TWM650377U - Warehouse space management system - Google Patents

Abstract

A warehouse space management system is provided, which includes a display device, an image capture device and a computing device. The image capture device captures a warehouse space image of the warehouse space. The computing device is connected to the image capture device and the display device, and receives the warehouse space image. The computing device detects whether a replenishment event occurs based on the warehouse space image. When the replenishment event occurs, the computing device uses the image capture device to capture at least one goods image. The computing device performs a warehouse-in registration procedure of the goods and establishes a digital model of the goods according to at least one goods image. The computing device determines a storage location of the goods according to the digital model and the warehouse space model of the warehouse space. The display device prompts the storage location of the goods.

Description

Warehouse space management system

This new creation relates to a warehouse management system, and in particular to a warehouse space management system based on artificial intelligence models.

Warehousing plays a very important role in modern factory production and logistics. Good warehouse management can effectively reduce production costs or logistics costs. Traditional warehouse space management often relies on manual management and manual replenishment to store goods. However, when the scale of the warehouse is relatively large, manual management of the warehouse space will consume a lot of labor costs and time costs. In addition, manual management and manual replenishment often lead to low utilization of storage space or goods being placed in unideal storage locations due to human error or the limited field of vision of the replenishment personnel.

The novel creation embodiment provides a warehouse space management system, which includes a display device, an image capture device and a computer device. The image capturing device captures images of the storage space. The computer device connects the image capturing device and the display device, and receives the storage space image. The computer device detects and supplements the images based on the storage space. Whether the cargo incident occurred. When a replenishment event occurs, the computer device uses an image capturing device to capture at least one image of the goods. The computer device performs a warehousing registration process of the goods and creates a digital clone model of the goods based on at least one goods image. The computer device determines the placement location of the goods based on the digital clone model and the storage space model of the storage space. The display device prompts the placement location of the goods.

Based on the above, in the embodiments of this new creation, the replenishment behavior of replenishment personnel can be detected based on the warehouse space image, and the quick registration and digital clone simulation of the warehousing goods can be realized based on the cargo image. Therefore, based on the digital clone model of the goods, the cargo information and the storage space model, the ideal placement of the goods can be automatically predicted, thereby intelligently managing the storage space. This will not only improve the utilization rate of storage space, but also improve the efficiency of storage space management.

In order to make the above-mentioned features and advantages of the present invention more obvious and easy to understand, examples are given below and explained in detail with the accompanying drawings.

10: Warehouse space management system

110:Image capture device

120:Computer device

130:Display device

U1: replenishment staff

S1: Shelves

121:Storage device

122: Processor

1201:Database

1202: Replenishment event detection module

1203: Cargo identification module

1204: Digital clone model creation module

1205: Space Optimization Module

1206: Graphical interface module

S410~S460: steps

51~58,541,542,551,552: Operation

Figure 1 is a schematic diagram of a warehouse space management system according to an embodiment of the present invention.

Figure 2 is a block diagram of a warehouse space management system according to an embodiment of the present invention.

Figure 3 is a schematic diagram of the system functions of a warehouse space management system according to an embodiment of the present invention.

Figure 4 is a flow chart of a storage space management method according to an embodiment of the present invention.

Figure 5 is a schematic diagram of a storage space management method according to an embodiment of the present invention.

Some embodiments of the present invention will be described in detail with reference to the drawings. The component symbols cited in the following description will be regarded as the same or similar components when the same component symbols appear in different drawings. These embodiments are only part of the invention and do not disclose all possible implementation modes of the invention. Rather, these embodiments are only examples of systems within the scope of the patent application for this novel creation.

Referring to Figures 1 and 2, the storage space management system 10 is used to manage the placement of goods in a storage space. The storage space can be a three-dimensional storage space or a flat storage space, and this disclosure is not limited to this. In some embodiments, the storage space may include one or more shelves S1. Shelf S1 is used to store goods. The goods on shelf S1 can be picked up or placed manually or by a truck. In other embodiments, the storage space may include multiple storage compartments for storing goods. The warehouse space management system 10 may include an image capture device 110, a computer device 120, and a display device 130.

The image capturing device 110 captures images of the storage space. The image capturing device 110 may include one or more camera lenses, and the camera lenses may have optical lenses and photosensitive elements. The photosensitive element may be, for example, a charge coupled device (CCD) or a complementary oxide metal semiconductor (CCD). metal-oxide semiconductor (CMOS) components or other components, this disclosure is not limited here.

The display device 130 may include a liquid crystal display (LCD), a light-emitting diode (LED) display, a field emission display (Field Emission Display, FED), or an organic light-emitting diode display (Organic Light-Emitting Diode). Emitting Diode (OLED) or other types of displays, the present invention is not limited to this. The display device 130 can be used to provide a graphical user interface for warehouse managers or replenishment personnel to operate. From another perspective, the display device 130 can also be implemented by a mobile phone, a tablet computer, or other electronic devices with display capabilities.

The computer device 120 connects the image capturing device 110 and the display device 130 . The computer device 120 is, for example, a computer or a server, and the present disclosure is not limited thereto. In some embodiments, the computer device 120 and the display device 130 in the warehouse space management system 10 can be implemented as an integrated electronic device. Alternatively, in some embodiments, the computer device 120 and the display device 130 may be connected to each other via a wired or wireless signal transmission interface. In addition, in some embodiments, the computer device 120 can be implemented through multiple electronic devices with computing capabilities and data storage capabilities, and these electronic devices can be connected through wired or wireless communication interfaces.

The computer device 120 is connected to the checkout platform 110 and may include a storage device 121 and a processor 122 . The storage device 121 is used to store data and software modules (such as operating systems, applications, drivers) for the processor 122 to access, and it can be, for example, any type of fixed or removable random access memory. (random access memory, RAM), read-only memory (read-only memory, ROM), flash memory (flash memory), hard disk, or a combination thereof.

The processor 122 is coupled to the storage device 121, such as a central processing unit (CPU), an application processor (AP), or other programmable general-purpose or special-purpose microprocessor (microprocessor). ), digital signal processor (DSP), image signal processor (ISP), graphics processing unit (GPU) or other similar devices, integrated circuits and combinations thereof.

In some embodiments, the processor 122 can access and execute the software module recorded in the storage device 121 to implement the storage space management method in the creative embodiment of the present invention. The software modules described above may be broadly construed to mean instructions, instruction sets, code, code, programs, applications, software packages, threads, programs, functions, etc., whether referred to as software, firmware, middleware or the like. Software, microcode, hardware description language, or others.

As shown in FIG. 1 , when the replenishment personnel U1 transports goods to the storage space, the computer device 120 can detect the replenishment behavior of the replenishment personnel U1 based on the image of the storage space captured by the image capture device 110 . Therefore, the computer device 120 can perform the warehousing registration process of the goods based on the goods images and create a digital clone model thereof. The digital avatar is a three-dimensional model. In the case of a warehouse empty model with a warehouse space, the computer device 120 can determine the placement position of the goods based on the digital clone model of the goods and the goods information. Prompt replenishment through the graphical interface displayed by the display device 130 Personnel U1 is concerned with the placement of goods. Based on this, the replenishment personnel U1 does not need to manually determine the placement of goods by inspecting the status of the warehouse space with human eyes, thus greatly improving the efficiency of warehouse management and space utilization.

From another point of view, please refer to Figure 3. The computer device 120 may include a database 1201, a replenishment event detection module 1202, a goods identification module 1203, a digital avatar model creation module 1204, and a space optimization module. 1205, and graphical interface module 1206.

The database 1201 is used to record the cargo information of the cargo stored in the warehouse space. Cargo information may include cargo number, cargo name, cargo type, cargo size, cargo weight, warehousing date or cargo placement, etc.

The replenishment event detection module 1202 is used to detect whether a replenishment event occurs. Specifically, the replenishment event detection module 1202 can input the warehouse space image to the human skeleton detection model for analysis to obtain multiple skeleton feature points of the replenishment personnel U1. It is added that the replenishment event detection module 1202 can use a convolutional neural network model or other skeleton identification algorithms to identify multiple skeleton feature points in the warehouse space image. The replenishment event detection module 1202 can determine whether the human posture of the replenisher U1 complies with the replenishment behavior based on the relative positional relationship of these skeleton feature points. When it is determined that the human body posture of the replenisher U1 is consistent with the replenishment behavior, the replenishment event detection module 1202 can determine that the replenishment event occurs.

In some embodiments, the replenishment event detection module 1202 also determines whether there are goods near multiple skeleton feature points of the replenisher U1 to further accurately confirm whether the replenishment event occurs. If the multiple skeleton feature points of replenishment personnel U1 are not near When the goods are detected, it can be determined that the replenishment event has not occurred.

The cargo identification module 1203 is used to detect cargo and identify cargo information, and perform the warehousing registration process of the cargo based on the cargo information. Specifically, when it is determined that a replenishment event occurs, the cargo identification module 1203 can analyze at least one cargo image to obtain cargo information. In some embodiments, the cargo image may be a partial image block of the warehouse space image. In some embodiments, the above-mentioned cargo image may include one or more images captured by the image capture device 110 of the cargo transported by the replenishment personnel U1.

The cargo identification module 1203 can input the warehoused cargo image into the cargo information identification model for analysis to obtain cargo information. The cargo information recognition model can be a convolutional neural network model used for object classification, object detection or text recognition. In some embodiments, the cargo identification module 1203 can use the cargo information recognition model to identify the barcode information on the surface of the cargo from the cargo image, and obtain the cargo information of the cargo transported by the replenishment personnel U1 based on the barcode information. The barcode information is, for example, a one-dimensional barcode or a two-dimensional barcode, which is not limited by this disclosure. Or, in some embodiments, the cargo identification module 1203 can use the cargo information recognition model to identify the text content on the surface of the cargo from the cargo image, and obtain the cargo information of the cargo transported by the replenishment personnel U1 based on the text content on the cargo surface. . Or, in some embodiments, the cargo identification module 1203 can use the cargo information recognition model to identify the cargo type of the cargo based on the cargo image, so as to obtain other cargo information of the cargo transported by the replenishment personnel U1 based on this cargo category.

After obtaining the cargo information of the goods, the cargo identification module 1203 can complete the warehousing registration process according to the cargo information of the goods, so as to store the goods transported by the replenishment personnel U1. The item is registered as one of the inventory goods. Specifically, the cargo identification module 1203 can record the cargo information of the cargo into the database 1201 to complete the warehousing registration process.

The digital clone model creation module 1204 is used to create a digital clone model of goods. Specifically, the cargo images captured by the image capture device 110 may include multiple cargo images corresponding to multiple shooting angles. The digital clone model creation module 1204 can input these multiple cargo images from multiple shooting angles into the three-dimensional model reconstruction model to generate a digital clone model of the cargo. In some embodiments, the three-dimensional model reconstruction model includes a deep learning model applying a Transformer model architecture. In some embodiments, the three-dimensional model reconstruction model may also include a three-dimensional information reconstruction model based on generative adversarial networks (GAN) or other deep learning models. The digital clone model creation module 1204 can refer to various three-dimensional reconstruction technologies to simulate the digital clone model of goods without specific restrictions.

The space optimization module 1205 is used to determine the placement position of goods based on the digital clone model of the goods and the spatial information of the storage space. The space optimization module 1205 can input the digital clone model of the goods and/or the goods information and the storage space model into a placement recommendation model for analysis to determine the placement location of the goods in the storage space. In some embodiments, the space optimization module 1205 can distinguish the storage space in the warehouse space between occupied and unoccupied according to the inventory records in the database. The space optimization module 1205 can decide to place goods in unoccupied storage space in the warehouse space.

In some embodiments, the placement recommendation model is established based on spatial optimization technology analysis of neural networks. The placement recommendation model can be established based on training with a reinforcement learning algorithm or a supervised learning algorithm. That is, the placement push Recommendation models can be trained based on loss functions or reward functions. In some embodiments, by utilizing the placement recommendation model trained by the reinforcement learning mechanism, the space optimization module 1205 can recommend the placement location to the replenisher U1 according to the reinforcement learning placement strategy. Through the training process of reinforcement learning, the placement recommendation model can learn how to select the best placement location for goods based on the current status (digital clone model and storage space model of goods) to maximize long-term cumulative rewards. This approach can adapt to different environments and needs, and automatically adjust storage location policies to adapt to changing conditions.

In some embodiments, the space optimization module 1205 can divide the unoccupied storage space in the warehouse space into multiple sub-areas, and generate recommendation weights for each sub-area based on the regional attributes of each sub-area and the cargo information of the goods. . For example, the space optimization module 1205 can obtain the corresponding weight value based on whether the storage category of the sub-area matches the category of the cargo. In this way, goods of the same category will not be too dispersed in the warehouse space, making it easier to transport or manage the goods.

The graphical interface module 1206 can control the display device 130 to display a graphical interface. The placement position of the goods determined by the space optimization module 1205 can be prompted to the replenishment staff U1 through a graphical interface, so that the replenishment staff U1 can quickly understand the placement location of the goods and improve processing efficiency.

Please refer to FIG. 1 and FIG. 4 . The method of this embodiment is applicable to the storage space management system 10 in the above embodiment. The detailed steps of this embodiment will be described below with various components in the storage space management system 10 .

In step S410, the image capturing device 110 captures the storage space of the storage space. images. The computer device 120 is connected to the image capture device 110 and receives the warehouse space image. In some embodiments, the image capture device 110 can be deployed at the personnel entrance of the warehouse space.

In step S420, the computer device 120 detects whether a replenishment event occurs based on the warehouse space image.

In some embodiments, the computer device 120 determines whether the human posture in the warehouse space image is consistent with the replenishment behavior. When it is determined that the human body posture conforms to the replenishment behavior, the computer device 120 determines that the replenishment event occurs. On the contrary, when it is determined that the human body posture does not comply with the replenishment behavior, the computer device 120 determines that the replenishment event has not occurred. In some embodiments, the computer device 120 uses a human skeleton detection model to capture multiple skeleton feature points of the human skeleton in the warehouse space image, and determines whether the human posture in the warehouse space image meets the replenishment requirements based on the multiple skeleton feature points. behavior.

In step S430, when a replenishment event occurs, the computer device 120 uses the image capture device 110 to capture at least one product image.

In step S440, the computer device 120 performs the warehousing registration process of the goods and creates a digital clone model of the goods based on at least one goods image.

In some embodiments, when performing the warehousing registration process of goods, the computer device 120 uses the goods information recognition model to perform image recognition on the goods image recognition, and identifies the goods information of the goods based on the goods images. Cargo information includes cargo number, cargo name, cargo weight, cargo type or cargo size.

In some embodiments, at least one cargo image includes multiple cargo images corresponding to multiple shooting angles. The computer device 120 will correspond to multiple shooting angles Multiple cargo images are transmitted to a three-dimensional model to reconstruct the model, so as to generate a digital clone model of the cargo through the three-dimensional model reconstruction.

In step S450, the computer device 120 determines the placement position of the goods based on the digital clone model and the storage space model of the storage space.

In some embodiments, the computer device 120 uses a placement recommendation model to determine the placement location of the goods in the storage space based on the warehouse space model, the digital avatar model of the goods, and the goods information. The computer device 120 uses a reinforcement learning algorithm or a supervised learning algorithm to train the placement recommendation model.

In step S460, the display device 130 prompts the placement location of the goods. The display device 130 displays a graphical interface to prompt the placement location of the goods.

Please refer to FIG. 1 and FIG. 5 . The method of this embodiment is applicable to the storage space management system 10 in the above embodiment. The detailed steps of this embodiment will be described below with various components in the storage space management system 10 .

In operation 51, the computer device 120 uses the AI model to identify replenishment behavior. When the replenishment behavior is detected, in operation 52, the computer device 120 locates the goods to learn the current location of the goods. Next, in operation 53, the computer device 120 controls the image capture device 110 to capture multiple images of the cargo corresponding to multiple shooting angles based on the current location of the cargo.

In operation 54, the computer device 120 performs quick registration of goods. In operation 541, the computer device 120 uses the AI model to identify the cargo information. In operation 542, the computer device 120 performs a warehousing registration process according to the cargo information.

In operation 55, the computer device 120 creates the digital clone model. in operation 551. The computer device 120 uses the AI model to perform three-dimensional surface reconstruction. In operation 552, the computer device 120 creates a digital clone model based on the three-dimensional model data generated by the three-dimensional surface reconstruction.

In operation 56, the computer device 120 creates a warehouse space model. The warehousing space model may be a shelf space model. The shelf space model may include shelf size information and occupancy status information. In operation 57, the computer device 120 determines the placement position using the AI model. The computer device 120 recommends the placement location of the goods based on the shelf space model, the digital avatar model of the goods, and the goods information. In operation 58, the display device 130 uses a graphical interface to display the placement position of the goods.

In addition, it should be noted that the various AI models trained based on machine learning algorithms or deep learning algorithms mentioned above can be constructed in advance based on their respective training data sets, which can be stored in the storage device 121 . In other words, the model parameters of the trained AI model (such as the number of neural network layers and the weight of each neural network layer, etc.) have been determined by prior training and stored in the storage device 121 .

To sum up, in embodiments of the present invention, the AI model can be used to detect the replenishment behavior of replenishment personnel, and the AI model can be used to realize quick registration of goods and digital clone simulation. In addition, AI models can also be applied to determine the placement of goods. Based on this, the management efficiency and space utilization rate of warehousing space can be improved, and human errors and labor costs can be reduced.

Although the embodiments of the present invention have been disclosed above, they are not intended to limit the invention. Anyone with ordinary knowledge in the technical field can make some modifications and changes without departing from the spirit and scope of the invention. Retouch, make the original new The scope of protection for a type of creation shall be determined by the scope of the patent application attached.

10: Warehouse space management system

110:Image capture device

120:Computer device

130:Display device

U1: replenishment staff

S1: Shelf

Claims (10)

A storage space management system includes: a display device; an image capture device to capture a storage space image of a storage space; and a computer device connected to the image capture device and the display device to receive the Warehousing space images, and detecting whether a replenishment event occurs based on the warehouse space images, wherein when the replenishment event occurs, the computer device uses the image capture device to capture at least one cargo image, and the computer The device performs a warehousing registration procedure for a cargo and establishes a digital clone model of the cargo based on the at least one cargo image, and determines the placement position of the cargo based on the digital clone model and the storage space model of the storage space. The display device prompts the placement position of the goods. The storage space management system of claim 1, wherein the computer device determines whether the human body posture in the storage space image conforms to the replenishment behavior. When it is determined that the human body posture conforms to the replenishment behavior, the computer device It is determined that the replenishment event occurs. The storage space management system of claim 2, wherein the computer device uses a human skeleton detection model to capture multiple skeleton feature points of a human skeleton in the storage space image, and based on the multiple skeleton features Click to determine whether the human posture in the warehouse space image conforms to the replenishment behavior. The warehousing space management system as claimed in claim 1, wherein when performing the warehousing registration process of the goods, the computer device uses a goods information recognition model to perform image recognition on the goods image recognition, and based on the goods image Cargo information identifying the goods in question. The warehousing space management system of claim 4, wherein the cargo information includes cargo number, cargo name, cargo weight, cargo type or cargo size. The warehouse space management system of claim 1, wherein at least one cargo image includes multiple cargo images corresponding to multiple shooting angles, and the computer device inputs the multiple cargo images corresponding to the multiple shooting angles. Reconstruct the model into a three-dimensional model to generate a digital clone model of the goods through the three-dimensional model reconstruction model. The warehousing space management system of claim 6, wherein the three-dimensional model reconstruction model includes a deep learning model applying a Transformer model architecture. The storage space management system of claim 1, wherein the computer device uses a placement recommendation model to determine the location of the goods based on the storage space model, the digital avatar model of the goods, and the goods information. Describe the placement location in the storage space. The storage space management system of claim 8, wherein the computer device uses a reinforcement learning algorithm or a supervised learning algorithm to train the placement recommendation model. The storage space management system of claim 1, wherein the display device displays a graphical interface to prompt the placement location of the goods.

Images