of regional visualization.

9. The method for diagnosing and evaluating warehouse performance according to claim 8, characterized in that, The enhanced screening scheduling model is constructed by G enhanced screening scheduling sub-models; the G enhanced screening scheduling sub-models are integrated into the edge control nodes corresponding to Q corresponding warehouses; The screening process of the enhanced screening scheduling sub-model includes: Establish a frequent index variable set through the set of evaluation variable indicators of the warehouse to be evaluated corresponding to each warehouse after each evaluation; Establish a frequent index connection between the frequent index variable set and the corresponding enhanced screening scheduling sub-model, and build the frequent index connection into the corresponding enhanced screening scheduling sub-model; When evaluating the warehouse corresponding to the current enhanced screening scheduling sub-model, index the set of evaluation variable indicators of the warehouse to be evaluated from the evaluation association index library through the frequent index connection combined with the attribute configuration of the current warehouse to be evaluated, and feedback the index frequency and joint index frequency of the corresponding index variables to the hierarchical association index space to adjust the association degree marked on the corresponding intra-layer and inter-layer connection relationships in real time; When the set of evaluation variable indicators of the currently indexed warehouse to be evaluated does not belong to any community clustering node group in the hierarchical association index space, construct a new community clustering node group through the set of evaluation variable indicators of the currently indexed warehouse to be evaluated and save the index variables and build a frequent index connection as a new super-node in the hierarchical super-node association space.

10. A warehouse performance diagnosis and evaluation system for implementing the warehouse performance diagnosis and evaluation method according to any one of claims 1-9, characterized in that, Including: A three-dimensional simulation module, an index screening module, an evaluation module, and a mapping and recommendation module; The three-dimensional simulation module obtains a distributed three-dimensional virtual warehouse based on different warehouse attributes and a three-dimensional modeling algorithm; The said index screening module, based on the distributed three-dimensional virtual warehouse, combines the enhanced screening scheduling model and the evaluation correlation index library to obtain a set of differential correlation evaluation indexes; The said evaluation module, based on the set of differential correlation evaluation indexes and the correlation evaluation model configured for each three-dimensional virtual warehouse, obtains a distributed evaluation result level cluster; The said mapping and recommendation module, based on the distributed evaluation result level cluster and the preset mapping of differential area evaluation results, visually maps the evaluation results in real time to the corresponding three-dimensional virtual warehouse area, and at the same time, through the configured integrated reasoning model, generates an evaluation solution and synchronously maps it to the corresponding visual area of the three-dimensional virtual warehouse.

Images