Dynamic adjustment method and system for storage layout and storage medium

Abstract

The invention discloses a storage layout dynamic adjustment method, a storage layout dynamic adjustment system and a storage medium, when a storage request is received, storage requirement descriptions of various to-be-stored goods are determined according to the storage request, and then according to the free storage space, meeting the storage requirement descriptions, of a to-be-stored warehouse, the to-be-stored goods are stored in the to-be-stored warehouse, and the to-be-stored goods are stored in the to-be-stored warehouse. And generating at least one storage scheme corresponding to the warehousing request, further determining an ex-warehouse efficiency score corresponding to each storage scheme based on an ex-warehouse simulation model, and finally taking the storage scheme with the highest ex-warehouse efficiency score as a target storage scheme of the warehousing request. And executing a storage action based on the target storage scheme. Therefore, the warehousing request can be responded by the current optimal scheme during each warehousing, and the purpose of dynamically adjusting the warehousing layout is achieved. In this way, by dynamically adjusting the storage layout, the effect of improving the storage efficiency is achieved.

Description

Technical Field

[0001] The present application relates to the field of communications, and in particular, to a method for dynamically adjusting a warehouse layout, a system for dynamically adjusting a warehouse layout, and a storage medium. Background Art

[0002] With the increasing diversification of consumer demands, the warehouse, as a key node in the logistics network, its operation efficiency and response speed directly affect the competitiveness of enterprises and customer satisfaction. Related static warehouse layouts are often planned based on experience and are difficult to adapt to the rapidly changing market demands and logistics environment. The storage locations of goods are fixed, and the inbound and outbound processes are rigid. In the face of sudden situations such as seasonal demand fluctuations, emergency order processing, or the introduction of new products, the static layout leads to low warehouse efficiency and high costs. Summary of the Invention

[0003] The main purpose of the present application is to provide a method for dynamically adjusting a warehouse layout, a system for dynamically adjusting a warehouse layout, and a storage medium, aiming to solve the technical problem of low efficiency in monitoring video analysis in related technologies.

[0004] To achieve the above object, an embodiment of the present application provides a method for dynamically adjusting a warehouse layout, and the method includes:

[0005] Receiving an inbound request, and determining a storage requirement description for various types of goods to be inbound according to the inbound request;

[0006] Generating at least one storage plan corresponding to the inbound request according to the storage requirement description and the available storage space in the warehouse to be inbound;

[0007] Determining an outbound efficiency score corresponding to each storage plan based on an outbound simulation model;

[0008] Taking the storage plan with the highest outbound efficiency score as the target storage plan for the inbound request, and performing an inbound action based on the target storage plan.

[0009] In an embodiment of the present application, the step of generating at least one storage plan corresponding to the inbound request according to the storage requirement description and the available storage space in the warehouse to be inbound includes:

[0010] Encoding the storage requirement description based on a preset encoding rule to obtain storage requirement encoded data;

[0011] Tokenizing the storage requirement encoded data through a natural language processing model, and generating a storage requirement description vector according to the tokenized storage requirement encoded data;

[0012] Obtain a storage location description vector corresponding to an idle storage location in the idle storage space;

[0013] Determine the matching degree between the storage requirement description vector and the storage location description vector, and select available storage locations for each category of goods from the idle storage locations according to the matching degree;

[0014] Generate a storage plan corresponding to at least one of the inbound requests according to the available storage locations.

[0015] In the embodiment of the present application, the step of generating a storage plan corresponding to at least one of the inbound requests according to the available storage locations includes:

[0016] Determine the size information, quantity information, weight information and load-bearing information of the cargo units corresponding to each type of goods to be warehoused;

[0017] Use the size information, the weight information and the quantity information as the input of the stacking algorithm, and use the load-bearing information as the constraint condition of the stacking algorithm, and determine the stacking plan for each type of goods to be warehoused based on the stacking algorithm;

[0018] Filter out optional stacking plans according to the size of the cargo stacks corresponding to each stacking plan and the size of the available storage locations;

[0019] Determine sub-storage plans corresponding to each type of goods to be warehoused according to the optional stacking plans and the available storage locations;

[0020] Generate a storage plan corresponding to at least one of the inbound requests according to the sub-storage plans.

[0021] In the embodiment of the present application, the step of obtaining a storage location description vector corresponding to an idle storage location in the idle storage space includes:

[0022] Encode the location requirement description of the idle storage location to obtain storage location description encoded data;

[0023] Tokenize the storage location description encoded data through a natural language processing model, and generate the storage location description vector according to the tokenized storage location description encoded data.

[0024] In the embodiment of the present application, the step of determining the outbound efficiency score corresponding to each storage plan based on the outbound simulation model includes:

[0025] Generate at least one outbound request according to historical outbound data;

[0026] Determine the outbound route score and picking energy consumption score of each of the storage solutions in response to the outbound request;

[0027] Determine the outbound efficiency score of each of the storage solutions in response to each of the outbound requests according to the outbound route score and the picking energy consumption score.

[0028] In the embodiment of the present application, after the step of determining the outbound route score and the picking energy consumption score of each of the storage solutions in response to the outbound request, the method further includes:

[0029] Determine the initial outbound efficiency score of each of the storage solutions in response to each of the outbound requests according to the outbound route score and the picking energy consumption score;

[0030] Determine the weight value of the outbound request according to the occurrence probability corresponding to the outbound request;

[0031] Perform weighted summation on the initial outbound efficiency score of the storage solution in response to the outbound request according to the weight value corresponding to each of the outbound requests to obtain the outbound efficiency score.

[0032] In the embodiment of the present application, the step of using the storage solution with the highest outbound efficiency score as the target storage solution for the inbound request and performing the inbound action based on the target storage solution includes:

[0033] Use the storage solution with the highest outbound efficiency score as the target storage solution for the goods unit;

[0034] Obtain the location description corresponding to the target storage solution, and generate a robot control instruction based on the location description;

[0035] Send the robot control instruction to the inbound robot to control the inbound robot to carry the goods to be stored to the location corresponding to the target storage solution.

[0036] In the embodiment of the present application, after the step of using the storage solution with the highest outbound efficiency score as the target storage solution for the inbound request and performing the inbound action based on the target storage solution, the method further includes:

[0037] Update the inventory information according to the target inbound plan.

[0038] The embodiment of the present application further provides a dynamic adjustment system for warehouse layout, and the dynamic adjustment system for warehouse layout includes:

[0039] A receiving module, configured to receive an inbound request and determine a storage requirement description of various goods to be stored according to the inbound request;

[0040] A generation module, configured to generate at least one storage plan corresponding to the inbound request according to the storage requirement description and the available storage space of the warehouse to be warehoused.

[0041] A calculation module, configured to determine the outbound efficiency score corresponding to each storage plan based on the outbound simulation model.

[0042] An output module, configured to use the storage plan with the highest outbound efficiency score as the target storage plan for the inbound request, and perform an inbound action based on the target storage plan.

[0043] An embodiment of the present application further provides a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the method for dynamically adjusting the warehouse layout as described above are implemented.

[0044] An embodiment of the present application discloses a method for dynamically adjusting the warehouse layout and a system for dynamically adjusting the warehouse layout. When an inbound request is received, a storage requirement description for various types of goods to be warehoused is determined according to the inbound request, and then at least one storage plan corresponding to the inbound request is generated according to the available storage space of the warehouse to be warehoused that meets the storage requirement description. Further, the outbound efficiency score corresponding to each storage plan is determined based on the outbound simulation model. Finally, the storage plan with the highest outbound efficiency score is used as the target storage plan for the inbound request, and an inbound action is performed based on the target storage plan. In this way, each time an inbound operation is performed, the inbound request can be responded with the current optimal plan, so as to achieve the purpose of dynamically adjusting the warehouse layout. In this way, by dynamically adjusting the warehouse layout, the effect of improving the warehouse storage efficiency is achieved. Description of the Drawings

[0045] Figure 1 is a schematic flowchart of an embodiment of the method for dynamically adjusting the warehouse layout according to the embodiment of the present application;

[0046] Figure 2 is a schematic diagram of the logic for determining available storage locations according to the embodiment of the present application;

[0047] Figure 3 is a schematic flowchart of another embodiment of the method for dynamically adjusting the warehouse layout according to the embodiment of the present application;

[0048] Figure 4 is a schematic structural diagram of the device for dynamically adjusting the warehouse layout according to the present application;

[0049] Figure 5 is a schematic modular structure diagram of the system for dynamically adjusting the warehouse layout according to the present application.

[0050] The realization, functional features and advantages of the present application will be further described in conjunction with embodiments with reference to the accompanying drawings. Detailed implementation manners

[0051] It should be understood that the specific embodiments described herein are merely used to explain the present application and are not used to limit the present application.

[0052] With the booming rise of e-commerce and the increasing diversification of consumer demands, warehouses, as key nodes in the logistics network, their operation efficiency and response speed directly affect the competitiveness of enterprises and customer satisfaction.

[0053] Traditional static warehouse layouts are often planned based on historical data and experience, and it is difficult to adapt to the rapidly changing market demands and logistics environment. The storage locations of goods are fixed, and the inbound and outbound processes are rigid, resulting in low warehouse efficiency and high costs. Especially when facing sudden situations such as seasonal demand fluctuations, emergency order processing, or new product introductions, due to the dynamic changes in inventory demands, the inventory efficiency will show dynamic fluctuations.

[0054] To solve these problems, it is particularly important to develop a dynamic adjustment method for warehouse layouts. The core of the dynamic adjustment method lies in real-time monitoring of the operation status of the warehouse, and then based on the current status of the warehouse and the outbound demands in the future stage, generating corresponding storage plans dynamically when goods are inbound, so that the storage efficiency of the warehouse can be maintained in a good state for a long time and the waste of storage capacity can be avoided.

[0055] In addition, with the continuous development of advanced technologies such as the Internet of Things, big data, and artificial intelligence, intelligent warehouse systems have gradually become a reality. These systems can optimize scheduling and allocation strategies, providing strong technical support for the dynamic adjustment method. By integrating intelligent warehouse systems, enterprises can achieve digitalization, intelligentization, and visualization of warehouse operations, further enhancing the flexibility and response speed of warehouse layouts.

[0056] Based on the above background, the present application provides a dynamic adjustment method for warehouse layouts. The method aims to, when receiving an inbound request, determine the storage requirement descriptions of various types of goods to be inbound according to the inbound request, and then generate at least one storage plan corresponding to the inbound request based on the idle storage space of the warehouse to be inbound that meets the storage requirement descriptions. Further, based on an outbound simulation model, determine the outbound efficiency scores corresponding to each storage plan. Finally, take the storage plan with the highest outbound efficiency score as the target storage plan for the inbound request, and execute the inbound action based on the target storage plan. In this way, each time when inbound, the inbound request can be responded with the current optimal plan, thus achieving the purpose of dynamically adjusting the warehouse layout. In this way, by dynamically adjusting the warehouse layout, the effect of improving warehouse storage efficiency is achieved.

[0057] For ease of understanding, the technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings in the embodiments of the present application.

[0058] Please refer to Figure 1 , in an optional implementation, the method for dynamically adjusting the warehouse layout includes the following steps:

[0059] S10: Receive the inbound request, and determine the storage requirement descriptions of various types of goods to be stored according to the inbound request;

[0060] In this embodiment, the inbound request may be an inbound request triggered by the management system or manually when the goods arrive at the warehouse to be stored. The inbound request records the relevant information of the goods to be stored. Among them, it includes storage parameters such as the size information, weight information, and storage requirement description information of each goods unit corresponding to the goods to be stored. It can be understood that the goods unit referred to here is an independent unit during the storage process. For example, if the goods are multi-pack handkerchief papers, the handkerchief papers exist in the form of a whole box during the inventory stage. Therefore, the corresponding goods unit is a box of multi-pack handkerchief papers. Of course, different goods are limited by the packaging method, and the corresponding goods units can be different. There is no need to enumerate them here.

[0061] In addition, the above storage requirement description may include specific storage requirements such as whether refrigerated storage is required, storage temperature, storage humidity, maximum bearing pressure, fire safety requirements, and impact on surrounding goods. It can be understood that the storage requirement is text content, and the semantic information expressed by its specific content changes with the change of the goods content, that is, in different application scenarios and warehouse environments, it can be customized according to requirements.

[0062] Exemplarily, in an embodiment, after the goods transport vehicle arrives at the warehouse inbound area, the warehouse management personnel can scan the two-dimensional code corresponding to the inbound goods list based on a scanning gun. Then, based on the scanning result, the inbound goods list is read. Optionally, the goods list may be from the goods management system. Based on the above inbound goods list, the storage parameters of its corresponding various goods units can be obtained. Or, in the dynamic adjustment system of the warehouse layout, the storage parameters associated with each goods name are pre-saved, and then the goods name is determined based on the inbound goods list, and then according to the goods name, the corresponding storage parameters are retrieved from the preset database. In this way, the method for dynamically adjusting the warehouse layout provided in this embodiment can adapt to the new and old sets of goods management systems. Thus, a better implementation basis is provided.

[0063] S20: Generate at least one storage plan corresponding to the inbound request according to the storage requirement description and the idle storage space in the warehouse to be stored;

[0064] In this embodiment, after obtaining the storage requirement description of the goods to be warehoused corresponding to the warehousing request, the category of goods included in the warehousing request can also be determined. Because the storage requirement descriptions corresponding to different categories of goods to be warehoused may be different. Therefore, the available storage locations for the goods to be warehoused corresponding to each category can be determined first according to the storage requirement descriptions of various goods to be warehoused and the available storage space in the warehouse. Furthermore, according to the size information, load-bearing information, and quantity information of the goods units corresponding to various goods to be warehoused, as well as their corresponding available storage locations, sub-storage plans corresponding to various goods to be warehoused are generated. Furthermore, the sub-storage plans for various goods to be warehoused are arranged and combined to generate one or more storage plans for the warehousing request.

[0065] It should be noted that when a warehousing request contains only one category of goods, the sub-storage plan corresponding to this category of goods can be directly used as the storage plan corresponding to this warehousing request.

[0066] For ease of understanding, this application provides two implementation schemes for determining the available storage locations corresponding to various goods to be warehoused. In an alternative implementation scheme, the location descriptions of the available storage locations in the available storage space and the storage requirement descriptions of various goods to be warehoused can be directly analyzed based on a semantic analysis model, and then according to the analysis results, it can be determined which locations in the available storage locations can be used as the available storage locations for the corresponding categories of goods to be warehoused.

[0067] In another alternative implementation scheme for determining the available storage locations corresponding to various goods to be warehoused, the available storage locations corresponding to various goods to be warehoused can be determined based on a vector matching method.

[0068] In this embodiment, after obtaining the storage requirement descriptions of various goods to be warehoused, the storage requirement descriptions can be encoded first based on a preset coding rule to obtain storage requirement coding data. For example, when the storage requirement description includes descriptions such as requiring refrigerated storage, storing at 0°C - 4°C, and storing at low temperature, this content can be encoded as 1. When the storage requirement description includes descriptions such as frozen storage and storing below 0°C, it is encoded as 0. When the storage requirement description includes descriptions such as storing at normal temperature, it is encoded as 2. That is, a storage requirement description of "it is recommended to store at 0°C - 4°C" can be encoded as "storage temperature: 1". It can be understood that in different warehousing scenarios and requirements, when implementing the solution provided by this application, the corresponding coding rules can be customized according to specific requirements. The purpose of encoding is that due to different manufacturers or other objective factors of different goods, there will be significant differences in their storage requirement descriptions. Through encoding, the corresponding descriptions can be unified, so as to ensure that in the subsequent matching process, errors will not be introduced due to description differences, and thus the problem of unsuccessful matching will not occur.

[0069] After completing the encoding and obtaining the encoded data of the storage requirements, the encoded data of the storage requirements can be tokenized through a natural language processing (NLP) model, and a storage requirement description vector for this type of goods to be warehoused can be generated based on the tokenized encoded data of the storage requirements. Among them, tokenization is a basic step in NLP, which refers to converting the original text into a series of discrete symbol sequences that the model can understand and process. In the encoded data of the storage requirements corresponding to the goods category, these symbols usually correspond to the attributes of the goods preservation requirements.

[0070] Exemplarily, the connotation of the above storage requirements description can include one or more of the physical attributes, environmental attributes, safety attributes, and management attributes of the goods preservation. Optionally, the material attributes include temperature, humidity, dust prevention, etc. In terms of humidity, different types of goods have different requirements for humidity. For example, some electronic products and foods need to avoid high humidity environments to prevent moisture and damage. In terms of dust prevention, goods are prone to accumulating dust during long-term storage. Therefore, the storage area should be kept clean and dust prevention measures should be taken. The environmental attributes include the air circulation situation, the lighting situation, etc. For some goods, a good air circulation system is required in the storage area to keep the air fresh and avoid the accumulation of peculiar smells and harmful gases. For example, for volatile items, sufficient ventilation equipment is needed. In addition, some goods such as medicines and cosmetics need to avoid direct sunlight. Therefore, the storage area should be designed with appropriate shading measures.

[0071] The safety attributes can include flammability, explosiveness, corrosiveness, toxicity, and harmfulness, etc. For flammable and explosive goods, special safety measures should be taken, such as setting up fire prevention equipment and using explosion-proof electrical appliances. Corrosive goods should be stored separately to avoid contact with other goods and prevent corrosion of other items or equipment. Toxic and harmful goods need to be strictly managed to prevent leakage and pollution. Obvious warning signs should be set up during storage, and necessary protective measures should be taken.

[0072] The management attributes include the shelf life, etc. For goods with shelf life requirements such as foods and medicines, the shelf life needs to be strictly managed, and the inventory should be checked regularly to ensure timely sales.

[0073] Since the physical requirements that can be provided vary for different storage locations in the warehouse, the storage location that can meet the requirements can be determined as the available storage location based on the storage requirement description of the goods to be warehoused. Therefore, after tokenization, a set of tokens representing the storage requirement attributes of the goods can be obtained. However, these tokens are still in text form and need to be converted into numerical vector form, that is, word embedding is performed. Word embedding can map the tokens into a high-dimensional vector space, so that tokens that are semantically similar are also close in distance in the vector space. In this way, each token is converted into a numerical vector of a fixed length, and these vectors contain the semantic information of the tokens, enabling the model to understand the relationships and meanings between the tokens. Additionally, when generating the description vector of the goods unit based on the tokenized storage parameter encoded data (i.e., the vector representation of the tokens), an aggregation operation also needs to be performed on the token vectors. The aggregation method can be simple averaging, summing, or using more complex neural network structures such as recurrent neural networks (RNNs), Transformers, etc. The aggregated vector is the description vector of the goods unit, which synthesizes all the key attribute information of the goods unit and retains the semantic relationships between these attributes.

[0074] After vectorizing the storage requirement description, a vector that can be used to express the obtained storage requirements of the category is obtained. Then, by obtaining the storage location description vector corresponding to the available storage location in the idle storage space and determining the matching degree between the storage requirement description vector and the storage location description vector, the available storage location for each goods unit can be selected from the idle storage locations according to the matching degree.

[0075] It should be noted that position descriptions corresponding to the storage requirement descriptions are preset for each storage location. Therefore, a corresponding storage location description vector can be generated in a manner similar to generating the storage requirement description vector. That is, the position requirement description of the storage location is encoded to obtain the storage location description encoded data, and then the storage location description encoded data is tokenized through a natural language processing model, and the storage location description vector is generated according to the tokenized storage location description encoded data. In addition, since the storage location is relatively fixed, when implementing the solution provided in this application, the determination process of the storage location description vector corresponding to the idle storage location can be executed at any time before vector matching, and it is not necessarily fixed to be generated after triggering the matching. For example, in an alternative implementation, after the warehouse construction is completed, the storage location description vectors corresponding to each storage location can be pre-generated and associated with the identifiers of the storage locations for storage. In this way, in the subsequent matching process, the storage location description vector can be directly obtained according to the identifier without generating the vector every time a match is made. This can effectively reduce the computational overhead.

[0076] In addition, when determining the matching degree between the storage requirement description vector and the storage location description vector, the matching degree can be set as the similarity distance between the vectors. For example, the cosine similarity, Manhattan distance, or Euclidean distance between the vectors can be used as the matching degree between the two vectors.

[0077] After obtaining the matching degrees between the storage requirement description vector corresponding to the goods category of the storage location to be determined and the storage location description vectors of each idle storage location, the top m idle storage locations with the highest to lowest matching degrees can be selected as the available storage locations for the goods of this type to be warehoused. Alternatively, the idle storage location with the maximum matching degree can be selected as the available storage location for the goods of this type to be warehoused. The former can provide more selection options, so that there is more basic data for the subsequent optimization process, thereby improving the quality of the optimization selection result. The latter has a smaller demand for computing power. Therefore, in the implementation process, the solution can be selected according to the hardware architecture of the system and the actual requirements.

[0078] Exemplarily, please refer to Figure 2, the goods categories corresponding to the warehousing requests include the to-be-warehoused goods category 1 and the to-be-warehoused goods category 2. Storage requirement description vectors 1 and 2 corresponding to each of them can be generated respectively based on the storage requirement descriptions of the to-be-warehoused goods category 1 and the to-be-warehoused goods category 2. Then, the degrees of match 1 to n between them and the location description vectors 1 to n corresponding to the idle storage locations 1 to n are determined respectively. And based on the degrees of match, the available storage locations Ai and Bi corresponding to the to-be-warehoused goods category 1 and the to-be-warehoused goods category 2 are selected respectively. Among them, when only the idle storage location with the maximum degree of match is selected, i is 1; when the first m idle storage locations with the degrees of match from high to low are used as the available storage locations, i is a positive integer between 1 and m.

[0079] After determining the available storage locations, a storage plan corresponding to at least one of the warehousing requests can be generated according to the available storage locations.

[0080] After determining the available storage locations, the size information corresponding to the available storage locations can be determined first. For example, a three-dimensional model of the warehouse can be obtained, and according to the mapping relationship between the three-dimensional model and the actual space, the size information of the available storage location can be determined.

[0081] Then, according to the warehousing request, the size information, quantity information, weight information and load-bearing information of the corresponding goods units of various to-be-warehoused goods are obtained, and the size information, the weight information and the quantity information are used as the input of the stacking algorithm, and the load-bearing information is used as the constraint condition of the stacking algorithm. Based on the stacking algorithm, the stacking plans of various to-be-warehoused goods are determined.

[0082] Exemplarily, the system first obtains the relevant information corresponding to a goods unit of the goods to be warehoused in a category, which specifically includes the size (length, width, height), weight, quantity of each goods unit, and the load-bearing information of a single piece of goods. And preprocess these data to ensure the accuracy and integrity of the data, such as verifying the rationality of the size and weight, and processing goods with special shapes, etc. Then, based on the above data, a three-dimensional model is constructed for each piece of goods, and its weight and quantity attributes are assigned. These models will be used in the subsequent stacking simulation process. At the same time, according to the load-bearing constraint, the maximum load-bearing threshold of the stacking area is set. The core of the stacking algorithm lies in how to efficiently stack goods under the premise of meeting the load-bearing constraint. Strategies such as greedy algorithm, backtracking algorithm, or heuristic algorithm can be adopted. For example, goods with lighter weight and smaller size can be stacked first, and at the same time, the stacking of the next piece of goods is continuously constrained according to the current stacking result, and the constraint condition is the load-bearing limit. After the algorithm generates a preliminary stacking plan, the algorithm can also evaluate and optimize it. The evaluation indicators can include the stability of the stack, the space utilization rate, and whether all constraint conditions are met. According to the evaluation results, necessary adjustments and optimizations are made to the plan until an optimal or satisfactory stacking plan is obtained. Or other existing stacking algorithms can also be used to generate the stacking plan.

[0083] It should be noted that the purpose of generating the stacking plan here is to determine all possible stacking situations of the goods to be warehoused in this category. Of course, when generating the stacking plan, the quantity can also be used as another constraint condition, so that one or more stacks can be generated for the same category of goods. This is the content that can be selectively set according to the actual situation.

[0084] Furthermore, as an implementation solution, the size of the available storage location can also be used as a constraint condition for the stacking algorithm, so that the algorithm automatically removes the stacks that do not meet the size of the available storage location during the generation process. Or, a filtering algorithm can also be set after generating the initial stack, and the invalid stacks with mismatched sizes in the optional stacking plans generated by the stacking algorithm are removed through the size of the available storage location. In this way, the sub-storage plan of the goods to be warehoused in this category under the corresponding available storage location can be generated.

[0085] Optionally, when a warehousing request includes multiple categories, multiple sub-storage plans may be generated for one category. Therefore, by arranging and combining the multiple sub-storage plans, at least one storage plan corresponding to the warehousing request can be generated.

[0086] Step S30: Determine the outbound efficiency score corresponding to each of the storage plans based on the outbound simulation model;

[0087] Step S40: Use the storage plan with the highest outbound efficiency score as the target storage plan for the inbound request, and perform the inbound action based on the target storage plan.

[0088] In this embodiment, an outbound simulation model can be constructed first. After the model construction is completed, each storage plan can be used as the dynamic input condition of the simulation model, and the outbound efficiency score corresponding to each storage plan can be calculated through the model. Use the storage plan with the highest outbound efficiency score as the target storage plan for the inbound request, and perform the inbound action based on the target storage plan.

[0089] In an alternative implementation, a 3D model of the warehouse can be obtained first, because the 3D model can map the layout of the warehouse shelves, the height and capacity of each shelf, and the width of the aisles. Then, based on the 3D model, an outbound simulation model can be constructed according to the type of handling equipment and its moving speed, and the number of pickers and their picking speed basic data.

[0090] As an alternative implementation, after the above-mentioned outbound simulation model is constructed, an outbound test order associated with the corresponding goods to be inbound can be created first. Then, using the outbound test order as the input of the outbound simulation model and the multiple storage plans corresponding to the inbound request as variables, multiple simulation calculations are performed. According to the simulation calculation results, the scores corresponding to each outbound efficiency evaluation index can be determined, and then based on the scores corresponding to each outbound efficiency evaluation index and the weight values corresponding to the outbound efficiency evaluation index, the outbound efficiency score corresponding to this storage plan can be determined. Among them, the outbound efficiency evaluation index can be set according to different warehouse types. For example, in an automated warehouse, indicators such as picking order duration, cumulative picking path length, equipment failure rate, average outbound time, picking accuracy rate, and handling equipment utilization rate can be used as outbound efficiency evaluation indicators.

[0091] Optionally, in another implementation, at least one outbound request is generated according to historical outbound data, and then the outbound route score and picking energy consumption score of each storage plan in response to the outbound request are determined, and based on the outbound route score and picking energy consumption score, and their corresponding weight values, the outbound efficiency score of each storage plan in response to each outbound request is determined.

[0092] When generating an outbound request, possible future goods outbound requests can be generated based on historical outbound data. First, extract historical outbound data including key information such as goods numbers, outbound dates, outbound quantities, and customer numbers from the warehouse management system or enterprise resource planning system. Clean the obtained data to remove duplicate, incorrect, or missing records. And perform standardization processing on the data to ensure the consistency of data formats and units. Then use time series-based analysis methods such as moving average, exponential smoothing, or ARIMA models to analyze the change trends of historical outbound data. Obtain characteristics such as seasonal fluctuations and periodic changes of the outbound data. Furthermore, through machine learning algorithms (such as random forests, neural networks, etc.) or statistical prediction methods (such as regression analysis, time series analysis, etc.). Use the historical outbound data as the training set to train the prediction model. And use the trained prediction model to predict the outbound requests within a future period of time. Obtain information such as the goods numbers, predicted outbound dates, and predicted outbound quantities corresponding to the future period's shipment requests, and generate outbound requests based on this.

[0093] Optionally, when generating multiple inbound requests, the outbound route scores and picking energy consumption scores of each of the storage schemes in response to each outbound request can be determined first, and then the weighted sum of the outbound route scores and picking energy consumption scores is used as the initial outbound efficiency score of each of the storage schemes in response to each outbound request. Furthermore, according to the occurrence probability corresponding to the outbound request, the weight value of the outbound request is determined, and according to the weight values corresponding to each of the outbound requests, the initial outbound efficiency scores of the storage schemes in response to the outbound request are weighted and summed to obtain the outbound efficiency score.

[0094] Optionally, in another implementation, the length of the outbound path corresponding to each storage scheme can also be determined based on the three-dimensional model of the warehouse, and the difference between the lengths of the outbound paths is used as the outbound efficiency score. Wherein, the outbound path length is the length of the optimal path from the goods storage location to the picking area.

[0095] Optionally, the storage scheme with the highest outbound efficiency score can be used as the target storage scheme for the goods unit. After determining the target storage scheme, obtain the location description corresponding to the target storage scheme, and generate a robot control instruction based on the location description. Send the robot control instruction to the inbound robot to control the inbound robot to transport the goods unit to the location corresponding to the target storage scheme.

[0096] Exemplarily, first, it is necessary to determine the format of the location description. The location description should contain sufficient information so that the robot can accurately find the target location. For example, the format of "shelf number - layer number - column number - row number" can be used to describe the storage location. Then, the location description is converted into coordinate information that the robot can understand. And according to the control protocol of the inbound robot, the format of the control instruction is determined. The instruction should contain information such as the moving path, speed, and target location of the robot. During the instruction generation process, corresponding control instructions can be generated based on the parsed location coordinates. Furthermore, based on the communication method supported by the robot, the generated control instructions are sent to the inbound robot.

[0097] In the technical solution provided in this embodiment, when an inbound request is received, a storage requirement description for various types of goods to be stored is determined according to the inbound request. Then, based on the free storage space in the inbound warehouse that meets the storage requirement description, at least one storage plan corresponding to the inbound request is generated. Further, based on the outbound simulation model, an outbound efficiency score corresponding to each storage plan is determined. Finally, the storage plan with the highest outbound efficiency score is used as the target storage plan for the inbound request, and the inbound action is executed based on the target storage plan. This can ensure that each time an inbound operation is performed, the current optimal plan is used to respond to the inbound request, thereby achieving the purpose of dynamically adjusting the warehouse layout. In this way, by dynamically adjusting the warehouse layout, the effect of improving the warehouse storage efficiency is achieved.

[0098] Please refer to Figure 3 , in another embodiment of the present application, based on the above embodiment, after step S40, the method further includes:

[0099] S50: Update the inventory information according to the target inbound plan.

[0100] After completing the inbound behavior of the goods corresponding to the inbound request according to the target inbound plan, updating the inventory information can ensure the accuracy and real-time nature of the inventory data. In an alternative solution, the automatic update of the inventory information can be realized based on the warehouse management system and related warehouse management automation equipment, such as barcode scanners, RFID tags, etc. At the same time, combined with regular inventory checks and manual audits, the accuracy of the inventory data is ensured.

[0101] Exemplarily, during the execution of the inbound operation, data collection is performed. That is, during the process of executing the inbound operation of the goods according to the target inbound plan, relevant information of the goods, such as product number, quantity, batch, etc., can be read based on the use of a barcode scanner or an RFID tag. And the collected data is transmitted to the warehouse management system in real time. After the system receives the inbound data, it automatically updates the inventory quantity of the corresponding goods. The system also records additional information such as the inbound time, the corresponding inbound request, and the source of the goods.

[0102] Then the system automatically verifies the inventory information, such as checking whether the quantities match and whether the batches are consistent. If abnormal data is found, the system can issue a warning and prompt for manual review. After the manual review confirms that there are no errors, the inventory information becomes officially effective.

[0103] Optionally, a regular inventory plan can also be formulated, such as conducting a comprehensive inventory once a month or once a quarter. Use the system or mobile devices to assist in the inventory, quickly record the actual inventory quantities. Then compare the inventory results with the inventory data in the system, find the differences and make adjustments. Record the reasons for the inventory differences and take measures to prevent the same problems from occurring in the future.

[0104] This application provides a device for dynamically adjusting a warehouse layout. The device for dynamically adjusting a warehouse layout includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method for dynamically adjusting a warehouse layout in Embodiment 1 above.

[0105] Next, refer to Figure 4 , which shows a schematic structural diagram of a device for dynamically adjusting a warehouse layout suitable for implementing the embodiments of this application. The device for dynamically adjusting a warehouse layout in the embodiments of this application may include, but is not limited to, devices such as mobile phones, tablets, PCs, servers, and smart wearable devices. Figure 4 The device for dynamically adjusting a warehouse layout shown is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of this application.

[0106] As Figure 4As shown, the dynamic adjustment device for the storage layout may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 into the random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the dynamic adjustment device for the storage layout are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the dynamic adjustment device for the storage layout to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows a dynamic adjustment device for the storage layout with various systems, it should be understood that it is not required to implement or have all the shown systems. Instead, more or fewer systems can be implemented or had.

[0107] Specifically, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above functions defined in the method of the embodiments disclosed in the present application are executed.

[0108] The dynamic adjustment device for the storage layout provided by the present application adopts the method of the dynamic adjustment device for the storage layout in the above embodiments to solve the technical problem of low storage efficiency caused by the static layout. Compared with the related art, the beneficial effects of the dynamic adjustment device for the storage layout provided by the present application are the same as those of the dynamic adjustment method for the storage layout provided by the above embodiments, and the other technical features in the dynamic adjustment device for the storage layout are the same as the features disclosed in the method of the previous embodiment, and will not be elaborated here.

[0109] It should be understood that each part disclosed in this application can be implemented by hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0110] As mentioned above, the above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0111] Please refer to Figure 5 , this application provides a dynamic adjustment system for warehouse layout. The dynamic adjustment system 100 for warehouse layout includes:

[0112] A receiving module 110, configured to receive a warehousing request and determine a storage requirement description for various types of goods to be warehoused according to the warehousing request;

[0113] A generating module 120, configured to generate at least one storage plan corresponding to the warehousing request according to the storage requirement description and the idle storage space of the warehouse to be warehoused;

[0114] A calculating module 130, configured to determine an outbound efficiency score corresponding to each storage plan based on an outbound simulation model;

[0115] An output module 140, configured to use the storage plan with the highest outbound efficiency score as the target storage plan for the warehousing request and perform a warehousing action based on the target storage plan.

[0116] This application provides a computer-readable storage medium with computer-readable program instructions (i.e., computer programs) stored thereon. The computer-readable program instructions are used to execute the dynamic adjustment method for warehouse layout in the above embodiments.

[0117] The computer-readable storage medium provided by the present application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, device, or component. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0118] The above computer-readable storage medium can be included in the dynamic adjustment device of the storage layout; it can also exist separately and not be assembled into the dynamic adjustment device of the storage layout.

[0119] The above computer-readable storage medium carries one or more programs. When the above one or more programs are executed by the dynamic adjustment device of the storage layout, the dynamic adjustment device of the storage layout can improve the storage efficiency of the warehouse based on the above method.

[0120] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0121] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutively represented blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0122] The modules described in the embodiments of this application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation on the unit itself in some cases.

[0123] The readable storage medium provided by this application is a computer-readable storage medium. The computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for performing the above-mentioned dynamic adjustment method of warehouse layout, and can solve the technical problem of low warehouse efficiency caused by static layout. Compared with the related art, the beneficial effects of the computer-readable storage medium provided by this application are the same as those of the dynamic adjustment method of warehouse layout provided by the above embodiments, and will not be elaborated here.

[0124] An embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the steps of the dynamic adjustment method of the above-mentioned warehouse layout.

[0125] The computer program product provided by the present application can solve the technical problem of low warehouse efficiency caused by static layout. Compared with the related art, the beneficial effects of the computer program product provided by the embodiment of the present application are the same as those of the dynamic adjustment method of the warehouse layout provided by the above embodiment, and will not be elaborated here.

[0126] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent scope of the present application.

[0127] It should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of another identical element in the process, method, article or system including the element. In the intervals given in the present application, the boundary values are included without explicit limitation.

[0128] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0129] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A method for dynamically adjusting storage layout, characterized in that: The dynamic adjustment method of the storage layout includes: Receiving a warehousing request, and determining storage requirement descriptions of various types of goods to be warehousing according to the warehousing request; Generate at least one storage solution corresponding to the warehousing request according to the storage requirement description and the free storage space of the warehouse to be loaded; Determine the outbound efficiency score corresponding to each storage solution based on the outbound simulation model; The storage solution with the highest outbound efficiency score is used as the target storage solution for the inbound request, and the inbound action is performed based on the target storage solution.

2. The method for dynamically adjusting storage layout according to claim 1, characterized in that: The step of generating at least one storage solution corresponding to the warehousing request according to the storage requirement description and the free storage space of the warehouse to be warehousing includes: Encode the storage requirement description based on a preset encoding rule to obtain storage requirement encoding data; Tokenizing the storage requirement encoded data through a natural language processing model, and generating the storage requirement description vector according to the tokenized storage requirement encoded data; Obtaining a storage location description vector corresponding to an idle storage location in the idle storage space; Determining a matching degree between the storage requirement description vector and the storage location description vector, and selecting an available storage location for each cargo category from the free storage locations according to the matching degree; A storage solution corresponding to at least one of the warehousing requests is generated according to the available storage locations.

3. The method for dynamically adjusting storage layout according to claim 2, characterized in that: The step of generating at least one storage solution corresponding to the warehousing request according to the available storage locations comprises: Determine the size information, quantity information, weight information and load-bearing information of the cargo units corresponding to each type of cargo to be stored; The size information, the weight information and the quantity information are used as inputs of a stacking algorithm, the load-bearing information is used as a constraint condition of the stacking algorithm, and a stacking scheme for each type of goods to be stored is determined based on the stacking algorithm; Filter out optional stacking solutions according to the size of the cargo pile corresponding to each stacking solution and the size of the available storage location; Determine, according to the optional stacking schemes and the available storage locations, sub-storage schemes corresponding to the various types of goods to be stored; At least one storage plan corresponding to the warehousing request is generated according to the sub-storage plan.

4. The method for dynamically adjusting storage layout according to claim 2, characterized in that: The step of obtaining a storage location description vector corresponding to an idle storage location in the idle storage space comprises: Encoding the location requirement description of the free storage location to obtain storage location description encoding data; The storage location description encoding data is tokenized through a natural language processing model, and the storage location description vector is generated according to the tokenized storage location description encoding data.

5. The method for dynamically adjusting storage layout according to claim 1, characterized in that: The step of determining the outbound efficiency score corresponding to each storage scheme based on the outbound simulation model comprises: Generate at least one shipment request based on historical shipment data; Determine the outbound route score and the pickup energy consumption score of each storage solution in response to the outbound request; According to the outbound route score and the picking energy consumption score, the outbound efficiency score of each storage solution in response to each outbound request is determined.

6. The method for dynamically adjusting storage layout according to claim 1, characterized in that: After the step of determining the outbound route score and the pickup energy consumption score of each storage solution in response to the outbound request, the method further includes: Determine, according to the outbound route score and the pickup energy consumption score, an initial outbound efficiency score of each storage solution in response to each outbound request; Determining a weight value of the outbound request according to the occurrence probability corresponding to the outbound request; According to the weight values ​​corresponding to the respective outbound requests, a weighted sum is performed on the initial outbound efficiency scores of the storage solutions in response to the outbound requests to obtain the outbound efficiency score.

7. The method for dynamically adjusting storage layout according to claim 1, characterized in that: The step of using the storage solution with the highest outbound efficiency score as the target storage solution for the inbound request and executing the inbound action based on the target storage solution includes: The storage solution with the highest outbound efficiency score is used as the target storage solution for the cargo unit: Obtaining a position description corresponding to the target storage solution, and generating a robot control instruction based on the position description; The robot control instruction is sent to the warehousing robot to control the warehousing robot to move the goods to be stored to the position corresponding to the target storage solution.

8. The method for dynamically adjusting storage layout according to claim 1, characterized in that: After the step of using the storage solution with the highest outbound efficiency score as the target storage solution for the inbound request and performing the inbound action based on the target storage solution, the method further includes: Update inventory information according to the target warehousing plan.

9. A dynamic adjustment system for storage layout, characterized in that: The dynamic adjustment system of the storage layout includes: A receiving module, used to receive a warehousing request and determine the storage requirement description of various types of goods to be warehousing according to the warehousing request; A generating module, configured to generate at least one storage solution corresponding to the warehousing request according to the storage requirement description and the free storage space of the warehouse to be loaded; A calculation module, used for determining the outbound efficiency score corresponding to each storage scheme based on the outbound simulation model; The output module is used to use the storage solution with the highest outbound efficiency score as the target storage solution for the inbound request, and perform the inbound action based on the target storage solution.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for dynamically adjusting the warehouse layout according to any one of claims 1 to 8 are implemented.

Images