CN118261522A

CN118261522A - Warehouse monitoring method, device, equipment and storage medium

Info

Publication number: CN118261522A
Application number: CN202410179797.XA
Authority: CN
Inventors: 朱磊; 张磊; 马菲菲; 程振丽; 宋海明
Original assignee: Wanjun Green Building Technology Co ltd
Current assignee: Wanjun Green Building Technology Co ltd
Priority date: 2024-02-18
Filing date: 2024-02-18
Publication date: 2024-06-28

Abstract

The application provides a warehouse monitoring method, a warehouse monitoring device, warehouse monitoring equipment and a storage medium, wherein the warehouse monitoring method comprises the following steps: generating a virtual model of the target warehouse based on the acquisition signals for the target warehouse, the target warehouse being used for storing the articles, the virtual model being used for displaying the target warehouse and the articles included in the target warehouse; under the condition that an in-out request aiming at a target warehouse is received, determining target article information corresponding to the in-out request; generating a warehouse-in and warehouse-out route aiming at target article information; displaying the virtual model after the warehouse-in and warehouse-out processing, wherein the virtual model is used for relevant personnel to watch so as to realize the supervision of the target warehouse. According to the embodiment of the application, the storage condition of the actual warehouse can be visually displayed by establishing the virtual model consistent with the actual warehouse, and a reasonable warehouse-in and warehouse-out route can be planned under the condition of warehouse-in and warehouse-out processing based on the storage condition, so that the operation and management efficiency of the warehouse is effectively improved.

Description

Warehouse monitoring method, device, equipment and storage medium

Technical Field

The application belongs to the technical field of data processing, and particularly relates to a warehouse monitoring method, a warehouse monitoring device, warehouse monitoring equipment and a storage medium.

Background

Bulk commodity warehouse management is one of important links of an industrial chain, but traditional bulk commodity steel warehouse management is small in site, scattered and chaotic in management, and poor in storage environment.

In addition, in the commodity warehouse-in and warehouse-out process, people are required to check and manage, so that the problem of higher management operation cost and lower efficiency of a target on bulk commodities is caused.

Disclosure of Invention

The application provides a warehouse monitoring method, a warehouse monitoring device, warehouse monitoring equipment and a warehouse monitoring storage medium, which can solve the technical problems that the warehouse management of bulk commodity steel products is small in site and scattered and disordered in management, the storage environment is poor, and in the commodity warehouse-in and warehouse-out process, the commodity needs to be checked and managed manually, so that the management operation cost of a target on the bulk commodity is high, and the efficiency is low.

An embodiment of a first aspect of the present application provides a warehouse monitoring method, including:

Generating a virtual model of a target warehouse based on an acquisition signal for the target warehouse, the target warehouse being used for storing items, the virtual model being used for displaying the target warehouse and the items included in the target warehouse;

under the condition that an access request aiming at the target warehouse is received, determining target article information corresponding to the access request;

generating an access route aiming at the target article information, wherein the access route is used for indicating articles corresponding to the target article information in the target warehouse to be subjected to access processing according to the access route;

Displaying the virtual model after the warehouse-in and warehouse-out processing, wherein the virtual model is used for relevant personnel to watch so as to realize the supervision of the target warehouse.

An embodiment of the second aspect of the present application provides a warehouse monitoring device, including:

The generation module is used for generating a virtual model of a target warehouse based on an acquisition signal aiming at the target warehouse, wherein the target warehouse is used for storing articles, and the virtual model is used for displaying the target warehouse and the articles included in the target warehouse;

the determining module is used for determining target article information corresponding to the warehouse-in and warehouse-out request under the condition that the warehouse-in and warehouse-out request aiming at the target warehouse is received;

The generation module is further used for generating a warehouse-in and warehouse-out route aiming at the target article information, and the warehouse-in and warehouse-out route is used for indicating articles corresponding to the target article information in the target warehouse to be subjected to warehouse-in and warehouse-out processing according to the warehouse-in and warehouse-out route;

The display module is used for displaying the virtual model after the warehouse-in and warehouse-out processing, and the virtual model is used for relevant personnel to watch so as to realize the supervision of the target warehouse.

An embodiment of a third aspect of the present application provides a computing device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor running the computer program to implement the method of the first aspect.

An embodiment of the fourth aspect of the present application provides a computer-readable storage medium having stored thereon a computer program for execution by a processor to perform the method of the first aspect described above.

The technical scheme provided by the embodiment of the application has at least the following technical effects or advantages:

In the embodiment of the application, firstly, a virtual model of a target warehouse is generated based on a collection signal aiming at the target warehouse, the target warehouse is used for storing articles, and the virtual model is used for displaying the target warehouse and the articles included in the target warehouse; under the condition that an in-out request aiming at a target warehouse is received, determining target article information corresponding to the in-out request; generating a warehouse-in and warehouse-out route aiming at target article information; displaying the virtual model after the warehouse-in and warehouse-out processing, wherein the virtual model is used for relevant personnel to watch so as to realize the supervision of the target warehouse. According to the embodiment of the application, the storage condition of the actual warehouse can be visually displayed by establishing the virtual model consistent with the actual warehouse, and a reasonable warehouse-in and warehouse-out route can be planned under the condition of warehouse-in and warehouse-out processing based on the storage condition, so that the operation and management efficiency of the warehouse is effectively improved.

Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the figures.

In the drawings:

FIG. 1 is a flow chart of a warehouse monitoring method according to an embodiment of the present application;

FIG. 2 is an interface diagram of a virtual model according to an embodiment of the present application;

FIG. 3 illustrates an interface diagram of yet another virtual model provided by an embodiment of the present application;

FIG. 4 is a schematic diagram of a warehouse interface according to an embodiment of the present application;

FIG. 5 is a schematic diagram of yet another warehouse interface provided by an embodiment of the present application;

FIG. 6 is a schematic diagram of yet another warehouse interface provided by an embodiment of the present application;

FIG. 7 is a schematic diagram of a scenario for determining a warehouse entry route according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of a warehouse monitoring device according to an embodiment of the present application;

FIG. 9 illustrates a schematic diagram of a computing device according to an embodiment of the present application;

fig. 10 is a schematic diagram of a storage medium according to an embodiment of the present application.

Detailed Description

Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art.

It is noted that unless otherwise indicated, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs.

By adopting the background technology, the prior bulk steel product storage management is random in the process of delivering and warehousing, for example, the warehoused commodity is simply placed at an idle position in the warehouse when a commodity is warehoused, and when the commodity is delivered, delivery personnel are required to search, so that delivery efficiency is low.

In order to solve the technical problems, the application provides a warehouse monitoring method, device, equipment and storage medium, which are used for generating a virtual model of a target warehouse based on acquisition signals aiming at the target warehouse, wherein the target warehouse is used for storing articles, and the virtual model is used for displaying the target warehouse and the articles contained in the target warehouse; under the condition that an in-out request aiming at a target warehouse is received, determining target article information corresponding to the in-out request; generating a warehouse-in and warehouse-out route aiming at target article information; displaying the virtual model after the warehouse-in and warehouse-out processing, wherein the virtual model is used for relevant personnel to watch so as to realize the supervision of the target warehouse. According to the embodiment of the application, the storage condition of the actual warehouse can be visually displayed by establishing the virtual model consistent with the actual warehouse, and a reasonable warehouse-in and warehouse-out route can be planned under the condition of warehouse-in and warehouse-out processing based on the storage condition, so that the operation and management efficiency of the warehouse is effectively improved.

The warehouse monitoring method of the present application may be executed by a computing device, which may be a server, for example, one server, a plurality of servers, a server cluster, a cloud computing platform, or the like, and optionally, the computing device may also be a terminal device, for example, a mobile phone, a tablet computer, a game machine, a portable computer, a desktop computer, an advertisement machine, an all-in-one machine, or the like.

A warehouse monitoring method, apparatus, device and storage medium according to embodiments of the present application are described below with reference to the accompanying drawings, where in each embodiment of the present application, a warehouse system is described by way of example, and the warehouse system includes a server for data processing and an interface for displaying a virtual model.

Referring to fig. 1, the method specifically includes the steps of:

S101, generating a virtual model of the target warehouse based on the acquisition signals aiming at the target warehouse.

The target repository is for storing items and the virtual model is for displaying the target repository and items included in the target repository.

In some embodiments, the warehousing system may be used to manage a plurality of warehouses, and the target warehouse may be any of the plurality of warehouses.

The collecting signals can be collected by collecting equipment arranged in the target warehouse, the collecting equipment can be a sensor, a scanning equipment, a data interface and the like, for example, the collecting signals of physical layout, storage equipment, goods information and goods positions, environmental conditions and the like of the target warehouse can be obtained through the sensor and the scanning equipment, and the data of the work flow, carrying equipment and the like of the target warehouse can be obtained through a data structure.

Wherein, the data synchronization mechanism can be developed or integrated to ensure that the virtual model can be updated in real time to reflect the changes of the physical warehouse.

A virtual model of the target warehouse, including shelves, handling equipment, work areas, cargo, etc., is created by three-dimensional modeling software (e.g., autoCAD, blender, etc.) using the acquired signals.

Simulation software (e.g., anyLogic, flexSim, etc.) is integrated to virtualize warehouse operations such as warehousing, storage, picking, and ex-warehouse, etc.

In some embodiments, generating a virtual model of the target warehouse based on the acquisition signals for the target warehouse includes: generating a virtual sub-model corresponding to the plurality of storage areas based on the acquisition signals for the target warehouse; dividing the virtual sub-model into a plurality of physical locations; and generating a virtual model of the target warehouse based on the filling condition of the articles corresponding to each of the plurality of physical positions.

The creation of the virtual model for the target warehouse is mainly used for displaying the target warehouse and the articles included in the target warehouse, so that the virtual sub-model corresponding to a plurality of storage areas can be generated firstly based on the acquisition signals for the target warehouse, for example, the virtual sub-model corresponding to a plurality of storage areas can be generated according to the distance between the virtual sub-model and a warehouse door, and the plurality of storage areas can comprise a common goods shelf area, a dangerous article storage area, a distribution area, a high-value article storage area and the like. For example, the closest physical location to the garage door may be a distribution area, and the location farther from the garage door may be a hazardous materials storage area, a high value items storage area, or the like. The physical positions can be represented by a bin position, a zone position, a stack position, a layer number and a serial number, and can be flexibly set based on practical situations, for example, each steel product corresponds to one serial number, and then the physical positions can be represented by a bin position 1, a zone position 1, a stack position 1, a layer number 1 and a serial number 1, or by a bin position 2, a zone position 2, a stack position 2, a layer number 2, a serial number 2 and the like.

Further, the filling condition corresponding to each of the plurality of physical locations may be determined based on the acquired signal, and the filling condition may be whether the physical locations have goods, for example, whether there is goods in the bin 1, the zone 1, the stack 1, the layer number 1, the serial number 1, or whether there is goods in the bin 2, the zone 2, the stack 2, the layer number 2, the serial number 2 may be determined, so that a virtual model of the target warehouse is generated based on the filling condition of the goods corresponding to each of the plurality of physical locations.

Further, the virtual model may be displayed for viewing by the relevant person.

The related personnel can be management personnel of the warehouse system or clients with articles stored in the target warehouse.

In an alternative embodiment, fig. 2 provides an interface diagram of a virtual model of an embodiment of the present application, as shown in fig. 2,The shelf is shown as a shelf,Indicating that the shelf is empty and that,The goods are arranged on the goods shelves, a plurality of goods shelves close to the warehouse door form a distribution area, two positions far away from the warehouse door are respectively a dangerous goods storage area and a high-value goods storage area, other goods shelves form a common goods shelf area, each goods shelf is represented by a stack position, each goods shelf is provided with multiple layers, each layer is represented by a corresponding layer number, each layer can store a plurality of goods, each goods is represented by a serial number, and therefore each goods is provided with a corresponding area position, a stack position, a layer number and a serial number. Through the virtual model, related personnel can clearly see the layout of each zone and the filling condition of the articles of each zone.

S102, under the condition that the warehouse-in and warehouse-out request in the target warehouse is received, determining target article information corresponding to the warehouse-in request.

Besides the display interface for displaying the virtual model, the warehousing system can be provided with a warehousing interface, the warehousing interface can be used for users to submit a warehouse-in and warehouse-out request, the triggering of the warehouse-in and warehouse-out request can receive list materials submitted by the users on the warehousing interface, and the list materials can be pictures, characters, voices and the like.

In some embodiments, the material information may be identified, and the item corresponding to the material information may be determined, so that the target item information corresponding to the outbound-inbound request may be determined based on the item corresponding to the material information.

In some embodiments, in order to improve the identification speed of the article corresponding to the material information, the material information may be labeled according to a preset standard by using a labeling model, so as to identify the labeled material information.

In some embodiments, the labeling model may be used to label the material information according to a preset standard, and the labeling result is further displayed on a warehouse interface, so that the user can check the material information, receive the operation of the user, and determine the final target article information based on the operation of the user.

S103, generating a warehouse-in and warehouse-out route aiming at the target article information.

The warehouse-in and warehouse-out route is used for indicating that the articles corresponding to the target article information in the target warehouse are subjected to warehouse-in and warehouse-out processing according to the warehouse-in and warehouse-out route.

In some embodiments, after the target article information is determined, the physical position corresponding to each piece of target article information may be determined based on the collected collection signal, or the physical position corresponding to each piece of target article information may be determined based on the target article information, and the physical position of the handling device and the warehouse-in and warehouse-out position to be subjected to warehouse-in and warehouse-out are determined by combining the collection signal, so as to determine the warehouse-in and warehouse-out route.

Through the storage layout of the virtual target warehouse and maintains synchronization with the target warehouse. When goods need to be stored or searched, the system can provide optimal storage positions and paths through the virtual model, so that human errors and time waste are reduced.

S104, displaying the virtual model after the warehouse-in and warehouse-out processing.

The virtual model is used for relevant personnel to watch so as to realize supervision of the target warehouse.

In some embodiments, the recording analysis of each lot of goods going in and out of the warehouse comprises: and (3) recording auxiliary data such as traffic flow, people flow and the like related to the goods, classifying and recording according to storage points and time points, and displaying the increase or decrease of the goods on corresponding positions on the virtual model so as to facilitate the viewing of related personnel, thereby realizing the supervision of the target warehouse.

In an alternative embodiment, assuming that FIG. 2 is a virtual model before the in-and-out process, FIG. 3 is a virtual model after the in-and-out process, as shown in FIGS. 2 and 3, the first shelf and the second shelf in the distribution area of FIG. 3 are defined byBecomes as followsIt is known that the target article to be put in and out is located on the first shelf and the second shelf. Thus, the related personnel can monitor the whole warehouse-in and warehouse-out process and the articles in the warehouse-in and warehouse-out.

In the embodiment of the application, a virtual model of a target warehouse is generated based on a collection signal aiming at the target warehouse, the target warehouse is used for storing articles, and the virtual model is used for displaying the target warehouse and the articles included in the target warehouse; under the condition that an in-out request aiming at a target warehouse is received, determining target article information corresponding to the in-out request; generating a warehouse-in and warehouse-out route aiming at target article information; displaying the virtual model after the warehouse-in and warehouse-out processing, wherein the virtual model is used for relevant personnel to watch so as to realize the supervision of the target warehouse. According to the embodiment of the application, the storage condition of the actual warehouse can be visually displayed by establishing the virtual model consistent with the actual warehouse, and a reasonable warehouse-in and warehouse-out route can be planned under the condition of warehouse-in and warehouse-out processing based on the storage condition, so that the operation and management efficiency of the warehouse is effectively improved.

In some embodiments, in order to improve management efficiency, list materials in the warehouse-in and warehouse-out request may be expressed in advance, and in the case that the warehouse-in and warehouse-out request for the target warehouse is received, determining target article information corresponding to the warehouse-in request includes:

acquiring material information in the warehouse-in and warehouse-out request, wherein the material information is used for representing original article information in the warehouse-in and warehouse-out request;

determining a trained target annotation model based on the selection operation of the user on the annotation model;

labeling the material information based on the trained target labeling model, and outputting labeling results;

Receiving preset operation of a user on the labeling result, and determining a target labeling result;

and determining the target labeling result as target article information corresponding to the warehouse-in and warehouse-out request.

The material information may be a product which is filled by the user and needs to be put in and put out in the warehouse, but may not be standard, for example, only the product name is not used, and various attributes of the product, such as the size, the weight and the position of the product, are not used, so that the material information needs to be marked, and the warehouse system can determine that the product to be put in and put out is in the position of the target warehouse, thereby carrying out the put in and put out processing.

In some embodiments, after receiving the material information input by the user, the material information may be first cleaned and classified, where the cleaning and classifying of the data generally includes the following steps:

Data cleaning: the data cleaning refers to performing operations such as de-duplication, noise removal, missing value processing and the like on the data so as to ensure the accuracy and the integrity of the data. During the data cleansing process, it is necessary to use a data cleansing tool or write specific program codes.

Data classification: data classification refers to the classification of data into different categories or groups according to certain rules or criteria. Data classification may be based on different attributes, such as time, place, product type, user population, etc., for subsequent analysis and application.

Data archiving: data archiving refers to the organization and storage of data in a prescribed manner to facilitate querying and backtracking. In the process of data archiving, the security and privacy protection of data need to be considered.

Data conversion: data conversion refers to converting data from one format or structure to another. For example, converting data from a text format to a database format, or converting data from an Excel form to a CSV file, etc.

And (3) data verification: data verification refers to checking the cleaned and classified data to ensure the accuracy and usability of the data. The data verification can be performed by means of manual auditing, a data mining algorithm and the like.

Cleaning and classifying the data can improve the quality and usability of the data, and provide a basis for subsequent analysis and application.

Pre-labeling is used as the first step of the labeling process, and the goal is to quickly perform preliminary processing on a large amount of material information. This requires the warehousing system to automatically identify key features in the material information and make corresponding marks. The efficiency of pre-labeling is critical to shorten the overall project cycle, and therefore advanced algorithms and sufficient computational resources are required to guarantee speed. Meanwhile, in order to ensure the accuracy of the follow-up manual labeling, the pre-labeling result should have certain accuracy, so that the workload of manual correction is reduced.

The manual labeling is a detailed auditing and correction work performed by professionals on the basis of pre-labeling. This stage requires the system to provide an intuitive and easy-to-use interface so that the operator can efficiently complete the labeling task. Manual labeling focuses on accuracy and detail handling, so the system should support multiple labeling tools and allow users to customize labeling rules. In addition, in order to cope with the complex and changeable labeling requirements, the system should also have good expandability and flexibility.

In order to improve the labeling speed, a plurality of pre-trained labeling models are stored in the warehousing system, and a user can determine a corresponding model based on the type of the material information, so that the warehousing system can receive selection operation aiming at the labeling models, and the trained target labeling models are determined.

The method can be used for marking the model on line in advance, or storing a plurality of trained models in a warehouse system, and marking the material information by directly using the target marking model after the target marking model is selected by a user.

Fig. 4 is a schematic diagram of a warehouse interface provided by an embodiment of the present application, where, as shown in fig. 4, the warehouse interface provides an input box of a model name, a label to be marked, such as a title, a date, a weight, a specification, and the like, and provides a deployment mode, including: the local deployment and cloud deployment provide application types, including: the application type A and the application type B are used for receiving the operation of a user, as shown in fig. 4, the model name input by the user is model A, namely the target labeling model is model A, and the data set version of the last step is selected: model A/V3, and select a plurality of labels to be marked, and select application type A deployed locally.

Further, the warehousing system trains the target labeling model based on the model selected by the user, the version of the data set, the label and the application type of the last step.

After the training of the target annotation model is completed, the target annotation model can be downloaded.

Fig. 5 shows a schematic diagram of an interface for inputting material information, which is provided by the embodiment of the present application, and as shown in fig. 5, the interface includes an input box of a model and a model version set application type, and an input box of material information, and a user may drag the material information to the input box of material information to complete inputting the material information, receive an input operation of the user with respect to the input boxes of the model and the model version set application type, determine a target labeling model for labeling, and receive the input box of the user with respect to the material information, and obtain the material information, where, as shown in fig. 5, the target labeling model is a model a, and the application type is a locally deployed V3-application type a. Further, clicking operation for a control for starting annotation is received, and the target annotation model is used for annotating the material information used for input.

And further, labeling the material information based on the target labeling model, and outputting a labeling result at the storage interface. For example, if the material information includes the name, the material and the specification of the target object, it may be determined that the current target warehouse accords with the corresponding target object in the material information, and other corresponding attribute information, such as the library, the current position, the number, the steel number, the departments and the like, is marked.

In some embodiments, the labeling results that are output are shown in table 1.

TABLE 1

Further, a manual labeling process can be performed, that is, a preset operation of a user on a labeling result is received, a target labeling result is determined, and the target labeling result is shown in table 2.

TABLE 2

From tables 1 and 2, it can be seen that the user modifies the number of items with the names "middle plate" and the quality "Q355B" specification "20 x 2500 x 11760" from "4.616" to "5.616", and modifies the number of items with the names "middle plate" and the quality "Q355B" specification "14 x 2500 x 11840" from "3.253" to: "4.253".

The current bin bits in tables 1 and 2 represent bin bit-zone bits and sequence numbers, e.g., "A-1-1" for A bin-1 zone-sequence number 1.

Further, the item information shown in table 2 is determined as the target item information corresponding to the warehouse-in request.

In some embodiments, after labeling the material information based on the trained target labeling model, outputting a labeling result, inputting the labeling result into a pre-trained recognition model, determining a recognition result, and further determining the recognition result as target article information corresponding to the warehouse-in and warehouse-out request.

In some embodiments, the training process of the target annotation model includes:

Obtaining multiple groups of sample data and label data corresponding to each group of sample data in a preset time period, wherein each group of sample data comprises: the material information in the warehouse-in and warehouse-out request, and the label data are label labeling results corresponding to the material information in the corresponding sample data;

Inputting target sample data into a target labeling model to obtain a prediction labeling result corresponding to material information in the target sample data, wherein the target sample data is any one group of data in a plurality of groups of sample data;

Calculating to obtain a loss function value based on the prediction labeling result and a label labeling result corresponding to the material information in the target sample data;

And adjusting model parameters of the target labeling model based on the loss function value, and continuing training until a preset training completion condition is met, so as to obtain the trained target labeling model.

The preset time period can be flexibly set based on practical situations, such as one month, one week and the like.

The sample data can be material information input by a user at any time, namely, the warehousing system can train the labeling model in the process of entering and exiting the warehouse.

The loss function value may be a loss function value of any one of a mean square error function, an average absolute error function, a cross entropy loss function, a logarithmic function, and the like.

The preset training completion condition may be that the number of training times reaches an iteration number threshold or the loss function value is smaller than the preset loss function value, and so on.

The training process of the recognition model is consistent with the training process of the labeling model, and will not be described in detail herein.

It should be noted that, the warehouse model may also store various model structures for model training, and after labeling, various models may be provided in the corresponding model selection interface, as shown in fig. 6, where the models may include: object detection model, hybrid model, classification model, OCR model, image comparison model, search comparison model, etc., after receiving a selection operation for any model, training a target annotation model based on the model, as shown in FIG. 6, receiving a selection operation for the OCR model by a user, training the target annotation model by utilizing the structure and the loss function of the OCR model.

In some embodiments, generating an in-and-out route for target item information includes:

determining the physical position of a target object corresponding to the target object information in a target warehouse;

acquiring the warehouse-in and warehouse-out position and the carrying equipment position of the target article information;

A warehouse-in route for the target item is determined based on the physical location, the warehouse-in location, and the handling equipment location.

The physical position of each target object in the target warehouse can be determined based on the target object information, the warehouse-in and warehouse-out position can be obtained through user input or can be determined based on the warehouse-in and warehouse-out position on the virtual model, the position of the carrying equipment can be determined through acquisition signals, and the carrying equipment can be one or more.

The physical position, the warehouse-in position and the carrying equipment position are a plurality of points, route planning is carried out based on the plurality of points, an optimal path passing through the plurality of points is determined, and the optimal path is determined to be a warehouse-in route.

The warehouse-out position and the warehouse-in position of the target object can be consistent or inconsistent, and the embodiment of the application takes the warehouse-out position and the warehouse-in position as examples.

In some embodiments, determining the in-and-out route for the target item based on the physical location, the in-and-out location, and the handling device location includes:

determining a plurality of routes from the warehouse-in position to the carrying equipment position based on the physical position, the warehouse-in position and the carrying equipment position;

acquiring initial pheromone concentrations of a plurality of routes;

Determining target pheromone concentrations corresponding to the routes respectively based on initial pheromone concentrations corresponding to the routes respectively, products of pheromone volatilization factors and the initial pheromone concentrations, and the accumulated amount of the pheromones of the routes passing through the positions from the warehouse-in position to the carrying equipment position;

and determining the route with the maximum concentration of the target pheromone as the warehouse-in and warehouse-out route of the target object.

In general, there may be a plurality of routes at the physical location of the target warehouse, each of which is started at the warehouse-in/out location, ended at the transport facility location, or ended at the transport facility location, and which passes through the target article. Since there may be a plurality of handling devices, there may be a plurality of handling device positions. The following describes a process of determining a route for entering and exiting a warehouse in the case where the position of the transporting apparatus is one in the embodiment of the present application.

A plurality of routes may be first determined that start at the warehouse entry location, end at the handling equipment, or end at the handling equipment, end at the warehouse entry location, and pass through the physical location of the target item at the target warehouse.

The initial pheromone concentration corresponding to each route can be preset, and the pheromone concentration is a physical quantity reflecting the advantages and disadvantages of the routes, for example, the route is less in time consumption, the route is shorter, the obstacles in the route are fewer, the pheromone concentration of the route is higher, and otherwise, the pheromone concentration of the route is lower.

In some embodiments, the target pheromone concentration may be expressed by the following formula:

τ_ij(t+1)＝(1-ρ)*τ_ij(t)+Δτ_ij

Where τij (t+1) is a target pheromone concentration, that is, the pheromone concentration corresponding to each of the plurality of routes at time t+1, time t+1 is the time when each route is completed, time t is the time when each route is started, i is an in-out position or a transporting device position, j is a transporting device position, i is a transporting device position, j is an in-out position, (1- ρ) τij (t) is the volatilization of the pheromone in each route in the process from time t to time t+1, ρ is the pheromone volatilization factor, τij (t) is the initial pheromone concentration, and Δτij is the pheromone accumulation amount.

The above formula can be used to determine the target pheromone concentration of each route, and as the pheromone concentration is higher, the corresponding routes are less in time, the routes are shorter, and the obstacles in the routes are less, so that the route with the highest pheromone concentration in the multiple routes can be determined as the warehouse-in route.

Fig. 7 shows a schematic view of a scenario for determining a warehouse-in route according to an embodiment of the present application, where, as shown in fig. 7, point a is a location of a handling device, point B is a warehouse-out location, point C, point D, and point E are physical locations of target objects, respectively, a starting point of the location of the handling device is assumed, a warehouse-out location is an end point, and the number of handling devices is 1, and it is assumed that it is determined that a route from a to B may be: a- > C- > D- > E- > B, or A- > D- > C- > E- > B, or A- > E- > C- > D- > B, respectively calculating the target pheromone concentration of A- > C- > D- > E- > B to be 3, the target pheromone concentration of A- > D- > C- > E- > B to be2, and the target pheromone concentration of A- > E- > C- > D- > B to be1 according to the calculation mode of the target pheromone concentration, and finally determining the delivery route to be A- > C- > D- > E- > B.

In addition to the planning of the warehouse-in and warehouse-out route, the carrying sequence of the articles can be planned, in the warehouse-out process, the warehouse-in information of each target article and the warehouse-in and warehouse-out information of the articles related to each target in the warehouse-in time to the warehouse-out time can be obtained, and the carrying sequence of the target articles is determined based on the warehouse-in information of each target article and the warehouse-in and warehouse-out information of the articles related to each target.

For example, when the object is a steel plate, the carrying device stacks 4 steel plates with the same specification as the object and the object at the same time in the 1 zone, the object is at the bottommost, the system numbers the 5 steel plates according to the sequence from top to bottom, after a period of time, the carrying device stacks 4 steel plates on the 5 steel plates, at the moment, the carrying device receives the warehouse-out operation for the object, and determines that the carrying sequence of the object is that 8 steel plates above the object are carried away at first and the object is carried away further based on the warehouse-in information of the object and the warehouse-out information of the object related to the object.

In some embodiments, to supervise the abnormal situation, the method further comprises:

Based on the supervision information of the article supervision equipment arranged in the target warehouse, determining the storage conditions of a plurality of articles in the target warehouse, wherein the storage conditions comprise: at least one of a storage quantity, a storage volume, and a degree of damage to the item;

And displaying alarm information aiming at any article on the virtual model under the condition that the storage condition of any article meets the preset requirement.

The article supervision device may include an internet of things device and a sensor.

In some embodiments, the target warehouse is generally provided with internet of things equipment and sensors, such as a temperature and humidity sensor, a displacement sensor, a weight sensor, a camera and the like. The equipment can monitor conditions of environment, goods, personnel and the like in the warehouse in real time.

Through thing networking equipment and sensor, data in the real-time collection warehouse, information such as volume, quantity, the position of goods, and information such as temperature, the humidity of environment. Meanwhile, people are identified and monitored through face recognition and other technologies.

And uploading the acquired data to a cloud or server of the warehousing system, and processing and analyzing the acquired data through a big data analysis technology. By comparing the historical data with preset rules, abnormal conditions such as reduction of goods quantity, abnormal personnel behaviors and the like can be found.

In some embodiments, the change of volume and weight of bulk commodity of a manager can be timely reminded through modes of historical data comparison, ring ratio and the like, once a data abnormal change person is found, the manager corresponds to a warehouse position on an electronic map, and the manager flashes and alarms, and simultaneously pops up a real-time video image for the manager to remotely check.

The preset requirement can be flexibly set based on actual conditions, for example, the storage amount of a certain article in the target warehouse of the present month is less than 80% of the storage amount of the same time of the previous month, for example, the volume or weight of the certain article in the target warehouse of the present month is less than 80% of the volume or weight of the same time of the previous month.

In some embodiments, the target warehouse may be further monitored based on the historical order amount, for example, the order amount of an item in the previous month is 5 tons, the storage amount of the item in the current month is only 4 tons, and the alarm information of insufficient storage amount of the item may be displayed on the virtual model when the order amount in the previous month is insufficient.

In some embodiments, in addition to displaying the alarm information on the virtual model, a real-time screen corresponding to the alarm information may be displayed for the supervisory personnel to watch.

The embodiment of the application also provides a warehouse monitoring device which is used for executing the warehouse monitoring method provided by any embodiment. As shown in fig. 8, the apparatus includes: a generation module 801, a determination module 808 and a display module 803.

A generating module 801, configured to generate a virtual model of a target warehouse, based on an acquisition signal for the target warehouse, where the target warehouse is used to store items, and the virtual model is used to display the target warehouse and items included in the target warehouse;

A determining module 802, configured to determine, when receiving a warehouse entry request for a target warehouse, target article information corresponding to the warehouse entry request;

The generating module 801 is further configured to generate an access route for the target item information, where the access route is used to instruct to perform access processing on an item corresponding to the target item information in the target warehouse according to the access route;

The display module 803 is configured to display the virtual model after the warehouse-in and warehouse-out processing, where the virtual model is used for viewing by related personnel, so as to implement supervision on the target warehouse.

The embodiment of the application provides a warehouse monitoring device, which comprises the steps of firstly, generating a virtual model of a target warehouse based on a collection signal aiming at the target warehouse, wherein the target warehouse is used for storing articles, and the virtual model is used for displaying the target warehouse and the articles included in the target warehouse; under the condition that an in-out request aiming at a target warehouse is received, determining target article information corresponding to the in-out request; generating a warehouse-in and warehouse-out route aiming at target article information; displaying the virtual model after the warehouse-in and warehouse-out processing, wherein the virtual model is used for relevant personnel to watch so as to realize the supervision of the target warehouse. According to the embodiment of the application, the storage condition of the actual warehouse can be visually displayed by establishing the virtual model consistent with the actual warehouse, and a reasonable warehouse-in and warehouse-out route can be planned under the condition of warehouse-in and warehouse-out processing based on the storage condition, so that the operation and management efficiency of the warehouse is effectively improved.

In some embodiments, the determining module 802 is specifically configured to:

In some embodiments, the determining module 802 is further specifically configured to:

In some embodiments, the generating module 801 is specifically configured to:

generating a virtual sub-model corresponding to the plurality of storage areas based on the acquisition signals for the target warehouse;

dividing the virtual sub-model into a plurality of physical locations;

and generating a virtual model of the target warehouse based on the filling condition of the articles corresponding to each of the plurality of physical positions.

In some embodiments, the generating module 801 is further specifically configured to:

acquiring initial pheromone concentrations of a plurality of routes;

In some embodiments of the present invention,

The determining module 802 is further configured to: based on the supervision information of the article supervision equipment arranged in the target warehouse, determining the storage conditions of a plurality of articles in the target warehouse, wherein the storage conditions comprise: at least one of a storage quantity, a storage volume, and a degree of damage to the item;

the display module 803 is further configured to display, on the virtual model, alarm information for any item if the storage condition of any item meets a preset requirement.

The embodiment of the application also provides a computing device for executing the warehouse monitoring method. Reference is made to fig. 9, which is a schematic diagram illustrating a computing device according to some embodiments of the present application. As shown in fig. 9, the computing device 7 includes: processor 700, memory 701, bus 702, and communication interface 703, processor 700, communication interface 703, and memory 701 being connected by bus 702; the memory 701 stores a computer program executable on the processor 700, and the processor 700 executes the warehouse monitoring method according to any of the foregoing embodiments of the present application when the computer program is executed.

The memory 701 may include a high-speed random access memory (RAM: random Access Memory), and may further include a non-volatile memory (non-volatile memory), such as at least one disk memory. The communication connection between the device network element and at least one other network element is achieved through at least one communication interface 703 (which may be wired or wireless), the internet, a wide area network, a local network, a metropolitan area network, etc. may be used.

Bus 702 may be an ISA bus, a PCI bus, an EISA bus, or the like. The buses may be divided into address buses, data buses, control buses, etc. The memory 701 is configured to store a program, and the processor 700 executes the program after receiving an execution instruction, and the warehouse monitoring method disclosed in any of the foregoing embodiments of the present application may be applied to the processor 700 or implemented by the processor 700.

The processor 700 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the methods described above may be performed by integrated logic circuitry in hardware or instructions in software in processor 700. The processor 700 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but may also be a Digital Signal Processor (DSP), application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 701, and the processor 700 reads information in the memory 701, and in combination with its hardware, performs the steps of the above method.

The computing device provided by the embodiment of the application and the warehouse monitoring method provided by the embodiment of the application have the same beneficial effects as the method adopted, operated or realized by the computing device and the warehouse monitoring method provided by the embodiment of the application due to the same inventive concept.

The embodiment of the present application further provides a computer readable storage medium corresponding to the warehouse monitoring method provided in the foregoing embodiment, referring to fig. 10, the computer readable storage medium is shown as an optical disc 30, on which a computer program (i.e. a program product) is stored, where the computer program, when executed by a processor, performs the warehouse monitoring method provided in any of the foregoing embodiments.

It should be noted that examples of the computer readable storage medium may also include, but are not limited to, a phase change memory (PRAM), a Static Random Access Memory (SRAM), a Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a flash memory, or other optical or magnetic storage medium, which will not be described in detail herein.

The computer readable storage medium provided by the above embodiment of the present application has the same advantages as the method adopted, operated or implemented by the application program stored therein, because of the same inventive concept as the warehouse monitoring method provided by the embodiment of the present application.

It should be noted that:

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application may be practiced without these specific details. In some instances, well-known structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the above description of exemplary embodiments of the application, various features of the application are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the following schematic diagram: i.e., the claimed application requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this application.

Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the application and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

The present application is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present application are intended to be included in the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.

Claims

1. A warehouse monitoring method, comprising:

2. The method of claim 1, wherein the determining, in the case of receiving a warehouse-in request for the target warehouse, target item information corresponding to the warehouse-in request comprises:

receiving preset operation of a user for the labeling result, and determining a target labeling result;

3. The method of claim 2, wherein the training process of the target annotation model comprises:

Obtaining a plurality of groups of sample data and label data corresponding to each group of sample data in a preset time period, wherein each group of sample data comprises: the label data is label labeling results corresponding to the material information in the corresponding sample data;

Inputting target sample data into a target labeling model to obtain a prediction labeling result corresponding to material information in the target sample data, wherein the target sample data is any one group of data in the plurality of groups of sample data;

Calculating a loss function value based on the prediction labeling result and a label labeling result corresponding to the material information in the target sample data;

And adjusting model parameters of the target labeling model based on the loss function value, and continuing training until a preset training completion condition is met, so as to obtain a trained target labeling model.

4. The method of claim 1, wherein the generating a virtual model of the target warehouse based on the acquisition signals for the target warehouse comprises:

Dividing the virtual sub-model into a plurality of physical locations;

5. The method of claim 1, wherein generating an in-and-out route for the target item information comprises:

Determining the physical position of a target object corresponding to the target object information in the target warehouse;

and determining a warehouse-in route of the target object based on the physical position, the warehouse-in position and the handling equipment position.

6. The method of claim 5, wherein the determining the in-and-out route for the target item based on the physical location, the in-and-out location, and the handling device location comprises:

determining a plurality of routes corresponding to the warehouse-in and warehouse-out positions to the conveying equipment positions based on the physical positions, the warehouse-in and warehouse-out positions and the conveying equipment positions;

Acquiring initial pheromone concentrations of the multiple routes;

determining target pheromone concentrations corresponding to the routes based on the initial pheromone concentrations, the products of the pheromone volatilization factors and the initial pheromone concentrations corresponding to the routes and the accumulated amount of the pheromones of the routes passing through the positions from the warehouse-in position to the carrying equipment position;

7. The method according to claim 1, wherein the method further comprises:

Determining storage conditions of a plurality of articles in the target warehouse based on supervision information of article supervision equipment arranged in the target warehouse, wherein the storage conditions comprise: at least one of a storage quantity, a storage volume, and a degree of damage to the item;

8. A warehouse monitoring device, comprising:

9. A computing device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor runs the computer program to implement the method of any one of claims 1-7.

10. A computer readable storage medium having stored thereon a computer program, wherein the program is executed by a processor to implement the method of any of claims 1-7.