Camera point supplementing cloud storage data method and system based on RFID article checking

Abstract

The invention discloses a camera additional point cloud storage data method and system based on RFID article checking, and the method comprises the steps: S1, carrying out the analysis, obtaining the historical checking data of a checking robot, and enabling the historical checking data to comprise historical route data and historical access data; s2, determining the weight of each article based on historical inventory data; s3, based on the weight of each article, judging whether a camera needs to be arranged for point supplementation or not; and S4, based on the monitoring content of the camera, judging whether the supplementary point and the position and the visual angle of the supplementary point need to be adjusted. According to the invention, comprehensive acquisition and unified processing of inventory article information are facilitated, specific positions of inventory articles are positioned, data acquisition and cloud multi-modal storage are realized, and efficient management and real-time control of a large number of inventory articles can be realized through multi-modal cloud intelligent management, so that the management efficiency of the inventory articles is improved. Therefore, the intelligent level of the application of the Internet of Things is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management of Internet of Things, and in particular to a camera supplementary cloud storage data method and system based on RFID article inventory. Background Art

[0002] RFID inventory management is to conduct batch inventory through handheld RFID readers. In actual applications, electronic tags are attached to the surface of the object to be identified. The reader can read and identify the electronic data stored in the electronic tag without contact, thereby achieving the purpose of automatic identification of objects.

[0003] Modern factories and logistics companies use RFID to conduct inventory of equipment and other assets. However, due to the wide variety of assets, scattered locations, and complex inventory process scenarios, it is difficult to obtain the specific shape and location information of the goods through RFID. Summary of the invention

[0004] The present invention provides a method and system for camera supplementary cloud storage data based on RFID item inventory to improve the intelligence, flexibility and efficiency of inventory item supervision, which can solve at least one of the above-mentioned technical problems.

[0005] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0006] The camera supplementary cloud storage data method based on RFID item inventory includes the following steps:

[0007] S1. Analyze and obtain historical inventory data of the inventory counting robot, where the historical inventory counting data includes historical route data and historical access data;

[0008] S2. Determine the weight of each item based on the historical inventory data;

[0009] S3. Based on the weight of each item, determine whether it is necessary to deploy cameras to fill in the points;

[0010] S4. Based on the monitoring content of the camera, determine whether it is necessary to adjust the supplementary points and the positions and viewing angles of the supplementary points.

[0011] Furthermore, in S1, the historical route data is the walking route of each inventory count recorded by tracking the moving path of the inventory counting robot in the warehouse through sensors or GPS, and the historical access data is to identify which areas are frequently visited and the inventory counting frequency of each item in such area based on the historical route data.

[0012] Furthermore, in S2, for any item, the weight of the item is mainly composed of the weighted sum of three indicators: inventory frequency, item importance and item liquidity:

[0013] W1=b+γ*P+α*F+β*I (1)

[0014] Among them, W1 is the weight value, P is the inventory frequency, F is the item flow frequency, I is the item importance, γ, α and β are all weight vectors, and b is the deviation value set by the system.

[0015] Furthermore, in S2, the inventory route data and the inventory frequency data in the historical inventory data are combined to identify the items on the inventory route and whose inventory frequency is higher than the average as key items. The key items are given a higher weight, and the above linear formula (1) is adjusted according to the following nonlinear formula (2):

[0016] W=α*F p +β*I q (2)

[0017] Among them, p and q are both exponents, which are used to adjust the nonlinear influence of inventory frequency and item importance on weight.

[0018] Furthermore, in S3, when the calculated weight exceeds a preset threshold, it is determined to deploy a new camera.

[0019] Furthermore, the S4 further comprises:

[0020] S41, determining a target object to be displayed in the surveillance video according to the location attribute and weight information of the object, and matching the obtained physical coordinate conversion mapping to the visual coordinate recognized by the camera according to the location coordinates of the target object in the surveillance video;

[0021] S42, after the monitoring terminal determines that various target objects need to be counted and displayed, it is determined whether the visual coordinates of the target objects are within the display range of the current video channel, and whether the display size and display clarity meet the requirements according to the current camera PTZ value and field of view;

[0022] S43, according to the judgment result, install or supplement the cameras in the surrounding environment, confirm the installation and configuration position and viewing angle of the new cameras, build a new monitoring channel, select and supplement the cameras, and the PTZ value and field of view of the supplemented cameras cover the multiple target objects with high weights;

[0023] S44, scan and obtain the RFID electronic tag of the asset to be managed, and at the same time trigger the platform system to collect video images of the asset through the monitoring camera. If the appropriate video cannot be collected, it is necessary to perform a 5G camera supplement operation;

[0024] S45. Use 5G cameras to fill in the gaps anytime and anywhere based on location information. The surveillance video content after filling in the gaps is analyzed by AI to obtain the target object. The rationality of the filling in the gaps is verified by whether it is reasonably displayed in the surveillance video. At the same time, the target object is analyzed by AI and associated storage.

[0025] Furthermore, in S4, the distance between the camera and the object is calculated according to the following formula (3):

[0026]

[0027] Where d is the effective monitoring distance of the object within the camera, and x / y / z are the three-dimensional coordinates of the object and the existing camera.

[0028] The camera point supplement cloud storage data system based on RFID item inventory is applicable to the camera point supplement cloud storage data method based on RFID item inventory, including:

[0029] An RFID data collection module, which is used to scan items and determine whether additional points are needed based on inventory route data and inventory frequency data;

[0030] A video acquisition module, which is used to adjust the number of additional supplementary points, the position of the supplementary points and the viewing angle according to the judgment result of the RFID data acquisition module;

[0031] An AI object recognition module, which is used to recognize the objects scanned by the RFID data acquisition module and the monitoring content of the video acquisition module, and to uniformly process, analyze and store the multimodal data of the objects;

[0032] A video system platform, which is used to receive and display the video images output by the AI ​​object recognition module.

[0033] The beneficial effects of the present invention are embodied in:

[0034] 1. In order to solve the problems of unknown quantity, waste of resources, and complex data processing faced by factories and logistics companies when taking inventory of assets, the present invention proposes a method and system for cloud storage of data using cameras based on RFID inventory, which is helpful for comprehensive collection and unified processing of inventory information, locating the specific location of inventory items, and realizing multimodal storage from data collection to cloud. Through this multimodal cloud-based intelligent management, efficient management and real-time control of a large number of inventory items can be achieved, thereby improving the intelligence level of IoT applications.

[0035] 2. The management method of the present invention can add new video acquisition points (5G cameras) in real time through 5G network connection, and can temporarily change and add or delete monitoring videos according to the importance and liquidity of items in RFID inventory counts. The system greatly improves the efficiency and flexibility of managing various types of items through cloud, modular, intelligent and dynamic means, and provides stronger functional expansion and remote management capabilities for inventory management, making inventory count and inventory supervision more intelligent, flexible and efficient. It is suitable for the comprehensive inventory count system of the Internet of Things, and has a wide range of application scenarios and adaptability in industrial, community and commercial building inventory counts. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings described herein are used to provide further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute improper limitations on the present application.

[0037] Figure 1 It is a flow chart of a method for supplementing points in the cloud and storing data using a camera based on RFID item inventory according to an embodiment of the present invention.

[0038] Figure 2 It is an overall block diagram of a camera point-filling cloud storage data system based on RFID item inventory according to an embodiment of the present invention.

[0039] Figure 3 It is a structural block diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. In the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0041] It should be noted that, in addition, the meaning of "and / or" in the full text includes three parallel solutions. Taking "A and / or B" as an example, it includes solution A, solution B, or solutions that satisfy both A and B. In addition, "plurality" means more than two.

[0042] See also Figure 1 The embodiment of the present invention provides a method for camera supplementary cloud storage data based on RFID item inventory, comprising the following steps:

[0043] S1. Analyze and obtain historical inventory data of the inventory counting robot, where the historical inventory counting data includes historical route data and historical access data;

[0044] S2. Determine the weight of each item based on the historical inventory data;

[0045] S3. Based on the weight of each item, determine whether it is necessary to deploy cameras to fill in the points;

[0046] S4. Based on the monitoring content of the camera, determine whether it is necessary to adjust the supplementary points and the positions and viewing angles of the supplementary points.

[0047] This method adds new video collection points (5G cameras) in real time through 5G network connections. It can temporarily change and add or delete monitoring videos according to the importance of items in RFID inventory and the liquidity of items. By gradually optimizing the replenishment points, monitoring and replenishing points in batches, and automatically replenishing monitoring points, it greatly improves the efficiency and flexibility of various types of item management, and provides stronger functional expansion and remote management capabilities for inventory management, making item inventory and inventory supervision more intelligent, flexible and efficient.

[0048] In this embodiment, in S1, the historical route data is the walking route of each inventory count recorded by tracking the movement path of the inventory counting robot in the warehouse through sensors or GPS, and the historical access data is to identify which areas are frequently visited and the inventory frequency of each item in this area based on the historical route data.

[0049] Areas with high visit frequencies generally store high-value or high-liquidity items. Recording the number of times each item is counted can reflect the importance of the item. At the same time, the liquidity of the item is recorded. By combining the three indicators of inventory frequency, item importance, and item liquidity, a weight value can be assigned to each item image.

[0050] In this embodiment, in S2, for any item, the weight of the item is mainly composed of the weighted sum of three indicators: inventory frequency, item importance and item liquidity:

[0051] W1=b+γ*P+α*F+β*I (1)

[0052] Among them, W1 is the weight value, P is the inventory frequency, F is the item flow frequency, I is the item importance, γ, α and β are all weight vectors, and b is the deviation value set by the system.

[0053] In the above embodiment, the inventory route data and the inventory frequency data in the historical inventory data are combined to identify the items on the inventory route and whose inventory frequency is higher than the average as key items. The key items are given a higher weight, and the above linear formula (1) is adjusted according to the following nonlinear formula (2):

[0054] W=α*F p+β*I q (2)

[0055] Among them, p and q are both exponents, which are used to adjust the nonlinear influence of inventory frequency and item importance on weight.

[0056] In this embodiment, in S3, when the calculated weight exceeds a preset threshold, it is determined to deploy a new camera.

[0057] In this embodiment, the S4 further includes:

[0058] S41, determining a target object to be displayed in the surveillance video according to the location attribute and weight information of the object, and matching the obtained physical coordinate conversion mapping to the visual coordinate recognized by the camera according to the location coordinates of the target object in the surveillance video;

[0059] S42, after the monitoring terminal determines that various target objects need to be counted and displayed, it is determined whether the visual coordinates of the target objects are within the display range of the current video channel, and whether the display size and display clarity meet the requirements according to the current camera PTZ value and field of view;

[0060] S43, according to the judgment result, install or supplement the cameras in the surrounding environment, confirm the installation and configuration position and viewing angle of the new cameras, build a new monitoring channel, select and supplement the cameras, and the PTZ value and field of view of the supplemented cameras cover the multiple target objects with high weights;

[0061] S44, scan and obtain the RFID electronic tag of the asset to be managed, and at the same time trigger the platform system to collect video images of the asset through the monitoring camera. If the appropriate video cannot be collected, it is necessary to perform a 5G camera supplement operation;

[0062] S45. Use 5G cameras to fill in the gaps anytime and anywhere based on location information. The surveillance video content after filling in the gaps is analyzed by AI to obtain the target object. The rationality of the filling in the gaps is verified by whether it is reasonably displayed in the surveillance video. At the same time, the target object is analyzed by AI and associated storage.

[0063] In the above embodiment, the distance between the camera and the object is calculated according to the following formula (3):

[0064]

[0065] Where d is the effective monitoring distance of the object within the camera, and x / y / z are the three-dimensional coordinates of the object and the existing camera.

[0066] See also Figure 2The embodiment of the present invention further provides a camera point supplement cloud storage data system based on RFID item inventory counting, which is applicable to the camera point supplement cloud storage data method based on RFID item inventory counting, including:

[0067] An RFID data collection module, which is used to scan items and determine whether additional points are needed based on inventory route data and inventory frequency data;

[0068] A video acquisition module, which is used to adjust the number of additional supplementary points, the position of the supplementary points and the viewing angle according to the judgment result of the RFID data acquisition module;

[0069] An AI object recognition module, which is used to recognize the objects scanned by the RFID data acquisition module and the monitoring content of the video acquisition module, and to uniformly process, analyze and store the multimodal data of the objects;

[0070] A video system platform, which is used to receive and display the video images output by the AI ​​object recognition module.

[0071] This system uses RFID inventory point cameras to monitor the inventory time and location information of items through the linkage of RFID and video surveillance, and conducts multi-information and comprehensive supervision of assets in real time, making the entire management process more intelligent. The AI ​​item recognition module analyzes the characteristics of items, labels the items in the video, and stores multi-modal information such as positioning information, added label information, and scanning time in a unified cloud.

[0072] Specifically, this system determines the installation and configuration position and viewing angle of new cameras according to RFID requirements, builds new monitoring channels, selects and supplements cameras, and supplements PTZ values ​​and field of view to cover monitoring targets. 5G cameras are used to supplement points anytime and anywhere according to location information. After supplementation, the video content is analyzed and associated with the video object through the AI ​​analysis module. Through real-time monitoring of inventory items, AI intelligently analyzes the shape of the items, and realizes unified processing, storage and analysis of multimodal data such as item name, inventory time, location information, and video. The operation of the entire system involves equipment data collection, intelligent processing, and cloud storage. Through this cloud-based intelligent management, efficient management and real-time control of warehouse materials can be achieved, thereby improving the intelligence level of IoT applications and providing more accurate decision support.

[0073] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps of the above-mentioned camera point supplement cloud storage data method based on RFID item inventory.

[0074] See also Figure 3 An embodiment of the present invention further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above method.

[0075] An embodiment of the present invention also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the steps of the above-mentioned camera point supplement and cloud storage data method based on RFID item inventory.

[0076] It is understandable that the system, device and storage medium provided in the embodiments of the present invention correspond to the method provided in the embodiments of the present invention, and the explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts of the above-mentioned camera point supplement cloud storage data method based on RFID item inventory.

[0077] It should be noted that those skilled in the art can understand that all or part of the steps implemented in the embodiments of the present invention can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using hardware, it can be implemented in whole or in part in the form of purchasing standard parts or modified parts. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0078] In summary, in order to clarify the asset location and video viewing status, the present invention provides an AI point-filling method, which can use the point-filling camera to conduct video tracing and viewing of items, remotely view the status and location of asset inventory in real time, and realize inventory monitoring and viewing of items. By gradually optimizing the points, performing monitoring points in batches, and automatically filling monitoring points, it not only saves the labor cost investment in on-site measurement and wiring, but also monitors the inventory process in real time remotely, realizes scanning process supervision, and cloud storage for real-time evidence, which improves the intelligence, flexibility and efficiency of asset supervision, and solves the problems of unknown quantity, waste of resources, and complex data processing in asset inventory of factories and logistics companies in traditional methods.

[0079] It should be understood that the examples and implementation modes described herein are for illustrative purposes only and are not intended to limit the present invention. Those skilled in the art may make various modifications or changes based on the examples and implementation modes. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A camera supplementary cloud storage data method based on RFID item inventory, characterized in that: The following steps are involved: S1. Analyze and obtain historical inventory data of the inventory counting robot, where the historical inventory counting data includes historical route data and historical access data; S2. Determine the weight of each item based on the historical inventory data; S3. Based on the weight of each item, determine whether it is necessary to deploy cameras to fill in the points; S4. Based on the monitoring content of the camera, determine whether it is necessary to adjust the supplementary points and the positions and viewing angles of the supplementary points.

2. The camera point supplement cloud storage data method based on RFID item inventory as claimed in claim 1, characterized in that: In S1, the historical route data is the walking route of each inventory count recorded by tracking the moving path of the inventory counting robot in the warehouse through sensors or GPS, and the historical access data is to identify which areas are frequently visited and the inventory counting frequency of each item in such area based on the historical route data.

3. The camera point supplement cloud storage data method based on RFID item inventory as claimed in claim 1, characterized in that: In S2, for any item, the weight of the item is mainly composed of the weighted sum of three indicators: inventory frequency, item importance and item liquidity: W1=b+γ*P+α*F+β*I (1) Among them, W1 is the weight value, P is the inventory frequency, F is the item flow frequency, I is the item importance, γ, α and β are all weight vectors, and b is the deviation value set by the system.

4. The camera point supplement cloud storage data method based on RFID item inventory as claimed in claim 3, characterized in that: In S2, the inventory route data and the inventory frequency data in the historical inventory data are combined to identify the items on the inventory route and whose inventory frequency is higher than the average as key items. The key items are given a higher weight, and the linear formula (1) is adjusted according to the following nonlinear formula (2): W=α*F p +β*I q (2) Among them, p and q are both exponents, which are used to adjust the nonlinear influence of inventory frequency and item importance on weight.

5. The camera supplementary cloud storage data method based on RFID item inventory as claimed in claim 1, characterized in that: In S3, when the calculated weight exceeds a preset threshold, it is determined to deploy a new camera.

6. The camera supplementary cloud storage data method based on RFID item inventory as claimed in claim 5, characterized in that: The S4 further comprises: S41, determining a target object to be displayed in the surveillance video according to the location attribute and weight information of the object, and matching the obtained physical coordinate conversion mapping to the visual coordinate recognized by the camera according to the location coordinates of the target object in the surveillance video; S42, after the monitoring terminal determines that various target objects need to be counted and displayed, it is determined whether the visual coordinates of the target objects are within the display range of the current video channel, and whether the display size and display clarity meet the requirements according to the current camera PTZ value and field of view; S43, according to the judgment result, install or supplement the cameras in the surrounding environment, confirm the installation and configuration position and viewing angle of the new cameras, build a new monitoring channel, select and supplement the cameras, and the PTZ value and field of view of the supplemented cameras cover the multiple target objects with high weights; S44, scan and obtain the RFID electronic tag of the asset to be managed, and at the same time trigger the platform system to collect video images of the asset through the monitoring camera. If the appropriate video cannot be collected, it is necessary to perform a 5G camera supplement operation; S45. Use 5G cameras to fill in the gaps anytime and anywhere based on location information. The surveillance video content after filling in the gaps is analyzed by AI to obtain the target object. The rationality of the filling in the gaps is verified by whether it is reasonably displayed in the surveillance video. At the same time, the target object is analyzed by AI and associated storage.

7. The camera point supplement cloud storage data method based on RFID item inventory as claimed in claim 6, characterized in that: In S4, the distance between the camera and the object is calculated according to the following formula (3): Where d is the effective monitoring distance of the object within the camera, and x / y / z are the three-dimensional coordinates of the object and the existing camera.

8. A camera point-supplement cloud data storage system based on RFID item inventory, applicable to a camera point-supplement cloud data storage method based on RFID item inventory as claimed in any one of claims 1 to 7, characterized in that: include: An RFID data collection module, which is used to scan items and determine whether additional points are needed based on inventory route data and inventory frequency data; A video acquisition module, which is used to adjust the number of additional supplementary points, the position of the supplementary points and the viewing angle according to the judgment result of the RFID data acquisition module; An AI object recognition module, which is used to recognize the objects scanned by the RFID data acquisition module and the monitoring content of the video acquisition module, and to uniformly process, analyze and store the multimodal data of the objects; A video system platform, which is used to receive and display the video images output by the AI ​​object recognition module.

Images